{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.6"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":10445,"databundleVersionId":200747,"sourceType":"competition"}],"dockerImageVersionId":21695,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"This is my revised kernel inspired by Chau Ngoc Huynh's kernel (3.699).\n\n**New Update : Application of Interaction on Categorical Variables followed by Stacking using Bayesian Ridge on Stratified K Folds**","metadata":{"_uuid":"1dee50e02ba20b8aabe9775e0f8b19c40e1bcff8"}},{"cell_type":"code","source":"# Import the necessary libraries\nimport numpy as np\nimport pandas as pd\nimport os\nimport time\nimport warnings\nimport gc\ngc.collect()\nimport os\nfrom six.moves import urllib\nimport matplotlib\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport datetime\nwarnings.filterwarnings('ignore')\n%matplotlib inline\nplt.style.use('seaborn')\nfrom scipy.stats import norm, skew\nfrom sklearn.preprocessing import StandardScaler","metadata":{"_uuid":"a594abe9f66c5a090177dff966d6bedf63718a9c","execution":{"iopub.status.busy":"2023-12-21T11:21:40.685461Z","iopub.execute_input":"2023-12-21T11:21:40.685776Z","iopub.status.idle":"2023-12-21T11:21:41.872573Z","shell.execute_reply.started":"2023-12-21T11:21:40.685722Z","shell.execute_reply":"2023-12-21T11:21:41.871045Z"},"trusted":true},"execution_count":1,"outputs":[]},{"cell_type":"code","source":"#Add All the Models Libraries\n\n# Scalers\nfrom sklearn.utils import shuffle\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.pipeline import FeatureUnion\n\n# Models\n\nfrom sklearn.linear_model import Lasso\nfrom sklearn.metrics import mean_squared_log_error,mean_squared_error, r2_score,mean_absolute_error\n\nfrom sklearn.model_selection import train_test_split #training and testing data split\nfrom sklearn import metrics #accuracy measure\nfrom sklearn.metrics import confusion_matrix #for confusion matrix\nfrom scipy.stats import reciprocal, uniform\n\nfrom sklearn.model_selection import StratifiedKFold, RepeatedKFold\n\n# Cross-validation\nfrom sklearn.model_selection import KFold #for K-fold cross validation\nfrom sklearn.model_selection import cross_val_score #score evaluation\nfrom sklearn.model_selection import cross_val_predict #prediction\nfrom sklearn.model_selection import cross_validate\n\n# GridSearchCV\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.model_selection import RandomizedSearchCV\n\n#Common data processors\nfrom sklearn.preprocessing import OneHotEncoder, LabelEncoder\nfrom sklearn import feature_selection\nfrom sklearn import model_selection\nfrom sklearn import metrics\nfrom sklearn.base import BaseEstimator, TransformerMixin\nfrom sklearn.utils import check_array\nfrom scipy import sparse","metadata":{"_uuid":"bfbbf30dcb4c354827aae6fff1aeaa632a9e874e","execution":{"iopub.status.busy":"2023-12-21T11:21:45.187962Z","iopub.execute_input":"2023-12-21T11:21:45.188242Z","iopub.status.idle":"2023-12-21T11:21:45.417Z","shell.execute_reply.started":"2023-12-21T11:21:45.188203Z","shell.execute_reply":"2023-12-21T11:21:45.41579Z"},"trusted":true},"execution_count":2,"outputs":[]},{"cell_type":"code","source":"# to make this notebook's output stable across runs\nnp.random.seed(123)\ngc.collect()\n# To plot pretty figures\n%matplotlib inline\nplt.rcParams['axes.labelsize'] = 14\nplt.rcParams['xtick.labelsize'] = 12\nplt.rcParams['ytick.labelsize'] = 12","metadata":{"_uuid":"798008f46ddb84ca5ec248990d56b64e5ec84e5a","execution":{"iopub.status.busy":"2023-12-21T11:22:13.396552Z","iopub.execute_input":"2023-12-21T11:22:13.397042Z","iopub.status.idle":"2023-12-21T11:22:13.460725Z","shell.execute_reply.started":"2023-12-21T11:22:13.396992Z","shell.execute_reply":"2023-12-21T11:22:13.459994Z"},"trusted":true},"execution_count":7,"outputs":[]},{"cell_type":"code","source":"#Reduce the memory usage - Inspired by Panchajanya Banerjee\ndef reduce_mem_usage(df, verbose=True):\n numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']\n start_mem = df.memory_usage().sum() / 1024**2 \n for col in df.columns:\n col_type = df[col].dtypes\n if col_type in numerics:\n c_min = df[col].min()\n c_max = df[col].max()\n if str(col_type)[:3] == 'int':\n if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:\n df[col] = df[col].astype(np.int8)\n elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:\n df[col] = df[col].astype(np.int16)\n elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:\n df[col] = df[col].astype(np.int32)\n elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:\n df[col] = df[col].astype(np.int64) \n else:\n if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:\n df[col] = df[col].astype(np.float16)\n elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:\n df[col] = df[col].astype(np.float32)\n else:\n df[col] = df[col].astype(np.float64) \n end_mem = df.memory_usage().sum() / 1024**2\n if verbose: print('Mem. usage decreased to {:5.2f} Mb ({:.1f}% reduction)'.format(end_mem, 100 * (start_mem - end_mem) / start_mem))\n return df","metadata":{"_uuid":"47d5d544fa7e4bf9305814409c3cabc148b0169a","execution":{"iopub.status.busy":"2023-12-21T11:22:23.128905Z","iopub.execute_input":"2023-12-21T11:22:23.129196Z","iopub.status.idle":"2023-12-21T11:22:23.139263Z","shell.execute_reply.started":"2023-12-21T11:22:23.129151Z","shell.execute_reply":"2023-12-21T11:22:23.13795Z"},"trusted":true},"execution_count":12,"outputs":[]},{"cell_type":"code","source":"def one_hot_encoder(df, nan_as_category=True):\n original_columns = df.columns.tolist()\n\n categorical_columns = list(filter(lambda c: c in ['object'], df.dtypes))\n df = pd.get_dummies(df, columns=categorical_columns, dummy_na=nan_as_category)\n\n new_columns = list(filter(lambda c: c not in original_columns, df.columns))\n return df, new_columns","metadata":{"_uuid":"56152464b49828f018e84cf114f520239342270e","execution":{"iopub.status.busy":"2023-12-21T11:22:32.526352Z","iopub.execute_input":"2023-12-21T11:22:32.526702Z","iopub.status.idle":"2023-12-21T11:22:32.531949Z","shell.execute_reply.started":"2023-12-21T11:22:32.526641Z","shell.execute_reply":"2023-12-21T11:22:32.531015Z"},"trusted":true},"execution_count":16,"outputs":[]},{"cell_type":"code","source":"train = reduce_mem_usage(pd.read_csv('../input/train.csv',parse_dates=[\"first_active_month\"]))\ntest = reduce_mem_usage(pd.read_csv('../input/test.csv', parse_dates=[\"first_active_month\"]))","metadata":{"_uuid":"450f05f1bb8bd470972ec8a8f80a96f4b56402a7","scrolled":true,"execution":{"iopub.status.busy":"2023-12-21T11:22:35.283288Z","iopub.execute_input":"2023-12-21T11:22:35.283608Z","iopub.status.idle":"2023-12-21T11:22:35.868744Z","shell.execute_reply.started":"2023-12-21T11:22:35.283555Z","shell.execute_reply":"2023-12-21T11:22:35.867649Z"},"trusted":true},"execution_count":17,"outputs":[{"name":"stdout","text":"Mem. usage decreased to 4.04 Mb (56.2% reduction)\nMem. usage decreased to 2.24 Mb (52.5% reduction)\n","output_type":"stream"}]},{"cell_type":"code","source":"train.shape","metadata":{"_uuid":"2352513f1d53487e789e41fbfa050199154f8916","execution":{"iopub.status.busy":"2023-12-21T11:22:38.418569Z","iopub.execute_input":"2023-12-21T11:22:38.419104Z","iopub.status.idle":"2023-12-21T11:22:38.426237Z","shell.execute_reply.started":"2023-12-21T11:22:38.418813Z","shell.execute_reply":"2023-12-21T11:22:38.425077Z"},"trusted":true},"execution_count":18,"outputs":[{"execution_count":18,"output_type":"execute_result","data":{"text/plain":"(201917, 6)"},"metadata":{}}]},{"cell_type":"code","source":"train.info()","metadata":{"_uuid":"78407176c3c40b9d15227165028d6b61f94f3ba3","execution":{"iopub.status.busy":"2023-12-21T11:22:41.21104Z","iopub.execute_input":"2023-12-21T11:22:41.211438Z","iopub.status.idle":"2023-12-21T11:22:41.254786Z","shell.execute_reply.started":"2023-12-21T11:22:41.211402Z","shell.execute_reply":"2023-12-21T11:22:41.253346Z"},"trusted":true},"execution_count":19,"outputs":[{"name":"stdout","text":"\nRangeIndex: 201917 entries, 0 to 201916\nData columns (total 6 columns):\nfirst_active_month 201917 non-null datetime64[ns]\ncard_id 201917 non-null object\nfeature_1 201917 non-null int8\nfeature_2 201917 non-null int8\nfeature_3 201917 non-null int8\ntarget 201917 non-null float16\ndtypes: datetime64[ns](1), float16(1), int8(3), object(1)\nmemory usage: 4.0+ MB\n","output_type":"stream"}]},{"cell_type":"code","source":"plt.subplot(1, 2, 2)\nsns.distplot(train.target, kde=True, fit = norm)\nplt.xlabel('Customer Loyality (Skewed)')","metadata":{"_uuid":"1858899e8d6a7a6808204567ded690e4a10810d7","execution":{"iopub.status.busy":"2023-12-21T11:22:45.340305Z","iopub.execute_input":"2023-12-21T11:22:45.340685Z","iopub.status.idle":"2023-12-21T11:22:45.829803Z","shell.execute_reply.started":"2023-12-21T11:22:45.340626Z","shell.execute_reply":"2023-12-21T11:22:45.829141Z"},"trusted":true},"execution_count":20,"outputs":[{"execution_count":20,"output_type":"execute_result","data":{"text/plain":"Text(0.5,0,'Customer Loyality (Skewed)')"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}]},{"cell_type":"code","source":"# Remove the Outliers if any \ntrain['outliers'] = 0\ntrain.loc[train['target'] < -30, 'outliers'] = 1\ntrain['outliers'].value_counts()\n\nfor features in ['feature_1','feature_2','feature_3']:\n order_label = train.groupby([features])['outliers'].mean()\n train[features] = train[features].map(order_label)\n test[features] = test[features].map(order_label)","metadata":{"_uuid":"f1dc9399de447ff96d064b085e6152a543ece278","execution":{"iopub.status.busy":"2023-12-21T11:22:58.741639Z","iopub.execute_input":"2023-12-21T11:22:58.741957Z","iopub.status.idle":"2023-12-21T11:22:58.796291Z","shell.execute_reply.started":"2023-12-21T11:22:58.741887Z","shell.execute_reply":"2023-12-21T11:22:58.795093Z"},"trusted":true},"execution_count":22,"outputs":[]},{"cell_type":"code","source":"# Now extract the days and Qtr\ntrain['days'] = (datetime.date(2018, 2, 1) - train['first_active_month'].dt.date).dt.days\ntrain['quarter'] = train['first_active_month'].dt.quarter\n\nfeature_cols = ['feature_1', 'feature_2', 'feature_3']\nfor f in feature_cols:\n train['days_' + f] = train['days'] * train[f]\n train['days_' + f + '_ratio'] = train[f] / train['days']\n\ntest['days'] = (datetime.date(2018, 2, 1) - test['first_active_month'].dt.date).dt.days\ntest['quarter'] = test['first_active_month'].dt.quarter\n\nfeature_cols = ['feature_1', 'feature_2', 'feature_3']\nfor f in feature_cols:\n test['days_' + f] = test['days'] * test[f]\n test['days_' + f + '_ratio'] = test[f] / test['days']\n\ngc.collect()","metadata":{"_uuid":"ce244a5a05abaa8c91ff3c73d8c5f86ba592c9a1","execution":{"iopub.status.busy":"2023-12-21T11:23:01.301533Z","iopub.execute_input":"2023-12-21T11:23:01.302281Z","iopub.status.idle":"2023-12-21T11:23:02.424552Z","shell.execute_reply.started":"2023-12-21T11:23:01.301773Z","shell.execute_reply":"2023-12-21T11:23:02.423363Z"},"trusted":true},"execution_count":23,"outputs":[{"execution_count":23,"output_type":"execute_result","data":{"text/plain":"261"},"metadata":{}}]},{"cell_type":"markdown","source":"Now we will try to extract more features from Transactions Data","metadata":{"_uuid":"b54460353af274062f649afe26f034c4126a6a84"}},{"cell_type":"code","source":"def aggregate_transaction_hist(trans, prefix): \n \n agg_func = {\n 'purchase_amount' : ['sum','max','min','mean','var','skew'],\n 'installments' : ['sum','max','mean','var','skew'],\n 'purchase_date' : ['max','min'],\n 'month_lag' : ['max','min','mean','var','skew'],\n 'month_diff' : ['max','min','mean','var','skew'],\n 'weekend' : ['sum', 'mean'],\n 'weekday' : ['sum', 'mean'],\n 'authorized_flag': ['sum', 'mean'],\n 'category_1': ['sum','mean', 'max','min'],\n 'card_id' : ['size','count'],\n 'month': ['nunique', 'mean', 'min', 'max'],\n 'hour': ['nunique', 'mean', 'min', 'max'],\n 'weekofyear': ['nunique', 'mean', 'min', 'max'],\n 'day': ['nunique', 'mean', 'min', 'max'],\n 'subsector_id': ['nunique'],\n 'merchant_category_id' : ['nunique'],\n 'price' :['sum','mean','max','min','var'],\n 'duration' : ['mean','min','max','var','skew'],\n 'amount_month_ratio':['mean','min','max','var','skew']\n \n }\n \n agg_trans = trans.groupby(['card_id']).agg(agg_func)\n agg_trans.columns = [prefix + '_'.join(col).strip() \n for col in agg_trans.columns.values]\n agg_trans.reset_index(inplace=True)\n \n df = (trans.groupby('card_id')\n .size()\n .reset_index(name='{}transactions_count'.format(prefix)))\n \n agg_trans = pd.merge(df, agg_trans, on='card_id', how='left')\n \n return agg_trans","metadata":{"_uuid":"f9835dd6582d3e9c36954b498810929c8438d2d2","execution":{"iopub.status.busy":"2023-12-21T11:23:05.936834Z","iopub.execute_input":"2023-12-21T11:23:05.937129Z","iopub.status.idle":"2023-12-21T11:23:05.955608Z","shell.execute_reply.started":"2023-12-21T11:23:05.93708Z","shell.execute_reply":"2023-12-21T11:23:05.954846Z"},"trusted":true},"execution_count":25,"outputs":[]},{"cell_type":"code","source":"transactions = reduce_mem_usage(pd.read_csv('../input/historical_transactions.csv'))\ngc.collect()","metadata":{"_uuid":"06a04f3393a83cb2687b76deba417012e18ef606","scrolled":true,"execution":{"iopub.status.busy":"2023-12-21T11:23:19.63341Z","iopub.execute_input":"2023-12-21T11:23:19.633712Z","iopub.status.idle":"2023-12-21T11:24:46.981819Z","shell.execute_reply.started":"2023-12-21T11:23:19.633651Z","shell.execute_reply":"2023-12-21T11:24:46.980957Z"},"trusted":true},"execution_count":27,"outputs":[{"name":"stdout","text":"Mem. usage decreased to 1749.11 Mb (43.7% reduction)\n","output_type":"stream"},{"execution_count":27,"output_type":"execute_result","data":{"text/plain":"0"},"metadata":{}}]},{"cell_type":"code","source":"#impute missing values - This is now excluded.\ntransactions['category_2'] = transactions['category_2'].fillna(1.0,inplace=True)\ntransactions['category_3'] = transactions['category_3'].fillna('A',inplace=True)\ntransactions['merchant_id'] = transactions['merchant_id'].fillna('M_ID_00a6ca8a8a',inplace=True)\ntransactions['installments'].replace(-1, np.nan,inplace=True)\ntransactions['installments'].replace(999, np.nan,inplace=True)\ntransactions['purchase_amount'] = transactions['purchase_amount'].apply(lambda x: min(x, 0.8))\n\n#Feature Engineering - Adding new features inspired by Chau's first kernel\ntransactions['authorized_flag'] = transactions['authorized_flag'].map({'Y': 1, 'N': 0})\ntransactions['category_1'] = transactions['category_1'].map({'Y': 1, 'N': 0})\ntransactions['category_3'] = transactions['category_3'].map({'A':0, 'B':1, 'C':2})\n\ntransactions['purchase_date'] = pd.to_datetime(transactions['purchase_date'])\ntransactions['weekofyear'] = transactions['purchase_date'].dt.weekofyear\ntransactions['month'] = transactions['purchase_date'].dt.month\ntransactions['day'] = transactions['purchase_date'].dt.day\ntransactions['weekday'] = transactions.purchase_date.dt.weekday\ntransactions['weekend'] = (transactions.purchase_date.dt.weekday >=5).astype(int)\ntransactions['hour'] = transactions['purchase_date'].dt.hour \ntransactions['month_diff'] = ((datetime.datetime.today() - transactions['purchase_date']).dt.days)//30\ntransactions['month_diff'] += transactions['month_lag']\n\n# additional features\ntransactions['duration'] = transactions['purchase_amount']*transactions['month_diff']\ntransactions['amount_month_ratio'] = transactions['purchase_amount']/transactions['month_diff']\ntransactions['price'] = transactions['purchase_amount'] / transactions['installments']\n\ngc.collect()","metadata":{"_uuid":"1decf075c9422fe20823691972f055b8a1c84f50","scrolled":true,"execution":{"iopub.status.busy":"2023-12-21T11:25:07.398836Z","iopub.execute_input":"2023-12-21T11:25:07.400584Z","iopub.status.idle":"2023-12-21T11:25:49.384627Z","shell.execute_reply.started":"2023-12-21T11:25:07.400498Z","shell.execute_reply":"2023-12-21T11:25:49.383358Z"},"trusted":true},"execution_count":28,"outputs":[{"execution_count":28,"output_type":"execute_result","data":{"text/plain":"181"},"metadata":{}}]},{"cell_type":"code","source":"agg_func = {\n 'mean': ['mean'],\n }\nfor col in ['category_2','category_3']:\n transactions[col+'_mean'] = transactions['purchase_amount'].groupby(transactions[col]).agg('mean')\n transactions[col+'_max'] = transactions['purchase_amount'].groupby(transactions[col]).agg('max')\n transactions[col+'_min'] = transactions['purchase_amount'].groupby(transactions[col]).agg('min')\n transactions[col+'_sum'] = transactions['purchase_amount'].groupby(transactions[col]).agg('sum')\n agg_func[col+'_mean'] = ['mean']\n \ngc.collect()","metadata":{"_uuid":"93a165f209a8853e4c8e1f624becd0506e6fb0f1","execution":{"iopub.status.busy":"2023-12-21T11:25:58.48637Z","iopub.execute_input":"2023-12-21T11:25:58.486791Z","iopub.status.idle":"2023-12-21T11:26:23.812569Z","shell.execute_reply.started":"2023-12-21T11:25:58.486742Z","shell.execute_reply":"2023-12-21T11:26:23.811031Z"},"trusted":true},"execution_count":29,"outputs":[{"execution_count":29,"output_type":"execute_result","data":{"text/plain":"168"},"metadata":{}}]},{"cell_type":"code","source":"merge_trans = aggregate_transaction_hist(transactions, prefix='hist_')\ndel transactions\ngc.collect()\ntrain = pd.merge(train, merge_trans, on='card_id',how='left')\ntest = pd.merge(test, merge_trans, on='card_id',how='left')\ndel merge_trans\ngc.collect()","metadata":{"_uuid":"95128e635d5c0ad26b170652971aca4fc9c41ad1","execution":{"iopub.status.busy":"2023-12-21T11:26:47.310236Z","iopub.execute_input":"2023-12-21T11:26:47.310548Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Feature Engineering - Adding new features inspired by Chau's first kernel\ntrain['hist_purchase_date_max'] = pd.to_datetime(train['hist_purchase_date_max'])\ntrain['hist_purchase_date_min'] = pd.to_datetime(train['hist_purchase_date_min'])\ntrain['hist_purchase_date_diff'] = (train['hist_purchase_date_max'] - train['hist_purchase_date_min']).dt.days\ntrain['hist_purchase_date_average'] = train['hist_purchase_date_diff']/train['hist_card_id_size']\ntrain['hist_purchase_date_uptonow'] = (datetime.datetime.today() - train['hist_purchase_date_max']).dt.days\ntrain['hist_purchase_date_uptomin'] = (datetime.datetime.today() - train['hist_purchase_date_min']).dt.days\ntrain['hist_first_buy'] = (train['hist_purchase_date_min'] - train['first_active_month']).dt.days\ntrain['hist_last_buy'] = (train['hist_purchase_date_max'] - train['first_active_month']).dt.days\n\nfor feature in ['hist_purchase_date_max','hist_purchase_date_min']:\n train[feature] = train[feature].astype(np.int64) * 1e-9\ngc.collect()\n","metadata":{"_uuid":"a3e6c6e3dec6f2153d02a684fb7ddbbace4c5550","execution":{"iopub.status.busy":"2023-12-19T12:41:30.448051Z","iopub.execute_input":"2023-12-19T12:41:30.448406Z","iopub.status.idle":"2023-12-19T12:41:30.644219Z","shell.execute_reply.started":"2023-12-19T12:41:30.448348Z","shell.execute_reply":"2023-12-19T12:41:30.643176Z"},"trusted":true},"execution_count":18,"outputs":[{"execution_count":18,"output_type":"execute_result","data":{"text/plain":"110"},"metadata":{}}]},{"cell_type":"code","source":"#Feature Engineering - Adding new features inspired by Chau's first kernel\ntest['hist_purchase_date_max'] = pd.to_datetime(test['hist_purchase_date_max'])\ntest['hist_purchase_date_min'] = pd.to_datetime(test['hist_purchase_date_min'])\ntest['hist_purchase_date_diff'] = (test['hist_purchase_date_max'] - test['hist_purchase_date_min']).dt.days\ntest['hist_purchase_date_average'] = test['hist_purchase_date_diff']/test['hist_card_id_size']\ntest['hist_purchase_date_uptonow'] = (datetime.datetime.today() - test['hist_purchase_date_max']).dt.days\ntest['hist_purchase_date_uptomin'] = (datetime.datetime.today() - test['hist_purchase_date_min']).dt.days\n\ntest['hist_first_buy'] = (test['hist_purchase_date_min'] - test['first_active_month']).dt.days\ntest['hist_last_buy'] = (test['hist_purchase_date_max'] - test['first_active_month']).dt.days\n\nfor feature in ['hist_purchase_date_max','hist_purchase_date_min']:\n test[feature] = test[feature].astype(np.int64) * 1e-9\n\ngc.collect()","metadata":{"_uuid":"370757bfba37b643f463f385d9e878ff27e320bc","execution":{"iopub.status.busy":"2023-12-19T12:41:30.64559Z","iopub.execute_input":"2023-12-19T12:41:30.645921Z","iopub.status.idle":"2023-12-19T12:41:30.809816Z","shell.execute_reply.started":"2023-12-19T12:41:30.645859Z","shell.execute_reply":"2023-12-19T12:41:30.808985Z"},"trusted":true},"execution_count":19,"outputs":[{"execution_count":19,"output_type":"execute_result","data":{"text/plain":"92"},"metadata":{}}]},{"cell_type":"code","source":"train.head(10)","metadata":{"_uuid":"0c374b5e1327cd726ddfb85f7d1afceb2fd9c5df","scrolled":true,"execution":{"iopub.status.busy":"2023-12-19T12:41:30.810885Z","iopub.execute_input":"2023-12-19T12:41:30.811144Z","iopub.status.idle":"2023-12-19T12:41:31.02365Z","shell.execute_reply.started":"2023-12-19T12:41:30.811104Z","shell.execute_reply":"2023-12-19T12:41:31.022571Z"},"trusted":true},"execution_count":20,"outputs":[{"execution_count":20,"output_type":"execute_result","data":{"text/plain":" first_active_month ... hist_last_buy\n0 2017-06-01 ... 269\n1 2017-01-01 ... 395\n2 2016-08-01 ... 575\n3 2017-09-01 ... 180\n4 2017-11-01 ... 119\n5 2016-09-01 ... 331\n6 2016-12-01 ... 449\n7 2017-09-01 ... 111\n8 2017-08-01 ... 130\n9 2016-08-01 ... 576\n\n[10 rows x 90 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
first_active_monthcard_idfeature_1feature_2feature_3targetoutliersdaysquarterdays_feature_1days_feature_1_ratiodays_feature_2days_feature_2_ratiodays_feature_3days_feature_3_ratiohist_transactions_counthist_purchase_amount_sumhist_purchase_amount_maxhist_purchase_amount_minhist_purchase_amount_meanhist_purchase_amount_varhist_purchase_amount_skewhist_installments_sumhist_installments_maxhist_installments_meanhist_installments_varhist_installments_skewhist_purchase_date_maxhist_purchase_date_minhist_month_lag_maxhist_month_lag_minhist_month_lag_meanhist_month_lag_varhist_month_lag_skewhist_month_diff_maxhist_month_diff_minhist_month_diff_meanhist_month_diff_varhist_month_diff_skewhist_weekend_sum...hist_card_id_counthist_month_nuniquehist_month_meanhist_month_minhist_month_maxhist_hour_nuniquehist_hour_meanhist_hour_minhist_hour_maxhist_weekofyear_nuniquehist_weekofyear_meanhist_weekofyear_minhist_weekofyear_maxhist_day_nuniquehist_day_meanhist_day_minhist_day_maxhist_subsector_id_nuniquehist_merchant_category_id_nuniquehist_price_sumhist_price_meanhist_price_maxhist_price_minhist_price_varhist_duration_meanhist_duration_minhist_duration_maxhist_duration_varhist_duration_skewhist_amount_month_ratio_meanhist_amount_month_ratio_minhist_amount_month_ratio_maxhist_amount_month_ratio_varhist_amount_month_ratio_skewhist_purchase_date_diffhist_purchase_date_averagehist_purchase_date_uptonowhist_purchase_date_uptominhist_first_buyhist_last_buy
02017-06-01C_ID_92a20055570.0131450.0087520.011428-0.820312024523.2204310.0000542.1442700.0000362.7997430.000047260-167.4271340.800000-0.739395-0.6439510.0205615.1354884.01.00.0153850.0152067.9207701.519551e+091.498573e+090-8-3.9115385.7489010.065960717070.6884620.215310-0.81860490...26098.0576921122313.3153850233533.0730771523115.5115381312141NaNNaNinf-infNaN-45.514575-52.49701356.800000102.9010245.149833-0.009111-0.0105410.0112684.116444e-065.1054342420.9307692123236526269
12017-01-01C_ID_3d0044924f0.0107120.0113850.0102830.392822039614.2417900.0000274.5083700.0000294.0720030.000026350-215.3949950.800000-0.742400-0.6154140.0585983.747456545.010.01.5660922.2578673.8011781.517438e+091.483720e+090-12-5.03142914.477519-0.258151727171.6714290.221244-0.733105132...350126.2200001122414.7171430235025.2200001523116.6657141312457-202.218491-0.5810880.400000-0.7424000.060272-44.107017-53.45278657.600000300.3784693.745193-0.008587-0.0104350.0112681.143975e-053.7456933901.114286214725375395
22016-08-01C_ID_d639edf6cd0.0106100.0087520.0102830.687988054935.8248290.0000194.8049150.0000165.6452760.00001943-29.167391-0.145847-0.730138-0.6783110.0076355.6261980.00.00.0000000.0000000.0000001.519759e+091.484123e+090-13-8.60465114.7685490.725371717070.6279070.239203-0.54856211...43104.5581401121417.9069778232218.3720932491919.32558123078-inf-inf-inf-infNaN-47.920634-51.839811-10.20931238.8750705.497794-0.009602-0.010284-0.0020841.507757e-065.7099434129.58139521202533163575
32017-09-01C_ID_186d6a69010.0107120.0141660.0102830.142456015331.6388740.0000702.1674600.0000931.5732740.00006777-50.1369600.800000-0.740897-0.6511290.0383815.75752986.03.01.1466670.2349553.3053031.519818e+091.506443e+090-5-2.8311693.2474370.557757717070.6103900.240943-0.46177511...7767.7402601121614.4415580232032.0129871522516.8701302311325-47.474445-0.6329930.800000-0.7408970.053342-45.980521-52.44473656.000000189.6076945.757373-0.009221-0.0105840.0114297.778549e-065.7469961542.0000002120227425180
42017-11-01C_ID_cdbd2c0db20.0080580.0141660.010283-0.15979009240.7413810.0000881.3033090.0001540.9460210.000112133-75.2459310.800000-0.746156-0.5657590.1038893.267681182.012.01.3684213.5980865.4198921.519850e+091.510445e+090-3-1.2857141.054113-0.295876717070.5714290.246753-0.29197842...13345.4060151122213.0451130231721.7819551523016.0977441311726-78.531851-0.5904650.304197-0.7461560.049641-39.942089-52.97710856.000000513.6844303.263895-0.008014-0.0106060.0114292.102078e-053.2692211080.8120302119222811119
52016-09-01C_ID_0894217f2f0.0107120.0087520.0102830.871582051835.5486040.0000214.5335990.0000175.3265090.00002033-13.7762310.033719-0.679289-0.4174620.0331050.79659399.010.03.0000003.8750001.9101561.501343e+091.484068e+090-6-2.5454554.130682-0.262901787777.6060610.246212-0.45507410...3374.454545171314.2424240231617.7575762301718.030303429814-7.696680-0.2332330.011240-0.6792890.049340-32.411890-52.9845042.630120200.8205590.782867-0.005377-0.0087090.0004325.459915e-060.8092881996.03030323332533131331
62016-12-01C_ID_7e63323c000.0104790.0087520.0114280.230103042744.4746990.0000253.7371560.0000204.8795510.000027260-185.421580-0.550722-0.742129-0.7131600.0009182.4040770.00.00.0000000.0000000.0000001.519402e+091.483619e+090-13-6.64615417.874309-0.012556717070.8192310.148663-1.66873119...260126.0153851121614.3807690214823.9461541513113.0653851311223-inf-inf-inf-infNaN-50.503954-52.658110-39.1012374.5330762.421714-0.010071-0.010602-0.0077571.919725e-072.2454444141.5923082124253935449
72017-09-01C_ID_dfa21fc1240.0104790.0087520.0114282.136719015331.6033460.0000681.3390750.0000571.7484110.00007522-13.565845-0.055688-0.745405-0.6166290.0330532.2044530.00.00.0000000.0000000.0000001.513885e+091.506634e+090-3-1.7272730.9696970.378094737272.3181820.2272730.8390474...22410.272727912916.409091023843.27272739511019.90909142967-inf-inf-inf-infNaN-44.617084-54.414575-4.009554173.9863262.195383-0.008522-0.010353-0.0007736.286973e-062.208211833.7727272188227227111
82017-08-01C_ID_fe0fdac8ea0.0106100.0113850.010283-0.065430018431.9522200.0000582.0947980.0000621.8920420.00005615-8.708374-0.251424-0.746156-0.5805580.0258190.76157116.02.01.0666670.0666673.8729831.512825e+091.503073e+09-2-6-4.2000001.6000000.674373717171.0000000.0000000.0000002...1559.800000812813.666667422639.533333334985.93333321844-8.582663-0.572178-0.125712-0.7461560.032784-41.219639-52.977108-17.851075130.1541110.761571-0.008177-0.010509-0.0035415.121822e-060.7615711127.4666672200231317130
92016-08-01C_ID_bf62c0b49d0.0106100.0087520.0102830.300049054935.8248290.0000194.8049150.0000165.6452760.000019113-76.997124-0.371335-0.743301-0.6813900.0071532.2062323.01.00.0265490.0260755.9696941.519837e+091.483978e+090-13-5.87610617.466656-0.186689717070.8141590.152655-1.63711813...113125.2566371121414.6902650203320.6371681512512.5663721311329-inf-inf-0.657906-infNaN-48.252794-52.774403-25.99346035.9313032.212971-0.009622-0.010606-0.0052331.429789e-062.1831714153.67256621192534161576
\n
"},"metadata":{}}]},{"cell_type":"code","source":"# Taking Reference from Other Kernels\ndef aggregate_transaction_new(trans, prefix): \n \n agg_func = {\n 'purchase_amount' : ['sum','max','min','mean','var','skew'],\n 'installments' : ['sum','max','mean','var','skew'],\n 'purchase_date' : ['max','min'],\n 'month_lag' : ['max','min','mean','var','skew'],\n 'month_diff' : ['max','min','mean','var','skew'],\n 'weekend' : ['sum', 'mean'],\n 'weekday' : ['sum', 'mean'],\n 'authorized_flag': ['sum', 'mean'],\n 'category_1': ['sum','mean', 'max','min'],\n 'card_id' : ['size','count'],\n 'month': ['nunique', 'mean', 'min', 'max'],\n 'hour': ['nunique', 'mean', 'min', 'max'],\n 'weekofyear': ['nunique', 'mean', 'min', 'max'],\n 'day': ['nunique', 'mean', 'min', 'max'],\n 'subsector_id': ['nunique'],\n 'merchant_category_id' : ['nunique'],\n 'price' :['sum','mean','max','min','var'],\n 'duration' : ['mean','min','max','var','skew'],\n 'amount_month_ratio':['mean','min','max','var','skew']\n }\n \n agg_trans = trans.groupby(['card_id']).agg(agg_func)\n agg_trans.columns = [prefix + '_'.join(col).strip() \n for col in agg_trans.columns.values]\n agg_trans.reset_index(inplace=True)\n \n df = (trans.groupby('card_id')\n .size()\n .reset_index(name='{}transactions_count'.format(prefix)))\n \n agg_trans = pd.merge(df, agg_trans, on='card_id', how='left')\n \n return agg_trans","metadata":{"_uuid":"88381a0c6e50924860a133e7d61838c86ee1eab1","execution":{"iopub.status.busy":"2023-12-19T12:41:31.025629Z","iopub.execute_input":"2023-12-19T12:41:31.025949Z","iopub.status.idle":"2023-12-19T12:41:31.0557Z","shell.execute_reply.started":"2023-12-19T12:41:31.025898Z","shell.execute_reply":"2023-12-19T12:41:31.054409Z"},"trusted":true},"execution_count":21,"outputs":[]},{"cell_type":"code","source":"# Now extract the data from the new transactions\nnew_transactions = reduce_mem_usage(pd.read_csv('../input/new_merchant_transactions.csv'))","metadata":{"_uuid":"9c653335214ef763a6d9e13de46db5800a75c5a3","execution":{"iopub.status.busy":"2023-12-19T12:41:31.057768Z","iopub.execute_input":"2023-12-19T12:41:31.058227Z","iopub.status.idle":"2023-12-19T12:41:41.185884Z","shell.execute_reply.started":"2023-12-19T12:41:31.058157Z","shell.execute_reply":"2023-12-19T12:41:41.184679Z"},"trusted":true},"execution_count":22,"outputs":[{"name":"stdout","text":"Mem. usage decreased to 114.20 Mb (45.5% reduction)\n","output_type":"stream"}]},{"cell_type":"code","source":"#impute missing values\nnew_transactions['category_2'] = new_transactions['category_2'].fillna(1.0,inplace=True)\nnew_transactions['category_3'] = new_transactions['category_3'].fillna('A',inplace=True)\nnew_transactions['merchant_id'] = new_transactions['merchant_id'].fillna('M_ID_00a6ca8a8a',inplace=True)\nnew_transactions['installments'].replace(-1, np.nan,inplace=True)\nnew_transactions['installments'].replace(999, np.nan,inplace=True)\nnew_transactions['purchase_amount'] = new_transactions['purchase_amount'].apply(lambda x: min(x, 0.8))\n\n#Feature Engineering - Adding new features inspired by Chau's first kernel\nnew_transactions['authorized_flag'] = new_transactions['authorized_flag'].map({'Y': 1, 'N': 0})\nnew_transactions['category_1'] = new_transactions['category_1'].map({'Y': 1, 'N': 0})\nnew_transactions['category_3'] = new_transactions['category_3'].map({'A':0, 'B':1, 'C':2}) \n\nnew_transactions['purchase_date'] = pd.to_datetime(new_transactions['purchase_date'])\nnew_transactions['month'] = new_transactions['purchase_date'].dt.month\nnew_transactions['weekofyear'] = new_transactions['purchase_date'].dt.weekofyear\nnew_transactions['day'] = new_transactions['purchase_date'].dt.day\nnew_transactions['weekday'] = new_transactions.purchase_date.dt.weekday\nnew_transactions['weekend'] = (new_transactions.purchase_date.dt.weekday >=5).astype(int)\nnew_transactions['hour'] = new_transactions['purchase_date'].dt.hour \nnew_transactions['month_diff'] = ((datetime.datetime.today() - new_transactions['purchase_date']).dt.days)//30\nnew_transactions['month_diff'] += new_transactions['month_lag']\n\ngc.collect()\n\n# additional features\nnew_transactions['duration'] = new_transactions['purchase_amount']*new_transactions['month_diff']\nnew_transactions['amount_month_ratio'] = new_transactions['purchase_amount']/new_transactions['month_diff']\nnew_transactions['price'] = new_transactions['purchase_amount'] / new_transactions['installments']\n\naggs = {\n 'mean': ['mean'],\n }\n\nfor col in ['category_2','category_3']:\n new_transactions[col+'_mean'] = new_transactions['purchase_amount'].groupby(new_transactions[col]).agg('mean')\n new_transactions[col+'_max'] = new_transactions['purchase_amount'].groupby(new_transactions[col]).agg('max')\n new_transactions[col+'_min'] = new_transactions['purchase_amount'].groupby(new_transactions[col]).agg('min')\n new_transactions[col+'_var'] = new_transactions['purchase_amount'].groupby(new_transactions[col]).agg('var')\n aggs[col+'_mean'] = ['mean']\n\ngc.collect()","metadata":{"_uuid":"fd7fc65f351e45fdd1e8a43b730b8ed50b2e4456","execution":{"iopub.status.busy":"2023-12-19T12:41:41.187961Z","iopub.execute_input":"2023-12-19T12:41:41.188633Z","iopub.status.idle":"2023-12-19T12:41:50.613115Z","shell.execute_reply.started":"2023-12-19T12:41:41.188321Z","shell.execute_reply":"2023-12-19T12:41:50.611037Z"},"trusted":true},"execution_count":23,"outputs":[{"execution_count":23,"output_type":"execute_result","data":{"text/plain":"189"},"metadata":{}}]},{"cell_type":"code","source":"merge_new = aggregate_transaction_new(new_transactions, prefix='new_')\ndel new_transactions\ngc.collect()\n\ntrain = pd.merge(train, merge_new, on='card_id',how='left')\ntest = pd.merge(test, merge_new, on='card_id',how='left')\ndel merge_new\n\ngc.collect()","metadata":{"_uuid":"5ebf2d2ac4064c8e9a008f555c7f902ca0fdf853","execution":{"iopub.status.busy":"2023-12-19T12:41:50.61457Z","iopub.execute_input":"2023-12-19T12:41:50.614887Z","iopub.status.idle":"2023-12-19T12:49:00.406508Z","shell.execute_reply.started":"2023-12-19T12:41:50.614834Z","shell.execute_reply":"2023-12-19T12:49:00.405412Z"},"trusted":true},"execution_count":24,"outputs":[{"execution_count":24,"output_type":"execute_result","data":{"text/plain":"28"},"metadata":{}}]},{"cell_type":"code","source":"#Feature Engineering - Adding new features inspired by Chau's first kernel\ntrain['new_purchase_date_max'] = pd.to_datetime(train['new_purchase_date_max'])\ntrain['new_purchase_date_min'] = pd.to_datetime(train['new_purchase_date_min'])\ntrain['new_purchase_date_diff'] = (train['new_purchase_date_max'] - train['new_purchase_date_min']).dt.days\ntrain['new_purchase_date_average'] = train['new_purchase_date_diff']/train['new_card_id_size']\ntrain['new_purchase_date_uptonow'] = (datetime.datetime.today() - train['new_purchase_date_max']).dt.days\ntrain['new_purchase_date_uptomin'] = (datetime.datetime.today() - train['new_purchase_date_min']).dt.days\ntrain['new_first_buy'] = (train['new_purchase_date_min'] - train['first_active_month']).dt.days\ntrain['new_last_buy'] = (train['new_purchase_date_max'] - train['first_active_month']).dt.days\nfor feature in ['new_purchase_date_max','new_purchase_date_min']:\n train[feature] = train[feature].astype(np.int64) * 1e-9\n\n#Feature Engineering - Adding new features inspired by Chau's first kernel\ntest['new_purchase_date_max'] = pd.to_datetime(test['new_purchase_date_max'])\ntest['new_purchase_date_min'] = pd.to_datetime(test['new_purchase_date_min'])\ntest['new_purchase_date_diff'] = (test['new_purchase_date_max'] - test['new_purchase_date_min']).dt.days\ntest['new_purchase_date_average'] = test['new_purchase_date_diff']/test['new_card_id_size']\ntest['new_purchase_date_uptonow'] = (datetime.datetime.today() - test['new_purchase_date_max']).dt.days\ntest['new_purchase_date_uptomin'] = (datetime.datetime.today() - test['new_purchase_date_min']).dt.days\ntest['new_first_buy'] = (test['new_purchase_date_min'] - test['first_active_month']).dt.days\ntest['new_last_buy'] = (test['new_purchase_date_max'] - test['first_active_month']).dt.days\n\nfor feature in ['new_purchase_date_max','new_purchase_date_min']:\n test[feature] = test[feature].astype(np.int64) * 1e-9\n \ngc.collect()","metadata":{"_uuid":"4741d24d2c897ebd286807d0d3bd658800e316ca","execution":{"iopub.status.busy":"2023-12-19T12:49:00.408153Z","iopub.execute_input":"2023-12-19T12:49:00.408487Z","iopub.status.idle":"2023-12-19T12:49:00.623515Z","shell.execute_reply.started":"2023-12-19T12:49:00.408411Z","shell.execute_reply":"2023-12-19T12:49:00.62257Z"},"trusted":true},"execution_count":25,"outputs":[{"execution_count":25,"output_type":"execute_result","data":{"text/plain":"184"},"metadata":{}}]},{"cell_type":"code","source":"#NEW Features referred from https://www.kaggle.com/mfjwr1/simple-lightgbm-without-blending\ntrain['card_id_total'] = train['new_card_id_size']+train['hist_card_id_size']\ntrain['card_id_cnt_total'] = train['new_card_id_count']+train['hist_card_id_count']\ntrain['card_id_cnt_ratio'] = train['new_card_id_count']/train['hist_card_id_count']\ntrain['purchase_amount_total'] = train['new_purchase_amount_sum']+train['hist_purchase_amount_sum']\ntrain['purchase_amount_mean'] = train['new_purchase_amount_mean']+train['hist_purchase_amount_mean']\ntrain['purchase_amount_max'] = train['new_purchase_amount_max']+train['hist_purchase_amount_max']\ntrain['purchase_amount_min'] = train['new_purchase_amount_min']+train['hist_purchase_amount_min']\ntrain['purchase_amount_ratio'] = train['new_purchase_amount_sum']/train['hist_purchase_amount_sum']\ntrain['month_diff_mean'] = train['new_month_diff_mean']+train['hist_month_diff_mean']\ntrain['month_diff_ratio'] = train['new_month_diff_mean']/train['hist_month_diff_mean']\ntrain['month_lag_mean'] = train['new_month_lag_mean']+train['hist_month_lag_mean']\ntrain['month_lag_max'] = train['new_month_lag_max']+train['hist_month_lag_max']\ntrain['month_lag_min'] = train['new_month_lag_min']+train['hist_month_lag_min']\ntrain['category_1_mean'] = train['new_category_1_mean']+train['hist_category_1_mean']\ntrain['installments_total'] = train['new_installments_sum']+train['hist_installments_sum']\ntrain['installments_mean'] = train['new_installments_mean']+train['hist_installments_mean']\ntrain['installments_max'] = train['new_installments_max']+train['hist_installments_max']\ntrain['installments_ratio'] = train['new_installments_sum']/train['hist_installments_sum']\ntrain['price_total'] = train['purchase_amount_total'] / train['installments_total']\ntrain['price_mean'] = train['purchase_amount_mean'] / train['installments_mean']\ntrain['price_max'] = train['purchase_amount_max'] / train['installments_max']\ntrain['duration_mean'] = train['new_duration_mean']+train['hist_duration_mean']\ntrain['duration_min'] = train['new_duration_min']+train['hist_duration_min']\ntrain['duration_max'] = train['new_duration_max']+train['hist_duration_max']\ntrain['amount_month_ratio_mean']=train['new_amount_month_ratio_mean']+train['hist_amount_month_ratio_mean']\ntrain['amount_month_ratio_min']=train['new_amount_month_ratio_min']+train['hist_amount_month_ratio_min']\ntrain['amount_month_ratio_max']=train['new_amount_month_ratio_max']+train['hist_amount_month_ratio_max']\ntrain['new_CLV'] = train['new_card_id_count'] * train['new_purchase_amount_sum'] / train['new_month_diff_mean']\ntrain['hist_CLV'] = train['hist_card_id_count'] * train['hist_purchase_amount_sum'] / train['hist_month_diff_mean']\ntrain['CLV_ratio'] = train['new_CLV'] / train['hist_CLV']\n\ntest['card_id_total'] = test['new_card_id_size']+test['hist_card_id_size']\ntest['card_id_cnt_total'] = test['new_card_id_count']+test['hist_card_id_count']\ntest['card_id_cnt_ratio'] = test['new_card_id_count']/test['hist_card_id_count']\ntest['purchase_amount_total'] = test['new_purchase_amount_sum']+test['hist_purchase_amount_sum']\ntest['purchase_amount_mean'] = test['new_purchase_amount_mean']+test['hist_purchase_amount_mean']\ntest['purchase_amount_max'] = test['new_purchase_amount_max']+test['hist_purchase_amount_max']\ntest['purchase_amount_min'] = test['new_purchase_amount_min']+test['hist_purchase_amount_min']\ntest['purchase_amount_ratio'] = test['new_purchase_amount_sum']/test['hist_purchase_amount_sum']\ntest['month_diff_mean'] = test['new_month_diff_mean']+test['hist_month_diff_mean']\ntest['month_diff_ratio'] = test['new_month_diff_mean']/test['hist_month_diff_mean']\ntest['month_lag_mean'] = test['new_month_lag_mean']+test['hist_month_lag_mean']\ntest['month_lag_max'] = test['new_month_lag_max']+test['hist_month_lag_max']\ntest['month_lag_min'] = test['new_month_lag_min']+test['hist_month_lag_min']\ntest['category_1_mean'] = test['new_category_1_mean']+test['hist_category_1_mean']\ntest['installments_total'] = test['new_installments_sum']+test['hist_installments_sum']\ntest['installments_mean'] = test['new_installments_mean']+test['hist_installments_mean']\ntest['installments_max'] = test['new_installments_max']+test['hist_installments_max']\ntest['installments_ratio'] = test['new_installments_sum']/test['hist_installments_sum']\ntest['price_total'] = test['purchase_amount_total'] / test['installments_total']\ntest['price_mean'] = test['purchase_amount_mean'] / test['installments_mean']\ntest['price_max'] = test['purchase_amount_max'] / test['installments_max']\ntest['duration_mean'] = test['new_duration_mean']+test['hist_duration_mean']\ntest['duration_min'] = test['new_duration_min']+test['hist_duration_min']\ntest['duration_max'] = test['new_duration_max']+test['hist_duration_max']\ntest['amount_month_ratio_mean']=test['new_amount_month_ratio_mean']+test['hist_amount_month_ratio_mean']\ntest['amount_month_ratio_min']=test['new_amount_month_ratio_min']+test['hist_amount_month_ratio_min']\ntest['amount_month_ratio_max']=test['new_amount_month_ratio_max']+test['hist_amount_month_ratio_max']\ntest['new_CLV'] = test['new_card_id_count'] * test['new_purchase_amount_sum'] / test['new_month_diff_mean']\ntest['hist_CLV'] = test['hist_card_id_count'] * test['hist_purchase_amount_sum'] / test['hist_month_diff_mean']\ntest['CLV_ratio'] = test['new_CLV'] / test['hist_CLV']","metadata":{"_uuid":"12b0f46661a53ead1c430acc0ec0a83eee4d3b0f","execution":{"iopub.status.busy":"2023-12-19T12:49:00.625304Z","iopub.execute_input":"2023-12-19T12:49:00.625598Z","iopub.status.idle":"2023-12-19T12:49:01.096557Z","shell.execute_reply.started":"2023-12-19T12:49:00.625549Z","shell.execute_reply":"2023-12-19T12:49:01.095384Z"},"trusted":true},"execution_count":26,"outputs":[]},{"cell_type":"code","source":"train.head(10)","metadata":{"_uuid":"e977529f1ee19cf2b79c1a08fbf65a10bc047f14","execution":{"iopub.status.busy":"2023-12-19T12:49:01.098244Z","iopub.execute_input":"2023-12-19T12:49:01.098658Z","iopub.status.idle":"2023-12-19T12:49:01.30804Z","shell.execute_reply.started":"2023-12-19T12:49:01.098589Z","shell.execute_reply":"2023-12-19T12:49:01.30695Z"},"trusted":true},"execution_count":27,"outputs":[{"execution_count":27,"output_type":"execute_result","data":{"text/plain":" first_active_month card_id ... hist_CLV CLV_ratio\n0 2017-06-01 C_ID_92a2005557 ... -615.815564 0.007001\n1 2017-01-01 C_ID_3d0044924f ... -1051.859154 0.000346\n2 2016-08-01 C_ID_d639edf6cd ... -17.757822 0.000563\n3 2017-09-01 C_ID_186d6a6901 ... -54.673907 0.008411\n4 2017-11-01 C_ID_cdbd2c0db2 ... -141.809640 0.071554\n5 2016-09-01 C_ID_0894217f2f ... -5.857991 0.012254\n6 2016-12-01 C_ID_7e63323c00 ... -680.741802 0.000373\n7 2017-09-01 C_ID_dfa21fc124 ... -4.126882 0.020989\n8 2017-08-01 C_ID_fe0fdac8ea ... -1.839797 0.019478\n9 2016-08-01 C_ID_bf62c0b49d ... -122.866318 0.000736\n\n[10 rows x 195 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
first_active_monthcard_idfeature_1feature_2feature_3targetoutliersdaysquarterdays_feature_1days_feature_1_ratiodays_feature_2days_feature_2_ratiodays_feature_3days_feature_3_ratiohist_transactions_counthist_purchase_amount_sumhist_purchase_amount_maxhist_purchase_amount_minhist_purchase_amount_meanhist_purchase_amount_varhist_purchase_amount_skewhist_installments_sumhist_installments_maxhist_installments_meanhist_installments_varhist_installments_skewhist_purchase_date_maxhist_purchase_date_minhist_month_lag_maxhist_month_lag_minhist_month_lag_meanhist_month_lag_varhist_month_lag_skewhist_month_diff_maxhist_month_diff_minhist_month_diff_meanhist_month_diff_varhist_month_diff_skewhist_weekend_sum...new_amount_month_ratio_minnew_amount_month_ratio_maxnew_amount_month_ratio_varnew_amount_month_ratio_skewnew_purchase_date_diffnew_purchase_date_averagenew_purchase_date_uptonownew_purchase_date_uptominnew_first_buynew_last_buycard_id_totalcard_id_cnt_totalcard_id_cnt_ratiopurchase_amount_totalpurchase_amount_meanpurchase_amount_maxpurchase_amount_minpurchase_amount_ratiomonth_diff_meanmonth_diff_ratiomonth_lag_meanmonth_lag_maxmonth_lag_mincategory_1_meaninstallments_totalinstallments_meaninstallments_maxinstallments_ratioprice_totalprice_meanprice_maxduration_meanduration_minduration_maxamount_month_ratio_meanamount_month_ratio_minamount_month_ratio_maxnew_CLVhist_CLVCLV_ratio
02017-06-01C_ID_92a20055570.0131450.0087520.011428-0.820312024523.2204310.0000542.1442700.0000362.7997430.000047260-167.4271340.800000-0.739395-0.6439510.0205615.1354884.01.00.0153850.0152067.9207701.519551e+091.498573e+090-8-3.9115385.7489010.065960717070.6884620.215310-0.81860490...-0.010352-0.0041713.686011e-060.90047254.02.3478262060.02114.0277.0332.0283.0283.00.088462-180.671030-1.2197720.503857-1.4640040.079102141.3406350.999487-2.4332782.0-7.00.0000004.00.0153851.00.000000-45.167758-79.2851870.503857-86.201035-103.59759936.070020-0.017261-0.0208930.007097-4.311398-615.8155640.007001
12017-01-01C_ID_3d0044924f0.0107120.0113850.0102830.392822039614.2417900.0000274.5083700.0000294.0720030.000026350-215.3949950.800000-0.742400-0.6154140.0585983.747456545.010.01.5660922.2578673.8011781.517438e+091.483720e+090-12-5.03142914.477519-0.258151727171.6714290.221244-0.733105132...-0.010267-0.0098832.454318e-080.79398656.09.3333332090.02146.0396.0453.0356.0356.00.017143-219.750464-1.3413260.098340-1.4816580.020221143.5047621.002259-3.5314292.0-11.00.088571551.02.56609211.00.011009-0.398821-0.5227110.008940-96.255699-106.6793497.782129-0.018692-0.0207030.001385-0.363798-1051.8591540.000346
22016-08-01C_ID_d639edf6cd0.0106100.0087520.0102830.687988054935.8248290.0000194.8049150.0000165.6452760.00001943-29.167391-0.145847-0.730138-0.6783110.0076355.6261980.00.00.0000000.0000000.0000001.519759e+091.484123e+090-13-8.60465114.7685490.725371717070.6279070.239203-0.54856211...-0.010003-0.010003NaNNaN0.00.0000002060.02060.0635.0635.044.044.00.023256-29.867586-1.378507-0.846043-1.4303330.024006140.6279070.991110-6.6046512.0-11.00.0000000.00.0000000.0NaN-inf-inf-inf-96.934306-100.853483-59.222984-0.019605-0.020286-0.012086-0.010003-17.7578220.000563
32017-09-01C_ID_186d6a69010.0107120.0141660.0102830.142456015331.6388740.0000702.1674600.0000931.5732740.00006777-50.1369600.800000-0.740897-0.6511290.0383815.75752986.03.01.1466670.2349553.3053031.519818e+091.506443e+090-5-2.8311693.2474370.557757717070.6103900.240943-0.46177511...-0.010343-0.0079848.177220e-070.80910541.05.8571432071.02113.0187.0229.084.084.00.090909-54.791745-1.3160990.233105-1.4752720.092841141.4675321.003495-1.1168832.0-4.00.29870192.02.1466674.00.069767-0.595562-0.6130890.058276-93.110264-104.58536115.750488-0.018604-0.0209280.003444-0.459848-54.6739070.008411
42017-11-01C_ID_cdbd2c0db20.0080580.0141660.010283-0.15979009240.7413810.0000881.3033090.0001540.9460210.000112133-75.2459310.800000-0.746156-0.5657590.1038893.267681182.012.01.3684213.5980865.4198921.519850e+091.510445e+090-3-1.2857141.054113-0.295876717070.5714290.246753-0.29197842...-0.0104560.0063519.995584e-062.88505057.01.5833332060.02118.0121.0178.0169.0169.00.270677-95.172079-1.1192631.250928-1.4854140.264814141.2658731.0017430.2698412.0-2.00.168338218.02.39699214.00.197802-0.436569-0.4669450.089352-79.067886-105.46441388.015869-0.015845-0.0210620.017780-10.147068-141.8096400.071554
52016-09-01C_ID_0894217f2f0.0107120.0087520.0102830.871582051835.5486040.0000214.5335990.0000175.3265090.00002033-13.7762310.033719-0.679289-0.4174620.0331050.79659399.010.03.0000003.8750001.9101561.501343e+091.484068e+090-6-2.5454554.130682-0.262901787777.6060610.246212-0.45507410...-0.008388-0.0000011.291167e-050.40161431.07.7500002285.02317.0348.0379.037.037.00.121212-15.175979-0.7673990.033629-1.3335850.101606155.6060611.005076-0.7954552.0-5.00.030303110.05.75000015.00.111111-0.137963-0.1334610.002242-59.706984-104.0196602.623086-0.009863-0.0170970.000431-0.071782-5.8579910.012254
62016-12-01C_ID_7e63323c000.0104790.0087520.0114280.230103042744.4746990.0000253.7371560.0000204.8795510.000027260-185.421580-0.550722-0.742129-0.7131600.0009182.4040770.00.00.0000000.0000000.0000001.519402e+091.483619e+090-13-6.64615417.874309-0.012556717070.8192310.148663-1.66873119...-0.010453-0.0096977.608963e-081.24945331.06.2000002082.02114.0460.0491.0265.0265.00.019231-189.024119-1.433668-1.239198-1.4843170.019429141.8192311.002553-5.4461542.0-12.00.0000000.00.0000000.0NaN-inf-inf-inf-101.660009-105.353422-87.983073-0.020219-0.021055-0.017453-0.253700-680.7418020.000373
72017-09-01C_ID_dfa21fc1240.0104790.0087520.0114282.136719015331.6033460.0000681.3390750.0000571.7484110.00007522-13.565845-0.055688-0.745405-0.6166290.0330532.2044530.00.00.0000000.0000000.0000001.513885e+091.506634e+090-3-1.7272730.9696970.378094737272.3181820.2272730.8390474...-0.009684-0.0095782.930873e-09-1.01868312.04.0000002129.02142.0158.0170.025.025.00.136364-15.663989-1.316011-0.752954-1.4470650.154664144.9848481.0048190.2727272.0-1.00.0000000.00.0000000.0NaN-inf-inf-inf-95.439512-105.635766-54.212679-0.018147-0.020037-0.010352-0.086621-4.1268820.020989
82017-08-01C_ID_fe0fdac8ea0.0106100.0113850.010283-0.065430018431.9522200.0000582.0947980.0000621.8920420.00005615-8.708374-0.251424-0.746156-0.5805580.0258190.76157116.02.01.0666670.0666673.8729831.512825e+091.503073e+09-2-6-4.2000001.6000000.674373717171.0000000.0000000.0000002...-0.009752-0.0081771.239812e-06NaN3.01.5000002099.02102.0228.0231.017.017.00.133333-9.971558-1.212150-0.831990-1.4287740.145054141.5000000.992958-3.200000-1.0-5.00.26666718.02.0666673.00.125000-0.553975-0.586524-0.277330-85.721348-100.760311-59.071290-0.017141-0.020261-0.011718-0.035835-1.8397970.019478
92016-08-01C_ID_bf62c0b49d0.0106100.0087520.0102830.300049054935.8248290.0000194.8049150.0000165.6452760.000019113-76.997124-0.371335-0.743301-0.6813900.0071532.2062323.01.00.0265490.0260755.9696941.519837e+091.483978e+090-13-5.87610617.466656-0.186689717070.8141590.152655-1.63711813...-0.010446-0.0093813.380237e-071.6341477.02.3333332080.02088.0608.0615.0116.0116.00.026549-79.137261-1.394769-1.037351-1.4850010.027795141.8141591.002624-3.8761062.0-11.00.0000003.00.0265491.00.000000-26.379087-52.536313-1.037351-98.902696-105.435048-73.280570-0.019670-0.021052-0.014614-0.090428-122.8663180.000736
\n
"},"metadata":{}}]},{"cell_type":"code","source":"train = train.drop(['card_id', 'first_active_month'], axis = 1)\ntest = test.drop(['card_id', 'first_active_month'], axis = 1)","metadata":{"_uuid":"b9aa541a016e5f0c3c66d9eebd30e6c713711d6a","execution":{"iopub.status.busy":"2023-12-19T12:49:01.309519Z","iopub.execute_input":"2023-12-19T12:49:01.309829Z","iopub.status.idle":"2023-12-19T12:49:01.835054Z","shell.execute_reply.started":"2023-12-19T12:49:01.309778Z","shell.execute_reply":"2023-12-19T12:49:01.834138Z"},"trusted":true},"execution_count":28,"outputs":[]},{"cell_type":"code","source":"# Get the X and Y\ndf_train_columns = [c for c in train.columns if c not in ['first_active_month', 'target', 'card_id', 'outliers',\n 'hist_purchase_date_max', 'hist_purchase_date_min', 'hist_card_id_size',\n 'new_purchase_date_max', 'new_purchase_date_min', 'new_card_id_size']] \ntarget = train['target']\ndel train['target']","metadata":{"_uuid":"d8323aef4eb43a9821d808578fa00514fc1ea063","execution":{"iopub.status.busy":"2023-12-19T12:49:01.836785Z","iopub.execute_input":"2023-12-19T12:49:01.837059Z","iopub.status.idle":"2023-12-19T12:49:01.844817Z","shell.execute_reply.started":"2023-12-19T12:49:01.837017Z","shell.execute_reply":"2023-12-19T12:49:01.843651Z"},"trusted":true},"execution_count":29,"outputs":[]},{"cell_type":"code","source":"train.shape","metadata":{"_uuid":"1067b18790d511ed78b7ad1896bba120dcdf2990","execution":{"iopub.status.busy":"2023-12-19T12:49:01.846491Z","iopub.execute_input":"2023-12-19T12:49:01.846878Z","iopub.status.idle":"2023-12-19T12:49:01.85675Z","shell.execute_reply.started":"2023-12-19T12:49:01.846786Z","shell.execute_reply":"2023-12-19T12:49:01.855871Z"},"trusted":true},"execution_count":30,"outputs":[{"execution_count":30,"output_type":"execute_result","data":{"text/plain":"(201917, 192)"},"metadata":{}}]},{"cell_type":"code","source":"test.shape","metadata":{"execution":{"iopub.status.busy":"2023-12-19T12:49:01.858405Z","iopub.execute_input":"2023-12-19T12:49:01.858916Z","iopub.status.idle":"2023-12-19T12:49:01.870869Z","shell.execute_reply.started":"2023-12-19T12:49:01.858848Z","shell.execute_reply":"2023-12-19T12:49:01.869934Z"},"trusted":true},"execution_count":31,"outputs":[{"execution_count":31,"output_type":"execute_result","data":{"text/plain":"(123623, 191)"},"metadata":{}}]},{"cell_type":"code","source":"pd.set_option('display.max_columns', None)","metadata":{"execution":{"iopub.status.busy":"2023-12-19T12:49:01.87238Z","iopub.execute_input":"2023-12-19T12:49:01.87269Z","iopub.status.idle":"2023-12-19T12:49:01.88271Z","shell.execute_reply.started":"2023-12-19T12:49:01.872642Z","shell.execute_reply":"2023-12-19T12:49:01.881599Z"},"trusted":true},"execution_count":32,"outputs":[]},{"cell_type":"code","source":"test.dropna(inplace=True)","metadata":{"execution":{"iopub.status.busy":"2023-12-19T12:49:01.88461Z","iopub.execute_input":"2023-12-19T12:49:01.884891Z","iopub.status.idle":"2023-12-19T12:49:02.371289Z","shell.execute_reply.started":"2023-12-19T12:49:01.884846Z","shell.execute_reply":"2023-12-19T12:49:02.370296Z"},"trusted":true},"execution_count":33,"outputs":[]},{"cell_type":"code","source":"test","metadata":{"execution":{"iopub.status.busy":"2023-12-19T12:49:02.372896Z","iopub.execute_input":"2023-12-19T12:49:02.373233Z","iopub.status.idle":"2023-12-19T12:49:03.073416Z","shell.execute_reply.started":"2023-12-19T12:49:02.373179Z","shell.execute_reply":"2023-12-19T12:49:03.072557Z"},"trusted":true},"execution_count":34,"outputs":[{"execution_count":34,"output_type":"execute_result","data":{"text/plain":" feature_1 feature_2 feature_3 days quarter days_feature_1 \\\n0 0.010479 0.014166 0.011428 306.0 2.0 3.206693 \n1 0.010610 0.014166 0.010283 396.0 1.0 4.201516 \n3 0.010610 0.011385 0.010283 62.0 4.0 0.657813 \n4 0.013145 0.011385 0.011428 793.0 4.0 10.423680 \n6 0.008058 0.008752 0.010283 123.0 4.0 0.991194 \n9 0.013145 0.011385 0.011428 702.0 1.0 9.227520 \n15 0.010610 0.014166 0.010283 92.0 4.0 0.976110 \n17 0.010712 0.014166 0.010283 153.0 3.0 1.638874 \n18 0.010479 0.014166 0.011428 92.0 4.0 0.964104 \n19 0.010610 0.011385 0.010283 396.0 1.0 4.201516 \n21 0.010610 0.011385 0.010283 245.0 2.0 2.599423 \n23 0.013145 0.011385 0.011428 153.0 3.0 2.011126 \n30 0.010479 0.011385 0.011428 365.0 1.0 3.824977 \n32 0.010479 0.014166 0.011428 306.0 2.0 3.206693 \n34 0.010712 0.011385 0.010283 337.0 1.0 3.609806 \n35 0.010610 0.011385 0.010283 123.0 4.0 1.305016 \n37 0.010479 0.014166 0.011428 215.0 3.0 2.253068 \n38 0.010610 0.011385 0.010283 337.0 1.0 3.575533 \n49 0.013145 0.011385 0.011428 153.0 3.0 2.011126 \n53 0.010610 0.011385 0.010283 62.0 4.0 0.657813 \n56 0.010610 0.014166 0.010283 245.0 2.0 2.599423 \n59 0.010610 0.011385 0.010283 123.0 4.0 1.305016 \n64 0.010610 0.011385 0.010283 306.0 2.0 3.246626 \n66 0.010610 0.011385 0.010283 306.0 2.0 3.246626 \n67 0.013145 0.011385 0.011428 518.0 3.0 6.808911 \n69 0.010610 0.011385 0.010283 153.0 3.0 1.623313 \n73 0.010479 0.014166 0.011428 92.0 4.0 0.964104 \n82 0.010610 0.011385 0.010283 92.0 4.0 0.976110 \n85 0.008058 0.014166 0.010283 92.0 4.0 0.741381 \n88 0.010712 0.011385 0.010283 306.0 2.0 3.277747 \n... ... ... ... ... ... ... \n123530 0.008058 0.014166 0.010283 245.0 2.0 1.974329 \n123531 0.010610 0.014166 0.010283 184.0 3.0 1.952220 \n123534 0.010479 0.014166 0.011428 1188.0 4.0 12.449513 \n123538 0.008058 0.011385 0.010283 123.0 4.0 0.991194 \n123545 0.008058 0.011385 0.010283 365.0 1.0 2.941348 \n123547 0.010610 0.011385 0.010283 306.0 2.0 3.246626 \n123552 0.010610 0.011385 0.010283 276.0 2.0 2.928329 \n123556 0.008058 0.011385 0.010283 184.0 3.0 1.482761 \n123557 0.010712 0.011385 0.010283 276.0 2.0 2.956399 \n123559 0.010479 0.014166 0.011428 92.0 4.0 0.964104 \n123560 0.010712 0.014166 0.010283 365.0 1.0 3.909731 \n123564 0.013145 0.011385 0.011428 184.0 3.0 2.418609 \n123565 0.010610 0.011385 0.010283 184.0 3.0 1.952220 \n123566 0.013145 0.011385 0.011428 1280.0 3.0 16.825108 \n123570 0.010712 0.014166 0.010283 123.0 4.0 1.317526 \n123571 0.010479 0.014166 0.011428 1249.0 3.0 13.088755 \n123572 0.008058 0.011385 0.010283 92.0 4.0 0.741381 \n123574 0.010610 0.011385 0.010283 215.0 3.0 2.281126 \n123577 0.010610 0.011385 0.010283 215.0 3.0 2.281126 \n123580 0.010610 0.011385 0.010283 306.0 2.0 3.246626 \n123583 0.010610 0.011385 0.010283 123.0 4.0 1.305016 \n123588 0.008058 0.014166 0.010283 215.0 3.0 1.732575 \n123592 0.010479 0.014166 0.011428 153.0 3.0 1.603346 \n123598 0.010712 0.011385 0.010283 92.0 4.0 0.985466 \n123601 0.010610 0.011385 0.010283 153.0 3.0 1.623313 \n123602 0.010712 0.014166 0.010283 396.0 1.0 4.241790 \n123603 0.008058 0.011385 0.010283 92.0 4.0 0.741381 \n123605 0.008058 0.011385 0.010283 276.0 2.0 2.224142 \n123606 0.013145 0.011385 0.011428 215.0 3.0 2.826092 \n123621 0.010610 0.011385 0.010283 245.0 2.0 2.599423 \n\n days_feature_1_ratio days_feature_2 days_feature_2_ratio \\\n0 0.000034 4.334919 0.000046 \n1 0.000027 5.609895 0.000036 \n3 0.000171 0.705856 0.000184 \n4 0.000017 9.028126 0.000014 \n6 0.000066 1.076511 0.000071 \n9 0.000019 7.992111 0.000016 \n15 0.000115 1.303309 0.000154 \n17 0.000070 2.167460 0.000093 \n18 0.000114 1.303309 0.000154 \n19 0.000027 4.508370 0.000029 \n21 0.000043 2.789270 0.000046 \n23 0.000086 1.741870 0.000074 \n30 0.000029 4.155443 0.000031 \n32 0.000034 4.334919 0.000046 \n34 0.000032 3.836669 0.000034 \n35 0.000086 1.400327 0.000093 \n37 0.000049 3.045777 0.000066 \n38 0.000031 3.836669 0.000034 \n49 0.000086 1.741870 0.000074 \n53 0.000171 0.705856 0.000184 \n56 0.000043 3.470769 0.000058 \n59 0.000086 1.400327 0.000093 \n64 0.000035 3.483741 0.000037 \n66 0.000035 3.483741 0.000037 \n67 0.000025 5.897313 0.000022 \n69 0.000069 1.741870 0.000074 \n73 0.000114 1.303309 0.000154 \n82 0.000115 1.047399 0.000124 \n85 0.000088 1.303309 0.000154 \n88 0.000035 3.483741 0.000037 \n... ... ... ... \n123530 0.000033 3.470769 0.000058 \n123531 0.000058 2.606618 0.000077 \n123534 0.000009 16.829686 0.000012 \n123538 0.000066 1.400327 0.000093 \n123545 0.000022 4.155443 0.000031 \n123547 0.000035 3.483741 0.000037 \n123552 0.000038 3.142198 0.000041 \n123556 0.000044 2.094798 0.000062 \n123557 0.000039 3.142198 0.000041 \n123559 0.000114 1.303309 0.000154 \n123560 0.000029 5.170737 0.000039 \n123564 0.000071 2.094798 0.000062 \n123565 0.000058 2.094798 0.000062 \n123566 0.000010 14.572511 0.000009 \n123570 0.000087 1.742467 0.000115 \n123571 0.000008 17.693837 0.000011 \n123572 0.000088 1.047399 0.000124 \n123574 0.000049 2.447726 0.000053 \n123577 0.000049 2.447726 0.000053 \n123580 0.000035 3.483741 0.000037 \n123583 0.000086 1.400327 0.000093 \n123588 0.000037 3.045777 0.000066 \n123592 0.000068 2.167460 0.000093 \n123598 0.000116 1.047399 0.000124 \n123601 0.000069 1.741870 0.000074 \n123602 0.000027 5.609895 0.000036 \n123603 0.000088 1.047399 0.000124 \n123605 0.000029 3.142198 0.000041 \n123606 0.000061 2.447726 0.000053 \n123621 0.000043 2.789270 0.000046 \n\n days_feature_3 days_feature_3_ratio hist_transactions_count \\\n0 3.496821 0.000037 68 \n1 4.072003 0.000026 78 \n3 0.637536 0.000166 26 \n4 9.062024 0.000014 110 \n6 1.264789 0.000084 48 \n9 8.022119 0.000016 48 \n15 0.946021 0.000112 11 \n17 1.573274 0.000067 61 \n18 1.051332 0.000124 29 \n19 4.072003 0.000026 81 \n21 2.519295 0.000042 97 \n23 1.748411 0.000075 23 \n30 4.171045 0.000031 262 \n32 3.496821 0.000037 110 \n34 3.465315 0.000031 645 \n35 1.264789 0.000084 20 \n37 2.456917 0.000053 52 \n38 3.465315 0.000031 89 \n49 1.748411 0.000075 76 \n53 0.637536 0.000166 32 \n56 2.519295 0.000042 45 \n59 1.264789 0.000084 100 \n64 3.146547 0.000034 64 \n66 3.146547 0.000034 75 \n67 5.919456 0.000022 7 \n69 1.573274 0.000067 12 \n73 1.051332 0.000124 23 \n82 0.946021 0.000112 49 \n85 0.946021 0.000112 85 \n88 3.146547 0.000034 346 \n... ... ... ... \n123530 2.519295 0.000042 69 \n123531 1.892042 0.000056 13 \n123534 13.575894 0.000010 42 \n123538 1.264789 0.000084 134 \n123545 3.753235 0.000028 333 \n123547 3.146547 0.000034 50 \n123552 2.838062 0.000037 43 \n123556 1.892042 0.000056 22 \n123557 2.838062 0.000037 189 \n123559 1.051332 0.000124 33 \n123560 3.753235 0.000028 85 \n123564 2.102664 0.000062 66 \n123565 1.892042 0.000056 10 \n123566 14.627226 0.000009 42 \n123570 1.264789 0.000084 33 \n123571 14.272973 0.000009 69 \n123572 0.946021 0.000112 94 \n123574 2.210810 0.000048 39 \n123577 2.210810 0.000048 13 \n123580 3.146547 0.000034 47 \n123583 1.264789 0.000084 18 \n123588 2.210810 0.000048 127 \n123592 1.748411 0.000075 28 \n123598 0.946021 0.000112 55 \n123601 1.573274 0.000067 36 \n123602 4.072003 0.000026 514 \n123603 0.946021 0.000112 216 \n123605 2.838062 0.000037 89 \n123606 2.456917 0.000053 54 \n123621 2.519295 0.000042 62 \n\n hist_purchase_amount_sum hist_purchase_amount_max \\\n0 -40.733733 0.235676 \n1 -49.136513 0.318817 \n3 -13.690715 0.087965 \n4 -46.093613 0.800000 \n6 -18.610816 0.743722 \n9 -29.421174 0.026356 \n15 -1.889265 0.800000 \n17 -35.480254 0.671595 \n18 -19.621950 -0.461404 \n19 -57.111504 0.154668 \n21 -62.275455 -0.054712 \n23 -12.784943 0.800000 \n30 -149.569871 0.760417 \n32 -70.761012 0.800000 \n34 -402.486298 0.800000 \n35 -9.076528 0.800000 \n37 -24.051612 0.800000 \n38 -56.061316 0.213286 \n49 -50.486300 0.070534 \n53 -19.702867 0.153180 \n56 -21.006402 0.650558 \n59 -68.672105 -0.242618 \n64 -40.207140 0.800000 \n66 -46.904189 0.513516 \n67 -3.396773 -0.206104 \n69 -5.197502 0.800000 \n73 -15.445391 -0.459511 \n82 -31.290532 -0.284091 \n85 -52.464961 0.043968 \n88 -218.394826 0.700972 \n... ... ... \n123530 -8.770417 0.800000 \n123531 -4.799175 0.800000 \n123534 -24.381793 -0.147350 \n123538 -77.864811 0.800000 \n123545 -114.608197 0.800000 \n123547 -21.363734 0.800000 \n123552 -27.673530 -0.296413 \n123556 -9.946815 0.680611 \n123557 -96.942271 0.800000 \n123559 -17.566007 0.328990 \n123560 -49.348402 0.071105 \n123564 -39.101283 0.755743 \n123565 -3.246523 0.634930 \n123566 -25.645237 0.755743 \n123570 -18.620132 -0.272611 \n123571 -43.277316 0.304948 \n123572 -59.050239 0.301943 \n123574 -23.386812 0.282408 \n123577 -5.904845 0.800000 \n123580 -24.258590 0.213286 \n123583 -8.768526 0.026958 \n123588 -80.662777 0.800000 \n123592 -15.056685 0.425160 \n123598 -30.012753 0.584441 \n123601 -24.003921 0.263851 \n123602 -319.051106 0.800000 \n123603 -129.923677 0.800000 \n123605 -46.285620 0.800000 \n123606 -13.588774 0.800000 \n123621 -39.123627 -0.115794 \n\n hist_purchase_amount_min hist_purchase_amount_mean \\\n0 -0.743903 -0.599025 \n1 -0.731881 -0.629955 \n3 -0.731881 -0.526566 \n4 -0.746758 -0.419033 \n6 -0.683887 -0.387725 \n9 -0.731881 -0.612941 \n15 -0.693804 -0.171751 \n17 -0.725871 -0.581644 \n18 -0.741062 -0.676619 \n19 -0.738643 -0.705080 \n21 -0.742099 -0.642015 \n23 -0.721513 -0.555867 \n30 -0.729687 -0.570877 \n32 -0.745405 -0.643282 \n34 -0.742415 -0.624010 \n35 -0.724368 -0.453826 \n37 -0.729477 -0.462531 \n38 -0.744443 -0.629902 \n49 -0.742400 -0.664293 \n53 -0.741859 -0.615715 \n56 -0.731896 -0.466809 \n59 -0.741498 -0.686721 \n64 -0.746156 -0.628237 \n66 -0.731881 -0.625389 \n67 -0.678883 -0.485253 \n69 -0.724368 -0.433125 \n73 -0.737141 -0.671539 \n82 -0.731881 -0.638582 \n85 -0.739019 -0.617235 \n88 -0.743151 -0.631199 \n... ... ... \n123530 -0.745405 -0.127107 \n123531 -0.724368 -0.369167 \n123534 -0.745405 -0.580519 \n123538 -0.740897 -0.581081 \n123545 -0.746156 -0.344169 \n123547 -0.726472 -0.427275 \n123552 -0.745405 -0.643570 \n123556 -0.686802 -0.452128 \n123557 -0.741348 -0.512922 \n123559 -0.731836 -0.532303 \n123560 -0.746156 -0.580569 \n123564 -0.723406 -0.592444 \n123565 -0.725119 -0.324652 \n123566 -0.729402 -0.610601 \n123570 -0.745405 -0.564246 \n123571 -0.737892 -0.627207 \n123572 -0.745405 -0.628194 \n123574 -0.739395 -0.599662 \n123577 -0.724368 -0.454219 \n123580 -0.738358 -0.516140 \n123583 -0.694465 -0.487140 \n123588 -0.745405 -0.635140 \n123592 -0.745405 -0.537739 \n123598 -0.727268 -0.545686 \n123601 -0.740431 -0.666776 \n123602 -0.745105 -0.620722 \n123603 -0.746156 -0.601499 \n123605 -0.746878 -0.520063 \n123606 -0.742415 -0.251644 \n123621 -0.737892 -0.631026 \n\n hist_purchase_amount_var hist_purchase_amount_skew \\\n0 0.036967 2.335008 \n1 0.024025 3.770723 \n3 0.048032 1.863770 \n4 0.248143 1.744851 \n6 0.106903 2.263653 \n9 0.024992 2.498140 \n15 0.268208 1.049076 \n17 0.043266 4.420414 \n18 0.008345 1.840385 \n19 0.011211 7.162982 \n21 0.020087 2.218796 \n23 0.091889 4.418935 \n30 0.066284 3.067938 \n32 0.048233 5.126908 \n34 0.036033 4.800378 \n35 0.296515 2.059834 \n37 0.109224 1.819521 \n38 0.039644 2.500260 \n49 0.013368 4.246150 \n53 0.040886 2.861635 \n56 0.075196 2.162051 \n59 0.007287 3.461134 \n64 0.054664 4.701807 \n66 0.026394 5.003554 \n67 0.025107 0.747104 \n69 0.264767 1.742257 \n73 0.004074 1.863901 \n82 0.011159 1.738731 \n85 0.017218 2.484953 \n88 0.033967 4.202115 \n... ... ... \n123530 0.273694 0.685207 \n123531 0.287538 1.901861 \n123534 0.023085 1.298955 \n123538 0.048074 3.402180 \n123545 0.168390 1.574247 \n123547 0.195996 2.159994 \n123552 0.010128 1.605423 \n123556 0.101214 2.512184 \n123557 0.071746 2.233143 \n123559 0.095467 1.598867 \n123560 0.033422 1.333102 \n123564 0.057648 4.038758 \n123565 0.287392 1.112143 \n123566 0.050437 5.747741 \n123570 0.023311 0.761301 \n123571 0.027527 3.567193 \n123572 0.055447 3.203060 \n123574 0.054295 3.120209 \n123577 0.294435 2.143930 \n123580 0.067954 1.149615 \n123583 0.039722 1.294468 \n123588 0.031259 5.253177 \n123592 0.065889 2.485711 \n123598 0.057382 3.239906 \n123601 0.030913 4.772301 \n123602 0.083669 3.868569 \n123603 0.047468 3.895862 \n123605 0.088905 2.315573 \n123606 0.428919 0.916201 \n123621 0.010948 2.304651 \n\n hist_installments_sum hist_installments_max hist_installments_mean \\\n0 141.0 12.0 2.073529 \n1 83.0 4.0 1.064103 \n3 40.0 6.0 1.666667 \n4 120.0 4.0 1.090909 \n6 76.0 6.0 1.688889 \n9 49.0 2.0 1.020833 \n15 39.0 10.0 3.545455 \n17 73.0 3.0 1.196721 \n18 29.0 3.0 1.074074 \n19 86.0 6.0 1.061728 \n21 151.0 10.0 1.589474 \n23 32.0 10.0 1.391304 \n30 346.0 12.0 1.330769 \n32 135.0 10.0 1.238532 \n34 697.0 6.0 1.085670 \n35 18.0 3.0 1.125000 \n37 70.0 6.0 1.346154 \n38 103.0 5.0 1.157303 \n49 81.0 5.0 1.094595 \n53 37.0 4.0 1.193548 \n56 117.0 10.0 2.659091 \n59 105.0 3.0 1.071429 \n64 85.0 12.0 1.328125 \n66 123.0 12.0 1.640000 \n67 10.0 3.0 1.428571 \n69 22.0 10.0 2.000000 \n73 23.0 1.0 1.000000 \n82 58.0 6.0 1.288889 \n85 94.0 5.0 1.105882 \n88 370.0 5.0 1.069364 \n... ... ... ... \n123530 119.0 5.0 1.750000 \n123531 21.0 8.0 1.615385 \n123534 76.0 10.0 1.900000 \n123538 200.0 12.0 1.515152 \n123545 651.0 12.0 1.990826 \n123547 150.0 12.0 3.125000 \n123552 61.0 5.0 1.452381 \n123556 28.0 6.0 1.400000 \n123557 252.0 10.0 1.362162 \n123559 45.0 10.0 1.406250 \n123560 115.0 5.0 1.369048 \n123564 68.0 2.0 1.046154 \n123565 32.0 10.0 3.200000 \n123566 58.0 6.0 1.414634 \n123570 92.0 12.0 2.875000 \n123571 76.0 4.0 1.117647 \n123572 94.0 1.0 1.000000 \n123574 54.0 6.0 1.459459 \n123577 31.0 10.0 2.384615 \n123580 56.0 2.0 1.217391 \n123583 56.0 6.0 3.500000 \n123588 127.0 1.0 1.000000 \n123592 49.0 8.0 2.041667 \n123598 140.0 6.0 2.692308 \n123601 39.0 3.0 1.083333 \n123602 594.0 10.0 1.160156 \n123603 303.0 12.0 1.429245 \n123605 173.0 12.0 1.965909 \n123606 94.0 5.0 1.807692 \n123621 120.0 5.0 1.935484 \n\n hist_installments_var hist_installments_skew hist_purchase_date_max \\\n0 4.248244 2.459019 1.514510e+09 \n1 0.164669 6.490915 1.518989e+09 \n3 1.797101 2.327560 1.519127e+09 \n4 0.193495 5.726916 1.519728e+09 \n6 1.128283 1.978406 1.519569e+09 \n9 0.020833 6.928203 1.506568e+09 \n15 11.872727 1.386055 1.519824e+09 \n17 0.260656 2.629338 1.519320e+09 \n18 0.148148 5.196152 1.517850e+09 \n19 0.308642 9.000000 1.493465e+09 \n21 3.223292 3.727042 1.519836e+09 \n23 3.521739 4.795832 1.519420e+09 \n30 2.114108 5.925500 1.519820e+09 \n32 1.312946 6.288853 1.518958e+09 \n34 0.193897 8.003427 1.519759e+09 \n35 0.250000 4.000000 1.516734e+09 \n37 1.015083 3.311583 1.508976e+09 \n38 0.270429 5.160052 1.514339e+09 \n49 0.278601 6.430604 1.514739e+09 \n53 0.361290 3.852912 1.519564e+09 \n56 5.020613 1.826853 1.514660e+09 \n59 0.108247 4.939063 1.517381e+09 \n64 2.255704 6.204408 1.519490e+09 \n66 3.665946 3.844218 1.519831e+09 \n67 0.619048 1.759815 1.502033e+09 \n69 7.400000 3.060082 1.511044e+09 \n73 0.000000 0.000000 1.519637e+09 \n82 1.028283 3.756856 1.518029e+09 \n85 0.286275 5.831203 1.519743e+09 \n88 0.140102 6.439296 1.519841e+09 \n... ... ... ... \n123530 1.085821 1.829695 1.519542e+09 \n123531 3.756410 3.486672 1.512833e+09 \n123534 4.194872 3.346049 1.518085e+09 \n123538 3.778395 4.070503 1.517430e+09 \n123545 5.266787 2.779756 1.519819e+09 \n123547 7.388298 1.825983 1.518779e+09 \n123552 0.985482 2.258529 1.519820e+09 \n123556 1.410526 3.510406 1.519627e+09 \n123557 1.340952 5.222879 1.519754e+09 \n123559 2.958669 4.591329 1.519838e+09 \n123560 0.573006 2.678198 1.517325e+09 \n123564 0.044712 4.428959 1.519837e+09 \n123565 13.733333 1.538501 1.517746e+09 \n123566 1.448780 2.923738 1.516474e+09 \n123570 10.887097 2.036994 1.512057e+09 \n123571 0.314311 4.752290 1.519557e+09 \n123572 0.000000 0.000000 1.519206e+09 \n123574 1.366366 2.860999 1.519749e+09 \n123577 11.423077 2.178717 1.519843e+09 \n123580 0.173913 1.416950 1.512998e+09 \n123583 2.533333 -0.056687 1.518697e+09 \n123588 0.000000 0.000000 1.514466e+09 \n123592 3.085145 1.979259 1.519196e+09 \n123598 2.609351 0.582276 1.519505e+09 \n123601 0.135714 4.714629 1.518770e+09 \n123602 0.639662 6.708233 1.517383e+09 \n123603 3.004449 5.051063 1.519817e+09 \n123605 4.332158 2.699507 1.519758e+09 \n123606 1.648567 1.241579 1.519856e+09 \n123621 1.307245 1.149820 1.509376e+09 \n\n hist_purchase_date_min hist_month_lag_max hist_month_lag_min \\\n0 1.491330e+09 0 -8 \n1 1.484321e+09 0 -13 \n3 1.512392e+09 0 -2 \n4 1.483444e+09 0 -13 \n6 1.507572e+09 0 -4 \n9 1.483614e+09 0 -8 \n15 1.510697e+09 0 -3 \n17 1.504619e+09 0 -5 \n18 1.509477e+09 0 -4 \n19 1.483810e+09 0 -3 \n21 1.496495e+09 0 -8 \n23 1.505855e+09 0 -5 \n30 1.486392e+09 0 -12 \n32 1.491915e+09 0 -10 \n34 1.490201e+09 0 -11 \n35 1.506853e+09 0 -3 \n37 1.500032e+09 0 -3 \n38 1.490048e+09 0 -9 \n49 1.505769e+09 0 -3 \n53 1.513261e+09 0 -2 \n56 1.497619e+09 0 -6 \n59 1.508627e+09 0 -3 \n64 1.492156e+09 0 -10 \n66 1.493124e+09 0 -10 \n67 1.487432e+09 0 -6 \n69 1.506614e+09 0 -2 \n73 1.510221e+09 0 -3 \n82 1.510525e+09 0 -3 \n85 1.510181e+09 0 -3 \n88 1.492619e+09 0 -10 \n... ... ... ... \n123530 1.497193e+09 0 -8 \n123531 1.503520e+09 -1 -5 \n123534 1.483540e+09 0 -13 \n123538 1.508847e+09 0 -3 \n123545 1.487015e+09 0 -12 \n123547 1.492007e+09 0 -10 \n123552 1.493899e+09 0 -9 \n123556 1.504114e+09 0 -6 \n123557 1.494104e+09 0 -9 \n123559 1.511874e+09 0 -3 \n123560 1.487117e+09 0 -11 \n123564 1.501615e+09 0 -6 \n123565 1.503345e+09 0 -6 \n123566 1.483622e+09 -1 -13 \n123570 1.507305e+09 0 -1 \n123571 1.483718e+09 0 -13 \n123572 1.510618e+09 0 -3 \n123574 1.501335e+09 0 -7 \n123577 1.500718e+09 0 -7 \n123580 1.492723e+09 0 -8 \n123583 1.508198e+09 0 -4 \n123588 1.500988e+09 0 -5 \n123592 1.504961e+09 0 -5 \n123598 1.510240e+09 0 -3 \n123601 1.506421e+09 0 -5 \n123602 1.484563e+09 0 -12 \n123603 1.511038e+09 0 -3 \n123605 1.496256e+09 0 -9 \n123606 1.499732e+09 0 -7 \n123621 1.496312e+09 0 -4 \n\n hist_month_lag_mean hist_month_lag_var hist_month_lag_skew \\\n0 -3.632353 6.026997 -0.116148 \n1 -10.410256 4.686647 2.716127 \n3 -1.230769 0.904615 0.502455 \n4 -6.227273 20.525855 0.091212 \n6 -1.750000 1.936170 -0.370837 \n9 -5.500000 6.170213 1.264590 \n15 -1.454545 1.472727 -0.128859 \n17 -2.344262 3.529508 -0.243751 \n18 -2.344828 1.519704 0.966616 \n19 -1.543210 1.251235 0.000983 \n21 -3.814433 5.527706 -0.036041 \n23 -2.652174 2.600791 0.086967 \n30 -5.000000 11.333333 -0.205827 \n32 -4.745455 9.127273 -0.159111 \n34 -5.148837 10.098931 0.034465 \n35 -1.200000 1.642105 -0.420198 \n37 -1.692308 1.393665 0.184376 \n38 -4.707865 7.800051 0.482517 \n49 -1.526316 0.625965 0.254595 \n53 -0.843750 0.781250 -0.322623 \n56 -3.133333 5.527273 -0.041389 \n59 -1.470000 1.039495 0.004721 \n64 -5.265625 9.214038 0.026229 \n66 -4.533333 7.468468 -0.054661 \n67 -1.714286 4.571429 -1.663284 \n69 -0.750000 0.750000 -0.566853 \n73 -1.565217 1.984190 0.092124 \n82 -1.857143 1.500000 0.567494 \n85 -0.658824 0.584594 -1.326620 \n88 -4.531792 9.298986 -0.159129 \n... ... ... ... \n123530 -4.608696 6.153453 0.648543 \n123531 -2.000000 1.500000 -1.608251 \n123534 -5.023810 14.804297 -0.606796 \n123538 -1.037313 0.637695 -0.022468 \n123545 -4.864865 14.147346 -0.401470 \n123547 -4.900000 9.928571 0.197740 \n123552 -4.674419 10.224806 -0.058762 \n123556 -2.681818 3.179654 0.134455 \n123557 -3.703704 7.379827 -0.225299 \n123559 -1.181818 1.090909 0.211367 \n123560 -1.858824 3.622689 -1.575622 \n123564 -2.303030 2.614452 0.016239 \n123565 -1.800000 3.288889 -1.766005 \n123566 -5.214286 10.757840 -0.871717 \n123570 -0.424242 0.251894 -0.321366 \n123571 -6.405797 15.832907 -0.202580 \n123572 -1.031915 1.106497 -0.558271 \n123574 -3.564103 3.936572 -0.155721 \n123577 -2.230769 8.358974 -1.048920 \n123580 -3.744681 9.411656 -0.082092 \n123583 -2.611111 1.898693 0.260125 \n123588 -2.007874 1.388826 0.429277 \n123592 -2.357143 4.015873 -0.062206 \n123598 -1.618182 0.981145 0.103818 \n123601 -2.750000 1.907143 0.073225 \n123602 -4.846304 9.307715 -0.114157 \n123603 -1.013889 0.925388 -0.541660 \n123605 -4.089888 6.219101 -0.129187 \n123606 -5.111111 5.798742 0.876313 \n123621 -2.145161 1.699894 -0.089070 \n\n hist_month_diff_max hist_month_diff_min hist_month_diff_mean \\\n0 73 72 72.632353 \n1 71 70 70.846154 \n3 71 70 70.769231 \n4 71 70 70.763636 \n6 71 70 70.479167 \n9 76 75 75.937500 \n15 71 70 70.454545 \n17 71 70 70.639344 \n18 71 70 70.310345 \n19 81 80 80.777778 \n21 71 70 70.618557 \n23 71 70 70.652174 \n30 71 70 70.622137 \n32 71 70 70.772727 \n34 71 70 70.671318 \n35 72 71 71.700000 \n37 75 74 74.961538 \n38 73 72 72.662921 \n49 73 72 72.631579 \n53 71 70 70.375000 \n56 73 72 72.600000 \n59 72 71 71.700000 \n64 71 70 70.640625 \n66 71 70 70.466667 \n67 77 76 76.857143 \n69 74 73 73.666667 \n73 71 70 70.478261 \n82 71 70 70.714286 \n85 71 70 70.576471 \n88 71 70 70.716763 \n... ... ... ... \n123530 71 70 70.579710 \n123531 72 71 71.461538 \n123534 71 70 70.595238 \n123538 72 71 71.567164 \n123545 71 70 70.654655 \n123547 71 70 70.720000 \n123552 71 70 70.418605 \n123556 71 70 70.363636 \n123557 71 70 70.708995 \n123559 71 70 70.666667 \n123560 72 71 71.576471 \n123564 71 70 70.878788 \n123565 71 70 70.600000 \n123566 71 70 70.690476 \n123570 74 73 73.727273 \n123571 71 70 70.710145 \n123572 71 70 70.617021 \n123574 71 70 70.307692 \n123577 71 70 70.692308 \n123580 73 72 72.957447 \n123583 71 70 70.388889 \n123588 73 72 72.606299 \n123592 71 70 70.892857 \n123598 71 70 70.509091 \n123601 71 70 70.777778 \n123602 72 71 71.698444 \n123603 71 70 70.537037 \n123605 71 70 70.528090 \n123606 71 70 70.796296 \n123621 75 74 74.709677 \n\n hist_month_diff_var hist_month_diff_skew hist_weekend_sum \\\n0 0.235953 -0.561457 12 \n1 0.131868 -1.956637 17 \n3 0.184615 -1.357634 7 \n4 0.182152 -1.258310 21 \n6 0.254876 0.086121 14 \n9 0.059840 -3.732451 15 \n15 0.272727 0.212762 0 \n17 0.234426 -0.595105 10 \n18 0.221675 0.865308 13 \n19 0.175000 -1.361653 26 \n21 0.238402 -0.495849 28 \n23 0.237154 -0.684484 4 \n30 0.235983 -0.506718 79 \n32 0.177231 -1.319647 25 \n34 0.220993 -0.731126 142 \n35 0.221053 -0.945300 10 \n37 0.037707 -4.943767 16 \n38 0.225996 -0.701178 22 \n49 0.235789 -0.556591 31 \n53 0.241935 0.542149 7 \n56 0.245455 -0.422463 10 \n59 0.212121 -0.886221 26 \n64 0.233879 -0.600323 21 \n66 0.252252 0.136373 31 \n67 0.142857 -2.645751 6 \n69 0.242424 -0.812404 6 \n73 0.260870 0.093233 4 \n82 0.208333 -0.978908 14 \n85 0.247059 -0.315112 25 \n88 0.203602 -0.966366 157 \n... ... ... ... \n123530 0.247229 -0.330193 20 \n123531 0.269231 0.175204 2 \n123534 0.246806 -0.402580 6 \n123538 0.247335 -0.274193 28 \n123545 0.226763 -0.653466 143 \n123547 0.205714 -1.010530 7 \n123552 0.249169 0.342032 8 \n123556 0.242424 0.609303 5 \n123557 0.207419 -0.927602 25 \n123559 0.229167 -0.741234 7 \n123560 0.247059 -0.315112 24 \n123564 0.108159 -2.375525 15 \n123565 0.266667 -0.484123 4 \n123566 0.218931 -0.854881 14 \n123570 0.204545 -1.069879 5 \n123571 0.208866 -0.947085 22 \n123572 0.238847 -0.489300 19 \n123574 0.218623 0.867044 4 \n123577 0.230769 -0.946212 7 \n123580 0.041628 -4.683414 13 \n123583 0.251634 0.498374 3 \n123588 0.240595 -0.440363 31 \n123592 0.099206 -2.686455 14 \n123598 0.254545 -0.037397 6 \n123601 0.177778 -1.395122 13 \n123602 0.211031 -0.867336 159 \n123603 0.249785 -0.149597 44 \n123605 0.252043 -0.114476 16 \n123606 0.165269 -1.513739 6 \n123621 0.209413 -0.946935 19 \n\n hist_weekend_mean hist_weekday_sum hist_weekday_mean \\\n0 0.176471 190 2.794118 \n1 0.217949 229 2.935897 \n3 0.269231 64 2.461538 \n4 0.190909 265 2.409091 \n6 0.291667 141 2.937500 \n9 0.312500 178 3.708333 \n15 0.000000 23 2.090909 \n17 0.163934 183 3.000000 \n18 0.448276 97 3.344828 \n19 0.320988 257 3.172840 \n21 0.288660 280 2.886598 \n23 0.173913 59 2.565217 \n30 0.301527 802 3.061069 \n32 0.227273 323 2.936364 \n34 0.220155 1843 2.857364 \n35 0.500000 77 3.850000 \n37 0.307692 181 3.480769 \n38 0.247191 252 2.831461 \n49 0.407895 234 3.078947 \n53 0.218750 80 2.500000 \n56 0.222222 135 3.000000 \n59 0.260000 302 3.020000 \n64 0.328125 215 3.359375 \n66 0.413333 256 3.413333 \n67 0.857143 33 4.714286 \n69 0.500000 41 3.416667 \n73 0.173913 63 2.739130 \n82 0.285714 166 3.387755 \n85 0.294118 244 2.870588 \n88 0.453757 1319 3.812139 \n... ... ... ... \n123530 0.289855 199 2.884058 \n123531 0.153846 37 2.846154 \n123534 0.142857 107 2.547619 \n123538 0.208955 365 2.723881 \n123545 0.429429 1162 3.489489 \n123547 0.140000 131 2.620000 \n123552 0.186047 117 2.720930 \n123556 0.227273 64 2.909091 \n123557 0.132275 466 2.465608 \n123559 0.212121 78 2.363636 \n123560 0.282353 259 3.047059 \n123564 0.227273 188 2.848485 \n123565 0.400000 39 3.900000 \n123566 0.333333 124 2.952381 \n123570 0.151515 90 2.727273 \n123571 0.318841 202 2.927536 \n123572 0.202128 264 2.808511 \n123574 0.102564 78 2.000000 \n123577 0.538462 50 3.846154 \n123580 0.276596 144 3.063830 \n123583 0.166667 61 3.388889 \n123588 0.244094 363 2.858268 \n123592 0.500000 99 3.535714 \n123598 0.109091 139 2.527273 \n123601 0.361111 119 3.305556 \n123602 0.309339 1579 3.071984 \n123603 0.203704 604 2.796296 \n123605 0.179775 221 2.483146 \n123606 0.111111 131 2.425926 \n123621 0.306452 195 3.145161 \n\n hist_authorized_flag_sum hist_authorized_flag_mean \\\n0 44 0.647059 \n1 77 0.987179 \n3 26 1.000000 \n4 87 0.790909 \n6 48 1.000000 \n9 43 0.895833 \n15 9 0.818182 \n17 60 0.983607 \n18 19 0.655172 \n19 81 1.000000 \n21 89 0.917526 \n23 23 1.000000 \n30 258 0.984733 \n32 104 0.945455 \n34 636 0.986047 \n35 16 0.800000 \n37 36 0.692308 \n38 73 0.820225 \n49 76 1.000000 \n53 32 1.000000 \n56 45 1.000000 \n59 91 0.910000 \n64 62 0.968750 \n66 61 0.813333 \n67 7 1.000000 \n69 11 0.916667 \n73 21 0.913043 \n82 40 0.816327 \n85 72 0.847059 \n88 345 0.997110 \n... ... ... \n123530 66 0.956522 \n123531 12 0.923077 \n123534 39 0.928571 \n123538 133 0.992537 \n123545 325 0.975976 \n123547 50 1.000000 \n123552 41 0.953488 \n123556 21 0.954545 \n123557 183 0.968254 \n123559 32 0.969697 \n123560 76 0.894118 \n123564 60 0.909091 \n123565 10 1.000000 \n123566 41 0.976190 \n123570 27 0.818182 \n123571 68 0.985507 \n123572 94 1.000000 \n123574 37 0.948718 \n123577 11 0.846154 \n123580 40 0.851064 \n123583 13 0.722222 \n123588 124 0.976378 \n123592 25 0.892857 \n123598 55 1.000000 \n123601 31 0.861111 \n123602 499 0.970817 \n123603 208 0.962963 \n123605 83 0.932584 \n123606 44 0.814815 \n123621 43 0.693548 \n\n hist_category_1_sum hist_category_1_mean hist_category_1_max \\\n0 23 0.338235 1 \n1 2 0.025641 1 \n3 0 0.000000 0 \n4 0 0.000000 0 \n6 1 0.020833 1 \n9 0 0.000000 0 \n15 3 0.272727 1 \n17 1 0.016393 1 \n18 0 0.000000 0 \n19 0 0.000000 0 \n21 51 0.525773 1 \n23 0 0.000000 0 \n30 16 0.061069 1 \n32 0 0.000000 0 \n34 118 0.182946 1 \n35 0 0.000000 0 \n37 0 0.000000 0 \n38 44 0.494382 1 \n49 3 0.039474 1 \n53 0 0.000000 0 \n56 0 0.000000 0 \n59 43 0.430000 1 \n64 8 0.125000 1 \n66 1 0.013333 1 \n67 0 0.000000 0 \n69 4 0.333333 1 \n73 0 0.000000 0 \n82 1 0.020408 1 \n85 16 0.188235 1 \n88 0 0.000000 0 \n... ... ... ... \n123530 53 0.768116 1 \n123531 0 0.000000 0 \n123534 0 0.000000 0 \n123538 12 0.089552 1 \n123545 25 0.075075 1 \n123547 11 0.220000 1 \n123552 15 0.348837 1 \n123556 0 0.000000 0 \n123557 6 0.031746 1 \n123559 2 0.060606 1 \n123560 61 0.717647 1 \n123564 0 0.000000 0 \n123565 1 0.100000 1 \n123566 0 0.000000 0 \n123570 17 0.515152 1 \n123571 1 0.014493 1 \n123572 47 0.500000 1 \n123574 0 0.000000 0 \n123577 0 0.000000 0 \n123580 5 0.106383 1 \n123583 0 0.000000 0 \n123588 0 0.000000 0 \n123592 12 0.428571 1 \n123598 2 0.036364 1 \n123601 21 0.583333 1 \n123602 0 0.000000 0 \n123603 68 0.314815 1 \n123605 3 0.033708 1 \n123606 34 0.629630 1 \n123621 0 0.000000 0 \n\n hist_category_1_min hist_card_id_size hist_card_id_count \\\n0 0 68 68 \n1 0 78 78 \n3 0 26 26 \n4 0 110 110 \n6 0 48 48 \n9 0 48 48 \n15 0 11 11 \n17 0 61 61 \n18 0 29 29 \n19 0 81 81 \n21 0 97 97 \n23 0 23 23 \n30 0 262 262 \n32 0 110 110 \n34 0 645 645 \n35 0 20 20 \n37 0 52 52 \n38 0 89 89 \n49 0 76 76 \n53 0 32 32 \n56 0 45 45 \n59 0 100 100 \n64 0 64 64 \n66 0 75 75 \n67 0 7 7 \n69 0 12 12 \n73 0 23 23 \n82 0 49 49 \n85 0 85 85 \n88 0 346 346 \n... ... ... ... \n123530 0 69 69 \n123531 0 13 13 \n123534 0 42 42 \n123538 0 134 134 \n123545 0 333 333 \n123547 0 50 50 \n123552 0 43 43 \n123556 0 22 22 \n123557 0 189 189 \n123559 0 33 33 \n123560 0 85 85 \n123564 0 66 66 \n123565 0 10 10 \n123566 0 42 42 \n123570 0 33 33 \n123571 0 69 69 \n123572 0 94 94 \n123574 0 39 39 \n123577 0 13 13 \n123580 0 47 47 \n123583 0 18 18 \n123588 0 127 127 \n123592 0 28 28 \n123598 0 55 55 \n123601 0 36 36 \n123602 0 514 514 \n123603 0 216 216 \n123605 0 89 89 \n123606 0 54 54 \n123621 0 62 62 \n\n hist_month_nunique hist_month_mean hist_month_min hist_month_max \\\n0 9 8.367647 4 12 \n1 5 3.282051 1 5 \n3 3 7.692308 1 12 \n4 12 4.827273 1 12 \n6 5 6.750000 1 12 \n9 7 3.500000 1 9 \n15 4 6.000000 1 12 \n17 5 7.524590 1 12 \n18 4 9.586207 2 12 \n19 4 2.456790 1 4 \n21 9 8.082474 1 12 \n23 6 8.739130 1 12 \n30 12 6.480916 1 12 \n32 11 6.636364 1 12 \n34 12 6.730233 1 12 \n35 4 6.400000 1 12 \n37 4 8.307692 7 10 \n38 9 7.292135 3 12 \n49 4 10.473684 9 12 \n53 3 4.906250 1 12 \n56 7 8.866667 6 12 \n59 4 9.010000 1 12 \n64 10 7.046875 1 11 \n66 11 7.226667 1 12 \n67 4 6.285714 2 8 \n69 3 10.250000 9 11 \n73 4 6.695652 1 12 \n82 4 8.224490 1 12 \n85 4 2.329412 1 12 \n88 11 7.005780 1 12 \n... ... ... ... ... \n123530 9 7.478261 1 12 \n123531 4 11.000000 8 12 \n123534 10 5.833333 1 11 \n123538 4 8.470149 1 12 \n123545 12 6.648649 1 12 \n123547 11 6.220000 1 12 \n123552 10 7.093023 1 12 \n123556 7 6.954545 1 12 \n123557 10 7.121693 1 12 \n123559 3 7.727273 2 12 \n123560 8 7.047059 1 12 \n123564 7 7.515152 1 12 \n123565 5 3.800000 1 12 \n123566 10 7.357143 1 12 \n123570 2 10.575758 10 11 \n123571 11 5.855072 1 12 \n123572 4 4.925532 1 12 \n123574 7 8.897436 1 12 \n123577 5 5.307692 1 12 \n123580 9 8.255319 4 12 \n123583 4 8.722222 1 12 \n123588 6 9.992126 7 12 \n123592 5 6.071429 1 11 \n123598 4 6.927273 1 12 \n123601 6 8.250000 1 12 \n123602 12 7.219844 1 12 \n123603 4 4.597222 1 12 \n123605 10 8.022472 1 12 \n123606 8 7.333333 1 12 \n123621 5 7.854839 6 10 \n\n hist_hour_nunique hist_hour_mean hist_hour_min hist_hour_max \\\n0 17 14.367647 0 23 \n1 18 14.423077 0 23 \n3 9 17.923077 8 22 \n4 21 14.436364 0 23 \n6 16 14.291667 6 22 \n9 18 14.604167 1 23 \n15 9 13.727273 1 23 \n17 16 13.278689 0 23 \n18 12 10.310345 0 23 \n19 13 13.061728 8 20 \n21 18 14.587629 0 23 \n23 12 14.913043 7 22 \n30 23 13.194656 0 23 \n32 20 12.609091 0 23 \n34 20 14.409302 0 23 \n35 7 11.300000 0 19 \n37 14 14.442308 0 23 \n38 21 11.808989 0 23 \n49 18 12.355263 0 23 \n53 13 13.531250 4 19 \n56 14 14.022222 0 22 \n59 21 13.920000 0 23 \n64 17 14.031250 0 23 \n66 15 14.800000 0 23 \n67 5 12.285714 7 15 \n69 9 13.000000 0 22 \n73 11 13.869565 0 19 \n82 13 15.714286 0 23 \n85 16 14.800000 0 23 \n88 21 14.939306 0 23 \n... ... ... ... ... \n123530 19 13.855072 1 23 \n123531 9 16.153846 0 23 \n123534 13 14.666667 0 21 \n123538 18 13.985075 0 22 \n123545 20 14.792793 0 23 \n123547 15 14.760000 9 23 \n123552 13 13.767442 8 22 \n123556 13 14.636364 0 23 \n123557 17 13.952381 0 22 \n123559 16 14.545455 1 23 \n123560 22 13.529412 0 23 \n123564 19 12.272727 0 23 \n123565 7 14.500000 8 19 \n123566 15 14.214286 7 21 \n123570 14 14.878788 0 22 \n123571 20 14.623188 0 23 \n123572 21 11.787234 0 23 \n123574 12 15.128205 9 21 \n123577 8 13.615385 8 19 \n123580 18 14.489362 0 23 \n123583 10 13.333333 0 19 \n123588 17 13.322835 0 23 \n123592 15 13.714286 0 22 \n123598 11 13.981818 10 21 \n123601 14 15.500000 0 23 \n123602 18 14.503891 0 23 \n123603 20 14.810185 0 23 \n123605 18 15.191011 0 23 \n123606 15 11.814815 0 22 \n123621 12 12.209677 0 18 \n\n hist_weekofyear_nunique hist_weekofyear_mean hist_weekofyear_min \\\n0 24 34.544118 14 \n1 20 12.435897 2 \n3 6 31.115385 4 \n4 34 18.836364 1 \n6 13 27.812500 1 \n9 15 12.520833 1 \n15 7 25.090909 4 \n17 14 30.754098 4 \n18 7 40.448276 5 \n19 16 9.049383 1 \n21 31 33.185567 1 \n23 16 36.521739 3 \n30 51 26.358779 1 \n32 37 26.809091 1 \n34 49 27.493023 1 \n35 9 25.650000 3 \n37 10 34.134615 28 \n38 26 30.089888 12 \n49 13 43.763158 38 \n53 9 20.281250 2 \n56 17 36.888889 24 \n59 15 37.330000 1 \n64 25 28.953125 3 \n66 32 29.853333 1 \n67 5 24.571429 7 \n69 6 42.750000 39 \n73 7 27.608696 1 \n82 10 33.591837 1 \n85 14 8.482353 1 \n88 46 28.390173 1 \n... ... ... ... \n123530 29 31.043478 5 \n123531 5 46.230769 34 \n123534 20 23.761905 1 \n123538 14 35.246269 1 \n123545 49 26.921922 1 \n123547 23 25.160000 1 \n123552 23 29.465116 4 \n123556 13 29.272727 2 \n123557 32 29.370370 2 \n123559 7 32.030303 7 \n123560 23 29.094118 1 \n123564 17 30.196970 1 \n123565 6 14.600000 2 \n123566 22 29.809524 1 \n123570 8 44.121212 40 \n123571 27 23.753623 1 \n123572 15 19.765957 1 \n123574 13 37.230769 4 \n123577 9 21.230769 4 \n123580 15 33.361702 16 \n123583 5 36.833333 4 \n123588 19 41.881890 30 \n123592 14 23.928571 1 \n123598 16 28.709091 1 \n123601 17 33.750000 1 \n123602 48 29.482490 1 \n123603 16 18.375000 1 \n123605 26 33.056180 1 \n123606 17 29.962963 1 \n123621 17 32.274194 22 \n\n hist_weekofyear_max hist_day_nunique hist_day_mean hist_day_min \\\n0 52 24 16.352941 1 \n1 21 27 16.512821 2 \n3 50 11 11.423077 4 \n4 52 27 13.272727 1 \n6 52 20 17.458333 2 \n9 39 19 10.916667 3 \n15 51 8 20.090909 8 \n17 50 25 14.590164 1 \n18 51 11 20.344828 2 \n19 17 26 17.876543 3 \n21 52 28 15.082474 1 \n23 52 17 17.869565 3 \n30 52 31 16.324427 1 \n32 52 28 14.600000 1 \n34 52 31 16.586047 1 \n35 48 12 14.000000 1 \n37 43 13 16.096154 6 \n38 52 29 18.112360 1 \n49 52 26 16.763158 1 \n53 52 17 19.875000 5 \n56 52 19 17.666667 2 \n59 52 26 15.840000 2 \n64 47 26 17.593750 1 \n66 52 22 18.493333 1 \n67 31 6 12.000000 6 \n69 46 11 16.666667 2 \n73 52 11 17.173913 2 \n82 50 18 13.530612 2 \n85 52 26 15.647059 1 \n88 52 31 15.263006 1 \n... ... ... ... ... \n123530 52 27 18.594203 1 \n123531 49 9 17.692308 1 \n123534 48 22 17.047619 3 \n123538 52 30 17.223881 2 \n123545 52 31 15.543544 1 \n123547 51 21 15.380000 1 \n123552 52 18 19.162791 3 \n123556 51 14 21.636364 6 \n123557 51 28 16.994709 1 \n123559 51 19 16.606061 4 \n123560 52 27 17.800000 1 \n123564 52 21 10.939394 1 \n123565 49 8 15.400000 4 \n123566 50 22 13.714286 1 \n123570 48 15 15.727273 2 \n123571 51 26 17.014493 1 \n123572 52 31 16.000000 1 \n123574 52 14 17.897436 1 \n123577 50 10 16.076923 1 \n123580 50 14 11.808511 5 \n123583 51 8 21.611111 15 \n123588 52 30 18.062992 1 \n123592 47 13 11.357143 1 \n123598 52 21 17.890909 2 \n123601 51 18 14.083333 3 \n123602 52 31 15.998054 1 \n123603 52 31 16.231481 1 \n123605 52 22 15.730337 1 \n123606 50 21 15.314815 2 \n123621 44 22 16.435484 1 \n\n hist_day_max hist_subsector_id_nunique \\\n0 31 12 \n1 30 12 \n3 24 11 \n4 30 15 \n6 31 14 \n9 28 10 \n15 28 4 \n17 30 14 \n18 31 8 \n19 31 8 \n21 31 12 \n23 30 6 \n30 31 21 \n32 31 12 \n34 31 28 \n35 24 6 \n37 27 10 \n38 31 11 \n49 31 15 \n53 31 10 \n56 30 15 \n59 31 19 \n64 31 11 \n66 31 19 \n67 27 5 \n69 30 7 \n73 30 8 \n82 27 13 \n85 31 13 \n88 31 21 \n... ... ... \n123530 31 12 \n123531 29 7 \n123534 30 9 \n123538 31 18 \n123545 31 27 \n123547 27 15 \n123552 31 13 \n123556 30 9 \n123557 31 20 \n123559 28 12 \n123560 31 16 \n123564 30 13 \n123565 22 5 \n123566 30 6 \n123570 30 9 \n123571 30 12 \n123572 31 9 \n123574 31 12 \n123577 28 6 \n123580 29 9 \n123583 26 4 \n123588 31 19 \n123592 25 8 \n123598 31 11 \n123601 30 11 \n123602 31 29 \n123603 31 21 \n123605 31 18 \n123606 31 9 \n123621 30 10 \n\n hist_merchant_category_id_nunique hist_price_sum hist_price_mean \\\n0 16 -34.806456 -0.511860 \n1 16 -48.475933 -0.621486 \n3 18 -11.504476 -0.479353 \n4 31 -46.693329 -0.424485 \n6 17 -15.890002 -0.353111 \n9 16 -29.348250 -0.611422 \n15 5 -2.506857 -0.227896 \n17 21 -34.215277 -0.560906 \n18 11 -18.382403 -0.680830 \n19 11 -57.240394 -0.706672 \n21 19 -57.381043 -0.604011 \n23 7 -13.504943 -0.587171 \n30 37 -143.810518 -0.553117 \n32 15 -69.819244 -0.640544 \n34 63 -399.374602 -0.622079 \n35 7 -10.591086 -0.661943 \n37 13 -23.334159 -0.448734 \n38 16 -54.337567 -0.610534 \n49 24 -49.208804 -0.664984 \n53 13 -18.410911 -0.593900 \n56 24 -15.249959 -0.346590 \n59 31 -66.376430 -0.677311 \n64 18 -40.111366 -0.626740 \n66 26 -43.306496 -0.577420 \n67 5 -2.953791 -0.421970 \n69 7 -6.273561 -0.570324 \n73 11 -15.445391 -0.671539 \n82 19 -27.978235 -0.621739 \n85 31 -51.634778 -0.607468 \n88 46 -216.826094 -0.626665 \n... ... ... ... \n123530 17 -8.978707 -0.132040 \n123531 8 -5.899175 -0.453783 \n123534 20 -19.427339 -0.485683 \n123538 34 -76.221793 -0.577438 \n123545 57 -124.052210 -0.379365 \n123547 22 -15.051954 -0.313582 \n123552 21 -24.423075 -0.581502 \n123556 15 -9.687257 -0.484363 \n123557 52 -93.749276 -0.506753 \n123559 14 -17.996077 -0.562377 \n123560 25 -44.310698 -0.527508 \n123564 21 -37.986864 -0.584413 \n123565 7 -4.038120 -0.403812 \n123566 7 -24.001753 -0.585409 \n123570 13 -14.042932 -0.438842 \n123571 20 -42.659866 -0.627351 \n123572 13 -59.050239 -0.628194 \n123574 19 -21.262702 -0.574668 \n123577 6 -7.277966 -0.559844 \n123580 17 -23.478909 -0.510411 \n123583 9 -3.485834 -0.217865 \n123588 26 -80.662777 -0.635140 \n123592 11 -11.626274 -0.484428 \n123598 11 -16.993578 -0.326800 \n123601 12 -23.492498 -0.652569 \n123602 63 -323.048961 -0.630955 \n123603 31 -124.920284 -0.589247 \n123605 26 -43.745371 -0.497106 \n123606 12 -21.404541 -0.411626 \n123621 15 -27.946076 -0.450743 \n\n hist_price_max hist_price_min hist_price_var hist_duration_mean \\\n0 0.117838 -0.743903 0.075928 -43.504279 \n1 0.318817 -0.731881 0.029578 -44.621400 \n3 -0.040662 -0.731881 0.055943 -37.266139 \n4 0.800000 -0.746758 0.230516 -29.627280 \n6 0.371861 -0.683887 0.066838 -27.330344 \n9 0.026356 -0.731881 0.026552 -46.539066 \n15 0.080000 -0.693804 0.092318 -11.986806 \n17 0.223865 -0.725871 0.037202 -41.076259 \n18 -0.153801 -0.741062 0.014285 -47.571866 \n19 0.025778 -0.738643 0.008646 -56.953930 \n21 -0.005471 -0.742099 0.047628 -45.322841 \n23 0.080000 -0.721513 0.025680 -39.246701 \n30 0.760417 -0.729687 0.072970 -40.311443 \n32 0.229815 -0.745405 0.032407 -45.538569 \n34 0.438684 -0.742415 0.028750 -44.098601 \n35 -0.144325 -0.724368 0.019964 -32.461790 \n37 0.555710 -0.729477 0.095221 -34.676857 \n38 0.061706 -0.744443 0.044697 -45.773959 \n49 -0.057885 -0.742400 0.013884 -48.250491 \n53 0.076590 -0.741859 0.046083 -43.338552 \n56 0.065056 -0.731896 0.071302 -33.903935 \n59 -0.080873 -0.741498 0.015540 -49.243726 \n64 0.066667 -0.746156 0.033437 -44.405596 \n66 0.042793 -0.731881 0.044365 -44.073025 \n67 -0.103052 -0.678883 0.048261 -37.335060 \n69 0.030346 -0.724368 0.085446 -31.819393 \n73 -0.459511 -0.737141 0.004074 -47.333326 \n82 -0.047349 -0.731881 0.029635 -45.154106 \n85 0.008794 -0.739019 0.021843 -43.565664 \n88 0.380081 -0.743151 0.031158 -44.630665 \n... ... ... ... ... \n123530 0.800000 -0.745405 0.173732 -8.964525 \n123531 0.400000 -0.724368 0.119601 -26.450200 \n123534 -0.014735 -0.745405 0.056188 -40.976678 \n123538 0.080000 -0.740897 0.039511 -41.590135 \n123545 0.800000 -0.746156 0.090422 -24.306078 \n123547 0.200000 -0.726472 0.070510 -30.205464 \n123552 -0.059283 -0.745405 0.046407 -45.317230 \n123556 0.113435 -0.686802 0.052680 -31.757478 \n123557 0.261236 -0.741348 0.060552 -36.265593 \n123559 0.065798 -0.731836 0.067926 -37.634914 \n123560 0.014221 -0.746156 0.056005 -41.546974 \n123564 0.755743 -0.723406 0.063799 -41.979790 \n123565 0.158733 -0.725119 0.123545 -22.923195 \n123566 0.151149 -0.729402 0.040548 -43.192088 \n123570 -0.022718 -0.745405 0.076734 -41.608347 \n123571 0.076237 -0.737892 0.025137 -44.348739 \n123572 0.301943 -0.745405 0.055447 -44.375878 \n123574 0.070602 -0.739395 0.051924 -42.177926 \n123577 0.080000 -0.724368 0.082152 -32.056128 \n123580 0.106643 -0.738358 0.074553 -37.647731 \n123583 0.005392 -0.694465 0.043296 -34.224312 \n123588 0.800000 -0.745405 0.031259 -46.116465 \n123592 -0.018419 -0.745405 0.071367 -38.114949 \n123598 0.194814 -0.727268 0.060701 -38.456761 \n123601 0.263851 -0.740431 0.039292 -47.216353 \n123602 0.800000 -0.745105 0.055988 -44.492556 \n123603 0.605478 -0.746156 0.045124 -42.419349 \n123605 0.133333 -0.746878 0.071913 -36.664948 \n123606 0.400000 -0.742415 0.168139 -17.814047 \n123621 -0.028949 -0.737892 0.057592 -47.130465 \n\n hist_duration_min hist_duration_max hist_duration_var \\\n0 -54.304883 17.204334 194.832141 \n1 -51.963570 22.636042 120.306523 \n3 -51.231688 6.245529 240.296238 \n4 -53.019783 56.800000 1245.259043 \n6 -48.555948 52.060550 531.468607 \n9 -55.622976 2.003094 143.699218 \n15 -48.566286 56.800000 1340.382119 \n17 -51.536817 47.683239 216.983111 \n18 -52.615435 -32.298284 41.174260 \n19 -59.830102 12.528099 73.390418 \n21 -52.603700 -3.884519 99.389612 \n23 -50.505908 56.800000 460.610453 \n30 -51.807805 53.229164 330.578906 \n32 -52.923765 56.000000 239.386323 \n34 -52.646374 56.800000 179.544343 \n35 -51.613542 57.600000 1528.864663 \n37 -54.710779 60.000000 613.748869 \n38 -54.344374 15.569901 210.202262 \n49 -53.646721 5.078481 70.340653 \n53 -51.930123 10.722618 202.644819 \n56 -53.428429 47.490721 397.592802 \n59 -53.387873 -17.225882 37.770188 \n64 -52.977108 56.000000 271.319559 \n66 -51.803539 36.459637 132.543340 \n67 -52.273974 -15.663876 150.344304 \n69 -53.603235 59.200000 1440.062695 \n73 -52.336978 -32.165752 20.681519 \n82 -51.963570 -20.170478 55.703373 \n85 -52.470339 3.077730 85.875291 \n88 -52.763734 49.768992 170.192231 \n... ... ... ... \n123530 -52.178360 56.800000 1360.258900 \n123531 -51.430131 56.800000 1456.476159 \n123534 -52.923765 -10.461848 114.698192 \n123538 -53.344597 56.800000 245.183743 \n123545 -52.230952 56.800000 841.041331 \n123547 -51.579492 56.800000 981.815258 \n123552 -52.923765 -20.748908 50.106367 \n123556 -48.240153 48.323369 502.919156 \n123557 -52.635706 56.800000 359.205800 \n123559 -51.960370 23.358323 478.750059 \n123560 -53.669170 5.048487 170.917005 \n123564 -51.361848 53.657780 289.451026 \n123565 -51.483474 44.445118 1429.912622 \n123566 -51.787534 52.902037 250.260695 \n123570 -55.159980 -20.173213 127.630086 \n123571 -52.390326 21.651310 138.013489 \n123572 -52.178360 21.135992 275.901711 \n123574 -51.757618 19.768579 267.859698 \n123577 -51.430131 56.800000 1479.005913 \n123580 -53.900114 15.569901 361.235230 \n123583 -48.612570 1.913987 193.461298 \n123588 -54.414575 57.600000 164.025548 \n123592 -52.923765 30.186368 331.513291 \n123598 -50.908771 41.495320 286.358178 \n123601 -52.570627 18.469536 154.668884 \n123602 -53.615075 57.600000 431.288181 \n123603 -52.977108 56.800000 236.099686 \n123605 -52.281441 56.000000 440.753057 \n123606 -52.710387 56.800000 2151.496916 \n123621 -54.778397 -8.684573 60.180253 \n\n hist_duration_skew hist_amount_month_ratio_mean \\\n0 2.340366 -0.008249 \n1 3.783589 -0.008894 \n3 1.867951 -0.007441 \n4 1.744943 -0.005927 \n6 2.250563 -0.005501 \n9 2.507977 -0.008073 \n15 1.056341 -0.002461 \n17 4.414642 -0.008237 \n18 1.850877 -0.009624 \n19 7.143986 -0.008729 \n21 2.236363 -0.009095 \n23 4.426561 -0.007873 \n30 3.062560 -0.008085 \n32 5.123051 -0.009087 \n34 4.796812 -0.008830 \n35 2.062542 -0.006345 \n37 1.821514 -0.006169 \n38 2.497337 -0.008669 \n49 4.239842 -0.009146 \n53 2.851911 -0.008748 \n56 2.161842 -0.006428 \n59 3.461789 -0.009577 \n64 4.679835 -0.008888 \n66 4.976073 -0.008875 \n67 0.762499 -0.006307 \n69 1.744396 -0.005896 \n73 1.867312 -0.009528 \n82 1.736244 -0.009031 \n85 2.471939 -0.008745 \n88 4.206718 -0.008927 \n... ... ... \n123530 0.685571 -0.001802 \n123531 1.906051 -0.005153 \n123534 1.301192 -0.008225 \n123538 3.392013 -0.008119 \n123545 1.576198 -0.004874 \n123547 2.157578 -0.006044 \n123552 1.600706 -0.009140 \n123556 2.532400 -0.006437 \n123557 2.231747 -0.007255 \n123559 1.597859 -0.007529 \n123560 1.325811 -0.008113 \n123564 4.050317 -0.008361 \n123565 1.106119 -0.004598 \n123566 5.719612 -0.008632 \n123570 0.749811 -0.007652 \n123571 3.562737 -0.008871 \n123572 3.201913 -0.008893 \n123574 3.122793 -0.008526 \n123577 2.139732 -0.006436 \n123580 1.151753 -0.007076 \n123583 1.327267 -0.006934 \n123588 5.228059 -0.008748 \n123592 2.482855 -0.007587 \n123598 3.250926 -0.007743 \n123601 4.740836 -0.009416 \n123602 3.870888 -0.008660 \n123603 3.902824 -0.008530 \n123605 2.314891 -0.007377 \n123606 0.916009 -0.003555 \n123621 2.343068 -0.008449 \n\n hist_amount_month_ratio_min hist_amount_month_ratio_max \\\n0 -0.010269 0.003228 \n1 -0.010308 0.004490 \n3 -0.010455 0.001239 \n4 -0.010649 0.011429 \n6 -0.009632 0.010625 \n9 -0.009758 0.000347 \n15 -0.009911 0.011268 \n17 -0.010224 0.009459 \n18 -0.010581 -0.006569 \n19 -0.009187 0.001909 \n21 -0.010601 -0.000771 \n23 -0.010307 0.011268 \n30 -0.010413 0.010863 \n32 -0.010499 0.011429 \n34 -0.010606 0.011429 \n35 -0.010202 0.011111 \n37 -0.009829 0.010667 \n38 -0.010290 0.002922 \n49 -0.010311 0.000980 \n53 -0.010598 0.002188 \n56 -0.010026 0.008912 \n59 -0.010435 -0.003417 \n64 -0.010509 0.011429 \n66 -0.010455 0.007233 \n67 -0.008817 -0.002712 \n69 -0.009923 0.010811 \n73 -0.010445 -0.006564 \n82 -0.010308 -0.004001 \n85 -0.010409 0.000628 \n88 -0.010563 0.009873 \n... ... ... \n123530 -0.010649 0.011429 \n123531 -0.010202 0.011268 \n123534 -0.010499 -0.002075 \n123538 -0.010370 0.011268 \n123545 -0.010659 0.011429 \n123547 -0.010243 0.011429 \n123552 -0.010499 -0.004234 \n123556 -0.009811 0.009586 \n123557 -0.010442 0.011268 \n123559 -0.010413 0.004634 \n123560 -0.010509 0.001001 \n123564 -0.010324 0.010644 \n123565 -0.010213 0.009070 \n123566 -0.010273 0.010796 \n123570 -0.010073 -0.003684 \n123571 -0.010541 0.004295 \n123572 -0.010649 0.004313 \n123574 -0.010563 0.004034 \n123577 -0.010348 0.011268 \n123580 -0.010114 0.002922 \n123583 -0.009921 0.000380 \n123588 -0.010305 0.011111 \n123592 -0.010499 0.005988 \n123598 -0.010390 0.008232 \n123601 -0.010429 0.003769 \n123602 -0.010494 0.011111 \n123603 -0.010584 0.011429 \n123605 -0.010670 0.011429 \n123606 -0.010606 0.011429 \n123621 -0.009972 -0.001544 \n\n hist_amount_month_ratio_var hist_amount_month_ratio_skew \\\n0 7.021478e-06 2.325093 \n1 4.802841e-06 3.750952 \n3 9.606558e-06 1.857336 \n4 4.945579e-05 1.744364 \n6 2.151042e-05 2.275851 \n9 4.348479e-06 2.485897 \n15 5.367649e-05 1.041465 \n17 8.634764e-06 4.420202 \n18 1.699686e-06 1.813646 \n19 1.716750e-06 7.154828 \n21 4.068498e-06 2.192202 \n23 1.833984e-05 4.408214 \n30 1.329936e-05 3.070345 \n32 9.725768e-06 5.125162 \n34 7.239933e-06 4.795825 \n35 5.751860e-05 2.056496 \n37 1.943868e-05 1.817331 \n38 7.484211e-06 2.498755 \n49 2.548476e-06 4.230909 \n53 8.258187e-06 2.865921 \n56 1.422780e-05 2.160744 \n59 1.413391e-06 3.429596 \n64 1.102244e-05 4.718124 \n66 5.264418e-06 5.018287 \n67 4.192287e-06 0.731400 \n69 4.868969e-05 1.739485 \n73 8.120549e-07 1.819961 \n82 2.242992e-06 1.729908 \n85 3.460653e-06 2.487402 \n88 6.786774e-06 4.189991 \n... ... ... \n123530 5.508064e-05 0.684789 \n123531 5.677488e-05 1.897249 \n123534 4.653994e-06 1.291636 \n123538 9.433991e-06 3.407686 \n123545 3.372245e-05 1.571850 \n123547 3.913459e-05 2.161948 \n123552 2.055753e-06 1.596826 \n123556 2.037677e-05 2.490857 \n123557 1.433661e-05 2.232838 \n123559 1.904434e-05 1.598586 \n123560 6.543049e-06 1.336710 \n123564 1.148584e-05 4.024532 \n123565 5.777533e-05 1.117836 \n123566 1.017299e-05 5.769637 \n123570 4.261955e-06 0.770890 \n123571 5.497623e-06 3.563788 \n123572 1.115247e-05 3.199864 \n123574 1.101365e-05 3.113859 \n123577 5.862459e-05 2.147626 \n123580 1.278513e-05 1.146973 \n123583 8.158079e-06 1.262023 \n123588 5.965258e-06 5.267443 \n123592 1.309892e-05 2.487557 \n123598 1.150697e-05 3.225176 \n123601 6.185196e-06 4.796626 \n123602 1.624012e-05 3.863249 \n123603 9.552742e-06 3.883310 \n123605 1.794239e-05 2.314442 \n123606 8.551966e-05 0.916314 \n123621 1.997562e-06 2.253555 \n\n hist_purchase_date_diff hist_purchase_date_average \\\n0 268 3.941176 \n1 401 5.141026 \n3 77 2.961538 \n4 419 3.809091 \n6 138 2.875000 \n9 265 5.520833 \n15 105 9.545455 \n17 170 2.786885 \n18 96 3.310345 \n19 111 1.370370 \n21 270 2.783505 \n23 157 6.826087 \n30 386 1.473282 \n32 312 2.836364 \n34 342 0.530233 \n35 114 5.700000 \n37 103 1.980769 \n38 281 3.157303 \n49 103 1.355263 \n53 72 2.250000 \n56 197 4.377778 \n59 101 1.010000 \n64 316 4.937500 \n66 309 4.120000 \n67 168 24.000000 \n69 51 4.250000 \n73 108 4.695652 \n82 86 1.755102 \n85 110 1.294118 \n88 315 0.910405 \n... ... ... \n123530 258 3.739130 \n123531 107 8.230769 \n123534 399 9.500000 \n123538 99 0.738806 \n123545 379 1.138138 \n123547 309 6.180000 \n123552 300 6.976744 \n123556 179 8.136364 \n123557 296 1.566138 \n123559 92 2.787879 \n123560 349 4.105882 \n123564 210 3.181818 \n123565 166 16.600000 \n123566 380 9.047619 \n123570 54 1.636364 \n123571 414 6.000000 \n123572 99 1.053191 \n123574 213 5.461538 \n123577 221 17.000000 \n123580 234 4.978723 \n123583 121 6.722222 \n123588 156 1.228346 \n123592 164 5.857143 \n123598 107 1.945455 \n123601 142 3.944444 \n123602 379 0.737354 \n123603 101 0.467593 \n123605 272 3.056180 \n123606 232 4.296296 \n123621 151 2.435484 \n\n hist_purchase_date_uptonow hist_purchase_date_uptomin \\\n0 2181 2449 \n1 2129 2530 \n3 2128 2205 \n4 2121 2541 \n6 2122 2261 \n9 2273 2539 \n15 2119 2225 \n17 2125 2295 \n18 2142 2239 \n19 2425 2536 \n21 2119 2389 \n23 2124 2281 \n30 2120 2506 \n32 2129 2442 \n34 2120 2462 \n35 2155 2270 \n37 2245 2349 \n38 2183 2464 \n49 2178 2282 \n53 2122 2195 \n56 2179 2376 \n59 2148 2249 \n64 2123 2440 \n66 2119 2428 \n67 2325 2494 \n69 2221 2272 \n73 2122 2231 \n82 2140 2227 \n85 2120 2231 \n88 2119 2434 \n... ... ... \n123530 2123 2381 \n123531 2200 2308 \n123534 2140 2539 \n123538 2147 2247 \n123545 2120 2499 \n123547 2132 2441 \n123552 2120 2420 \n123556 2122 2301 \n123557 2120 2417 \n123559 2119 2211 \n123560 2148 2498 \n123564 2119 2330 \n123565 2144 2310 \n123566 2158 2538 \n123570 2209 2264 \n123571 2123 2537 \n123572 2127 2226 \n123574 2120 2333 \n123577 2119 2341 \n123580 2198 2433 \n123583 2133 2254 \n123588 2181 2337 \n123592 2127 2291 \n123598 2123 2230 \n123601 2132 2275 \n123602 2148 2528 \n123603 2120 2221 \n123605 2120 2392 \n123606 2119 2352 \n123621 2240 2392 \n\n hist_first_buy hist_last_buy new_transactions_count \\\n0 3.0 272.0 3.0 \n1 12.0 413.0 9.0 \n3 3.0 81.0 10.0 \n4 399.0 819.0 6.0 \n6 8.0 147.0 9.0 \n9 310.0 576.0 9.0 \n15 13.0 119.0 4.0 \n17 4.0 174.0 6.0 \n18 -1.0 96.0 3.0 \n19 6.0 118.0 4.0 \n21 2.0 272.0 12.0 \n23 18.0 175.0 3.0 \n30 5.0 392.0 13.0 \n32 10.0 323.0 6.0 \n34 21.0 363.0 19.0 \n35 0.0 114.0 11.0 \n37 13.0 117.0 5.0 \n38 19.0 301.0 7.0 \n49 17.0 121.0 8.0 \n53 13.0 86.0 3.0 \n56 15.0 212.0 4.0 \n59 20.0 122.0 12.0 \n64 13.0 329.0 7.0 \n66 24.0 333.0 3.0 \n67 170.0 339.0 4.0 \n69 27.0 78.0 11.0 \n73 8.0 117.0 3.0 \n82 11.0 98.0 7.0 \n85 7.0 118.0 15.0 \n88 18.0 333.0 6.0 \n... ... ... ... \n123530 10.0 269.0 12.0 \n123531 22.0 130.0 16.0 \n123534 795.0 1195.0 4.0 \n123538 23.0 122.0 14.0 \n123545 12.0 392.0 14.0 \n123547 11.0 321.0 7.0 \n123552 3.0 303.0 6.0 \n123556 29.0 209.0 6.0 \n123557 5.0 302.0 3.0 \n123559 27.0 119.0 5.0 \n123560 14.0 363.0 9.0 \n123564 0.0 211.0 15.0 \n123565 20.0 187.0 3.0 \n123566 888.0 1268.0 8.0 \n123570 5.0 60.0 12.0 \n123571 858.0 1273.0 4.0 \n123572 13.0 112.0 3.0 \n123574 28.0 241.0 4.0 \n123577 21.0 242.0 8.0 \n123580 19.0 254.0 14.0 \n123583 16.0 137.0 4.0 \n123588 24.0 180.0 20.0 \n123592 8.0 173.0 7.0 \n123598 8.0 115.0 9.0 \n123601 25.0 168.0 5.0 \n123602 15.0 395.0 13.0 \n123603 17.0 119.0 44.0 \n123605 30.0 302.0 20.0 \n123606 10.0 242.0 5.0 \n123621 0.0 151.0 6.0 \n\n new_purchase_amount_sum new_purchase_amount_max \\\n0 -1.777344 -0.383301 \n1 -5.944336 -0.506348 \n3 -5.744385 -0.447998 \n4 -1.414844 0.800000 \n6 -4.311127 -0.019623 \n9 -6.023926 -0.568359 \n15 -2.579102 -0.593750 \n17 -3.561768 -0.476807 \n18 -2.014160 -0.641602 \n19 -2.807617 -0.649414 \n21 -4.705920 0.800000 \n23 -1.793945 -0.555664 \n30 -7.105255 0.038300 \n32 -3.714600 -0.131104 \n34 -11.530029 -0.440430 \n35 -7.253906 -0.553711 \n37 -2.830811 -0.308350 \n38 -4.842285 -0.604492 \n49 -5.030273 -0.511230 \n53 -2.017090 -0.621094 \n56 -1.822998 -0.116943 \n59 -6.925415 0.154663 \n64 -3.698242 0.329102 \n66 -2.003418 -0.596680 \n67 -0.735840 0.605469 \n69 -7.666504 -0.607422 \n73 -1.957520 -0.508789 \n82 -4.876465 -0.638184 \n85 -8.531609 -0.010612 \n88 -3.883301 -0.548340 \n... ... ... \n123530 -6.486816 -0.272217 \n123531 -7.307739 0.289551 \n123534 -2.651367 -0.558105 \n123538 -8.805664 -0.247559 \n123545 -4.497473 0.800000 \n123547 -2.771289 0.800000 \n123552 -3.654297 -0.506836 \n123556 0.520959 0.800000 \n123557 -1.221863 -0.042175 \n123559 -3.497070 -0.670410 \n123560 -4.352554 -0.026077 \n123564 -9.934082 -0.387695 \n123565 -0.594531 0.800000 \n123566 -5.353027 -0.551758 \n123570 -7.214844 -0.362793 \n123571 -2.594238 -0.584473 \n123572 -1.966309 -0.518555 \n123574 -2.426270 -0.437012 \n123577 -5.094971 -0.417725 \n123580 -9.939941 -0.636230 \n123583 -1.537842 -0.266113 \n123588 -13.917480 -0.560547 \n123592 -4.628906 -0.566406 \n123598 -4.471484 0.800000 \n123601 -2.116992 0.800000 \n123602 -8.375977 -0.418945 \n123603 -28.175598 -0.122375 \n123605 -10.515125 0.800000 \n123606 -1.956543 0.423340 \n123621 -3.779785 -0.499023 \n\n new_purchase_amount_min new_purchase_amount_mean \\\n0 -0.722168 -0.592448 \n1 -0.740723 -0.660482 \n3 -0.671875 -0.574438 \n4 -0.704102 -0.235807 \n6 -0.629883 -0.479014 \n9 -0.716797 -0.669325 \n15 -0.721191 -0.644775 \n17 -0.679199 -0.593628 \n18 -0.687012 -0.671387 \n19 -0.727539 -0.701904 \n21 -0.719727 -0.392160 \n23 -0.641602 -0.597982 \n30 -0.708008 -0.546558 \n32 -0.738281 -0.619100 \n34 -0.734375 -0.606844 \n35 -0.735352 -0.659446 \n37 -0.676758 -0.566162 \n38 -0.734863 -0.691755 \n49 -0.723633 -0.628784 \n53 -0.724609 -0.672363 \n56 -0.695801 -0.455750 \n59 -0.725586 -0.577118 \n64 -0.731934 -0.528320 \n66 -0.721680 -0.667806 \n67 -0.598145 -0.183960 \n69 -0.738281 -0.696955 \n73 -0.731934 -0.652507 \n82 -0.740723 -0.696638 \n85 -0.734863 -0.568774 \n88 -0.720703 -0.647217 \n... ... ... \n123530 -0.701172 -0.540568 \n123531 -0.732422 -0.456734 \n123534 -0.732910 -0.662842 \n123538 -0.728516 -0.628976 \n123545 -0.734863 -0.321248 \n123547 -0.704590 -0.395898 \n123552 -0.679199 -0.609049 \n123556 -0.717773 0.086827 \n123557 -0.658203 -0.407288 \n123559 -0.718262 -0.699414 \n123560 -0.729004 -0.483617 \n123564 -0.731934 -0.662272 \n123565 -0.705078 -0.198177 \n123566 -0.710938 -0.669128 \n123570 -0.742188 -0.601237 \n123571 -0.709473 -0.648560 \n123572 -0.724121 -0.655436 \n123574 -0.698242 -0.606567 \n123577 -0.723145 -0.636871 \n123580 -0.742188 -0.709996 \n123583 -0.471924 -0.384460 \n123588 -0.745605 -0.695874 \n123592 -0.727051 -0.661272 \n123598 -0.724609 -0.496832 \n123601 -0.740723 -0.423398 \n123602 -0.740723 -0.644306 \n123603 -0.745605 -0.640355 \n123605 -0.729004 -0.525756 \n123606 -0.628418 -0.391309 \n123621 -0.708008 -0.629964 \n\n new_purchase_amount_var new_purchase_amount_skew \\\n0 0.033439 1.585826 \n1 0.005061 1.278390 \n3 0.005352 0.379891 \n4 0.476882 1.048725 \n6 0.032530 2.485460 \n9 0.001767 1.929070 \n15 0.003196 -1.026003 \n17 0.005408 0.582216 \n18 0.000666 1.725774 \n19 0.001271 1.786786 \n21 0.183274 2.233973 \n23 0.001848 -0.136192 \n30 0.050368 1.800035 \n32 0.057400 2.425887 \n34 0.009109 0.388497 \n35 0.004793 0.383066 \n37 0.021997 1.926749 \n38 0.001958 1.487699 \n49 0.006979 0.425032 \n53 0.002680 -0.084864 \n56 0.067763 0.792408 \n59 0.057405 3.021042 \n64 0.144568 2.584308 \n66 0.004129 1.121062 \n67 0.288408 1.754694 \n69 0.002035 1.561365 \n73 0.015548 1.703381 \n82 0.001397 0.480258 \n85 0.031408 2.397950 \n88 0.005395 0.691475 \n... ... ... \n123530 0.017207 0.883361 \n123531 0.114236 1.222646 \n123534 0.006387 0.855405 \n123538 0.016273 2.330826 \n123545 0.291575 1.471117 \n123547 0.286800 2.482012 \n123552 0.005225 0.593504 \n123556 0.409314 0.016557 \n123557 0.104653 1.390565 \n123559 0.000337 1.092493 \n123560 0.086878 0.779028 \n123564 0.007027 2.762001 \n123565 0.747329 1.731414 \n123566 0.002906 1.776205 \n123570 0.010156 1.065906 \n123571 0.002668 0.175754 \n123572 0.014052 1.732018 \n123574 0.013625 1.637176 \n123577 0.009034 2.124155 \n123580 0.001085 1.287081 \n123583 0.008920 0.606833 \n123588 0.002123 1.615670 \n123592 0.002673 0.863244 \n123598 0.240069 2.916693 \n123601 0.467915 2.233753 \n123602 0.014632 1.236888 \n123603 0.014307 2.497845 \n123605 0.133347 2.988360 \n123606 0.208012 2.219455 \n123621 0.005558 1.174936 \n\n new_installments_sum new_installments_max new_installments_mean \\\n0 5.0 3.0 1.666667 \n1 11.0 3.0 1.222222 \n3 29.0 12.0 2.900000 \n4 6.0 2.0 1.200000 \n6 9.0 2.0 1.125000 \n9 9.0 1.0 1.000000 \n15 5.0 2.0 1.250000 \n17 5.0 1.0 1.000000 \n18 3.0 1.0 1.000000 \n19 4.0 1.0 1.000000 \n21 15.0 4.0 1.666667 \n23 3.0 1.0 1.000000 \n30 20.0 6.0 1.666667 \n32 8.0 3.0 1.333333 \n34 20.0 2.0 1.111111 \n35 10.0 1.0 1.000000 \n37 7.0 3.0 1.400000 \n38 8.0 2.0 1.142857 \n49 8.0 1.0 1.000000 \n53 4.0 2.0 1.333333 \n56 17.0 8.0 4.250000 \n59 13.0 2.0 1.181818 \n64 6.0 1.0 1.000000 \n66 6.0 4.0 2.000000 \n67 10.0 6.0 2.500000 \n69 10.0 1.0 1.000000 \n73 3.0 1.0 1.000000 \n82 7.0 1.0 1.000000 \n85 15.0 1.0 1.000000 \n88 6.0 1.0 1.000000 \n... ... ... ... \n123530 21.0 3.0 1.750000 \n123531 21.0 3.0 1.312500 \n123534 5.0 3.0 1.666667 \n123538 14.0 1.0 1.000000 \n123545 33.0 12.0 2.750000 \n123547 13.0 5.0 2.600000 \n123552 9.0 2.0 1.500000 \n123556 4.0 2.0 1.333333 \n123557 3.0 1.0 1.000000 \n123559 5.0 1.0 1.000000 \n123560 9.0 1.0 1.000000 \n123564 15.0 1.0 1.000000 \n123565 8.0 6.0 2.666667 \n123566 9.0 2.0 1.125000 \n123570 19.0 3.0 1.583333 \n123571 3.0 1.0 1.000000 \n123572 3.0 1.0 1.000000 \n123574 4.0 1.0 1.000000 \n123577 7.0 1.0 1.000000 \n123580 14.0 1.0 1.000000 \n123583 18.0 10.0 6.000000 \n123588 20.0 1.0 1.000000 \n123592 5.0 1.0 1.000000 \n123598 16.0 6.0 1.777778 \n123601 14.0 10.0 2.800000 \n123602 13.0 1.0 1.000000 \n123603 60.0 6.0 1.363636 \n123605 22.0 5.0 1.222222 \n123606 16.0 12.0 3.200000 \n123621 7.0 3.0 1.750000 \n\n new_installments_var new_installments_skew new_purchase_date_max \\\n0 1.333333 1.732051 1.519845e+09 \n1 0.444444 3.000000 1.524247e+09 \n3 11.211111 2.661292 1.524000e+09 \n4 0.200000 2.236068 1.523535e+09 \n6 0.125000 2.828427 1.524562e+09 \n9 0.000000 0.000000 1.511060e+09 \n15 0.250000 2.000000 1.523560e+09 \n17 0.000000 0.000000 1.522746e+09 \n18 0.000000 0.000000 1.524116e+09 \n19 0.000000 0.000000 1.497615e+09 \n21 1.250000 1.533304 1.525064e+09 \n23 0.000000 0.000000 1.521130e+09 \n30 2.242424 2.635071 1.525032e+09 \n32 0.666667 2.449490 1.524817e+09 \n34 0.104575 2.705788 1.525086e+09 \n35 0.000000 0.000000 1.521904e+09 \n37 0.800000 2.236068 1.513107e+09 \n38 0.142857 2.645751 1.518833e+09 \n49 0.000000 0.000000 1.519555e+09 \n53 0.333333 1.732051 1.521733e+09 \n56 8.916667 0.422521 1.518968e+09 \n59 0.163636 1.922718 1.521843e+09 \n64 0.000000 0.000000 1.525019e+09 \n66 3.000000 1.732051 1.521115e+09 \n67 5.666667 1.779179 1.509198e+09 \n69 0.000000 0.000000 1.516038e+09 \n73 0.000000 0.000000 1.522159e+09 \n82 0.000000 0.000000 1.523847e+09 \n85 0.000000 0.000000 1.525105e+09 \n88 0.000000 0.000000 1.524905e+09 \n... ... ... ... \n123530 0.568182 0.477594 1.524825e+09 \n123531 0.495833 2.081626 1.521986e+09 \n123534 1.333333 1.732051 1.524651e+09 \n123538 0.000000 0.000000 1.521216e+09 \n123545 15.113636 2.086667 1.524691e+09 \n123547 3.300000 0.567163 1.525106e+09 \n123552 0.300000 0.000000 1.522941e+09 \n123556 0.333333 1.732051 1.524988e+09 \n123557 0.000000 0.000000 1.521714e+09 \n123559 0.000000 0.000000 1.523985e+09 \n123560 0.000000 0.000000 1.521180e+09 \n123564 0.000000 0.000000 1.525114e+09 \n123565 8.333333 1.732051 1.523988e+09 \n123566 0.125000 2.828427 1.522508e+09 \n123570 0.628788 0.987605 1.516191e+09 \n123571 0.000000 0.000000 1.524035e+09 \n123572 0.000000 0.000000 1.523907e+09 \n123574 0.000000 0.000000 1.522922e+09 \n123577 0.000000 0.000000 1.523034e+09 \n123580 0.000000 0.000000 1.519523e+09 \n123583 13.000000 1.152070 1.524225e+09 \n123588 0.000000 0.000000 1.519728e+09 \n123592 0.000000 0.000000 1.525008e+09 \n123598 2.944444 2.347580 1.524675e+09 \n123601 16.200000 2.236068 1.524587e+09 \n123602 0.000000 0.000000 1.521740e+09 \n123603 1.492600 3.338334 1.525102e+09 \n123605 0.888889 4.242641 1.525023e+09 \n123606 24.200000 2.236068 1.523882e+09 \n123621 0.916667 0.854563 1.511654e+09 \n\n new_purchase_date_min new_month_lag_max new_month_lag_min \\\n0 1.517651e+09 2.0 2.0 \n1 1.520080e+09 2.0 1.0 \n3 1.520162e+09 2.0 1.0 \n4 1.520132e+09 2.0 1.0 \n6 1.520019e+09 2.0 1.0 \n9 1.507467e+09 2.0 1.0 \n15 1.523109e+09 2.0 2.0 \n17 1.520256e+09 2.0 1.0 \n18 1.519990e+09 2.0 1.0 \n19 1.493993e+09 2.0 1.0 \n21 1.520343e+09 2.0 1.0 \n23 1.520142e+09 1.0 1.0 \n30 1.520361e+09 2.0 1.0 \n32 1.521451e+09 2.0 1.0 \n34 1.520331e+09 2.0 1.0 \n35 1.517738e+09 2.0 1.0 \n37 1.512228e+09 2.0 2.0 \n38 1.518191e+09 2.0 2.0 \n49 1.515426e+09 2.0 1.0 \n53 1.521302e+09 1.0 1.0 \n56 1.515064e+09 2.0 1.0 \n59 1.520594e+09 2.0 2.0 \n64 1.520604e+09 2.0 1.0 \n66 1.519917e+09 1.0 1.0 \n67 1.504462e+09 2.0 1.0 \n69 1.513434e+09 2.0 1.0 \n73 1.521654e+09 1.0 1.0 \n82 1.519997e+09 2.0 1.0 \n85 1.520392e+09 2.0 1.0 \n88 1.521880e+09 2.0 1.0 \n... ... ... ... \n123530 1.521135e+09 2.0 1.0 \n123531 1.518883e+09 2.0 1.0 \n123534 1.520357e+09 2.0 1.0 \n123538 1.517690e+09 2.0 1.0 \n123545 1.520335e+09 2.0 1.0 \n123547 1.519890e+09 2.0 1.0 \n123552 1.520329e+09 2.0 1.0 \n123556 1.520292e+09 2.0 1.0 \n123557 1.520866e+09 1.0 1.0 \n123559 1.519938e+09 2.0 1.0 \n123560 1.517502e+09 2.0 1.0 \n123564 1.520097e+09 2.0 1.0 \n123565 1.521475e+09 2.0 1.0 \n123566 1.522143e+09 1.0 1.0 \n123570 1.512591e+09 2.0 1.0 \n123571 1.520789e+09 2.0 1.0 \n123572 1.521955e+09 2.0 1.0 \n123574 1.520572e+09 2.0 1.0 \n123577 1.520077e+09 2.0 1.0 \n123580 1.515586e+09 2.0 1.0 \n123583 1.520272e+09 2.0 1.0 \n123588 1.515267e+09 2.0 1.0 \n123592 1.520581e+09 2.0 1.0 \n123598 1.521050e+09 2.0 1.0 \n123601 1.520114e+09 2.0 1.0 \n123602 1.517842e+09 2.0 1.0 \n123603 1.520376e+09 2.0 1.0 \n123605 1.519895e+09 2.0 1.0 \n123606 1.519986e+09 2.0 1.0 \n123621 1.509494e+09 1.0 1.0 \n\n new_month_lag_mean new_month_lag_var new_month_lag_skew \\\n0 2.000000 0.000000 0.000000 \n1 1.444444 0.277778 0.271052 \n3 1.300000 0.233333 1.035098 \n4 1.166667 0.166667 2.449490 \n6 1.666667 0.250000 -0.857143 \n9 1.444444 0.277778 0.271052 \n15 2.000000 0.000000 0.000000 \n17 1.166667 0.166667 2.449490 \n18 1.666667 0.333333 -1.732051 \n19 1.500000 0.333333 0.000000 \n21 1.833333 0.151515 -2.055237 \n23 1.000000 0.000000 0.000000 \n30 1.692308 0.230769 -0.946212 \n32 1.666667 0.266667 -0.968246 \n34 1.315789 0.228070 0.862214 \n35 1.636364 0.254545 -0.660687 \n37 2.000000 0.000000 0.000000 \n38 2.000000 0.000000 0.000000 \n49 1.250000 0.214286 1.440165 \n53 1.000000 0.000000 0.000000 \n56 1.250000 0.250000 2.000000 \n59 2.000000 0.000000 0.000000 \n64 1.571429 0.285714 -0.374166 \n66 1.000000 0.000000 0.000000 \n67 1.250000 0.250000 2.000000 \n69 1.636364 0.254545 -0.660687 \n73 1.000000 0.000000 0.000000 \n82 1.428571 0.285714 0.374166 \n85 1.533333 0.266667 -0.148961 \n88 1.666667 0.266667 -0.968246 \n... ... ... ... \n123530 1.416667 0.265152 0.388403 \n123531 1.625000 0.250000 -0.571429 \n123534 1.250000 0.250000 2.000000 \n123538 1.285714 0.219780 1.066536 \n123545 1.285714 0.219780 1.066536 \n123547 1.428571 0.285714 0.374166 \n123552 1.333333 0.266667 0.968246 \n123556 1.500000 0.300000 0.000000 \n123557 1.000000 0.000000 0.000000 \n123559 1.400000 0.300000 0.608581 \n123560 1.666667 0.250000 -0.857143 \n123564 1.400000 0.257143 0.455083 \n123565 1.666667 0.333333 -1.732051 \n123566 1.000000 0.000000 0.000000 \n123570 1.583333 0.265152 -0.388403 \n123571 1.500000 0.333333 0.000000 \n123572 1.333333 0.333333 1.732051 \n123574 1.250000 0.250000 2.000000 \n123577 1.750000 0.214286 -1.440165 \n123580 1.928571 0.071429 -3.741657 \n123583 1.250000 0.250000 2.000000 \n123588 1.350000 0.239474 0.681161 \n123592 1.571429 0.285714 -0.374166 \n123598 1.333333 0.250000 0.857143 \n123601 1.400000 0.300000 0.608581 \n123602 1.692308 0.230769 -0.946212 \n123603 1.545455 0.253700 -0.189082 \n123605 1.700000 0.221053 -0.945300 \n123606 1.200000 0.200000 2.236068 \n123621 1.000000 0.000000 0.000000 \n\n new_month_diff_max new_month_diff_min new_month_diff_mean \\\n0 73.0 72.0 72.666667 \n1 71.0 70.0 70.777778 \n3 71.0 70.0 70.700000 \n4 71.0 71.0 71.000000 \n6 71.0 70.0 70.666667 \n9 76.0 76.0 76.000000 \n15 71.0 71.0 71.000000 \n17 71.0 70.0 70.833333 \n18 71.0 71.0 71.000000 \n19 81.0 81.0 81.000000 \n21 71.0 70.0 70.416667 \n23 71.0 71.0 71.000000 \n30 71.0 70.0 70.384615 \n32 71.0 70.0 70.833333 \n34 71.0 70.0 70.526316 \n35 72.0 71.0 71.818182 \n37 75.0 75.0 75.000000 \n38 73.0 73.0 73.000000 \n49 73.0 72.0 72.625000 \n53 71.0 70.0 70.333333 \n56 73.0 72.0 72.750000 \n59 72.0 71.0 71.916667 \n64 71.0 70.0 70.142857 \n66 71.0 71.0 71.000000 \n67 77.0 76.0 76.750000 \n69 74.0 73.0 73.909091 \n73 70.0 70.0 70.000000 \n82 71.0 71.0 71.000000 \n85 71.0 70.0 70.533333 \n88 71.0 70.0 70.166667 \n... ... ... ... \n123530 71.0 70.0 70.333333 \n123531 72.0 71.0 71.125000 \n123534 71.0 70.0 70.500000 \n123538 72.0 71.0 71.500000 \n123545 71.0 70.0 70.785714 \n123547 71.0 70.0 70.857143 \n123552 71.0 70.0 70.666667 \n123556 71.0 70.0 70.666667 \n123557 71.0 70.0 70.666667 \n123559 71.0 70.0 70.800000 \n123560 72.0 71.0 71.888889 \n123564 71.0 70.0 70.533333 \n123565 71.0 71.0 71.000000 \n123566 70.0 70.0 70.000000 \n123570 74.0 73.0 73.666667 \n123571 71.0 71.0 71.000000 \n123572 71.0 70.0 70.333333 \n123574 71.0 71.0 71.000000 \n123577 71.0 70.0 70.875000 \n123580 73.0 72.0 72.714286 \n123583 71.0 70.0 70.250000 \n123588 73.0 72.0 72.350000 \n123592 71.0 70.0 70.428571 \n123598 71.0 70.0 70.666667 \n123601 71.0 70.0 70.600000 \n123602 72.0 71.0 71.923077 \n123603 71.0 70.0 70.568182 \n123605 71.0 70.0 70.450000 \n123606 71.0 71.0 71.000000 \n123621 75.0 74.0 74.666667 \n\n new_month_diff_var new_month_diff_skew new_weekend_sum \\\n0 0.333333 -1.732051 1.0 \n1 0.194444 -1.619848 3.0 \n3 0.233333 -1.035098 3.0 \n4 0.000000 0.000000 2.0 \n6 0.250000 -0.857143 2.0 \n9 0.000000 0.000000 2.0 \n15 0.000000 0.000000 1.0 \n17 0.166667 -2.449490 1.0 \n18 0.000000 0.000000 0.0 \n19 0.000000 0.000000 1.0 \n21 0.265152 0.388403 3.0 \n23 0.000000 0.000000 1.0 \n30 0.256410 0.538593 6.0 \n32 0.166667 -2.449490 0.0 \n34 0.263158 -0.114668 9.0 \n35 0.163636 -1.922718 4.0 \n37 0.000000 0.000000 3.0 \n38 0.000000 0.000000 3.0 \n49 0.267857 -0.644061 1.0 \n53 0.333333 1.732051 1.0 \n56 0.250000 -2.000000 1.0 \n59 0.083333 -3.464102 8.0 \n64 0.142857 2.645751 3.0 \n66 0.000000 0.000000 0.0 \n67 0.250000 -2.000000 2.0 \n69 0.090909 -3.316625 8.0 \n73 0.000000 0.000000 0.0 \n82 0.000000 0.000000 2.0 \n85 0.266667 -0.148961 4.0 \n88 0.166667 2.449490 6.0 \n... ... ... ... \n123530 0.242424 0.812404 0.0 \n123531 0.116667 2.509457 5.0 \n123534 0.333333 0.000000 0.0 \n123538 0.269231 0.000000 4.0 \n123545 0.181319 -1.565624 4.0 \n123547 0.142857 -2.645751 0.0 \n123552 0.266667 -0.968246 2.0 \n123556 0.266667 -0.968246 1.0 \n123557 0.333333 -1.732051 0.0 \n123559 0.200000 -2.236068 1.0 \n123560 0.111111 -3.000000 0.0 \n123564 0.266667 -0.148961 6.0 \n123565 0.000000 0.000000 1.0 \n123566 0.000000 0.000000 1.0 \n123570 0.242424 -0.812404 1.0 \n123571 0.000000 0.000000 2.0 \n123572 0.333333 1.732051 1.0 \n123574 0.000000 0.000000 1.0 \n123577 0.125000 -2.828427 2.0 \n123580 0.219780 -1.066536 6.0 \n123583 0.250000 2.000000 2.0 \n123588 0.239474 0.681161 10.0 \n123592 0.285714 0.374166 1.0 \n123598 0.250000 -0.857143 3.0 \n123601 0.300000 -0.608581 1.0 \n123602 0.076923 -3.605551 2.0 \n123603 0.251057 -0.285112 17.0 \n123605 0.260526 0.217687 8.0 \n123606 0.000000 0.000000 2.0 \n123621 0.266667 -0.968246 2.0 \n\n new_weekend_mean new_weekday_sum new_weekday_mean \\\n0 0.333333 11.0 3.666667 \n1 0.333333 27.0 3.000000 \n3 0.300000 32.0 3.200000 \n4 0.333333 24.0 4.000000 \n6 0.222222 30.0 3.333333 \n9 0.222222 21.0 2.333333 \n15 0.250000 14.0 3.500000 \n17 0.166667 10.0 1.666667 \n18 0.000000 10.0 3.333333 \n19 0.250000 13.0 3.250000 \n21 0.250000 36.0 3.000000 \n23 0.333333 11.0 3.666667 \n30 0.461538 50.0 3.846154 \n32 0.000000 11.0 1.833333 \n34 0.473684 74.0 3.894737 \n35 0.363636 36.0 3.272727 \n37 0.600000 16.0 3.200000 \n38 0.428571 27.0 3.857143 \n49 0.125000 14.0 1.750000 \n53 0.333333 10.0 3.333333 \n56 0.250000 9.0 2.250000 \n59 0.666667 56.0 4.666667 \n64 0.428571 27.0 3.857143 \n66 0.000000 9.0 3.000000 \n67 0.500000 15.0 3.750000 \n69 0.727273 50.0 4.545455 \n73 0.000000 4.0 1.333333 \n82 0.285714 24.0 3.428571 \n85 0.266667 47.0 3.133333 \n88 1.000000 31.0 5.166667 \n... ... ... ... \n123530 0.000000 34.0 2.833333 \n123531 0.312500 51.0 3.187500 \n123534 0.000000 7.0 1.750000 \n123538 0.285714 40.0 2.857143 \n123545 0.285714 38.0 2.714286 \n123547 0.000000 12.0 1.714286 \n123552 0.333333 17.0 2.833333 \n123556 0.166667 18.0 3.000000 \n123557 0.000000 5.0 1.666667 \n123559 0.200000 17.0 3.400000 \n123560 0.000000 14.0 1.555556 \n123564 0.400000 41.0 2.733333 \n123565 0.333333 7.0 2.333333 \n123566 0.125000 22.0 2.750000 \n123570 0.083333 31.0 2.583333 \n123571 0.500000 13.0 3.250000 \n123572 0.333333 7.0 2.333333 \n123574 0.250000 16.0 4.000000 \n123577 0.250000 34.0 4.250000 \n123580 0.428571 44.0 3.142857 \n123583 0.500000 14.0 3.500000 \n123588 0.500000 77.0 3.850000 \n123592 0.142857 21.0 3.000000 \n123598 0.333333 28.0 3.111111 \n123601 0.200000 8.0 1.600000 \n123602 0.153846 33.0 2.538462 \n123603 0.386364 149.0 3.386364 \n123605 0.400000 75.0 3.750000 \n123606 0.400000 17.0 3.400000 \n123621 0.333333 19.0 3.166667 \n\n new_authorized_flag_sum new_authorized_flag_mean new_category_1_sum \\\n0 3.0 1.0 0.0 \n1 9.0 1.0 2.0 \n3 10.0 1.0 1.0 \n4 6.0 1.0 0.0 \n6 9.0 1.0 0.0 \n9 9.0 1.0 0.0 \n15 4.0 1.0 0.0 \n17 6.0 1.0 0.0 \n18 3.0 1.0 0.0 \n19 4.0 1.0 0.0 \n21 12.0 1.0 1.0 \n23 3.0 1.0 0.0 \n30 13.0 1.0 0.0 \n32 6.0 1.0 0.0 \n34 19.0 1.0 2.0 \n35 11.0 1.0 0.0 \n37 5.0 1.0 0.0 \n38 7.0 1.0 0.0 \n49 8.0 1.0 0.0 \n53 3.0 1.0 0.0 \n56 4.0 1.0 1.0 \n59 12.0 1.0 1.0 \n64 7.0 1.0 1.0 \n66 3.0 1.0 0.0 \n67 4.0 1.0 0.0 \n69 11.0 1.0 0.0 \n73 3.0 1.0 0.0 \n82 7.0 1.0 0.0 \n85 15.0 1.0 1.0 \n88 6.0 1.0 0.0 \n... ... ... ... \n123530 12.0 1.0 0.0 \n123531 16.0 1.0 1.0 \n123534 4.0 1.0 1.0 \n123538 14.0 1.0 0.0 \n123545 14.0 1.0 4.0 \n123547 7.0 1.0 0.0 \n123552 6.0 1.0 0.0 \n123556 6.0 1.0 2.0 \n123557 3.0 1.0 0.0 \n123559 5.0 1.0 0.0 \n123560 9.0 1.0 3.0 \n123564 15.0 1.0 1.0 \n123565 3.0 1.0 0.0 \n123566 8.0 1.0 0.0 \n123570 12.0 1.0 5.0 \n123571 4.0 1.0 0.0 \n123572 3.0 1.0 0.0 \n123574 4.0 1.0 0.0 \n123577 8.0 1.0 0.0 \n123580 14.0 1.0 1.0 \n123583 4.0 1.0 0.0 \n123588 20.0 1.0 2.0 \n123592 7.0 1.0 0.0 \n123598 9.0 1.0 0.0 \n123601 5.0 1.0 3.0 \n123602 13.0 1.0 0.0 \n123603 44.0 1.0 2.0 \n123605 20.0 1.0 2.0 \n123606 5.0 1.0 1.0 \n123621 6.0 1.0 1.0 \n\n new_category_1_mean new_category_1_max new_category_1_min \\\n0 0.000000 0.0 0.0 \n1 0.222222 1.0 0.0 \n3 0.100000 1.0 0.0 \n4 0.000000 0.0 0.0 \n6 0.000000 0.0 0.0 \n9 0.000000 0.0 0.0 \n15 0.000000 0.0 0.0 \n17 0.000000 0.0 0.0 \n18 0.000000 0.0 0.0 \n19 0.000000 0.0 0.0 \n21 0.083333 1.0 0.0 \n23 0.000000 0.0 0.0 \n30 0.000000 0.0 0.0 \n32 0.000000 0.0 0.0 \n34 0.105263 1.0 0.0 \n35 0.000000 0.0 0.0 \n37 0.000000 0.0 0.0 \n38 0.000000 0.0 0.0 \n49 0.000000 0.0 0.0 \n53 0.000000 0.0 0.0 \n56 0.250000 1.0 0.0 \n59 0.083333 1.0 0.0 \n64 0.142857 1.0 0.0 \n66 0.000000 0.0 0.0 \n67 0.000000 0.0 0.0 \n69 0.000000 0.0 0.0 \n73 0.000000 0.0 0.0 \n82 0.000000 0.0 0.0 \n85 0.066667 1.0 0.0 \n88 0.000000 0.0 0.0 \n... ... ... ... \n123530 0.000000 0.0 0.0 \n123531 0.062500 1.0 0.0 \n123534 0.250000 1.0 0.0 \n123538 0.000000 0.0 0.0 \n123545 0.285714 1.0 0.0 \n123547 0.000000 0.0 0.0 \n123552 0.000000 0.0 0.0 \n123556 0.333333 1.0 0.0 \n123557 0.000000 0.0 0.0 \n123559 0.000000 0.0 0.0 \n123560 0.333333 1.0 0.0 \n123564 0.066667 1.0 0.0 \n123565 0.000000 0.0 0.0 \n123566 0.000000 0.0 0.0 \n123570 0.416667 1.0 0.0 \n123571 0.000000 0.0 0.0 \n123572 0.000000 0.0 0.0 \n123574 0.000000 0.0 0.0 \n123577 0.000000 0.0 0.0 \n123580 0.071429 1.0 0.0 \n123583 0.000000 0.0 0.0 \n123588 0.100000 1.0 0.0 \n123592 0.000000 0.0 0.0 \n123598 0.000000 0.0 0.0 \n123601 0.600000 1.0 0.0 \n123602 0.000000 0.0 0.0 \n123603 0.045455 1.0 0.0 \n123605 0.100000 1.0 0.0 \n123606 0.200000 1.0 0.0 \n123621 0.166667 1.0 0.0 \n\n new_card_id_size new_card_id_count new_month_nunique \\\n0 3.0 3.0 1.0 \n1 9.0 9.0 2.0 \n3 10.0 10.0 2.0 \n4 6.0 6.0 2.0 \n6 9.0 9.0 2.0 \n9 9.0 9.0 2.0 \n15 4.0 4.0 1.0 \n17 6.0 6.0 2.0 \n18 3.0 3.0 2.0 \n19 4.0 4.0 2.0 \n21 12.0 12.0 2.0 \n23 3.0 3.0 1.0 \n30 13.0 13.0 2.0 \n32 6.0 6.0 2.0 \n34 19.0 19.0 2.0 \n35 11.0 11.0 2.0 \n37 5.0 5.0 1.0 \n38 7.0 7.0 1.0 \n49 8.0 8.0 2.0 \n53 3.0 3.0 1.0 \n56 4.0 4.0 2.0 \n59 12.0 12.0 1.0 \n64 7.0 7.0 2.0 \n66 3.0 3.0 1.0 \n67 4.0 4.0 2.0 \n69 11.0 11.0 2.0 \n73 3.0 3.0 1.0 \n82 7.0 7.0 2.0 \n85 15.0 15.0 2.0 \n88 6.0 6.0 2.0 \n... ... ... ... \n123530 12.0 12.0 2.0 \n123531 16.0 16.0 2.0 \n123534 4.0 4.0 2.0 \n123538 14.0 14.0 2.0 \n123545 14.0 14.0 2.0 \n123547 7.0 7.0 2.0 \n123552 6.0 6.0 2.0 \n123556 6.0 6.0 2.0 \n123557 3.0 3.0 1.0 \n123559 5.0 5.0 2.0 \n123560 9.0 9.0 2.0 \n123564 15.0 15.0 2.0 \n123565 3.0 3.0 2.0 \n123566 8.0 8.0 1.0 \n123570 12.0 12.0 2.0 \n123571 4.0 4.0 2.0 \n123572 3.0 3.0 2.0 \n123574 4.0 4.0 2.0 \n123577 8.0 8.0 2.0 \n123580 14.0 14.0 2.0 \n123583 4.0 4.0 2.0 \n123588 20.0 20.0 2.0 \n123592 7.0 7.0 2.0 \n123598 9.0 9.0 2.0 \n123601 5.0 5.0 2.0 \n123602 13.0 13.0 2.0 \n123603 44.0 44.0 2.0 \n123605 20.0 20.0 2.0 \n123606 5.0 5.0 2.0 \n123621 6.0 6.0 1.0 \n\n new_month_mean new_month_min new_month_max new_hour_nunique \\\n0 2.000000 2.0 2.0 3.0 \n1 3.444444 3.0 4.0 8.0 \n3 3.300000 3.0 4.0 7.0 \n4 3.166667 3.0 4.0 5.0 \n6 3.666667 3.0 4.0 7.0 \n9 10.444444 10.0 11.0 8.0 \n15 4.000000 4.0 4.0 3.0 \n17 3.166667 3.0 4.0 4.0 \n18 3.666667 3.0 4.0 2.0 \n19 5.500000 5.0 6.0 4.0 \n21 3.833333 3.0 4.0 8.0 \n23 3.000000 3.0 3.0 3.0 \n30 3.692308 3.0 4.0 9.0 \n32 3.666667 3.0 4.0 5.0 \n34 3.315789 3.0 4.0 13.0 \n35 2.636364 2.0 3.0 10.0 \n37 12.000000 12.0 12.0 5.0 \n38 2.000000 2.0 2.0 6.0 \n49 1.250000 1.0 2.0 5.0 \n53 3.000000 3.0 3.0 2.0 \n56 1.250000 1.0 2.0 4.0 \n59 3.000000 3.0 3.0 9.0 \n64 3.571429 3.0 4.0 7.0 \n66 3.000000 3.0 3.0 2.0 \n67 9.250000 9.0 10.0 4.0 \n69 5.000000 1.0 12.0 7.0 \n73 3.000000 3.0 3.0 3.0 \n82 3.428571 3.0 4.0 6.0 \n85 3.533333 3.0 4.0 8.0 \n88 3.666667 3.0 4.0 3.0 \n... ... ... ... ... \n123530 3.416667 3.0 4.0 6.0 \n123531 2.625000 2.0 3.0 10.0 \n123534 3.250000 3.0 4.0 4.0 \n123538 2.285714 2.0 3.0 11.0 \n123545 3.285714 3.0 4.0 10.0 \n123547 3.428571 3.0 4.0 6.0 \n123552 3.333333 3.0 4.0 4.0 \n123556 3.500000 3.0 4.0 5.0 \n123557 3.000000 3.0 3.0 3.0 \n123559 3.400000 3.0 4.0 5.0 \n123560 2.666667 2.0 3.0 8.0 \n123564 3.400000 3.0 4.0 9.0 \n123565 3.666667 3.0 4.0 3.0 \n123566 3.000000 3.0 3.0 8.0 \n123570 5.583333 1.0 12.0 7.0 \n123571 3.500000 3.0 4.0 4.0 \n123572 3.333333 3.0 4.0 3.0 \n123574 3.250000 3.0 4.0 4.0 \n123577 3.750000 3.0 4.0 6.0 \n123580 1.928571 1.0 2.0 9.0 \n123583 3.250000 3.0 4.0 3.0 \n123588 1.350000 1.0 2.0 10.0 \n123592 3.571429 3.0 4.0 6.0 \n123598 3.333333 3.0 4.0 6.0 \n123601 3.400000 3.0 4.0 4.0 \n123602 2.692308 2.0 3.0 7.0 \n123603 3.545455 3.0 4.0 13.0 \n123605 3.700000 3.0 4.0 11.0 \n123606 3.200000 3.0 4.0 2.0 \n123621 11.000000 11.0 11.0 4.0 \n\n new_hour_mean new_hour_min new_hour_max new_weekofyear_nunique \\\n0 13.666667 9.0 19.0 3.0 \n1 15.222222 9.0 23.0 6.0 \n3 18.200000 11.0 21.0 7.0 \n4 8.000000 0.0 16.0 3.0 \n6 14.000000 9.0 19.0 5.0 \n9 15.222222 0.0 23.0 3.0 \n15 15.500000 13.0 19.0 2.0 \n17 11.666667 8.0 14.0 3.0 \n18 7.000000 5.0 11.0 2.0 \n19 11.750000 10.0 14.0 4.0 \n21 11.166667 0.0 17.0 6.0 \n23 12.666667 5.0 17.0 2.0 \n30 15.692308 10.0 23.0 6.0 \n32 11.666667 8.0 16.0 4.0 \n34 12.789474 3.0 22.0 8.0 \n35 12.090909 5.0 18.0 6.0 \n37 16.400000 12.0 20.0 3.0 \n38 12.857143 2.0 23.0 2.0 \n49 13.250000 8.0 19.0 6.0 \n53 16.000000 15.0 18.0 2.0 \n56 13.000000 9.0 17.0 4.0 \n59 15.666667 11.0 22.0 3.0 \n64 12.714286 6.0 17.0 4.0 \n66 14.000000 12.0 15.0 2.0 \n67 15.250000 13.0 18.0 3.0 \n69 15.000000 9.0 21.0 5.0 \n73 11.666667 4.0 17.0 2.0 \n82 11.000000 2.0 17.0 6.0 \n85 14.133333 3.0 21.0 6.0 \n88 9.833333 8.0 14.0 4.0 \n... ... ... ... ... \n123530 14.833333 10.0 18.0 6.0 \n123531 16.125000 10.0 23.0 4.0 \n123534 11.500000 6.0 17.0 3.0 \n123538 13.071429 5.0 21.0 6.0 \n123545 13.357143 5.0 21.0 6.0 \n123547 11.285714 6.0 16.0 5.0 \n123552 12.000000 9.0 15.0 3.0 \n123556 11.000000 5.0 23.0 4.0 \n123557 13.333333 10.0 16.0 2.0 \n123559 15.800000 12.0 21.0 4.0 \n123560 15.111111 6.0 20.0 4.0 \n123564 14.333333 8.0 19.0 7.0 \n123565 16.333333 15.0 18.0 3.0 \n123566 14.125000 9.0 20.0 1.0 \n123570 12.666667 7.0 20.0 5.0 \n123571 12.000000 7.0 17.0 3.0 \n123572 11.000000 5.0 19.0 3.0 \n123574 9.750000 5.0 17.0 2.0 \n123577 13.125000 6.0 17.0 3.0 \n123580 14.642857 1.0 19.0 4.0 \n123583 11.500000 7.0 17.0 3.0 \n123588 15.150000 10.0 22.0 9.0 \n123592 12.142857 7.0 19.0 6.0 \n123598 13.333333 8.0 21.0 6.0 \n123601 15.800000 4.0 22.0 5.0 \n123602 14.615385 9.0 21.0 6.0 \n123603 15.681818 10.0 23.0 9.0 \n123605 13.150000 8.0 22.0 7.0 \n123606 11.600000 10.0 12.0 4.0 \n123621 8.000000 0.0 18.0 3.0 \n\n new_weekofyear_mean new_weekofyear_min new_weekofyear_max \\\n0 7.000000 5.0 9.0 \n1 12.444444 9.0 16.0 \n3 12.100000 9.0 16.0 \n4 10.500000 9.0 15.0 \n6 13.333333 9.0 17.0 \n9 43.111111 40.0 46.0 \n15 14.750000 14.0 15.0 \n17 11.166667 10.0 14.0 \n18 13.666667 9.0 16.0 \n19 21.000000 18.0 24.0 \n21 15.333333 10.0 18.0 \n23 10.333333 9.0 11.0 \n30 14.538462 10.0 17.0 \n32 14.000000 12.0 17.0 \n34 12.894737 10.0 18.0 \n35 9.272727 5.0 12.0 \n37 49.200000 48.0 50.0 \n38 6.571429 6.0 7.0 \n49 4.000000 2.0 8.0 \n53 11.666667 11.0 12.0 \n56 3.250000 1.0 7.0 \n59 11.000000 10.0 12.0 \n64 14.714286 10.0 17.0 \n66 9.666667 9.0 11.0 \n67 38.500000 35.0 43.0 \n69 19.454545 1.0 51.0 \n73 12.666667 12.0 13.0 \n82 12.142857 9.0 16.0 \n85 13.800000 10.0 18.0 \n88 14.666667 12.0 17.0 \n... ... ... ... \n123530 13.916667 11.0 17.0 \n123531 10.500000 7.0 12.0 \n123534 12.500000 10.0 17.0 \n123538 8.357143 5.0 11.0 \n123545 12.214286 10.0 17.0 \n123547 12.857143 9.0 18.0 \n123552 12.000000 10.0 14.0 \n123556 13.333333 10.0 17.0 \n123557 11.333333 11.0 12.0 \n123559 12.200000 9.0 16.0 \n123560 9.555556 5.0 11.0 \n123564 13.400000 9.0 18.0 \n123565 14.333333 12.0 16.0 \n123566 13.000000 13.0 13.0 \n123570 22.250000 1.0 52.0 \n123571 13.250000 10.0 16.0 \n123572 13.666667 12.0 16.0 \n123574 11.000000 10.0 14.0 \n123577 13.125000 9.0 14.0 \n123580 6.571429 2.0 8.0 \n123583 12.500000 10.0 16.0 \n123588 4.650000 1.0 9.0 \n123592 14.000000 10.0 17.0 \n123598 13.111111 11.0 17.0 \n123601 13.000000 9.0 17.0 \n123602 9.230769 6.0 12.0 \n123603 13.613636 10.0 18.0 \n123605 14.200000 9.0 17.0 \n123606 11.000000 9.0 16.0 \n123621 45.166667 44.0 47.0 \n\n new_day_nunique new_day_mean new_day_min new_day_max \\\n0 3.0 15.666667 3.0 28.0 \n1 7.0 11.333333 3.0 20.0 \n3 8.0 13.600000 4.0 31.0 \n4 5.0 7.333333 4.0 12.0 \n6 7.0 11.000000 2.0 26.0 \n9 6.0 12.333333 8.0 19.0 \n15 2.0 10.750000 7.0 12.0 \n17 4.0 9.666667 3.0 31.0 \n18 2.0 13.333333 2.0 19.0 \n19 4.0 9.750000 5.0 16.0 \n21 10.0 19.500000 6.0 30.0 \n23 3.0 11.000000 4.0 15.0 \n30 9.0 19.153846 4.0 29.0 \n32 5.0 14.166667 4.0 27.0 \n34 11.0 19.368421 6.0 30.0 \n35 9.0 13.363636 3.0 24.0 \n37 4.0 8.600000 2.0 12.0 \n38 5.0 12.857143 9.0 17.0 \n49 8.0 16.000000 6.0 29.0 \n53 3.0 20.000000 17.0 22.0 \n56 4.0 11.250000 4.0 18.0 \n59 6.0 16.666667 9.0 23.0 \n64 6.0 24.142857 9.0 31.0 \n66 2.0 5.666667 1.0 15.0 \n67 3.0 17.750000 3.0 28.0 \n69 8.0 13.636364 6.0 24.0 \n73 2.0 25.000000 21.0 27.0 \n82 7.0 10.142857 2.0 17.0 \n85 11.0 18.200000 7.0 30.0 \n88 5.0 22.166667 14.0 28.0 \n... ... ... ... ... \n123530 10.0 22.333333 12.0 30.0 \n123531 11.0 22.187500 17.0 28.0 \n123534 4.0 16.500000 6.0 27.0 \n123538 12.0 16.357143 3.0 25.0 \n123545 8.0 14.357143 6.0 25.0 \n123547 5.0 13.428571 1.0 30.0 \n123552 5.0 11.500000 2.0 24.0 \n123556 6.0 15.833333 5.0 29.0 \n123557 3.0 16.000000 12.0 22.0 \n123559 5.0 11.400000 1.0 23.0 \n123560 7.0 12.777778 1.0 26.0 \n123564 11.0 19.133333 3.0 31.0 \n123565 3.0 17.000000 15.0 19.0 \n123566 4.0 28.750000 27.0 31.0 \n123570 11.0 13.583333 1.0 30.0 \n123571 4.0 15.500000 11.0 18.0 \n123572 3.0 22.666667 16.0 27.0 \n123574 3.0 8.250000 5.0 10.0 \n123577 3.0 7.875000 3.0 24.0 \n123580 11.0 14.357143 6.0 25.0 \n123583 3.0 18.250000 5.0 24.0 \n123588 16.0 19.550000 3.0 29.0 \n123592 6.0 18.285714 9.0 30.0 \n123598 7.0 19.555556 5.0 31.0 \n123601 5.0 15.200000 3.0 24.0 \n123602 10.0 10.769231 2.0 22.0 \n123603 23.0 16.772727 1.0 30.0 \n123605 14.0 16.450000 1.0 29.0 \n123606 5.0 9.200000 2.0 16.0 \n123621 5.0 10.333333 1.0 26.0 \n\n new_subsector_id_nunique new_merchant_category_id_nunique \\\n0 3.0 3.0 \n1 6.0 8.0 \n3 8.0 10.0 \n4 4.0 5.0 \n6 6.0 6.0 \n9 7.0 7.0 \n15 3.0 4.0 \n17 3.0 5.0 \n18 2.0 3.0 \n19 4.0 4.0 \n21 10.0 10.0 \n23 2.0 3.0 \n30 10.0 11.0 \n32 4.0 4.0 \n34 11.0 15.0 \n35 9.0 10.0 \n37 4.0 4.0 \n38 6.0 7.0 \n49 7.0 7.0 \n53 3.0 3.0 \n56 4.0 4.0 \n59 7.0 9.0 \n64 7.0 7.0 \n66 3.0 3.0 \n67 4.0 4.0 \n69 8.0 9.0 \n73 3.0 3.0 \n82 6.0 6.0 \n85 9.0 12.0 \n88 3.0 4.0 \n... ... ... \n123530 8.0 12.0 \n123531 8.0 12.0 \n123534 4.0 4.0 \n123538 5.0 8.0 \n123545 12.0 14.0 \n123547 5.0 7.0 \n123552 4.0 5.0 \n123556 5.0 6.0 \n123557 3.0 3.0 \n123559 4.0 5.0 \n123560 7.0 9.0 \n123564 11.0 12.0 \n123565 3.0 3.0 \n123566 5.0 6.0 \n123570 9.0 10.0 \n123571 4.0 4.0 \n123572 3.0 3.0 \n123574 3.0 3.0 \n123577 7.0 8.0 \n123580 7.0 10.0 \n123583 4.0 4.0 \n123588 10.0 11.0 \n123592 6.0 6.0 \n123598 7.0 8.0 \n123601 4.0 4.0 \n123602 6.0 8.0 \n123603 17.0 22.0 \n123605 10.0 15.0 \n123606 3.0 3.0 \n123621 3.0 5.0 \n\n new_price_sum new_price_mean new_price_max new_price_min \\\n0 -1.521810 -0.507270 -0.127767 -0.722168 \n1 -5.606771 -0.622975 -0.168783 -0.740723 \n3 -3.805725 -0.380573 -0.037333 -0.671875 \n4 -2.307520 -0.461504 0.400000 -0.704102 \n6 -3.804977 -0.475622 -0.009811 -0.629883 \n9 -6.023926 -0.669325 -0.568359 -0.716797 \n15 -2.282227 -0.570557 -0.296875 -0.721191 \n17 -3.084961 -0.616992 -0.554199 -0.679199 \n18 -2.014160 -0.671387 -0.641602 -0.687012 \n19 -2.807617 -0.701904 -0.649414 -0.727539 \n21 -4.357259 -0.484140 -0.112142 -0.719727 \n23 -1.793945 -0.597982 -0.555664 -0.641602 \n30 -5.783112 -0.481926 0.038300 -0.708008 \n32 -3.627197 -0.604533 -0.043701 -0.738281 \n34 -10.542236 -0.585680 -0.220215 -0.734375 \n35 -6.700195 -0.670020 -0.566406 -0.735352 \n37 -2.625244 -0.525049 -0.102783 -0.676758 \n38 -4.540039 -0.648577 -0.302246 -0.734863 \n49 -5.030273 -0.628784 -0.511230 -0.723633 \n53 -1.681396 -0.560465 -0.335693 -0.724609 \n56 -0.995022 -0.248755 -0.014618 -0.695801 \n59 -6.470215 -0.588201 -0.303955 -0.725586 \n64 -4.027344 -0.671224 -0.601074 -0.731934 \n66 -1.555908 -0.518636 -0.149170 -0.721680 \n67 -1.051554 -0.262889 0.100911 -0.598145 \n69 -7.054688 -0.705469 -0.607422 -0.738281 \n73 -1.957520 -0.652507 -0.508789 -0.731934 \n82 -4.876465 -0.696638 -0.638184 -0.740723 \n85 -8.531609 -0.568774 -0.010612 -0.734863 \n88 -3.883301 -0.647217 -0.548340 -0.720703 \n... ... ... ... ... \n123530 -4.637939 -0.386495 -0.136108 -0.701172 \n123531 -7.224915 -0.451557 0.289551 -0.732422 \n123534 -1.664225 -0.554742 -0.214518 -0.732910 \n123538 -8.805664 -0.628976 -0.247559 -0.728516 \n123545 -5.868526 -0.489044 0.066667 -0.734863 \n123547 -1.656284 -0.331257 0.160000 -0.704590 \n123552 -2.819824 -0.469971 -0.253418 -0.679199 \n123556 -0.542938 -0.180979 0.227051 -0.717773 \n123557 -1.221863 -0.407288 -0.042175 -0.658203 \n123559 -3.497070 -0.699414 -0.670410 -0.718262 \n123560 -4.352554 -0.483617 -0.026077 -0.729004 \n123564 -9.934082 -0.662272 -0.387695 -0.731934 \n123565 -1.261198 -0.420399 0.133333 -0.705078 \n123566 -5.077148 -0.634644 -0.275879 -0.710938 \n123570 -5.761149 -0.480096 -0.120931 -0.742188 \n123571 -1.934570 -0.644857 -0.584473 -0.709473 \n123572 -1.966309 -0.655436 -0.518555 -0.724121 \n123574 -2.426270 -0.606567 -0.437012 -0.698242 \n123577 -4.677246 -0.668178 -0.607422 -0.723145 \n123580 -9.939941 -0.709996 -0.636230 -0.742188 \n123583 -0.255330 -0.085110 -0.044800 -0.157308 \n123588 -13.917480 -0.695874 -0.560547 -0.745605 \n123592 -3.428223 -0.685645 -0.656738 -0.727051 \n123598 -4.730273 -0.525586 0.133333 -0.724609 \n123601 -2.836992 -0.567398 0.080000 -0.740723 \n123602 -8.375977 -0.644306 -0.418945 -0.740723 \n123603 -27.019533 -0.614080 -0.020396 -0.745605 \n123605 -10.846836 -0.602602 0.160000 -0.729004 \n123606 -2.344604 -0.468921 0.035278 -0.628418 \n123621 -1.839193 -0.459798 -0.166341 -0.708008 \n\n new_price_var new_duration_mean new_duration_min new_duration_max \\\n0 0.108649 -43.007975 -51.996094 -27.980957 \n1 0.030730 -46.764974 -52.591309 -35.444336 \n3 0.058179 -40.618579 -47.703125 -31.807861 \n4 0.232595 -16.742318 -49.991211 56.800000 \n6 0.038423 -33.826976 -44.091797 -1.393219 \n9 0.001767 -50.868707 -54.476562 -43.195312 \n15 0.035328 -45.779053 -51.204590 -42.156250 \n17 0.002666 -42.055216 -48.223145 -33.853271 \n18 0.000666 -47.668457 -48.777832 -45.553711 \n19 0.001271 -56.854248 -58.930664 -52.602539 \n21 0.061824 -27.633870 -50.380859 56.000000 \n23 0.001848 -42.456706 -45.553711 -39.452148 \n30 0.086178 -38.459207 -50.233887 2.719269 \n32 0.075734 -43.833049 -51.679688 -9.308350 \n34 0.022824 -42.817768 -51.406250 -30.830078 \n35 0.003959 -47.350320 -52.945312 -39.867188 \n37 0.056947 -42.462158 -50.756836 -23.126221 \n38 0.023800 -50.498117 -53.645020 -44.127930 \n49 0.006979 -45.648621 -52.101562 -37.319824 \n53 0.040571 -47.272461 -50.722656 -44.097656 \n56 0.095182 -33.114929 -50.793457 -8.536865 \n59 0.024062 -41.497965 -52.242188 11.135742 \n64 0.001941 -37.075195 -51.235352 23.037109 \n66 0.102714 -47.414225 -51.239258 -42.364258 \n67 0.086918 -14.316284 -46.057129 46.015625 \n69 0.001375 -51.519043 -54.632812 -44.662598 \n73 0.015548 -45.675456 -51.235352 -35.615234 \n82 0.001397 -49.461286 -52.591309 -45.311035 \n85 0.031408 -40.130335 -51.440430 -0.742874 \n88 0.005395 -45.425293 -51.169922 -38.383789 \n... ... ... ... ... \n123530 0.051359 -37.988688 -49.783203 -19.327393 \n123531 0.116075 -32.414604 -52.001953 20.847656 \n123534 0.086879 -46.739014 -51.303711 -39.067383 \n123538 0.016273 -44.957241 -52.453125 -17.824219 \n123545 0.078440 -22.828342 -52.175293 56.800000 \n123547 0.137914 -28.017201 -50.025879 56.800000 \n123552 0.044896 -43.024821 -48.223145 -35.985352 \n123556 0.235608 6.112002 -50.961914 56.800000 \n123557 0.104653 -28.698018 -46.074219 -2.994446 \n123559 0.000337 -49.516211 -50.996582 -47.599121 \n123560 0.086878 -34.807515 -52.488281 -1.877563 \n123564 0.007027 -46.726693 -51.793945 -27.138672 \n123565 0.230026 -14.070573 -50.060547 56.800000 \n123566 0.021671 -46.838989 -49.765625 -38.623047 \n123570 0.052284 -44.275675 -54.179688 -26.846680 \n123571 0.003920 -46.047729 -50.372559 -41.497559 \n123572 0.014052 -46.053385 -50.688477 -36.817383 \n123574 0.013625 -43.066284 -49.575195 -31.027832 \n123577 0.001393 -45.127472 -50.620117 -29.658447 \n123580 0.001085 -51.625035 -54.179688 -46.444824 \n123583 0.003927 -27.030212 -33.506592 -18.627930 \n123588 0.002123 -50.353760 -53.716309 -40.359375 \n123592 0.000835 -46.567662 -51.620605 -40.214844 \n123598 0.087627 -35.067632 -51.447266 56.800000 \n123601 0.131171 -29.767344 -52.591309 56.800000 \n123602 0.014632 -46.335374 -53.332031 -30.164062 \n123603 0.032833 -45.185240 -52.937988 -8.688660 \n123605 0.045259 -36.975860 -51.759277 56.800000 \n123606 0.080064 -27.782910 -44.617676 30.057129 \n123621 0.071578 -47.033610 -53.100586 -37.426758 \n\n new_duration_var new_duration_skew new_amount_month_ratio_mean \\\n0 171.532930 1.633769 -0.008162 \n1 27.009073 1.296674 -0.009329 \n3 27.397220 0.344351 -0.008124 \n4 2403.961329 1.048725 -0.003321 \n6 161.787826 2.499442 -0.006784 \n9 10.206342 1.929070 -0.008807 \n15 16.108638 -1.026003 -0.009081 \n17 27.932990 0.514750 -0.008380 \n18 3.356817 1.725774 -0.009456 \n19 8.335964 1.786786 -0.008665 \n21 901.120864 2.239443 -0.005566 \n23 9.313676 -0.136192 -0.008422 \n30 250.885376 1.786639 -0.007768 \n32 286.946779 2.432759 -0.008744 \n34 47.014539 0.391139 -0.008601 \n35 23.808131 0.372131 -0.009184 \n37 123.733990 1.926749 -0.007549 \n38 10.435187 1.487699 -0.009476 \n49 35.320796 0.389082 -0.008662 \n53 11.029536 -0.370584 -0.009564 \n56 356.281141 0.784223 -0.006273 \n59 296.962500 3.020345 -0.008026 \n64 710.277049 2.586731 -0.007529 \n66 20.816755 1.121062 -0.009406 \n67 1685.528906 1.751108 -0.002363 \n69 11.947362 1.584495 -0.009429 \n73 76.186713 1.703381 -0.009322 \n82 7.042432 0.480258 -0.009812 \n85 155.718681 2.417088 -0.008062 \n88 28.007371 0.603551 -0.009222 \n... ... ... ... \n123530 83.597529 0.840574 -0.007692 \n123531 577.645813 1.227624 -0.006436 \n123534 32.679305 1.020203 -0.009401 \n123538 82.567950 2.329882 -0.008800 \n123545 1458.154495 1.467109 -0.004521 \n123547 1442.097622 2.483736 -0.005594 \n123552 24.782550 0.564664 -0.008622 \n123556 2039.476969 0.010041 0.001234 \n123557 515.975556 1.427990 -0.005781 \n123559 1.508254 0.845806 -0.009880 \n123560 451.146699 0.778798 -0.006719 \n123564 36.147248 2.708742 -0.009387 \n123565 3767.286257 1.731414 -0.002791 \n123566 14.237955 1.776205 -0.009559 \n123570 53.844151 1.097158 -0.008165 \n123571 13.449204 0.175754 -0.009135 \n123572 63.978100 1.732015 -0.009329 \n123574 68.683054 1.637176 -0.008543 \n123577 44.342421 2.203229 -0.008988 \n123580 5.649184 1.294614 -0.009765 \n123583 45.688575 0.548901 -0.005469 \n123588 11.935718 1.566142 -0.009617 \n123592 13.014655 0.586868 -0.009391 \n123598 1205.881207 2.911573 -0.007039 \n123601 2342.666549 2.234109 -0.006023 \n123602 75.326862 1.233767 -0.008959 \n123603 71.464022 2.474673 -0.009075 \n123605 665.254387 2.998082 -0.007476 \n123606 1048.589377 2.219455 -0.005511 \n123621 30.849413 1.087096 -0.008438 \n\n new_amount_month_ratio_min new_amount_month_ratio_max \\\n0 -0.010030 -0.005251 \n1 -0.010433 -0.007234 \n3 -0.009463 -0.006310 \n4 -0.009917 0.011268 \n6 -0.008998 -0.000276 \n9 -0.009432 -0.007478 \n15 -0.010158 -0.008363 \n17 -0.009566 -0.006716 \n18 -0.009676 -0.009037 \n19 -0.008982 -0.008017 \n21 -0.010282 0.011429 \n23 -0.009037 -0.007826 \n30 -0.010114 0.000539 \n32 -0.010547 -0.001847 \n34 -0.010491 -0.006292 \n35 -0.010226 -0.007690 \n37 -0.009023 -0.004111 \n38 -0.010067 -0.008281 \n49 -0.010050 -0.007003 \n53 -0.010352 -0.008748 \n56 -0.009532 -0.001602 \n59 -0.010078 0.002148 \n64 -0.010456 0.004701 \n66 -0.010165 -0.008404 \n67 -0.007768 0.007967 \n69 -0.009977 -0.008208 \n73 -0.010456 -0.007268 \n82 -0.010433 -0.008989 \n85 -0.010498 -0.000152 \n88 -0.010151 -0.007833 \n... ... ... \n123530 -0.009876 -0.003834 \n123531 -0.010316 0.004022 \n123534 -0.010470 -0.007973 \n123538 -0.010118 -0.003438 \n123545 -0.010350 0.011429 \n123547 -0.009924 0.011268 \n123552 -0.009703 -0.007139 \n123556 -0.010109 0.011429 \n123557 -0.009403 -0.000594 \n123559 -0.010156 -0.009442 \n123560 -0.010125 -0.000362 \n123564 -0.010456 -0.005539 \n123565 -0.009931 0.011268 \n123566 -0.010156 -0.007882 \n123570 -0.010167 -0.004903 \n123571 -0.009993 -0.008232 \n123572 -0.010345 -0.007304 \n123574 -0.009834 -0.006155 \n123577 -0.010331 -0.005883 \n123580 -0.010288 -0.008715 \n123583 -0.006647 -0.003802 \n123588 -0.010356 -0.007785 \n123592 -0.010240 -0.007978 \n123598 -0.010206 0.011268 \n123601 -0.010582 0.011268 \n123602 -0.010288 -0.005819 \n123603 -0.010519 -0.001724 \n123605 -0.010268 0.011268 \n123606 -0.008851 0.005963 \n123621 -0.009440 -0.006654 \n\n new_amount_month_ratio_var new_amount_month_ratio_skew \\\n0 6.525404e-06 1.530383 \n1 9.496697e-07 1.253863 \n3 1.050934e-06 0.413687 \n4 9.460064e-05 1.048725 \n6 6.547015e-06 2.466980 \n9 3.059256e-07 1.929070 \n15 6.339068e-07 -1.026003 \n17 1.050086e-06 0.659444 \n18 1.320974e-07 1.725774 \n19 1.936492e-07 1.786786 \n21 3.728146e-05 2.227895 \n23 3.665116e-07 -0.136192 \n30 1.011994e-05 1.810348 \n32 1.149011e-05 2.415524 \n34 1.770180e-06 0.379433 \n35 9.701857e-07 0.374061 \n37 3.910605e-06 1.926749 \n38 3.674589e-07 1.487699 \n49 1.385180e-06 0.444491 \n53 6.435898e-07 0.155222 \n56 1.289512e-05 0.798298 \n59 1.109982e-05 3.020369 \n64 2.943071e-05 2.581053 \n66 8.191806e-07 1.121062 \n67 4.935352e-05 1.758250 \n69 3.466852e-07 1.553000 \n73 3.173124e-06 1.703381 \n82 2.771336e-07 0.480258 \n85 6.342883e-06 2.373130 \n88 1.043731e-06 0.759917 \n... ... ... \n123530 3.545621e-06 0.920385 \n123531 2.259251e-05 1.217785 \n123534 1.259519e-06 0.655664 \n123538 3.215582e-06 2.319917 \n123545 5.831291e-05 1.475185 \n123547 5.704439e-05 2.479824 \n123552 1.107898e-06 0.596834 \n123556 8.216371e-05 0.023250 \n123557 2.123429e-05 1.351547 \n123559 8.252035e-08 0.870787 \n123560 1.672995e-05 0.779282 \n123564 1.374009e-06 2.785720 \n123565 1.482502e-04 1.731414 \n123566 5.930011e-07 1.776205 \n123570 1.921579e-06 1.025735 \n123571 5.292528e-07 0.175754 \n123572 3.075506e-06 1.732020 \n123574 2.702814e-06 1.637176 \n123577 1.845354e-06 2.031518 \n123580 2.163211e-07 1.183817 \n123583 1.743512e-06 0.658751 \n123588 3.845354e-07 1.592727 \n123592 5.590580e-07 1.085942 \n123598 4.780327e-05 2.920974 \n123601 9.347708e-05 2.232748 \n123602 2.845282e-06 1.236176 \n123603 2.873274e-06 2.507407 \n123605 2.673913e-05 2.977028 \n123606 4.126407e-05 2.219455 \n123621 1.008353e-06 1.242615 \n\n new_purchase_date_diff new_purchase_date_average \\\n0 25.0 8.333333 \n1 48.0 5.333333 \n3 44.0 4.400000 \n4 39.0 6.500000 \n6 52.0 5.777778 \n9 41.0 4.555556 \n15 5.0 1.250000 \n17 28.0 4.666667 \n18 47.0 15.666667 \n19 41.0 10.250000 \n21 54.0 4.500000 \n23 11.0 3.666667 \n30 54.0 4.153846 \n32 38.0 6.333333 \n34 55.0 2.894737 \n35 48.0 4.363636 \n37 10.0 2.000000 \n38 7.0 1.000000 \n49 47.0 5.875000 \n53 4.0 1.333333 \n56 45.0 11.250000 \n59 14.0 1.166667 \n64 51.0 7.285714 \n66 13.0 4.333333 \n67 54.0 13.500000 \n69 30.0 2.727273 \n73 5.0 1.666667 \n82 44.0 6.285714 \n85 54.0 3.600000 \n88 35.0 5.833333 \n... ... ... \n123530 42.0 3.500000 \n123531 35.0 2.187500 \n123534 49.0 12.250000 \n123538 40.0 2.857143 \n123545 50.0 3.571429 \n123547 60.0 8.571429 \n123552 30.0 5.000000 \n123556 54.0 9.000000 \n123557 9.0 3.000000 \n123559 46.0 9.200000 \n123560 42.0 4.666667 \n123564 58.0 3.866667 \n123565 29.0 9.666667 \n123566 4.0 0.500000 \n123570 41.0 3.416667 \n123571 37.0 9.250000 \n123572 22.0 7.333333 \n123574 27.0 6.750000 \n123577 34.0 4.250000 \n123580 45.0 3.214286 \n123583 45.0 11.250000 \n123588 51.0 2.550000 \n123592 51.0 7.285714 \n123598 41.0 4.555556 \n123601 51.0 10.200000 \n123602 45.0 3.461538 \n123603 54.0 1.227273 \n123605 59.0 2.950000 \n123606 45.0 9.000000 \n123621 25.0 4.166667 \n\n new_purchase_date_uptonow new_purchase_date_uptomin new_first_buy \\\n0 2119.0 2145.0 308.0 \n1 2068.0 2117.0 426.0 \n3 2071.0 2116.0 93.0 \n4 2077.0 2116.0 824.0 \n6 2065.0 2117.0 152.0 \n9 2221.0 2262.0 586.0 \n15 2076.0 2081.0 157.0 \n17 2086.0 2114.0 185.0 \n18 2070.0 2118.0 121.0 \n19 2377.0 2418.0 124.0 \n21 2059.0 2113.0 278.0 \n23 2104.0 2116.0 184.0 \n30 2059.0 2113.0 398.0 \n32 2062.0 2101.0 352.0 \n34 2059.0 2114.0 370.0 \n35 2095.0 2144.0 126.0 \n37 2197.0 2207.0 154.0 \n38 2131.0 2138.0 345.0 \n49 2123.0 2170.0 129.0 \n53 2097.0 2102.0 106.0 \n56 2129.0 2175.0 217.0 \n59 2096.0 2111.0 159.0 \n64 2059.0 2110.0 342.0 \n66 2105.0 2118.0 334.0 \n67 2242.0 2297.0 367.0 \n69 2163.0 2193.0 106.0 \n73 2092.0 2098.0 140.0 \n82 2073.0 2117.0 121.0 \n85 2058.0 2113.0 126.0 \n88 2061.0 2096.0 357.0 \n... ... ... ... \n123530 2062.0 2104.0 287.0 \n123531 2094.0 2130.0 200.0 \n123534 2064.0 2113.0 1221.0 \n123538 2103.0 2144.0 125.0 \n123545 2063.0 2114.0 398.0 \n123547 2058.0 2119.0 334.0 \n123552 2083.0 2114.0 309.0 \n123556 2060.0 2114.0 216.0 \n123557 2098.0 2107.0 315.0 \n123559 2071.0 2118.0 120.0 \n123560 2104.0 2146.0 365.0 \n123564 2058.0 2116.0 214.0 \n123565 2071.0 2100.0 230.0 \n123566 2088.0 2093.0 1334.0 \n123570 2162.0 2203.0 66.0 \n123571 2071.0 2108.0 1287.0 \n123572 2072.0 2095.0 144.0 \n123574 2084.0 2111.0 251.0 \n123577 2082.0 2117.0 245.0 \n123580 2123.0 2169.0 284.0 \n123583 2069.0 2114.0 155.0 \n123588 2121.0 2172.0 189.0 \n123592 2059.0 2111.0 189.0 \n123598 2063.0 2105.0 133.0 \n123601 2064.0 2116.0 183.0 \n123602 2097.0 2142.0 400.0 \n123603 2058.0 2113.0 125.0 \n123605 2059.0 2119.0 304.0 \n123606 2073.0 2118.0 244.0 \n123621 2214.0 2239.0 153.0 \n\n new_last_buy card_id_total card_id_cnt_total card_id_cnt_ratio \\\n0 333.0 71.0 71.0 0.044118 \n1 474.0 87.0 87.0 0.115385 \n3 137.0 36.0 36.0 0.384615 \n4 863.0 116.0 116.0 0.054545 \n6 205.0 57.0 57.0 0.187500 \n9 628.0 57.0 57.0 0.187500 \n15 162.0 15.0 15.0 0.363636 \n17 214.0 67.0 67.0 0.098361 \n18 169.0 32.0 32.0 0.103448 \n19 166.0 85.0 85.0 0.049383 \n21 333.0 109.0 109.0 0.123711 \n23 195.0 26.0 26.0 0.130435 \n30 452.0 275.0 275.0 0.049618 \n32 391.0 116.0 116.0 0.054545 \n34 425.0 664.0 664.0 0.029457 \n35 174.0 31.0 31.0 0.550000 \n37 164.0 57.0 57.0 0.096154 \n38 353.0 96.0 96.0 0.078652 \n49 177.0 84.0 84.0 0.105263 \n53 111.0 35.0 35.0 0.093750 \n56 262.0 49.0 49.0 0.088889 \n59 173.0 112.0 112.0 0.120000 \n64 393.0 71.0 71.0 0.109375 \n66 348.0 78.0 78.0 0.040000 \n67 422.0 11.0 11.0 0.571429 \n69 136.0 23.0 23.0 0.916667 \n73 146.0 26.0 26.0 0.130435 \n82 166.0 56.0 56.0 0.142857 \n85 180.0 100.0 100.0 0.176471 \n88 392.0 352.0 352.0 0.017341 \n... ... ... ... ... \n123530 330.0 81.0 81.0 0.173913 \n123531 236.0 29.0 29.0 1.230769 \n123534 1271.0 46.0 46.0 0.095238 \n123538 166.0 148.0 148.0 0.104478 \n123545 448.0 347.0 347.0 0.042042 \n123547 394.0 57.0 57.0 0.140000 \n123552 339.0 49.0 49.0 0.139535 \n123556 271.0 28.0 28.0 0.272727 \n123557 325.0 192.0 192.0 0.015873 \n123559 167.0 38.0 38.0 0.151515 \n123560 408.0 94.0 94.0 0.105882 \n123564 272.0 81.0 81.0 0.227273 \n123565 259.0 13.0 13.0 0.300000 \n123566 1338.0 50.0 50.0 0.190476 \n123570 108.0 45.0 45.0 0.363636 \n123571 1325.0 73.0 73.0 0.057971 \n123572 166.0 97.0 97.0 0.031915 \n123574 278.0 43.0 43.0 0.102564 \n123577 279.0 21.0 21.0 0.615385 \n123580 330.0 61.0 61.0 0.297872 \n123583 201.0 22.0 22.0 0.222222 \n123588 241.0 147.0 147.0 0.157480 \n123592 240.0 35.0 35.0 0.250000 \n123598 175.0 64.0 64.0 0.163636 \n123601 235.0 41.0 41.0 0.138889 \n123602 445.0 527.0 527.0 0.025292 \n123603 180.0 260.0 260.0 0.203704 \n123605 363.0 109.0 109.0 0.224719 \n123606 289.0 59.0 59.0 0.092593 \n123621 178.0 68.0 68.0 0.096774 \n\n purchase_amount_total purchase_amount_mean purchase_amount_max \\\n0 -42.511076 -1.191473 -0.147625 \n1 -55.080849 -1.290437 -0.187530 \n3 -19.435100 -1.101004 -0.360033 \n4 -47.508457 -0.654840 1.600000 \n6 -22.921942 -0.866739 0.724099 \n9 -35.445099 -1.282266 -0.542003 \n15 -4.468366 -0.816527 0.206250 \n17 -39.042022 -1.175271 0.194788 \n18 -21.636110 -1.348006 -1.103006 \n19 -59.919121 -1.406985 -0.494746 \n21 -66.981375 -1.034175 0.745288 \n23 -14.578889 -1.153849 0.244336 \n30 -156.675126 -1.117435 0.798716 \n32 -74.475611 -1.262382 0.668896 \n34 -414.016328 -1.230853 0.359570 \n35 -16.330435 -1.113272 0.246289 \n37 -26.882422 -1.028693 0.491650 \n38 -60.903601 -1.321657 -0.391206 \n49 -55.516573 -1.293078 -0.440696 \n53 -21.719957 -1.288078 -0.467913 \n56 -22.829400 -0.922558 0.533614 \n59 -75.597520 -1.263839 -0.087955 \n64 -43.905383 -1.156557 1.129102 \n66 -48.907607 -1.293195 -0.083164 \n67 -4.132613 -0.669213 0.399365 \n69 -12.864006 -1.130080 0.192578 \n73 -17.402910 -1.324045 -0.968300 \n82 -36.166997 -1.335220 -0.922275 \n85 -60.996569 -1.186009 0.033355 \n88 -222.278127 -1.278416 0.152632 \n... ... ... ... \n123530 -15.257234 -0.667676 0.527783 \n123531 -12.106915 -0.825901 1.089551 \n123534 -27.033160 -1.243361 -0.705455 \n123538 -86.670475 -1.210057 0.552441 \n123545 -119.105670 -0.665417 1.600000 \n123547 -24.135023 -0.823173 1.600000 \n123552 -31.327827 -1.252620 -0.803249 \n123556 -9.425855 -0.365301 1.480611 \n123557 -98.164134 -0.920210 0.757825 \n123559 -21.063078 -1.231717 -0.341420 \n123560 -53.700956 -1.064187 0.045028 \n123564 -49.035365 -1.254716 0.368048 \n123565 -3.841054 -0.522829 1.434930 \n123566 -30.998264 -1.279729 0.203986 \n123570 -25.834976 -1.165483 -0.635404 \n123571 -45.871554 -1.275767 -0.279525 \n123572 -61.016548 -1.283630 -0.216612 \n123574 -25.813082 -1.206229 -0.154603 \n123577 -10.999815 -1.091090 0.382275 \n123580 -34.198531 -1.226136 -0.422944 \n123583 -10.306367 -0.871601 -0.239156 \n123588 -94.580258 -1.331014 0.239453 \n123592 -19.685591 -1.199011 -0.141246 \n123598 -34.484237 -1.042518 1.384441 \n123601 -26.120913 -1.090174 1.063851 \n123602 -327.427083 -1.265028 0.381055 \n123603 -158.099275 -1.241853 0.677625 \n123605 -56.800744 -1.045819 1.600000 \n123606 -15.545317 -0.642953 1.223340 \n123621 -42.903412 -1.260990 -0.614818 \n\n purchase_amount_min purchase_amount_ratio month_diff_mean \\\n0 -1.466070 0.043633 145.299020 \n1 -1.472604 0.120976 141.623932 \n3 -1.403756 0.419583 141.469231 \n4 -1.450859 0.030695 141.763636 \n6 -1.313769 0.231646 141.145833 \n9 -1.448678 0.204748 151.937500 \n15 -1.414995 1.365135 141.454545 \n17 -1.405070 0.100387 141.472678 \n18 -1.428074 0.102648 141.310345 \n19 -1.466182 0.049160 161.777778 \n21 -1.461826 0.075566 141.035223 \n23 -1.363115 0.140317 141.652174 \n30 -1.437695 0.047505 141.006753 \n32 -1.483686 0.052495 141.606061 \n34 -1.476790 0.028647 141.197634 \n35 -1.459720 0.799194 143.518182 \n37 -1.406235 0.117697 149.961538 \n38 -1.479307 0.086375 145.662921 \n49 -1.466033 0.099636 145.256579 \n53 -1.466468 0.102375 140.708333 \n56 -1.427697 0.086783 145.350000 \n59 -1.467084 0.100848 143.616667 \n64 -1.478090 0.091980 140.783482 \n66 -1.453561 0.042713 141.466667 \n67 -1.277027 0.216629 153.607143 \n69 -1.462649 1.475036 147.575758 \n73 -1.469074 0.126738 140.478261 \n82 -1.472604 0.155845 141.714286 \n85 -1.473882 0.162615 141.109804 \n88 -1.463854 0.017781 140.883430 \n... ... ... ... \n123530 -1.446577 0.739625 140.913043 \n123531 -1.456790 1.522707 142.586538 \n123534 -1.478315 0.108744 141.095238 \n123538 -1.469413 0.113089 143.067164 \n123545 -1.481020 0.039242 141.440369 \n123547 -1.431062 0.129719 141.577143 \n123552 -1.424604 0.132050 141.085271 \n123556 -1.404575 -0.052375 141.030303 \n123557 -1.399551 0.012604 141.375661 \n123559 -1.450098 0.199082 141.466667 \n123560 -1.475160 0.088201 143.465359 \n123564 -1.455340 0.254060 141.412121 \n123565 -1.430197 0.183129 141.600000 \n123566 -1.440339 0.208734 140.690476 \n123570 -1.487593 0.387475 147.393939 \n123571 -1.447365 0.059945 141.710145 \n123572 -1.469526 0.033299 140.950355 \n123574 -1.437637 0.103745 141.307692 \n123577 -1.447513 0.862846 141.567308 \n123580 -1.480545 0.409749 145.671733 \n123583 -1.166389 0.175382 140.638889 \n123588 -1.491011 0.172539 144.956299 \n123592 -1.472456 0.307432 141.321429 \n123598 -1.451878 0.148986 141.175758 \n123601 -1.481154 0.088194 141.377778 \n123602 -1.485827 0.026253 143.621521 \n123603 -1.491762 0.216863 141.105219 \n123605 -1.475882 0.227179 140.978090 \n123606 -1.370833 0.143982 141.796296 \n123621 -1.445900 0.096611 149.376344 \n\n month_diff_ratio month_lag_mean month_lag_max month_lag_min \\\n0 1.000472 -1.632353 2.0 -6.0 \n1 0.999035 -8.965812 2.0 -12.0 \n3 0.999022 0.069231 2.0 -1.0 \n4 1.003340 -5.060606 2.0 -12.0 \n6 1.002660 -0.083333 2.0 -3.0 \n9 1.000823 -4.055556 2.0 -7.0 \n15 1.007742 0.545455 2.0 -1.0 \n17 1.002746 -1.177596 2.0 -4.0 \n18 1.009809 -0.678161 2.0 -3.0 \n19 1.002751 -0.043210 2.0 -2.0 \n21 0.997141 -1.981100 2.0 -7.0 \n23 1.004923 -1.652174 1.0 -4.0 \n30 0.996637 -3.307692 2.0 -11.0 \n32 1.000856 -3.078788 2.0 -9.0 \n34 0.997948 -3.833048 2.0 -10.0 \n35 1.001648 0.436364 2.0 -2.0 \n37 1.000513 0.307692 2.0 -1.0 \n38 1.004639 -2.707865 2.0 -7.0 \n49 0.999909 -0.276316 2.0 -2.0 \n53 0.999408 0.156250 1.0 -1.0 \n56 1.002066 -1.883333 2.0 -5.0 \n59 1.003022 0.530000 2.0 -1.0 \n64 0.992954 -3.694196 2.0 -9.0 \n66 1.007569 -3.533333 1.0 -9.0 \n67 0.998606 -0.464286 2.0 -5.0 \n69 1.003291 0.886364 2.0 -1.0 \n73 0.993214 -0.565217 1.0 -2.0 \n82 1.004040 -0.428571 2.0 -2.0 \n85 0.999389 0.874510 2.0 -2.0 \n88 0.992221 -2.865125 2.0 -9.0 \n... ... ... ... ... \n123530 0.996509 -3.192029 2.0 -7.0 \n123531 0.995291 -0.375000 1.0 -4.0 \n123534 0.998651 -3.773810 2.0 -12.0 \n123538 0.999062 0.248401 2.0 -2.0 \n123545 1.001855 -3.579151 2.0 -11.0 \n123547 1.001939 -3.471429 2.0 -9.0 \n123552 1.003523 -3.341085 2.0 -8.0 \n123556 1.004307 -1.181818 2.0 -5.0 \n123557 0.999401 -2.703704 1.0 -8.0 \n123559 1.001887 0.218182 2.0 -2.0 \n123560 1.004365 -0.192157 2.0 -10.0 \n123564 0.995126 -0.903030 2.0 -5.0 \n123565 1.005666 -0.133333 2.0 -5.0 \n123566 0.990232 -4.214286 0.0 -12.0 \n123570 0.999178 1.159091 2.0 0.0 \n123571 1.004099 -4.905797 2.0 -12.0 \n123572 0.995983 0.301418 2.0 -2.0 \n123574 1.009847 -2.314103 2.0 -6.0 \n123577 1.002584 -0.480769 2.0 -6.0 \n123580 0.996667 -1.816109 2.0 -7.0 \n123583 0.998027 -1.361111 2.0 -3.0 \n123588 0.996470 -0.657874 2.0 -4.0 \n123592 0.993451 -0.785714 2.0 -4.0 \n123598 1.002235 -0.284848 2.0 -2.0 \n123601 0.997488 -1.350000 2.0 -4.0 \n123602 1.003133 -3.153996 2.0 -11.0 \n123603 1.000442 0.531566 2.0 -2.0 \n123605 0.998893 -2.389888 2.0 -8.0 \n123606 1.002877 -3.911111 2.0 -6.0 \n123621 0.999424 -1.145161 1.0 -3.0 \n\n category_1_mean installments_total installments_mean \\\n0 0.338235 146.0 3.740196 \n1 0.247863 94.0 2.286325 \n3 0.100000 69.0 4.566667 \n4 0.000000 126.0 2.290909 \n6 0.020833 85.0 2.813889 \n9 0.000000 58.0 2.020833 \n15 0.272727 44.0 4.795455 \n17 0.016393 78.0 2.196721 \n18 0.000000 32.0 2.074074 \n19 0.000000 90.0 2.061728 \n21 0.609107 166.0 3.256140 \n23 0.000000 35.0 2.391304 \n30 0.061069 366.0 2.997436 \n32 0.000000 143.0 2.571865 \n34 0.288209 717.0 2.196781 \n35 0.000000 28.0 2.125000 \n37 0.000000 77.0 2.746154 \n38 0.494382 111.0 2.300161 \n49 0.039474 89.0 2.094595 \n53 0.000000 41.0 2.526882 \n56 0.250000 134.0 6.909091 \n59 0.513333 118.0 2.253247 \n64 0.267857 91.0 2.328125 \n66 0.013333 129.0 3.640000 \n67 0.000000 20.0 3.928571 \n69 0.333333 32.0 3.000000 \n73 0.000000 26.0 2.000000 \n82 0.020408 65.0 2.288889 \n85 0.254902 109.0 2.105882 \n88 0.000000 376.0 2.069364 \n... ... ... ... \n123530 0.768116 140.0 3.500000 \n123531 0.062500 42.0 2.927885 \n123534 0.250000 81.0 3.566667 \n123538 0.089552 214.0 2.515152 \n123545 0.360789 684.0 4.740826 \n123547 0.220000 163.0 5.725000 \n123552 0.348837 70.0 2.952381 \n123556 0.333333 32.0 2.733333 \n123557 0.031746 255.0 2.362162 \n123559 0.060606 50.0 2.406250 \n123560 1.050980 124.0 2.369048 \n123564 0.066667 83.0 2.046154 \n123565 0.100000 40.0 5.866667 \n123566 0.000000 67.0 2.539634 \n123570 0.931818 111.0 4.458333 \n123571 0.014493 79.0 2.117647 \n123572 0.500000 97.0 2.000000 \n123574 0.000000 58.0 2.459459 \n123577 0.000000 38.0 3.384615 \n123580 0.177812 70.0 2.217391 \n123583 0.000000 74.0 9.500000 \n123588 0.100000 147.0 2.000000 \n123592 0.428571 54.0 3.041667 \n123598 0.036364 156.0 4.470085 \n123601 1.183333 53.0 3.883333 \n123602 0.000000 607.0 2.160156 \n123603 0.360269 363.0 2.792882 \n123605 0.133708 195.0 3.188131 \n123606 0.829630 110.0 5.007692 \n123621 0.166667 127.0 3.685484 \n\n installments_max installments_ratio price_total price_mean \\\n0 15.0 0.035461 -0.291172 -0.318559 \n1 7.0 0.132530 -0.585966 -0.564415 \n3 18.0 0.725000 -0.281668 -0.241096 \n4 6.0 0.050000 -0.377051 -0.285843 \n6 8.0 0.118421 -0.269670 -0.308022 \n9 3.0 0.183673 -0.611122 -0.634523 \n15 12.0 0.128205 -0.101554 -0.170271 \n17 4.0 0.068493 -0.500539 -0.535012 \n18 4.0 0.103448 -0.676128 -0.649931 \n19 7.0 0.046512 -0.665768 -0.682430 \n21 14.0 0.099338 -0.403502 -0.317608 \n23 11.0 0.093750 -0.416540 -0.482519 \n30 18.0 0.057803 -0.428074 -0.372797 \n32 13.0 0.059259 -0.520808 -0.490843 \n34 8.0 0.028694 -0.577429 -0.560299 \n35 4.0 0.555556 -0.583230 -0.523893 \n37 9.0 0.100000 -0.349122 -0.374594 \n38 7.0 0.077670 -0.548681 -0.574594 \n49 6.0 0.098765 -0.623782 -0.617340 \n53 6.0 0.108108 -0.529755 -0.509750 \n56 18.0 0.145299 -0.170369 -0.133528 \n59 5.0 0.123810 -0.640657 -0.560897 \n64 13.0 0.070588 -0.482477 -0.496776 \n66 16.0 0.048780 -0.379129 -0.355273 \n67 9.0 1.000000 -0.206631 -0.170345 \n69 11.0 0.454545 -0.402000 -0.376693 \n73 2.0 0.130435 -0.669343 -0.662023 \n82 7.0 0.120690 -0.556415 -0.583349 \n85 6.0 0.159574 -0.559602 -0.563189 \n88 6.0 0.016216 -0.591165 -0.617782 \n... ... ... ... ... \n123530 8.0 0.176471 -0.108980 -0.190764 \n123531 11.0 1.000000 -0.288260 -0.282081 \n123534 13.0 0.065789 -0.333743 -0.348606 \n123538 13.0 0.070000 -0.405002 -0.481107 \n123545 24.0 0.050691 -0.174131 -0.140359 \n123547 17.0 0.086667 -0.148068 -0.143786 \n123552 7.0 0.147541 -0.447540 -0.424274 \n123556 8.0 0.142857 -0.294558 -0.133647 \n123557 11.0 0.011905 -0.384957 -0.389562 \n123559 11.0 0.111111 -0.421262 -0.511883 \n123560 6.0 0.078261 -0.433072 -0.449204 \n123564 3.0 0.220588 -0.590788 -0.613207 \n123565 16.0 0.250000 -0.096026 -0.089119 \n123566 8.0 0.155172 -0.462661 -0.503903 \n123570 15.0 0.206522 -0.232748 -0.261417 \n123571 5.0 0.039474 -0.580653 -0.602446 \n123572 2.0 0.031915 -0.629037 -0.641815 \n123574 7.0 0.074074 -0.445053 -0.490445 \n123577 11.0 0.225806 -0.289469 -0.322368 \n123580 3.0 0.250000 -0.488550 -0.552963 \n123583 16.0 0.321429 -0.139275 -0.091747 \n123588 2.0 0.157480 -0.643403 -0.665507 \n123592 9.0 0.102041 -0.364548 -0.394195 \n123598 12.0 0.114286 -0.221053 -0.233221 \n123601 13.0 0.358974 -0.492847 -0.280732 \n123602 11.0 0.021886 -0.539419 -0.585619 \n123603 18.0 0.198020 -0.435535 -0.444649 \n123605 17.0 0.127168 -0.291286 -0.328035 \n123606 17.0 0.170213 -0.141321 -0.128393 \n123621 8.0 0.058333 -0.337822 -0.342151 \n\n price_max duration_mean duration_min duration_max \\\n0 -0.009842 -86.512254 -106.300977 -10.776623 \n1 -0.026790 -91.386374 -104.554878 -12.808294 \n3 -0.020002 -77.884718 -98.934813 -25.562332 \n4 0.266667 -46.369598 -103.010994 113.600000 \n6 0.090512 -61.157319 -92.647745 50.667331 \n9 -0.180668 -97.407772 -110.099538 -41.192219 \n15 0.017188 -57.765858 -99.770876 14.643750 \n17 0.048697 -83.131476 -99.759962 13.829968 \n18 -0.275751 -95.240323 -101.393267 -77.851995 \n19 -0.070678 -113.808178 -118.760766 -40.074440 \n21 0.053235 -72.956712 -102.984559 52.115481 \n23 0.022212 -81.703406 -96.059619 17.347852 \n30 0.044373 -78.770650 -102.041692 55.948433 \n32 0.051454 -89.371618 -104.603452 46.691650 \n34 0.044946 -86.916370 -104.052624 25.969922 \n35 0.061572 -79.812109 -104.558855 17.732813 \n37 0.054628 -77.139015 -105.467615 36.873779 \n38 -0.055887 -96.272076 -107.989393 -28.558029 \n49 -0.073449 -93.899111 -105.748283 -32.241344 \n53 -0.077986 -90.611012 -102.652779 -33.375038 \n56 0.029645 -67.018864 -104.221886 38.953855 \n59 -0.017591 -90.741692 -105.630060 -6.090140 \n64 0.086854 -81.480792 -104.212460 79.037109 \n66 -0.005198 -91.487250 -103.042797 -5.904621 \n67 0.044374 -51.651344 -98.331103 30.351749 \n69 0.017507 -83.338436 -108.236047 14.537402 \n73 -0.484150 -93.008781 -103.572330 -67.780986 \n82 -0.131754 -94.615392 -104.554878 -65.481513 \n85 0.005559 -83.695999 -103.910769 2.334856 \n88 0.025439 -90.055958 -103.933656 11.385203 \n... ... ... ... ... \n123530 0.065973 -46.953213 -101.961563 37.472607 \n123531 0.099050 -58.864804 -103.432084 77.647656 \n123534 -0.054266 -87.715692 -104.227476 -49.529231 \n123538 0.042495 -86.547375 -105.797722 38.975781 \n123545 0.066667 -47.134420 -104.406245 113.600000 \n123547 0.094118 -58.222665 -101.605371 113.600000 \n123552 -0.114750 -88.342051 -101.146909 -56.734260 \n123556 0.185076 -25.645476 -99.202067 105.123369 \n123557 0.068893 -64.963612 -98.709925 53.805554 \n123559 -0.031038 -87.151125 -102.956952 -24.240798 \n123560 0.007505 -76.354489 -106.157451 3.170924 \n123564 0.122683 -88.706483 -103.155794 26.519108 \n123565 0.089683 -36.993768 -101.544021 101.245118 \n123566 0.025498 -90.031077 -101.553159 14.278990 \n123570 -0.042360 -85.884023 -109.339668 -47.019893 \n123571 -0.055905 -90.396469 -102.762884 -19.846248 \n123572 -0.108306 -90.429264 -102.866836 -15.681391 \n123574 -0.022086 -85.244210 -101.332814 -11.259253 \n123577 0.034752 -77.183600 -102.050248 27.141553 \n123580 -0.140981 -89.272766 -108.079801 -30.874924 \n123583 -0.014947 -61.254525 -82.119161 -16.713943 \n123588 0.119727 -96.470225 -108.130884 17.240625 \n123592 -0.015694 -84.682611 -104.544370 -10.028476 \n123598 0.115370 -73.524393 -102.356037 98.295320 \n123601 0.081835 -76.983697 -105.161936 75.269536 \n123602 0.034641 -90.827931 -106.947106 27.435938 \n123603 0.037646 -87.604589 -105.915097 48.111340 \n123605 0.094118 -73.640808 -104.040718 112.800000 \n123606 0.071961 -45.596957 -97.328062 86.857129 \n123621 -0.076852 -94.164075 -107.878983 -46.111330 \n\n amount_month_ratio_mean amount_month_ratio_min \\\n0 -0.016410 -0.020299 \n1 -0.018222 -0.020741 \n3 -0.015565 -0.019918 \n4 -0.009248 -0.020566 \n6 -0.012284 -0.018631 \n9 -0.016880 -0.019190 \n15 -0.011542 -0.020069 \n17 -0.016616 -0.019790 \n18 -0.019080 -0.020258 \n19 -0.017394 -0.018169 \n21 -0.014660 -0.020883 \n23 -0.016296 -0.019344 \n30 -0.015853 -0.020527 \n32 -0.017832 -0.021046 \n34 -0.017431 -0.021097 \n35 -0.015529 -0.020429 \n37 -0.013718 -0.018853 \n38 -0.018145 -0.020357 \n49 -0.017808 -0.020362 \n53 -0.018311 -0.020950 \n56 -0.012700 -0.019557 \n59 -0.017603 -0.020513 \n64 -0.016417 -0.020965 \n66 -0.018280 -0.020620 \n67 -0.008670 -0.016585 \n69 -0.015325 -0.019900 \n73 -0.018849 -0.020901 \n82 -0.018843 -0.020741 \n85 -0.016807 -0.020907 \n88 -0.018149 -0.020714 \n... ... ... \n123530 -0.009495 -0.020524 \n123531 -0.011588 -0.020518 \n123534 -0.017625 -0.020969 \n123538 -0.016919 -0.020488 \n123545 -0.009394 -0.021010 \n123547 -0.011639 -0.020167 \n123552 -0.017762 -0.020202 \n123556 -0.005204 -0.019921 \n123557 -0.013035 -0.019844 \n123559 -0.017409 -0.020569 \n123560 -0.014833 -0.020634 \n123564 -0.017748 -0.020780 \n123565 -0.007389 -0.020144 \n123566 -0.018191 -0.020430 \n123570 -0.015817 -0.020240 \n123571 -0.018005 -0.020534 \n123572 -0.018222 -0.020993 \n123574 -0.017069 -0.020397 \n123577 -0.015425 -0.020679 \n123580 -0.016841 -0.020402 \n123583 -0.012403 -0.016568 \n123588 -0.018365 -0.020660 \n123592 -0.016977 -0.020739 \n123598 -0.014783 -0.020595 \n123601 -0.015439 -0.021010 \n123602 -0.017620 -0.020782 \n123603 -0.017605 -0.021103 \n123605 -0.014853 -0.020937 \n123606 -0.009066 -0.019457 \n123621 -0.016887 -0.019412 \n\n amount_month_ratio_max new_CLV hist_CLV CLV_ratio \n0 -0.002022 -0.073377 -38.135813 0.001924 \n1 -0.002743 -0.755873 -54.098181 0.013972 \n3 -0.005071 -0.812501 -5.029850 0.161536 \n4 0.022696 -0.119564 -71.651171 0.001669 \n6 0.010348 -0.549059 -12.674939 0.043318 \n9 -0.007132 -0.713360 -18.597088 0.038359 \n15 0.002905 -0.145301 -0.294969 0.492599 \n17 0.002743 -0.301703 -30.638669 0.009847 \n18 -0.015606 -0.085105 -8.093212 0.010516 \n19 -0.006108 -0.138648 -57.268619 0.002421 \n21 0.010658 -0.801956 -85.540110 0.009375 \n23 0.003441 -0.075801 -4.161991 0.018213 \n30 0.011403 -1.312337 -554.887004 0.002365 \n32 0.009582 -0.314648 -109.981791 0.002861 \n34 0.005137 -3.106224 -3673.394957 0.000846 \n35 0.003421 -1.111041 -2.531807 0.438833 \n37 0.006555 -0.188721 -16.684340 0.011311 \n38 -0.005359 -0.464329 -68.665793 0.006762 \n49 -0.006024 -0.554109 -52.827693 0.010489 \n53 -0.006560 -0.086037 -8.959030 0.009603 \n56 0.007310 -0.100234 -13.020497 0.007698 \n59 -0.001269 -1.155573 -95.776995 0.012065 \n64 0.016130 -0.369071 -36.427438 0.010132 \n66 -0.001171 -0.084651 -49.921677 0.001696 \n67 0.005255 -0.038350 -0.309372 0.123961 \n69 0.002602 -1.141017 -0.846652 1.347682 \n73 -0.013833 -0.083894 -5.040476 0.016644 \n82 -0.012990 -0.480778 -21.682126 0.022174 \n85 0.000477 -1.814378 -63.187088 0.028714 \n88 0.002039 -0.332064 -1068.553009 0.000311 \n... ... ... ... ... \n123530 0.007595 -1.106755 -8.574118 0.129081 \n123531 0.015289 -1.643920 -0.873047 1.882969 \n123534 -0.010048 -0.150432 -14.505728 0.010371 \n123538 0.007829 -1.724186 -145.791506 0.011826 \n123545 0.022857 -0.889510 -540.155913 0.001647 \n123547 0.022696 -0.273777 -15.104450 0.018126 \n123552 -0.011373 -0.310270 -16.898401 0.018361 \n123556 0.021015 0.044232 -3.109986 -0.014223 \n123557 0.010674 -0.051872 -259.119641 0.000200 \n123559 -0.004809 -0.246968 -8.202994 0.030107 \n123560 0.000639 -0.544910 -58.603255 0.009298 \n123564 0.005106 -2.112636 -36.409830 0.058024 \n123565 0.020338 -0.025121 -0.459847 0.054629 \n123566 0.002914 -0.611775 -15.236847 0.040151 \n123570 -0.008587 -1.175269 -8.334289 0.141016 \n123571 -0.003937 -0.146154 -42.230641 0.003461 \n123572 -0.002990 -0.083871 -78.603181 0.001067 \n123574 -0.002121 -0.136691 -12.972772 0.010537 \n123577 0.005384 -0.575094 -1.085875 0.529613 \n123580 -0.005794 -1.913780 -15.627654 0.122461 \n123583 -0.003422 -0.087564 -2.242306 0.039051 \n123588 0.003326 -3.847265 -141.092066 0.027268 \n123592 -0.001989 -0.460074 -5.946822 0.077365 \n123598 0.019499 -0.569482 -23.411185 0.024325 \n123601 0.015037 -0.149929 -12.209216 0.012280 \n123602 0.005292 -1.513947 -2287.250047 0.000662 \n123603 0.009705 -17.567780 -397.855018 0.044156 \n123605 0.022696 -2.985131 -58.408220 0.051108 \n123606 0.017391 -0.137785 -10.364862 0.013293 \n123621 -0.008198 -0.303733 -32.467881 0.009355 \n\n[37198 rows x 191 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
feature_1feature_2feature_3daysquarterdays_feature_1days_feature_1_ratiodays_feature_2days_feature_2_ratiodays_feature_3days_feature_3_ratiohist_transactions_counthist_purchase_amount_sumhist_purchase_amount_maxhist_purchase_amount_minhist_purchase_amount_meanhist_purchase_amount_varhist_purchase_amount_skewhist_installments_sumhist_installments_maxhist_installments_meanhist_installments_varhist_installments_skewhist_purchase_date_maxhist_purchase_date_minhist_month_lag_maxhist_month_lag_minhist_month_lag_meanhist_month_lag_varhist_month_lag_skewhist_month_diff_maxhist_month_diff_minhist_month_diff_meanhist_month_diff_varhist_month_diff_skewhist_weekend_sumhist_weekend_meanhist_weekday_sumhist_weekday_meanhist_authorized_flag_sumhist_authorized_flag_meanhist_category_1_sumhist_category_1_meanhist_category_1_maxhist_category_1_minhist_card_id_sizehist_card_id_counthist_month_nuniquehist_month_meanhist_month_minhist_month_maxhist_hour_nuniquehist_hour_meanhist_hour_minhist_hour_maxhist_weekofyear_nuniquehist_weekofyear_meanhist_weekofyear_minhist_weekofyear_maxhist_day_nuniquehist_day_meanhist_day_minhist_day_maxhist_subsector_id_nuniquehist_merchant_category_id_nuniquehist_price_sumhist_price_meanhist_price_maxhist_price_minhist_price_varhist_duration_meanhist_duration_minhist_duration_maxhist_duration_varhist_duration_skewhist_amount_month_ratio_meanhist_amount_month_ratio_minhist_amount_month_ratio_maxhist_amount_month_ratio_varhist_amount_month_ratio_skewhist_purchase_date_diffhist_purchase_date_averagehist_purchase_date_uptonowhist_purchase_date_uptominhist_first_buyhist_last_buynew_transactions_countnew_purchase_amount_sumnew_purchase_amount_maxnew_purchase_amount_minnew_purchase_amount_meannew_purchase_amount_varnew_purchase_amount_skewnew_installments_sumnew_installments_maxnew_installments_meannew_installments_varnew_installments_skewnew_purchase_date_maxnew_purchase_date_minnew_month_lag_maxnew_month_lag_minnew_month_lag_meannew_month_lag_varnew_month_lag_skewnew_month_diff_maxnew_month_diff_minnew_month_diff_meannew_month_diff_varnew_month_diff_skewnew_weekend_sumnew_weekend_meannew_weekday_sumnew_weekday_meannew_authorized_flag_sumnew_authorized_flag_meannew_category_1_sumnew_category_1_meannew_category_1_maxnew_category_1_minnew_card_id_sizenew_card_id_countnew_month_nuniquenew_month_meannew_month_minnew_month_maxnew_hour_nuniquenew_hour_meannew_hour_minnew_hour_maxnew_weekofyear_nuniquenew_weekofyear_meannew_weekofyear_minnew_weekofyear_maxnew_day_nuniquenew_day_meannew_day_minnew_day_maxnew_subsector_id_nuniquenew_merchant_category_id_nuniquenew_price_sumnew_price_meannew_price_maxnew_price_minnew_price_varnew_duration_meannew_duration_minnew_duration_maxnew_duration_varnew_duration_skewnew_amount_month_ratio_meannew_amount_month_ratio_minnew_amount_month_ratio_maxnew_amount_month_ratio_varnew_amount_month_ratio_skewnew_purchase_date_diffnew_purchase_date_averagenew_purchase_date_uptonownew_purchase_date_uptominnew_first_buynew_last_buycard_id_totalcard_id_cnt_totalcard_id_cnt_ratiopurchase_amount_totalpurchase_amount_meanpurchase_amount_maxpurchase_amount_minpurchase_amount_ratiomonth_diff_meanmonth_diff_ratiomonth_lag_meanmonth_lag_maxmonth_lag_mincategory_1_meaninstallments_totalinstallments_meaninstallments_maxinstallments_ratioprice_totalprice_meanprice_maxduration_meanduration_minduration_maxamount_month_ratio_meanamount_month_ratio_minamount_month_ratio_maxnew_CLVhist_CLVCLV_ratio
00.0104790.0141660.011428306.02.03.2066930.0000344.3349190.0000463.4968210.00003768-40.7337330.235676-0.743903-0.5990250.0369672.335008141.012.02.0735294.2482442.4590191.514510e+091.491330e+090-8-3.6323536.026997-0.116148737272.6323530.235953-0.561457120.1764711902.794118440.647059230.33823510686898.3676474121714.3676470232434.54411814522416.3529411311216-34.806456-0.5118600.117838-0.7439030.075928-43.504279-54.30488317.204334194.8321412.340366-0.008249-0.0102690.0032287.021478e-062.3250932683.941176218124493.0272.03.0-1.777344-0.383301-0.722168-0.5924480.0334391.5858265.03.01.6666671.3333331.7320511.519845e+091.517651e+092.02.02.0000000.0000000.00000073.072.072.6666670.333333-1.7320511.00.33333311.03.6666673.01.00.00.0000000.00.03.03.01.02.0000002.02.03.013.6666679.019.03.07.0000005.09.03.015.6666673.028.03.03.0-1.521810-0.507270-0.127767-0.7221680.108649-43.007975-51.996094-27.980957171.5329301.633769-0.008162-0.010030-0.0052516.525404e-061.53038325.08.3333332119.02145.0308.0333.071.071.00.044118-42.511076-1.191473-0.147625-1.4660700.043633145.2990201.000472-1.6323532.0-6.00.338235146.03.74019615.00.035461-0.291172-0.318559-0.009842-86.512254-106.300977-10.776623-0.016410-0.020299-0.002022-0.073377-38.1358130.001924
10.0106100.0141660.010283396.01.04.2015160.0000275.6098950.0000364.0720030.00002678-49.1365130.318817-0.731881-0.6299550.0240253.77072383.04.01.0641030.1646696.4909151.518989e+091.484321e+090-13-10.4102564.6866472.716127717070.8461540.131868-1.956637170.2179492292.935897770.98717920.02564110787853.282051151814.4230770232012.4358972212716.5128212301216-48.475933-0.6214860.318817-0.7318810.029578-44.621400-51.96357022.636042120.3065233.783589-0.008894-0.0103080.0044904.802841e-063.7509524015.1410262129253012.0413.09.0-5.944336-0.506348-0.740723-0.6604820.0050611.27839011.03.01.2222220.4444443.0000001.524247e+091.520080e+092.01.01.4444440.2777780.27105271.070.070.7777780.194444-1.6198483.00.33333327.03.0000009.01.02.00.2222221.00.09.09.02.03.4444443.04.08.015.2222229.023.06.012.4444449.016.07.011.3333333.020.06.08.0-5.606771-0.622975-0.168783-0.7407230.030730-46.764974-52.591309-35.44433627.0090731.296674-0.009329-0.010433-0.0072349.496697e-071.25386348.05.3333332068.02117.0426.0474.087.087.00.115385-55.080849-1.290437-0.187530-1.4726040.120976141.6239320.999035-8.9658122.0-12.00.24786394.02.2863257.00.132530-0.585966-0.564415-0.026790-91.386374-104.554878-12.808294-0.018222-0.020741-0.002743-0.755873-54.0981810.013972
30.0106100.0113850.01028362.04.00.6578130.0001710.7058560.0001840.6375360.00016626-13.6907150.087965-0.731881-0.5265660.0480321.86377040.06.01.6666671.7971012.3275601.519127e+091.512392e+090-2-1.2307690.9046150.502455717070.7692310.184615-1.35763470.269231642.461538261.00000000.00000000262637.692308112917.923077822631.1153854501111.4230774241118-11.504476-0.479353-0.040662-0.7318810.055943-37.266139-51.2316886.245529240.2962381.867951-0.007441-0.0104550.0012399.606558e-061.857336772.961538212822053.081.010.0-5.744385-0.447998-0.671875-0.5744380.0053520.37989129.012.02.90000011.2111112.6612921.524000e+091.520162e+092.01.01.3000000.2333331.03509871.070.070.7000000.233333-1.0350983.00.30000032.03.20000010.01.01.00.1000001.00.010.010.02.03.3000003.04.07.018.20000011.021.07.012.1000009.016.08.013.6000004.031.08.010.0-3.805725-0.380573-0.037333-0.6718750.058179-40.618579-47.703125-31.80786127.3972200.344351-0.008124-0.009463-0.0063101.050934e-060.41368744.04.4000002071.02116.093.0137.036.036.00.384615-19.435100-1.101004-0.360033-1.4037560.419583141.4692310.9990220.0692312.0-1.00.10000069.04.56666718.00.725000-0.281668-0.241096-0.020002-77.884718-98.934813-25.562332-0.015565-0.019918-0.005071-0.812501-5.0298500.161536
40.0131450.0113850.011428793.04.010.4236800.0000179.0281260.0000149.0620240.000014110-46.0936130.800000-0.746758-0.4190330.2481431.744851120.04.01.0909090.1934955.7269161.519728e+091.483444e+090-13-6.22727320.5258550.091212717070.7636360.182152-1.258310210.1909092652.409091870.79090900.00000000110110124.8272731122114.4363640233418.8363641522713.2727271301531-46.693329-0.4244850.800000-0.7467580.230516-29.627280-53.01978356.8000001245.2590431.744943-0.005927-0.0106490.0114294.945579e-051.7443644193.80909121212541399.0819.06.0-1.4148440.800000-0.704102-0.2358070.4768821.0487256.02.01.2000000.2000002.2360681.523535e+091.520132e+092.01.01.1666670.1666672.44949071.071.071.0000000.0000000.0000002.00.33333324.04.0000006.01.00.00.0000000.00.06.06.02.03.1666673.04.05.08.0000000.016.03.010.5000009.015.05.07.3333334.012.04.05.0-2.307520-0.4615040.400000-0.7041020.232595-16.742318-49.99121156.8000002403.9613291.048725-0.003321-0.0099170.0112689.460064e-051.04872539.06.5000002077.02116.0824.0863.0116.0116.00.054545-47.508457-0.6548401.600000-1.4508590.030695141.7636361.003340-5.0606062.0-12.00.000000126.02.2909096.00.050000-0.377051-0.2858430.266667-46.369598-103.010994113.600000-0.009248-0.0205660.022696-0.119564-71.6511710.001669
60.0080580.0087520.010283123.04.00.9911940.0000661.0765110.0000711.2647890.00008448-18.6108160.743722-0.683887-0.3877250.1069032.26365376.06.01.6888891.1282831.9784061.519569e+091.507572e+090-4-1.7500001.936170-0.370837717070.4791670.2548760.086121140.2916671412.937500481.00000010.02083310484856.7500001121614.2916676221327.8125001522017.4583332311417-15.890002-0.3531110.371861-0.6838870.066838-27.330344-48.55594852.060550531.4686072.250563-0.005501-0.0096320.0106252.151042e-052.2758511382.875000212222618.0147.09.0-4.311127-0.019623-0.629883-0.4790140.0325302.4854609.02.01.1250000.1250002.8284271.524562e+091.520019e+092.01.01.6666670.250000-0.85714371.070.070.6666670.250000-0.8571432.00.22222230.03.3333339.01.00.00.0000000.00.09.09.02.03.6666673.04.07.014.0000009.019.05.013.3333339.017.07.011.0000002.026.06.06.0-3.804977-0.475622-0.009811-0.6298830.038423-33.826976-44.091797-1.393219161.7878262.499442-0.006784-0.008998-0.0002766.547015e-062.46698052.05.7777782065.02117.0152.0205.057.057.00.187500-22.921942-0.8667390.724099-1.3137690.231646141.1458331.002660-0.0833332.0-3.00.02083385.02.8138898.00.118421-0.269670-0.3080220.090512-61.157319-92.64774550.667331-0.012284-0.0186310.010348-0.549059-12.6749390.043318
90.0131450.0113850.011428702.01.09.2275200.0000197.9921110.0000168.0221190.00001648-29.4211740.026356-0.731881-0.6129410.0249922.49814049.02.01.0208330.0208336.9282031.506568e+091.483614e+090-8-5.5000006.1702131.264590767575.9375000.059840-3.732451150.3125001783.708333430.89583300.00000000484873.500000191814.6041671231512.5208331391910.9166673281016-29.348250-0.6114220.026356-0.7318810.026552-46.539066-55.6229762.003094143.6992182.507977-0.008073-0.0097580.0003474.348479e-062.4858972655.52083322732539310.0576.09.0-6.023926-0.568359-0.716797-0.6693250.0017671.9290709.01.01.0000000.0000000.0000001.511060e+091.507467e+092.01.01.4444440.2777780.27105276.076.076.0000000.0000000.0000002.00.22222221.02.3333339.01.00.00.0000000.00.09.09.02.010.44444410.011.08.015.2222220.023.03.043.11111140.046.06.012.3333338.019.07.07.0-6.023926-0.669325-0.568359-0.7167970.001767-50.868707-54.476562-43.19531210.2063421.929070-0.008807-0.009432-0.0074783.059256e-071.92907041.04.5555562221.02262.0586.0628.057.057.00.187500-35.445099-1.282266-0.542003-1.4486780.204748151.9375001.000823-4.0555562.0-7.00.00000058.02.0208333.00.183673-0.611122-0.634523-0.180668-97.407772-110.099538-41.192219-0.016880-0.019190-0.007132-0.713360-18.5970880.038359
150.0106100.0141660.01028392.04.00.9761100.0001151.3033090.0001540.9460210.00011211-1.8892650.800000-0.693804-0.1717510.2682081.04907639.010.03.54545511.8727271.3860551.519824e+091.510697e+090-3-1.4545451.472727-0.128859717070.4545450.2727270.21276200.000000232.09090990.81818230.27272710111146.000000112913.727273123725.090909451820.09090982845-2.506857-0.2278960.080000-0.6938040.092318-11.986806-48.56628656.8000001340.3821191.056341-0.002461-0.0099110.0112685.367649e-051.0414651059.5454552119222513.0119.04.0-2.579102-0.593750-0.721191-0.6447750.003196-1.0260035.02.01.2500000.2500002.0000001.523560e+091.523109e+092.02.02.0000000.0000000.00000071.071.071.0000000.0000000.0000001.00.25000014.03.5000004.01.00.00.0000000.00.04.04.01.04.0000004.04.03.015.50000013.019.02.014.75000014.015.02.010.7500007.012.03.04.0-2.282227-0.570557-0.296875-0.7211910.035328-45.779053-51.204590-42.15625016.108638-1.026003-0.009081-0.010158-0.0083636.339068e-07-1.0260035.01.2500002076.02081.0157.0162.015.015.00.363636-4.468366-0.8165270.206250-1.4149951.365135141.4545451.0077420.5454552.0-1.00.27272744.04.79545512.00.128205-0.101554-0.1702710.017188-57.765858-99.77087614.643750-0.011542-0.0200690.002905-0.145301-0.2949690.492599
170.0107120.0141660.010283153.03.01.6388740.0000702.1674600.0000931.5732740.00006761-35.4802540.671595-0.725871-0.5816440.0432664.42041473.03.01.1967210.2606562.6293381.519320e+091.504619e+090-5-2.3442623.529508-0.243751717070.6393440.234426-0.595105100.1639341833.000000600.98360710.01639310616157.5245901121613.2786890231430.7540984502514.5901641301421-34.215277-0.5609060.223865-0.7258710.037202-41.076259-51.53681747.683239216.9831114.414642-0.008237-0.0102240.0094598.634764e-064.4202021702.786885212522954.0174.06.0-3.561768-0.476807-0.679199-0.5936280.0054080.5822165.01.01.0000000.0000000.0000001.522746e+091.520256e+092.01.01.1666670.1666672.44949071.070.070.8333330.166667-2.4494901.00.16666710.01.6666676.01.00.00.0000000.00.06.06.02.03.1666673.04.04.011.6666678.014.03.011.16666710.014.04.09.6666673.031.03.05.0-3.084961-0.616992-0.554199-0.6791990.002666-42.055216-48.223145-33.85327127.9329900.514750-0.008380-0.009566-0.0067161.050086e-060.65944428.04.6666672086.02114.0185.0214.067.067.00.098361-39.042022-1.1752710.194788-1.4050700.100387141.4726781.002746-1.1775962.0-4.00.01639378.02.1967214.00.068493-0.500539-0.5350120.048697-83.131476-99.75996213.829968-0.016616-0.0197900.002743-0.301703-30.6386690.009847
180.0104790.0141660.01142892.04.00.9641040.0001141.3033090.0001541.0513320.00012429-19.621950-0.461404-0.741062-0.6766190.0083451.84038529.03.01.0740740.1481485.1961521.517850e+091.509477e+090-4-2.3448281.5197040.966616717070.3103450.2216750.865308130.448276973.344828190.65517200.00000000292949.5862072121210.310345023740.4482765511120.344828231811-18.382403-0.680830-0.153801-0.7410620.014285-47.571866-52.615435-32.29828441.1742601.850877-0.009624-0.010581-0.0065691.699686e-061.813646963.31034521422239-1.096.03.0-2.014160-0.641602-0.687012-0.6713870.0006661.7257743.01.01.0000000.0000000.0000001.524116e+091.519990e+092.01.01.6666670.333333-1.73205171.071.071.0000000.0000000.0000000.00.00000010.03.3333333.01.00.00.0000000.00.03.03.02.03.6666673.04.02.07.0000005.011.02.013.6666679.016.02.013.3333332.019.02.03.0-2.014160-0.671387-0.641602-0.6870120.000666-47.668457-48.777832-45.5537113.3568171.725774-0.009456-0.009676-0.0090371.320974e-071.72577447.015.6666672070.02118.0121.0169.032.032.00.103448-21.636110-1.348006-1.103006-1.4280740.102648141.3103451.009809-0.6781612.0-3.00.00000032.02.0740744.00.103448-0.676128-0.649931-0.275751-95.240323-101.393267-77.851995-0.019080-0.020258-0.015606-0.085105-8.0932120.010516
190.0106100.0113850.010283396.01.04.2015160.0000274.5083700.0000294.0720030.00002681-57.1115040.154668-0.738643-0.7050800.0112117.16298286.06.01.0617280.3086429.0000001.493465e+091.483810e+090-3-1.5432101.2512350.000983818080.7777780.175000-1.361653260.3209882573.172840811.00000000.00000000818142.456790141313.061728820169.0493831172617.876543331811-57.240394-0.7066720.025778-0.7386430.008646-56.953930-59.83010212.52809973.3904187.143986-0.008729-0.0091870.0019091.716750e-067.1548281111.370370242525366.0118.04.0-2.807617-0.649414-0.727539-0.7019040.0012711.7867864.01.01.0000000.0000000.0000001.497615e+091.493993e+092.01.01.5000000.3333330.00000081.081.081.0000000.0000000.0000001.00.25000013.03.2500004.01.00.00.0000000.00.04.04.02.05.5000005.06.04.011.75000010.014.04.021.00000018.024.04.09.7500005.016.04.04.0-2.807617-0.701904-0.649414-0.7275390.001271-56.854248-58.930664-52.6025398.3359641.786786-0.008665-0.008982-0.0080171.936492e-071.78678641.010.2500002377.02418.0124.0166.085.085.00.049383-59.919121-1.406985-0.494746-1.4661820.049160161.7777781.002751-0.0432102.0-2.00.00000090.02.0617287.00.046512-0.665768-0.682430-0.070678-113.808178-118.760766-40.074440-0.017394-0.018169-0.006108-0.138648-57.2686190.002421
210.0106100.0113850.010283245.02.02.5994230.0000432.7892700.0000462.5192950.00004297-62.275455-0.054712-0.742099-0.6420150.0200872.218796151.010.01.5894743.2232923.7270421.519836e+091.496495e+090-8-3.8144335.527706-0.036041717070.6185570.238402-0.495849280.2886602802.886598890.917526510.52577310979798.0824741121814.5876290233133.1855671522815.0824741311219-57.381043-0.604011-0.005471-0.7420990.047628-45.322841-52.603700-3.88451999.3896122.236363-0.009095-0.010601-0.0007714.068498e-062.1922022702.783505211923892.0272.012.0-4.7059200.800000-0.719727-0.3921600.1832742.23397315.04.01.6666671.2500001.5333041.525064e+091.520343e+092.01.01.8333330.151515-2.05523771.070.070.4166670.2651520.3884033.00.25000036.03.00000012.01.01.00.0833331.00.012.012.02.03.8333333.04.08.011.1666670.017.06.015.33333310.018.010.019.5000006.030.010.010.0-4.357259-0.484140-0.112142-0.7197270.061824-27.633870-50.38085956.000000901.1208642.239443-0.005566-0.0102820.0114293.728146e-052.22789554.04.5000002059.02113.0278.0333.0109.0109.00.123711-66.981375-1.0341750.745288-1.4618260.075566141.0352230.997141-1.9811002.0-7.00.609107166.03.25614014.00.099338-0.403502-0.3176080.053235-72.956712-102.98455952.115481-0.014660-0.0208830.010658-0.801956-85.5401100.009375
230.0131450.0113850.011428153.03.02.0111260.0000861.7418700.0000741.7484110.00007523-12.7849430.800000-0.721513-0.5558670.0918894.41893532.010.01.3913043.5217394.7958321.519420e+091.505855e+090-5-2.6521742.6007910.086967717070.6521740.237154-0.68448440.173913592.565217231.00000000.00000000232368.7391301121214.9130437221636.5217393521717.86956533067-13.504943-0.5871710.080000-0.7215130.025680-39.246701-50.50590856.800000460.6104534.426561-0.007873-0.0103070.0112681.833984e-054.4082141576.8260872124228118.0175.03.0-1.793945-0.555664-0.641602-0.5979820.001848-0.1361923.01.01.0000000.0000000.0000001.521130e+091.520142e+091.01.01.0000000.0000000.00000071.071.071.0000000.0000000.0000001.00.33333311.03.6666673.01.00.00.0000000.00.03.03.01.03.0000003.03.03.012.6666675.017.02.010.3333339.011.03.011.0000004.015.02.03.0-1.793945-0.597982-0.555664-0.6416020.001848-42.456706-45.553711-39.4521489.313676-0.136192-0.008422-0.009037-0.0078263.665116e-07-0.13619211.03.6666672104.02116.0184.0195.026.026.00.130435-14.578889-1.1538490.244336-1.3631150.140317141.6521741.004923-1.6521741.0-4.00.00000035.02.39130411.00.093750-0.416540-0.4825190.022212-81.703406-96.05961917.347852-0.016296-0.0193440.003441-0.075801-4.1619910.018213
300.0104790.0113850.011428365.01.03.8249770.0000294.1554430.0000314.1710450.000031262-149.5698710.760417-0.729687-0.5708770.0662843.067938346.012.01.3307692.1141085.9255001.519820e+091.486392e+090-12-5.00000011.333333-0.205827717070.6221370.235983-0.506718790.3015278023.0610692580.984733160.06106910262262126.4809161122313.1946560235126.3587791523116.3244271312137-143.810518-0.5531170.760417-0.7296870.072970-40.311443-51.80780553.229164330.5789063.062560-0.008085-0.0104130.0108631.329936e-053.0703453861.473282212025065.0392.013.0-7.1052550.038300-0.708008-0.5465580.0503681.80003520.06.01.6666672.2424242.6350711.525032e+091.520361e+092.01.01.6923080.230769-0.94621271.070.070.3846150.2564100.5385936.00.46153850.03.84615413.01.00.00.0000000.00.013.013.02.03.6923083.04.09.015.69230810.023.06.014.53846210.017.09.019.1538464.029.010.011.0-5.783112-0.4819260.038300-0.7080080.086178-38.459207-50.2338872.719269250.8853761.786639-0.007768-0.0101140.0005391.011994e-051.81034854.04.1538462059.02113.0398.0452.0275.0275.00.049618-156.675126-1.1174350.798716-1.4376950.047505141.0067530.996637-3.3076922.0-11.00.061069366.02.99743618.00.057803-0.428074-0.3727970.044373-78.770650-102.04169255.948433-0.015853-0.0205270.011403-1.312337-554.8870040.002365
320.0104790.0141660.011428306.02.03.2066930.0000344.3349190.0000463.4968210.000037110-70.7610120.800000-0.745405-0.6432820.0482335.126908135.010.01.2385321.3129466.2888531.518958e+091.491915e+090-10-4.7454559.127273-0.159111717070.7727270.177231-1.319647250.2272733232.9363641040.94545500.00000000110110116.6363641122012.6090910233726.8090911522814.6000001311215-69.819244-0.6405440.229815-0.7454050.032407-45.538569-52.92376556.000000239.3863235.123051-0.009087-0.0104990.0114299.725768e-065.1251623122.8363642129244210.0323.06.0-3.714600-0.131104-0.738281-0.6191000.0574002.4258878.03.01.3333330.6666672.4494901.524817e+091.521451e+092.01.01.6666670.266667-0.96824671.070.070.8333330.166667-2.4494900.00.00000011.01.8333336.01.00.00.0000000.00.06.06.02.03.6666673.04.05.011.6666678.016.04.014.00000012.017.05.014.1666674.027.04.04.0-3.627197-0.604533-0.043701-0.7382810.075734-43.833049-51.679688-9.308350286.9467792.432759-0.008744-0.010547-0.0018471.149011e-052.41552438.06.3333332062.02101.0352.0391.0116.0116.00.054545-74.475611-1.2623820.668896-1.4836860.052495141.6060611.000856-3.0787882.0-9.00.000000143.02.57186513.00.059259-0.520808-0.4908430.051454-89.371618-104.60345246.691650-0.017832-0.0210460.009582-0.314648-109.9817910.002861
340.0107120.0113850.010283337.01.03.6098060.0000323.8366690.0000343.4653150.000031645-402.4862980.800000-0.742415-0.6240100.0360334.800378697.06.01.0856700.1938978.0034271.519759e+091.490201e+090-11-5.14883710.0989310.034465717070.6713180.220993-0.7311261420.22015518432.8573646360.9860471180.18294610645645126.7302331122014.4093020234927.4930231523116.5860471312863-399.374602-0.6220790.438684-0.7424150.028750-44.098601-52.64637456.800000179.5443434.796812-0.008830-0.0106060.0114297.239933e-064.7958253420.5302332120246221.0363.019.0-11.530029-0.440430-0.734375-0.6068440.0091090.38849720.02.01.1111110.1045752.7057881.525086e+091.520331e+092.01.01.3157890.2280700.86221471.070.070.5263160.263158-0.1146689.00.47368474.03.89473719.01.02.00.1052631.00.019.019.02.03.3157893.04.013.012.7894743.022.08.012.89473710.018.011.019.3684216.030.011.015.0-10.542236-0.585680-0.220215-0.7343750.022824-42.817768-51.406250-30.83007847.0145390.391139-0.008601-0.010491-0.0062921.770180e-060.37943355.02.8947372059.02114.0370.0425.0664.0664.00.029457-414.016328-1.2308530.359570-1.4767900.028647141.1976340.997948-3.8330482.0-10.00.288209717.02.1967818.00.028694-0.577429-0.5602990.044946-86.916370-104.05262425.969922-0.017431-0.0210970.005137-3.106224-3673.3949570.000846
350.0106100.0113850.010283123.04.01.3050160.0000861.4003270.0000931.2647890.00008420-9.0765280.800000-0.724368-0.4538260.2965152.05983418.03.01.1250000.2500004.0000001.516734e+091.506853e+090-3-1.2000001.642105-0.420198727171.7000000.221053-0.945300100.500000773.850000160.80000000.00000000202046.400000112711.300000019925.6500003481214.00000012467-10.591086-0.661943-0.144325-0.7243680.019964-32.461790-51.61354257.6000001528.8646632.062542-0.006345-0.0102020.0111115.751860e-052.0564961145.700000215522700.0114.011.0-7.253906-0.553711-0.735352-0.6594460.0047930.38306610.01.01.0000000.0000000.0000001.521904e+091.517738e+092.01.01.6363640.254545-0.66068772.071.071.8181820.163636-1.9227184.00.36363636.03.27272711.01.00.00.0000000.00.011.011.02.02.6363642.03.010.012.0909095.018.06.09.2727275.012.09.013.3636363.024.09.010.0-6.700195-0.670020-0.566406-0.7353520.003959-47.350320-52.945312-39.86718823.8081310.372131-0.009184-0.010226-0.0076909.701857e-070.37406148.04.3636362095.02144.0126.0174.031.031.00.550000-16.330435-1.1132720.246289-1.4597200.799194143.5181821.0016480.4363642.0-2.00.00000028.02.1250004.00.555556-0.583230-0.5238930.061572-79.812109-104.55885517.732813-0.015529-0.0204290.003421-1.111041-2.5318070.438833
370.0104790.0141660.011428215.03.02.2530680.0000493.0457770.0000662.4569170.00005352-24.0516120.800000-0.729477-0.4625310.1092241.81952170.06.01.3461541.0150833.3115831.508976e+091.500032e+090-3-1.6923081.3936650.184376757474.9615380.037707-4.943767160.3076921813.480769360.69230800.00000000525248.3076927101414.4423080231034.13461528431316.0961546271013-23.334159-0.4487340.555710-0.7294770.095221-34.676857-54.71077960.000000613.7488691.821514-0.006169-0.0098290.0106671.943868e-051.8173311031.9807692245234913.0117.05.0-2.830811-0.308350-0.676758-0.5661620.0219971.9267497.03.01.4000000.8000002.2360681.513107e+091.512228e+092.02.02.0000000.0000000.00000075.075.075.0000000.0000000.0000003.00.60000016.03.2000005.01.00.00.0000000.00.05.05.01.012.00000012.012.05.016.40000012.020.03.049.20000048.050.04.08.6000002.012.04.04.0-2.625244-0.525049-0.102783-0.6767580.056947-42.462158-50.756836-23.126221123.7339901.926749-0.007549-0.009023-0.0041113.910605e-061.92674910.02.0000002197.02207.0154.0164.057.057.00.096154-26.882422-1.0286930.491650-1.4062350.117697149.9615381.0005130.3076922.0-1.00.00000077.02.7461549.00.100000-0.349122-0.3745940.054628-77.139015-105.46761536.873779-0.013718-0.0188530.006555-0.188721-16.6843400.011311
380.0106100.0113850.010283337.01.03.5755330.0000313.8366690.0000343.4653150.00003189-56.0613160.213286-0.744443-0.6299020.0396442.500260103.05.01.1573030.2704295.1600521.514339e+091.490048e+090-9-4.7078657.8000510.482517737272.6629210.225996-0.701178220.2471912522.831461730.820225440.49438210898997.2921353122111.8089890232630.08988812522918.1123601311116-54.337567-0.6105340.061706-0.7444430.044697-45.773959-54.34437415.569901210.2022622.497337-0.008669-0.0102900.0029227.484211e-062.4987552813.1573032183246419.0301.07.0-4.842285-0.604492-0.734863-0.6917550.0019581.4876998.02.01.1428570.1428572.6457511.518833e+091.518191e+092.02.02.0000000.0000000.00000073.073.073.0000000.0000000.0000003.00.42857127.03.8571437.01.00.00.0000000.00.07.07.01.02.0000002.02.06.012.8571432.023.02.06.5714296.07.05.012.8571439.017.06.07.0-4.540039-0.648577-0.302246-0.7348630.023800-50.498117-53.645020-44.12793010.4351871.487699-0.009476-0.010067-0.0082813.674589e-071.4876997.01.0000002131.02138.0345.0353.096.096.00.078652-60.903601-1.321657-0.391206-1.4793070.086375145.6629211.004639-2.7078652.0-7.00.494382111.02.3001617.00.077670-0.548681-0.574594-0.055887-96.272076-107.989393-28.558029-0.018145-0.020357-0.005359-0.464329-68.6657930.006762
490.0131450.0113850.011428153.03.02.0111260.0000861.7418700.0000741.7484110.00007576-50.4863000.070534-0.742400-0.6642930.0133684.24615081.05.01.0945950.2786016.4306041.514739e+091.505769e+090-3-1.5263160.6259650.254595737272.6315790.235789-0.556591310.4078952343.078947761.00000030.039474107676410.4736849121812.3552630231343.76315838522616.7631581311524-49.208804-0.664984-0.057885-0.7424000.013884-48.250491-53.6467215.07848170.3406534.239842-0.009146-0.0103110.0009802.548476e-064.2309091031.3552632178228217.0121.08.0-5.030273-0.511230-0.723633-0.6287840.0069790.4250328.01.01.0000000.0000000.0000001.519555e+091.515426e+092.01.01.2500000.2142861.44016573.072.072.6250000.267857-0.6440611.00.12500014.01.7500008.01.00.00.0000000.00.08.08.02.01.2500001.02.05.013.2500008.019.06.04.0000002.08.08.016.0000006.029.07.07.0-5.030273-0.628784-0.511230-0.7236330.006979-45.648621-52.101562-37.31982435.3207960.389082-0.008662-0.010050-0.0070031.385180e-060.44449147.05.8750002123.02170.0129.0177.084.084.00.105263-55.516573-1.293078-0.440696-1.4660330.099636145.2565790.999909-0.2763162.0-2.00.03947489.02.0945956.00.098765-0.623782-0.617340-0.073449-93.899111-105.748283-32.241344-0.017808-0.020362-0.006024-0.554109-52.8276930.010489
530.0106100.0113850.01028362.04.00.6578130.0001710.7058560.0001840.6375360.00016632-19.7028670.153180-0.741859-0.6157150.0408862.86163537.04.01.1935480.3612903.8529121.519564e+091.513261e+090-2-0.8437500.781250-0.322623717070.3750000.2419350.54214970.218750802.500000321.00000000.00000000323234.9062501121313.531250419920.2812502521719.8750005311013-18.410911-0.5939000.076590-0.7418590.046083-43.338552-51.93012310.722618202.6448192.851911-0.008748-0.0105980.0021888.258187e-062.865921722.2500002122219513.086.03.0-2.017090-0.621094-0.724609-0.6723630.002680-0.0848644.02.01.3333330.3333331.7320511.521733e+091.521302e+091.01.01.0000000.0000000.00000071.070.070.3333330.3333331.7320511.00.33333310.03.3333333.01.00.00.0000000.00.03.03.01.03.0000003.03.02.016.00000015.018.02.011.66666711.012.03.020.00000017.022.03.03.0-1.681396-0.560465-0.335693-0.7246090.040571-47.272461-50.722656-44.09765611.029536-0.370584-0.009564-0.010352-0.0087486.435898e-070.1552224.01.3333332097.02102.0106.0111.035.035.00.093750-21.719957-1.288078-0.467913-1.4664680.102375140.7083330.9994080.1562501.0-1.00.00000041.02.5268826.00.108108-0.529755-0.509750-0.077986-90.611012-102.652779-33.375038-0.018311-0.020950-0.006560-0.086037-8.9590300.009603
560.0106100.0141660.010283245.02.02.5994230.0000433.4707690.0000582.5192950.00004245-21.0064020.650558-0.731896-0.4668090.0751962.162051117.010.02.6590915.0206131.8268531.514660e+091.497619e+090-6-3.1333335.527273-0.041389737272.6000000.245455-0.422463100.2222221353.000000451.00000000.00000000454578.8666676121414.0222220221736.88888924521917.6666672301524-15.249959-0.3465900.065056-0.7318960.071302-33.903935-53.42842947.490721397.5928022.161842-0.006428-0.0100260.0089121.422780e-052.1607441974.3777782179237615.0212.04.0-1.822998-0.116943-0.695801-0.4557500.0677630.79240817.08.04.2500008.9166670.4225211.518968e+091.515064e+092.01.01.2500000.2500002.00000073.072.072.7500000.250000-2.0000001.00.2500009.02.2500004.01.01.00.2500001.00.04.04.02.01.2500001.02.04.013.0000009.017.04.03.2500001.07.04.011.2500004.018.04.04.0-0.995022-0.248755-0.014618-0.6958010.095182-33.114929-50.793457-8.536865356.2811410.784223-0.006273-0.009532-0.0016021.289512e-050.79829845.011.2500002129.02175.0217.0262.049.049.00.088889-22.829400-0.9225580.533614-1.4276970.086783145.3500001.002066-1.8833332.0-5.00.250000134.06.90909118.00.145299-0.170369-0.1335280.029645-67.018864-104.22188638.953855-0.012700-0.0195570.007310-0.100234-13.0204970.007698
590.0106100.0113850.010283123.04.01.3050160.0000861.4003270.0000931.2647890.000084100-68.672105-0.242618-0.741498-0.6867210.0072873.461134105.03.01.0714290.1082474.9390631.517381e+091.508627e+090-3-1.4700001.0394950.004721727171.7000000.212121-0.886221260.2600003023.020000910.910000430.4300001010010049.0100001122113.9200000231537.3300001522615.8400002311931-66.376430-0.677311-0.080873-0.7414980.015540-49.243726-53.387873-17.22588237.7701883.461789-0.009577-0.010435-0.0034171.413391e-063.4295961011.0100002148224920.0122.012.0-6.9254150.154663-0.725586-0.5771180.0574053.02104213.02.01.1818180.1636361.9227181.521843e+091.520594e+092.02.02.0000000.0000000.00000072.071.071.9166670.083333-3.4641028.00.66666756.04.66666712.01.01.00.0833331.00.012.012.01.03.0000003.03.09.015.66666711.022.03.011.00000010.012.06.016.6666679.023.07.09.0-6.470215-0.588201-0.303955-0.7255860.024062-41.497965-52.24218811.135742296.9625003.020345-0.008026-0.0100780.0021481.109982e-053.02036914.01.1666672096.02111.0159.0173.0112.0112.00.120000-75.597520-1.263839-0.087955-1.4670840.100848143.6166671.0030220.5300002.0-1.00.513333118.02.2532475.00.123810-0.640657-0.560897-0.017591-90.741692-105.630060-6.090140-0.017603-0.020513-0.001269-1.155573-95.7769950.012065
640.0106100.0113850.010283306.02.03.2466260.0000353.4837410.0000373.1465470.00003464-40.2071400.800000-0.746156-0.6282370.0546644.70180785.012.01.3281252.2557046.2044081.519490e+091.492156e+090-10-5.2656259.2140380.026229717070.6406250.233879-0.600323210.3281252153.359375620.96875080.125000106464107.0468751111714.0312500232528.9531253472617.5937501311118-40.111366-0.6267400.066667-0.7461560.033437-44.405596-52.97710856.000000271.3195594.679835-0.008888-0.0105090.0114291.102244e-054.7181243164.9375002123244013.0329.07.0-3.6982420.329102-0.731934-0.5283200.1445682.5843086.01.01.0000000.0000000.0000001.525019e+091.520604e+092.01.01.5714290.285714-0.37416671.070.070.1428570.1428572.6457513.00.42857127.03.8571437.01.01.00.1428571.00.07.07.02.03.5714293.04.07.012.7142866.017.04.014.71428610.017.06.024.1428579.031.07.07.0-4.027344-0.671224-0.601074-0.7319340.001941-37.075195-51.23535223.037109710.2770492.586731-0.007529-0.0104560.0047012.943071e-052.58105351.07.2857142059.02110.0342.0393.071.071.00.109375-43.905383-1.1565571.129102-1.4780900.091980140.7834820.992954-3.6941962.0-9.00.26785791.02.32812513.00.070588-0.482477-0.4967760.086854-81.480792-104.21246079.037109-0.016417-0.0209650.016130-0.369071-36.4274380.010132
660.0106100.0113850.010283306.02.03.2466260.0000353.4837410.0000373.1465470.00003475-46.9041890.513516-0.731881-0.6253890.0263945.003554123.012.01.6400003.6659463.8442181.519831e+091.493124e+090-10-4.5333337.468468-0.054661717070.4666670.2522520.136373310.4133332563.413333610.81333310.013333107575117.2266671121514.8000000233229.8533331522218.4933331311926-43.306496-0.5774200.042793-0.7318810.044365-44.073025-51.80353936.459637132.5433404.976073-0.008875-0.0104550.0072335.264418e-065.0182873094.1200002119242824.0333.03.0-2.003418-0.596680-0.721680-0.6678060.0041291.1210626.04.02.0000003.0000001.7320511.521115e+091.519917e+091.01.01.0000000.0000000.00000071.071.071.0000000.0000000.0000000.00.0000009.03.0000003.01.00.00.0000000.00.03.03.01.03.0000003.03.02.014.00000012.015.02.09.6666679.011.02.05.6666671.015.03.03.0-1.555908-0.518636-0.149170-0.7216800.102714-47.414225-51.239258-42.36425820.8167551.121062-0.009406-0.010165-0.0084048.191806e-071.12106213.04.3333332105.02118.0334.0348.078.078.00.040000-48.907607-1.293195-0.083164-1.4535610.042713141.4666671.007569-3.5333331.0-9.00.013333129.03.64000016.00.048780-0.379129-0.355273-0.005198-91.487250-103.042797-5.904621-0.018280-0.020620-0.001171-0.084651-49.9216770.001696
670.0131450.0113850.011428518.03.06.8089110.0000255.8973130.0000225.9194560.0000227-3.396773-0.206104-0.678883-0.4852530.0251070.74710410.03.01.4285710.6190481.7598151.502033e+091.487432e+090-6-1.7142864.571429-1.663284777676.8571430.142857-2.64575160.857143334.71428671.00000000.000000007746.28571428512.285714715524.571429731612.00000062755-2.953791-0.421970-0.103052-0.6788830.048261-37.335060-52.273974-15.663876150.3443040.762499-0.006307-0.008817-0.0027124.192287e-060.73140016824.00000023252494170.0339.04.0-0.7358400.605469-0.598145-0.1839600.2884081.75469410.06.02.5000005.6666671.7791791.509198e+091.504462e+092.01.01.2500000.2500002.00000077.076.076.7500000.250000-2.0000002.00.50000015.03.7500004.01.00.00.0000000.00.04.04.02.09.2500009.010.04.015.25000013.018.03.038.50000035.043.03.017.7500003.028.04.04.0-1.051554-0.2628890.100911-0.5981450.086918-14.316284-46.05712946.0156251685.5289061.751108-0.002363-0.0077680.0079674.935352e-051.75825054.013.5000002242.02297.0367.0422.011.011.00.571429-4.132613-0.6692130.399365-1.2770270.216629153.6071430.998606-0.4642862.0-5.00.00000020.03.9285719.01.000000-0.206631-0.1703450.044374-51.651344-98.33110330.351749-0.008670-0.0165850.005255-0.038350-0.3093720.123961
690.0106100.0113850.010283153.03.01.6233130.0000691.7418700.0000741.5732740.00006712-5.1975020.800000-0.724368-0.4331250.2647671.74225722.010.02.0000007.4000003.0600821.511044e+091.506614e+090-2-0.7500000.750000-0.566853747373.6666670.242424-0.81240460.500000413.416667110.91666740.333333101212310.250000911913.000000022642.75000039461116.66666723077-6.273561-0.5703240.030346-0.7243680.085446-31.819393-53.60323559.2000001440.0626951.744396-0.005896-0.0099230.0108114.868969e-051.739485514.2500002221227227.078.011.0-7.666504-0.607422-0.738281-0.6969550.0020351.56136510.01.01.0000000.0000000.0000001.516038e+091.513434e+092.01.01.6363640.254545-0.66068774.073.073.9090910.090909-3.3166258.00.72727350.04.54545511.01.00.00.0000000.00.011.011.02.05.0000001.012.07.015.0000009.021.05.019.4545451.051.08.013.6363646.024.08.09.0-7.054688-0.705469-0.607422-0.7382810.001375-51.519043-54.632812-44.66259811.9473621.584495-0.009429-0.009977-0.0082083.466852e-071.55300030.02.7272732163.02193.0106.0136.023.023.00.916667-12.864006-1.1300800.192578-1.4626491.475036147.5757581.0032910.8863642.0-1.00.33333332.03.00000011.00.454545-0.402000-0.3766930.017507-83.338436-108.23604714.537402-0.015325-0.0199000.002602-1.141017-0.8466521.347682
730.0104790.0141660.01142892.04.00.9641040.0001141.3033090.0001541.0513320.00012423-15.445391-0.459511-0.737141-0.6715390.0040741.86390123.01.01.0000000.0000000.0000001.519637e+091.510221e+090-3-1.5652171.9841900.092124717070.4782610.2608700.09323340.173913632.739130210.91304300.00000000232346.6956521121113.869565019727.6086961521117.173913230811-15.445391-0.671539-0.459511-0.7371410.004074-47.333326-52.336978-32.16575220.6815191.867312-0.009528-0.010445-0.0065648.120549e-071.8199611084.695652212222318.0117.03.0-1.957520-0.508789-0.731934-0.6525070.0155481.7033813.01.01.0000000.0000000.0000001.522159e+091.521654e+091.01.01.0000000.0000000.00000070.070.070.0000000.0000000.0000000.00.0000004.01.3333333.01.00.00.0000000.00.03.03.01.03.0000003.03.03.011.6666674.017.02.012.66666712.013.02.025.00000021.027.03.03.0-1.957520-0.652507-0.508789-0.7319340.015548-45.675456-51.235352-35.61523476.1867131.703381-0.009322-0.010456-0.0072683.173124e-061.7033815.01.6666672092.02098.0140.0146.026.026.00.130435-17.402910-1.324045-0.968300-1.4690740.126738140.4782610.993214-0.5652171.0-2.00.00000026.02.0000002.00.130435-0.669343-0.662023-0.484150-93.008781-103.572330-67.780986-0.018849-0.020901-0.013833-0.083894-5.0404760.016644
820.0106100.0113850.01028392.04.00.9761100.0001151.0473990.0001240.9460210.00011249-31.290532-0.284091-0.731881-0.6385820.0111591.73873158.06.01.2888891.0282833.7568561.518029e+091.510525e+090-3-1.8571431.5000000.567494717070.7142860.208333-0.978908140.2857141663.387755400.81632710.02040810494948.2244901121315.7142860231033.5918371501813.5306122271319-27.978235-0.621739-0.047349-0.7318810.029635-45.154106-51.963570-20.17047855.7033731.736244-0.009031-0.010308-0.0040012.242992e-061.729908861.7551022140222711.098.07.0-4.876465-0.638184-0.740723-0.6966380.0013970.4802587.01.01.0000000.0000000.0000001.523847e+091.519997e+092.01.01.4285710.2857140.37416671.071.071.0000000.0000000.0000002.00.28571424.03.4285717.01.00.00.0000000.00.07.07.02.03.4285713.04.06.011.0000002.017.06.012.1428579.016.07.010.1428572.017.06.06.0-4.876465-0.696638-0.638184-0.7407230.001397-49.461286-52.591309-45.3110357.0424320.480258-0.009812-0.010433-0.0089892.771336e-070.48025844.06.2857142073.02117.0121.0166.056.056.00.142857-36.166997-1.335220-0.922275-1.4726040.155845141.7142861.004040-0.4285712.0-2.00.02040865.02.2888897.00.120690-0.556415-0.583349-0.131754-94.615392-104.554878-65.481513-0.018843-0.020741-0.012990-0.480778-21.6821260.022174
850.0080580.0141660.01028392.04.00.7413810.0000881.3033090.0001540.9460210.00011285-52.4649610.043968-0.739019-0.6172350.0172182.48495394.05.01.1058820.2862755.8312031.519743e+091.510181e+090-3-0.6588240.584594-1.326620717070.5764710.247059-0.315112250.2941182442.870588720.847059160.18823510858542.3294121121614.800000023148.4823531522615.6470591311331-51.634778-0.6074680.008794-0.7390190.021843-43.565664-52.4703393.07773085.8752912.471939-0.008745-0.0104090.0006283.460653e-062.4874021101.294118212022317.0118.015.0-8.531609-0.010612-0.734863-0.5687740.0314082.39795015.01.01.0000000.0000000.0000001.525105e+091.520392e+092.01.01.5333330.266667-0.14896171.070.070.5333330.266667-0.1489614.00.26666747.03.13333315.01.01.00.0666671.00.015.015.02.03.5333333.04.08.014.1333333.021.06.013.80000010.018.011.018.2000007.030.09.012.0-8.531609-0.568774-0.010612-0.7348630.031408-40.130335-51.440430-0.742874155.7186812.417088-0.008062-0.010498-0.0001526.342883e-062.37313054.03.6000002058.02113.0126.0180.0100.0100.00.176471-60.996569-1.1860090.033355-1.4738820.162615141.1098040.9993890.8745102.0-2.00.254902109.02.1058826.00.159574-0.559602-0.5631890.005559-83.695999-103.9107692.334856-0.016807-0.0209070.000477-1.814378-63.1870880.028714
880.0107120.0113850.010283306.02.03.2777470.0000353.4837410.0000373.1465470.000034346-218.3948260.700972-0.743151-0.6311990.0339674.202115370.05.01.0693640.1401026.4392961.519841e+091.492619e+090-10-4.5317929.298986-0.159129717070.7167630.203602-0.9663661570.45375713193.8121393450.99711000.00000000346346117.0057801122114.9393060234628.3901731523115.2630061312146-216.826094-0.6266650.380081-0.7431510.031158-44.630665-52.76373449.768992170.1922314.206718-0.008927-0.0105630.0098736.786774e-064.1899913150.9104052119243418.0333.06.0-3.883301-0.548340-0.720703-0.6472170.0053950.6914756.01.01.0000000.0000000.0000001.524905e+091.521880e+092.01.01.6666670.266667-0.96824671.070.070.1666670.1666672.4494906.01.00000031.05.1666676.01.00.00.0000000.00.06.06.02.03.6666673.04.03.09.8333338.014.04.014.66666712.017.05.022.16666714.028.03.04.0-3.883301-0.647217-0.548340-0.7207030.005395-45.425293-51.169922-38.38378928.0073710.603551-0.009222-0.010151-0.0078331.043731e-060.75991735.05.8333332061.02096.0357.0392.0352.0352.00.017341-222.278127-1.2784160.152632-1.4638540.017781140.8834300.992221-2.8651252.0-9.00.000000376.02.0693646.00.016216-0.591165-0.6177820.025439-90.055958-103.93365611.385203-0.018149-0.0207140.002039-0.332064-1068.5530090.000311
................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................
1235300.0080580.0141660.010283245.02.01.9743290.0000333.4707690.0000582.5192950.00004269-8.7704170.800000-0.745405-0.1271070.2736940.685207119.05.01.7500001.0858211.8296951.519542e+091.497193e+090-8-4.6086966.1534530.648543717070.5797100.247229-0.330193200.2898551992.884058660.956522530.76811610696997.4782611121913.8550721232931.0434785522718.5942031311217-8.978707-0.1320400.800000-0.7454050.173732-8.964525-52.17836056.8000001360.2589000.685571-0.001802-0.0106490.0114295.508064e-050.6847892583.7391302123238110.0269.012.0-6.486816-0.272217-0.701172-0.5405680.0172070.88336121.03.01.7500000.5681820.4775941.524825e+091.521135e+092.01.01.4166670.2651520.38840371.070.070.3333330.2424240.8124040.00.00000034.02.83333312.01.00.00.0000000.00.012.012.02.03.4166673.04.06.014.83333310.018.06.013.91666711.017.010.022.33333312.030.08.012.0-4.637939-0.386495-0.136108-0.7011720.051359-37.988688-49.783203-19.32739383.5975290.840574-0.007692-0.009876-0.0038343.545621e-060.92038542.03.5000002062.02104.0287.0330.081.081.00.173913-15.257234-0.6676760.527783-1.4465770.739625140.9130430.996509-3.1920292.0-7.00.768116140.03.5000008.00.176471-0.108980-0.1907640.065973-46.953213-101.96156337.472607-0.009495-0.0205240.007595-1.106755-8.5741180.129081
1235310.0106100.0141660.010283184.03.01.9522200.0000582.6066180.0000771.8920420.00005613-4.7991750.800000-0.724368-0.3691670.2875381.90186121.08.01.6153853.7564103.4866721.512833e+091.503520e+09-1-5-2.0000001.500000-1.608251727171.4615380.2692310.17520420.153846372.846154120.92307700.000000001313411.000000812916.153846023546.2307693449917.69230812978-5.899175-0.4537830.400000-0.7243680.119601-26.450200-51.43013156.8000001456.4761591.906051-0.005153-0.0102020.0112685.677488e-051.8972491078.2307692200230822.0130.016.0-7.3077390.289551-0.732422-0.4567340.1142361.22264621.03.01.3125000.4958332.0816261.521986e+091.518883e+092.01.01.6250000.250000-0.57142972.071.071.1250000.1166672.5094575.00.31250051.03.18750016.01.01.00.0625001.00.016.016.02.02.6250002.03.010.016.12500010.023.04.010.5000007.012.011.022.18750017.028.08.012.0-7.224915-0.4515570.289551-0.7324220.116075-32.414604-52.00195320.847656577.6458131.227624-0.006436-0.0103160.0040222.259251e-051.21778535.02.1875002094.02130.0200.0236.029.029.01.230769-12.106915-0.8259011.089551-1.4567901.522707142.5865380.995291-0.3750001.0-4.00.06250042.02.92788511.01.000000-0.288260-0.2820810.099050-58.864804-103.43208477.647656-0.011588-0.0205180.015289-1.643920-0.8730471.882969
1235340.0104790.0141660.0114281188.04.012.4495130.00000916.8296860.00001213.5758940.00001042-24.381793-0.147350-0.745405-0.5805190.0230851.29895576.010.01.9000004.1948723.3460491.518085e+091.483540e+090-13-5.02381014.804297-0.606796717070.5952380.246806-0.40258060.1428571072.547619390.92857100.000000004242105.8333331111314.6666670212023.7619051482217.047619330920-19.427339-0.485683-0.014735-0.7454050.056188-40.976678-52.923765-10.461848114.6981921.301192-0.008225-0.010499-0.0020754.653994e-061.2916363999.50000021402539795.01195.04.0-2.651367-0.558105-0.732910-0.6628420.0063870.8554055.03.01.6666671.3333331.7320511.524651e+091.520357e+092.01.01.2500000.2500002.00000071.070.070.5000000.3333330.0000000.00.0000007.01.7500004.01.01.00.2500001.00.04.04.02.03.2500003.04.04.011.5000006.017.03.012.50000010.017.04.016.5000006.027.04.04.0-1.664225-0.554742-0.214518-0.7329100.086879-46.739014-51.303711-39.06738332.6793051.020203-0.009401-0.010470-0.0079731.259519e-060.65566449.012.2500002064.02113.01221.01271.046.046.00.095238-27.033160-1.243361-0.705455-1.4783150.108744141.0952380.998651-3.7738102.0-12.00.25000081.03.56666713.00.065789-0.333743-0.348606-0.054266-87.715692-104.227476-49.529231-0.017625-0.020969-0.010048-0.150432-14.5057280.010371
1235380.0080580.0113850.010283123.04.00.9911940.0000661.4003270.0000931.2647890.000084134-77.8648110.800000-0.740897-0.5810810.0480743.402180200.012.01.5151523.7783954.0705031.517430e+091.508847e+090-3-1.0373130.637695-0.022468727171.5671640.247335-0.274193280.2089553652.7238811330.992537120.0895521013413448.4701491121813.9850750221435.2462691523017.2238812311834-76.221793-0.5774380.080000-0.7408970.039511-41.590135-53.34459756.800000245.1837433.392013-0.008119-0.0103700.0112689.433991e-063.407686990.7388062147224723.0122.014.0-8.805664-0.247559-0.728516-0.6289760.0162732.33082614.01.01.0000000.0000000.0000001.521216e+091.517690e+092.01.01.2857140.2197801.06653672.071.071.5000000.2692310.0000004.00.28571440.02.85714314.01.00.00.0000000.00.014.014.02.02.2857142.03.011.013.0714295.021.06.08.3571435.011.012.016.3571433.025.05.08.0-8.805664-0.628976-0.247559-0.7285160.016273-44.957241-52.453125-17.82421982.5679502.329882-0.008800-0.010118-0.0034383.215582e-062.31991740.02.8571432103.02144.0125.0166.0148.0148.00.104478-86.670475-1.2100570.552441-1.4694130.113089143.0671640.9990620.2484012.0-2.00.089552214.02.51515213.00.070000-0.405002-0.4811070.042495-86.547375-105.79772238.975781-0.016919-0.0204880.007829-1.724186-145.7915060.011826
1235450.0080580.0113850.010283365.01.02.9413480.0000224.1554430.0000313.7532350.000028333-114.6081970.800000-0.746156-0.3441690.1683901.574247651.012.01.9908265.2667872.7797561.519819e+091.487015e+090-12-4.86486514.147346-0.401470717070.6546550.226763-0.6534661430.42942911623.4894893250.975976250.07507510333333126.6486491122014.7927930234926.9219221523115.5435441312757-124.052210-0.3793650.800000-0.7461560.090422-24.306078-52.23095256.800000841.0413311.576198-0.004874-0.0106590.0114293.372245e-051.5718503791.1381382120249912.0392.014.0-4.4974730.800000-0.734863-0.3212480.2915751.47111733.012.02.75000015.1136362.0866671.524691e+091.520335e+092.01.01.2857140.2197801.06653671.070.070.7857140.181319-1.5656244.00.28571438.02.71428614.01.04.00.2857141.00.014.014.02.03.2857143.04.010.013.3571435.021.06.012.21428610.017.08.014.3571436.025.012.014.0-5.868526-0.4890440.066667-0.7348630.078440-22.828342-52.17529356.8000001458.1544951.467109-0.004521-0.0103500.0114295.831291e-051.47518550.03.5714292063.02114.0398.0448.0347.0347.00.042042-119.105670-0.6654171.600000-1.4810200.039242141.4403691.001855-3.5791512.0-11.00.360789684.04.74082624.00.050691-0.174131-0.1403590.066667-47.134420-104.406245113.600000-0.009394-0.0210100.022857-0.889510-540.1559130.001647
1235470.0106100.0113850.010283306.02.03.2466260.0000353.4837410.0000373.1465470.00003450-21.3637340.800000-0.726472-0.4272750.1959962.159994150.012.03.1250007.3882981.8259831.518779e+091.492007e+090-10-4.9000009.9285710.197740717070.7200000.205714-1.01053070.1400001312.620000501.000000110.220000105050116.2200001121514.7600009232325.1600001512115.3800001271522-15.051954-0.3135820.200000-0.7264720.070510-30.205464-51.57949256.800000981.8152582.157578-0.006044-0.0102430.0114293.913459e-052.1619483096.1800002132244111.0321.07.0-2.7712890.800000-0.704590-0.3958980.2868002.48201213.05.02.6000003.3000000.5671631.525106e+091.519890e+092.01.01.4285710.2857140.37416671.070.070.8571430.142857-2.6457510.00.00000012.01.7142867.01.00.00.0000000.00.07.07.02.03.4285713.04.06.011.2857146.016.05.012.8571439.018.05.013.4285711.030.05.07.0-1.656284-0.3312570.160000-0.7045900.137914-28.017201-50.02587956.8000001442.0976222.483736-0.005594-0.0099240.0112685.704439e-052.47982460.08.5714292058.02119.0334.0394.057.057.00.140000-24.135023-0.8231731.600000-1.4310620.129719141.5771431.001939-3.4714292.0-9.00.220000163.05.72500017.00.086667-0.148068-0.1437860.094118-58.222665-101.605371113.600000-0.011639-0.0201670.022696-0.273777-15.1044500.018126
1235520.0106100.0113850.010283276.02.02.9283290.0000383.1421980.0000412.8380620.00003743-27.673530-0.296413-0.745405-0.6435700.0101281.60542361.05.01.4523810.9854822.2585291.519820e+091.493899e+090-9-4.67441910.224806-0.058762717070.4186050.2491690.34203280.1860471172.720930410.953488150.348837104343107.0930231121313.7674428222329.4651164521819.1627913311321-24.423075-0.581502-0.059283-0.7454050.046407-45.317230-52.923765-20.74890850.1063671.600706-0.009140-0.010499-0.0042342.055753e-061.5968263006.976744212024203.0303.06.0-3.654297-0.506836-0.679199-0.6090490.0052250.5935049.02.01.5000000.3000000.0000001.522941e+091.520329e+092.01.01.3333330.2666670.96824671.070.070.6666670.266667-0.9682462.00.33333317.02.8333336.01.00.00.0000000.00.06.06.02.03.3333333.04.04.012.0000009.015.03.012.00000010.014.05.011.5000002.024.04.05.0-2.819824-0.469971-0.253418-0.6791990.044896-43.024821-48.223145-35.98535224.7825500.564664-0.008622-0.009703-0.0071391.107898e-060.59683430.05.0000002083.02114.0309.0339.049.049.00.139535-31.327827-1.252620-0.803249-1.4246040.132050141.0852711.003523-3.3410852.0-8.00.34883770.02.9523817.00.147541-0.447540-0.424274-0.114750-88.342051-101.146909-56.734260-0.017762-0.020202-0.011373-0.310270-16.8984010.018361
1235560.0080580.0113850.010283184.03.01.4827610.0000442.0947980.0000621.8920420.00005622-9.9468150.680611-0.686802-0.4521280.1012142.51218428.06.01.4000001.4105263.5104061.519627e+091.504114e+090-6-2.6818183.1796540.134455717070.3636360.2424240.60930350.227273642.909091210.95454500.00000000222276.9545451121314.6363640231329.2727272511421.636364630915-9.687257-0.4843630.113435-0.6868020.052680-31.757478-48.24015348.323369502.9191562.532400-0.006437-0.0098110.0095862.037677e-052.4908571798.1363642122230129.0209.06.00.5209590.800000-0.7177730.0868270.4093140.0165574.02.01.3333330.3333331.7320511.524988e+091.520292e+092.01.01.5000000.3000000.00000071.070.070.6666670.266667-0.9682461.00.16666718.03.0000006.01.02.00.3333331.00.06.06.02.03.5000003.04.05.011.0000005.023.04.013.33333310.017.06.015.8333335.029.05.06.0-0.542938-0.1809790.227051-0.7177730.2356086.112002-50.96191456.8000002039.4769690.0100410.001234-0.0101090.0114298.216371e-050.02325054.09.0000002060.02114.0216.0271.028.028.00.272727-9.425855-0.3653011.480611-1.404575-0.052375141.0303031.004307-1.1818182.0-5.00.33333332.02.7333338.00.142857-0.294558-0.1336470.185076-25.645476-99.202067105.123369-0.005204-0.0199210.0210150.044232-3.109986-0.014223
1235570.0107120.0113850.010283276.02.02.9563990.0000393.1421980.0000412.8380620.000037189-96.9422710.800000-0.741348-0.5129220.0717462.233143252.010.01.3621621.3409525.2228791.519754e+091.494104e+090-9-3.7037047.379827-0.225299717070.7089950.207419-0.927602250.1322754662.4656081830.96825460.03174610189189107.1216931121713.9523810223229.3703702512816.9947091312052-93.749276-0.5067530.261236-0.7413480.060552-36.265593-52.63570656.800000359.2058002.231747-0.007255-0.0104420.0112681.433661e-052.2328382961.566138212024175.0302.03.0-1.221863-0.042175-0.658203-0.4072880.1046531.3905653.01.01.0000000.0000000.0000001.521714e+091.520866e+091.01.01.0000000.0000000.00000071.070.070.6666670.333333-1.7320510.00.0000005.01.6666673.01.00.00.0000000.00.03.03.01.03.0000003.03.03.013.33333310.016.02.011.33333311.012.03.016.00000012.022.03.03.0-1.221863-0.407288-0.042175-0.6582030.104653-28.698018-46.074219-2.994446515.9755561.427990-0.005781-0.009403-0.0005942.123429e-051.3515479.03.0000002098.02107.0315.0325.0192.0192.00.015873-98.164134-0.9202100.757825-1.3995510.012604141.3756610.999401-2.7037041.0-8.00.031746255.02.36216211.00.011905-0.384957-0.3895620.068893-64.963612-98.70992553.805554-0.013035-0.0198440.010674-0.051872-259.1196410.000200
1235590.0104790.0141660.01142892.04.00.9641040.0001141.3033090.0001541.0513320.00012433-17.5660070.328990-0.731836-0.5323030.0954671.59886745.010.01.4062502.9586694.5913291.519838e+091.511874e+090-3-1.1818181.0909090.211367717070.6666670.229167-0.74123470.212121782.363636320.96969720.06060610333337.7272732121614.545455123732.0303037511916.6060614281214-17.996077-0.5623770.065798-0.7318360.067926-37.634914-51.96037023.358323478.7500591.597859-0.007529-0.0104130.0046341.904434e-051.598586922.7878792119221127.0119.05.0-3.497070-0.670410-0.718262-0.6994140.0003371.0924935.01.01.0000000.0000000.0000001.523985e+091.519938e+092.01.01.4000000.3000000.60858171.070.070.8000000.200000-2.2360681.00.20000017.03.4000005.01.00.00.0000000.00.05.05.02.03.4000003.04.05.015.80000012.021.04.012.2000009.016.05.011.4000001.023.04.05.0-3.497070-0.699414-0.670410-0.7182620.000337-49.516211-50.996582-47.5991211.5082540.845806-0.009880-0.010156-0.0094428.252035e-080.87078746.09.2000002071.02118.0120.0167.038.038.00.151515-21.063078-1.231717-0.341420-1.4500980.199082141.4666671.0018870.2181822.0-2.00.06060650.02.40625011.00.111111-0.421262-0.511883-0.031038-87.151125-102.956952-24.240798-0.017409-0.020569-0.004809-0.246968-8.2029940.030107
1235600.0107120.0141660.010283365.01.03.9097310.0000295.1707370.0000393.7532350.00002885-49.3484020.071105-0.746156-0.5805690.0334221.333102115.05.01.3690480.5730062.6781981.517325e+091.487117e+090-11-1.8588243.622689-1.575622727171.5764710.247059-0.315112240.2823532593.047059760.894118610.71764710858587.0470591122213.5294120232329.0941181522717.8000001311625-44.310698-0.5275080.014221-0.7461560.056005-41.546974-53.6691705.048487170.9170051.325811-0.008113-0.0105090.0010016.543049e-061.3367103494.1058822148249814.0363.09.0-4.352554-0.026077-0.729004-0.4836170.0868780.7790289.01.01.0000000.0000000.0000001.521180e+091.517502e+092.01.01.6666670.250000-0.85714372.071.071.8888890.111111-3.0000000.00.00000014.01.5555569.01.03.00.3333331.00.09.09.02.02.6666672.03.08.015.1111116.020.04.09.5555565.011.07.012.7777781.026.07.09.0-4.352554-0.483617-0.026077-0.7290040.086878-34.807515-52.488281-1.877563451.1466990.778798-0.006719-0.010125-0.0003621.672995e-050.77928242.04.6666672104.02146.0365.0408.094.094.00.105882-53.700956-1.0641870.045028-1.4751600.088201143.4653591.004365-0.1921572.0-10.01.050980124.02.3690486.00.078261-0.433072-0.4492040.007505-76.354489-106.1574513.170924-0.014833-0.0206340.000639-0.544910-58.6032550.009298
1235640.0131450.0113850.011428184.03.02.4186090.0000712.0947980.0000622.1026640.00006266-39.1012830.755743-0.723406-0.5924440.0576484.03875868.02.01.0461540.0447124.4289591.519837e+091.501615e+090-6-2.3030302.6144520.016239717070.8787880.108159-2.375525150.2272731882.848485600.90909100.00000000666677.5151521121912.2727270231730.1969701522110.9393941301321-37.986864-0.5844130.755743-0.7234060.063799-41.979790-51.36184853.657780289.4510264.050317-0.008361-0.0103240.0106441.148584e-054.0245322103.181818211923300.0211.015.0-9.934082-0.387695-0.731934-0.6622720.0070272.76200115.01.01.0000000.0000000.0000001.525114e+091.520097e+092.01.01.4000000.2571430.45508371.070.070.5333330.266667-0.1489616.00.40000041.02.73333315.01.01.00.0666671.00.015.015.02.03.4000003.04.09.014.3333338.019.07.013.4000009.018.011.019.1333333.031.011.012.0-9.934082-0.662272-0.387695-0.7319340.007027-46.726693-51.793945-27.13867236.1472482.708742-0.009387-0.010456-0.0055391.374009e-062.78572058.03.8666672058.02116.0214.0272.081.081.00.227273-49.035365-1.2547160.368048-1.4553400.254060141.4121210.995126-0.9030302.0-5.00.06666783.02.0461543.00.220588-0.590788-0.6132070.122683-88.706483-103.15579426.519108-0.017748-0.0207800.005106-2.112636-36.4098300.058024
1235650.0106100.0113850.010283184.03.01.9522200.0000582.0947980.0000621.8920420.00005610-3.2465230.634930-0.725119-0.3246520.2873921.11214332.010.03.20000013.7333331.5385011.517746e+091.503345e+090-6-1.8000003.288889-1.766005717070.6000000.266667-0.48412340.400000393.900000101.00000010.10000010101053.800000112714.500000819614.600000249815.40000042257-4.038120-0.4038120.158733-0.7251190.123545-22.923195-51.48347444.4451181429.9126221.106119-0.004598-0.0102130.0090705.777533e-051.11783616616.6000002144231020.0187.03.0-0.5945310.800000-0.705078-0.1981770.7473291.7314148.06.02.6666678.3333331.7320511.523988e+091.521475e+092.01.01.6666670.333333-1.73205171.071.071.0000000.0000000.0000001.00.3333337.02.3333333.01.00.00.0000000.00.03.03.02.03.6666673.04.03.016.33333315.018.03.014.33333312.016.03.017.00000015.019.03.03.0-1.261198-0.4203990.133333-0.7050780.230026-14.070573-50.06054756.8000003767.2862571.731414-0.002791-0.0099310.0112681.482502e-041.73141429.09.6666672071.02100.0230.0259.013.013.00.300000-3.841054-0.5228291.434930-1.4301970.183129141.6000001.005666-0.1333332.0-5.00.10000040.05.86666716.00.250000-0.096026-0.0891190.089683-36.993768-101.544021101.245118-0.007389-0.0201440.020338-0.025121-0.4598470.054629
1235660.0131450.0113850.0114281280.03.016.8251080.00001014.5725110.00000914.6272260.00000942-25.6452370.755743-0.729402-0.6106010.0504375.74774158.06.01.4146341.4487802.9237381.516474e+091.483622e+09-1-13-5.21428610.757840-0.871717717070.6904760.218931-0.854881140.3333331242.952381410.97619000.000000004242107.3571431121514.2142867212229.8095241502213.71428613067-24.001753-0.5854090.151149-0.7294020.040548-43.192088-51.78753452.902037250.2606955.719612-0.008632-0.0102730.0107961.017299e-055.7696373809.04761921582538888.01268.08.0-5.353027-0.551758-0.710938-0.6691280.0029061.7762059.02.01.1250000.1250002.8284271.522508e+091.522143e+091.01.01.0000000.0000000.00000070.070.070.0000000.0000000.0000001.00.12500022.02.7500008.01.00.00.0000000.00.08.08.01.03.0000003.03.08.014.1250009.020.01.013.00000013.013.04.028.75000027.031.05.06.0-5.077148-0.634644-0.275879-0.7109380.021671-46.838989-49.765625-38.62304714.2379551.776205-0.009559-0.010156-0.0078825.930011e-071.7762054.00.5000002088.02093.01334.01338.050.050.00.190476-30.998264-1.2797290.203986-1.4403390.208734140.6904760.990232-4.2142860.0-12.00.00000067.02.5396348.00.155172-0.462661-0.5039030.025498-90.031077-101.55315914.278990-0.018191-0.0204300.002914-0.611775-15.2368470.040151
1235700.0107120.0141660.010283123.04.01.3175260.0000871.7424670.0001151.2647890.00008433-18.620132-0.272611-0.745405-0.5642460.0233110.76130192.012.02.87500010.8870972.0369941.512057e+091.507305e+090-1-0.4242420.251894-0.321366747373.7272730.204545-1.06987950.151515902.727273270.818182170.515152103333210.57575810111414.878788022844.12121240481515.727273230913-14.042932-0.438842-0.022718-0.7454050.076734-41.608347-55.159980-20.173213127.6300860.749811-0.007652-0.010073-0.0036844.261955e-060.770890541.636364220922645.060.012.0-7.214844-0.362793-0.742188-0.6012370.0101561.06590619.03.01.5833330.6287880.9876051.516191e+091.512591e+092.01.01.5833330.265152-0.38840374.073.073.6666670.242424-0.8124041.00.08333331.02.58333312.01.05.00.4166671.00.012.012.02.05.5833331.012.07.012.6666677.020.05.022.2500001.052.011.013.5833331.030.09.010.0-5.761149-0.480096-0.120931-0.7421880.052284-44.275675-54.179688-26.84668053.8441511.097158-0.008165-0.010167-0.0049031.921579e-061.02573541.03.4166672162.02203.066.0108.045.045.00.363636-25.834976-1.165483-0.635404-1.4875930.387475147.3939390.9991781.1590912.00.00.931818111.04.45833315.00.206522-0.232748-0.261417-0.042360-85.884023-109.339668-47.019893-0.015817-0.020240-0.008587-1.175269-8.3342890.141016
1235710.0104790.0141660.0114281249.03.013.0887550.00000817.6938370.00001114.2729730.00000969-43.2773160.304948-0.737892-0.6272070.0275273.56719376.04.01.1176470.3143114.7522901.519557e+091.483718e+090-13-6.40579715.832907-0.202580717070.7101450.208866-0.947085220.3188412022.927536680.98550710.014493106969115.8550721122014.6231880232723.7536231512617.0144931301220-42.659866-0.6273510.076237-0.7378920.025137-44.348739-52.39032621.651310138.0134893.562737-0.008871-0.0105410.0042955.497623e-063.5637884146.00000021232537858.01273.04.0-2.594238-0.584473-0.709473-0.6485600.0026680.1757543.01.01.0000000.0000000.0000001.524035e+091.520789e+092.01.01.5000000.3333330.00000071.071.071.0000000.0000000.0000002.00.50000013.03.2500004.01.00.00.0000000.00.04.04.02.03.5000003.04.04.012.0000007.017.03.013.25000010.016.04.015.50000011.018.04.04.0-1.934570-0.644857-0.584473-0.7094730.003920-46.047729-50.372559-41.49755913.4492040.175754-0.009135-0.009993-0.0082325.292528e-070.17575437.09.2500002071.02108.01287.01325.073.073.00.057971-45.871554-1.275767-0.279525-1.4473650.059945141.7101451.004099-4.9057972.0-12.00.01449379.02.1176475.00.039474-0.580653-0.602446-0.055905-90.396469-102.762884-19.846248-0.018005-0.020534-0.003937-0.146154-42.2306410.003461
1235720.0080580.0113850.01028392.04.00.7413810.0000881.0473990.0001240.9460210.00011294-59.0502390.301943-0.745405-0.6281940.0554473.20306094.01.01.0000000.0000000.0000001.519206e+091.510618e+090-3-1.0319151.106497-0.558271717070.6170210.238847-0.489300190.2021282642.808511941.000000470.50000010949444.9255321122111.7872340231519.7659571523116.000000131913-59.050239-0.6281940.301943-0.7454050.055447-44.375878-52.17836021.135992275.9017113.201913-0.008893-0.0106490.0043131.115247e-053.199864991.0531912127222613.0112.03.0-1.966309-0.518555-0.724121-0.6554360.0140521.7320183.01.01.0000000.0000000.0000001.523907e+091.521955e+092.01.01.3333330.3333331.73205171.070.070.3333330.3333331.7320511.00.3333337.02.3333333.01.00.00.0000000.00.03.03.02.03.3333333.04.03.011.0000005.019.03.013.66666712.016.03.022.66666716.027.03.03.0-1.966309-0.655436-0.518555-0.7241210.014052-46.053385-50.688477-36.81738363.9781001.732015-0.009329-0.010345-0.0073043.075506e-061.73202022.07.3333332072.02095.0144.0166.097.097.00.031915-61.016548-1.283630-0.216612-1.4695260.033299140.9503550.9959830.3014182.0-2.00.50000097.02.0000002.00.031915-0.629037-0.641815-0.108306-90.429264-102.866836-15.681391-0.018222-0.020993-0.002990-0.083871-78.6031810.001067
1235740.0106100.0113850.010283215.03.02.2811260.0000492.4477260.0000532.2108100.00004839-23.3868120.282408-0.739395-0.5996620.0542953.12020954.06.01.4594591.3663662.8609991.519749e+091.501335e+090-7-3.5641033.936572-0.155721717070.3076920.2186230.86704440.102564782.000000370.94871800.00000000393978.8974361121215.1282059211337.2307694521417.8974361311219-21.262702-0.5746680.070602-0.7393950.051924-42.177926-51.75761819.768579267.8596983.122793-0.008526-0.0105630.0040341.101365e-053.1138592135.4615382120233328.0241.04.0-2.426270-0.437012-0.698242-0.6065670.0136251.6371764.01.01.0000000.0000000.0000001.522922e+091.520572e+092.01.01.2500000.2500002.00000071.071.071.0000000.0000000.0000001.00.25000016.04.0000004.01.00.00.0000000.00.04.04.02.03.2500003.04.04.09.7500005.017.02.011.00000010.014.03.08.2500005.010.03.03.0-2.426270-0.606567-0.437012-0.6982420.013625-43.066284-49.575195-31.02783268.6830541.637176-0.008543-0.009834-0.0061552.702814e-061.63717627.06.7500002084.02111.0251.0278.043.043.00.102564-25.813082-1.206229-0.154603-1.4376370.103745141.3076921.009847-2.3141032.0-6.00.00000058.02.4594597.00.074074-0.445053-0.490445-0.022086-85.244210-101.332814-11.259253-0.017069-0.020397-0.002121-0.136691-12.9727720.010537
1235770.0106100.0113850.010283215.03.02.2811260.0000492.4477260.0000532.2108100.00004813-5.9048450.800000-0.724368-0.4542190.2944352.14393031.010.02.38461511.4230772.1787171.519843e+091.500718e+090-7-2.2307698.358974-1.048920717070.6923080.230769-0.94621270.538462503.846154110.84615400.00000000131355.307692112813.615385819921.2307694501016.07692312866-7.277966-0.5598440.080000-0.7243680.082152-32.056128-51.43013156.8000001479.0059132.139732-0.006436-0.0103480.0112685.862459e-052.14762622117.0000002119234121.0242.08.0-5.094971-0.417725-0.723145-0.6368710.0090342.1241557.01.01.0000000.0000000.0000001.523034e+091.520077e+092.01.01.7500000.214286-1.44016571.070.070.8750000.125000-2.8284272.00.25000034.04.2500008.01.00.00.0000000.00.08.08.02.03.7500003.04.06.013.1250006.017.03.013.1250009.014.03.07.8750003.024.07.08.0-4.677246-0.668178-0.607422-0.7231450.001393-45.127472-50.620117-29.65844744.3424212.203229-0.008988-0.010331-0.0058831.845354e-062.03151834.04.2500002082.02117.0245.0279.021.021.00.615385-10.999815-1.0910900.382275-1.4475130.862846141.5673081.002584-0.4807692.0-6.00.00000038.03.38461511.00.225806-0.289469-0.3223680.034752-77.183600-102.05024827.141553-0.015425-0.0206790.005384-0.575094-1.0858750.529613
1235800.0106100.0113850.010283306.02.03.2466260.0000353.4837410.0000373.1465470.00003447-24.2585900.213286-0.738358-0.5161400.0679541.14961556.02.01.2173910.1739131.4169501.512998e+091.492723e+090-8-3.7446819.411656-0.082092737272.9574470.041628-4.683414130.2765961443.063830400.85106450.10638310474798.2553194121814.4893620231533.36170216501411.808511529917-23.478909-0.5104110.106643-0.7383580.074553-37.647731-53.90011415.569901361.2352301.151753-0.007076-0.0101140.0029221.278513e-051.1469732344.9787232198243319.0254.014.0-9.939941-0.636230-0.742188-0.7099960.0010851.28708114.01.01.0000000.0000000.0000001.519523e+091.515586e+092.01.01.9285710.071429-3.74165773.072.072.7142860.219780-1.0665366.00.42857144.03.14285714.01.01.00.0714291.00.014.014.02.01.9285711.02.09.014.6428571.019.04.06.5714292.08.011.014.3571436.025.07.010.0-9.939941-0.709996-0.636230-0.7421880.001085-51.625035-54.179688-46.4448245.6491841.294614-0.009765-0.010288-0.0087152.163211e-071.18381745.03.2142862123.02169.0284.0330.061.061.00.297872-34.198531-1.226136-0.422944-1.4805450.409749145.6717330.996667-1.8161092.0-7.00.17781270.02.2173913.00.250000-0.488550-0.552963-0.140981-89.272766-108.079801-30.874924-0.016841-0.020402-0.005794-1.913780-15.6276540.122461
1235830.0106100.0113850.010283123.04.01.3050160.0000861.4003270.0000931.2647890.00008418-8.7685260.026958-0.694465-0.4871400.0397221.29446856.06.03.5000002.533333-0.0566871.518697e+091.508198e+090-4-2.6111111.8986930.260125717070.3888890.2516340.49837430.166667613.388889130.72222200.00000000181848.7222221121013.333333019536.833333451821.611111152649-3.485834-0.2178650.005392-0.6944650.043296-34.224312-48.6125701.913987193.4612981.327267-0.006934-0.0099210.0003808.158079e-061.2620231216.7222222133225416.0137.04.0-1.537842-0.266113-0.471924-0.3844600.0089200.60683318.010.06.00000013.0000001.1520701.524225e+091.520272e+092.01.01.2500000.2500002.00000071.070.070.2500000.2500002.0000002.00.50000014.03.5000004.01.00.00.0000000.00.04.04.02.03.2500003.04.03.011.5000007.017.03.012.50000010.016.03.018.2500005.024.04.04.0-0.255330-0.085110-0.044800-0.1573080.003927-27.030212-33.506592-18.62793045.6885750.548901-0.005469-0.006647-0.0038021.743512e-060.65875145.011.2500002069.02114.0155.0201.022.022.00.222222-10.306367-0.871601-0.239156-1.1663890.175382140.6388890.998027-1.3611112.0-3.00.00000074.09.50000016.00.321429-0.139275-0.091747-0.014947-61.254525-82.119161-16.713943-0.012403-0.016568-0.003422-0.087564-2.2423060.039051
1235880.0080580.0141660.010283215.03.01.7325750.0000373.0457770.0000662.2108100.000048127-80.6627770.800000-0.745405-0.6351400.0312595.253177127.01.01.0000000.0000000.0000001.514466e+091.500988e+090-5-2.0078741.3888260.429277737272.6062990.240595-0.440363310.2440943632.8582681240.97637800.0000000012712769.9921267121713.3228350231941.88189030523018.0629921311926-80.662777-0.6351400.800000-0.7454050.031259-46.116465-54.41457557.600000164.0255485.228059-0.008748-0.0103050.0111115.965258e-065.2674431561.2283462181233724.0180.020.0-13.917480-0.560547-0.745605-0.6958740.0021231.61567020.01.01.0000000.0000000.0000001.519728e+091.515267e+092.01.01.3500000.2394740.68116173.072.072.3500000.2394740.68116110.00.50000077.03.85000020.01.02.00.1000001.00.020.020.02.01.3500001.02.010.015.15000010.022.09.04.6500001.09.016.019.5500003.029.010.011.0-13.917480-0.695874-0.560547-0.7456050.002123-50.353760-53.716309-40.35937511.9357181.566142-0.009617-0.010356-0.0077853.845354e-071.59272751.02.5500002121.02172.0189.0241.0147.0147.00.157480-94.580258-1.3310140.239453-1.4910110.172539144.9562990.996470-0.6578742.0-4.00.100000147.02.0000002.00.157480-0.643403-0.6655070.119727-96.470225-108.13088417.240625-0.018365-0.0206600.003326-3.847265-141.0920660.027268
1235920.0104790.0141660.011428153.03.01.6033460.0000682.1674600.0000931.7484110.00007528-15.0566850.425160-0.745405-0.5377390.0658892.48571149.08.02.0416673.0851451.9792591.519196e+091.504961e+090-5-2.3571434.015873-0.062206717070.8928570.099206-2.686455140.500000993.535714250.892857120.42857110282856.0714291111513.7142860221423.9285711471311.357143125811-11.626274-0.484428-0.018419-0.7454050.071367-38.114949-52.92376530.186368331.5132912.482855-0.007587-0.0104990.0059881.309892e-052.4875571645.857143212722918.0173.07.0-4.628906-0.566406-0.727051-0.6612720.0026730.8632445.01.01.0000000.0000000.0000001.525008e+091.520581e+092.01.01.5714290.285714-0.37416671.070.070.4285710.2857140.3741661.00.14285721.03.0000007.01.00.00.0000000.00.07.07.02.03.5714293.04.06.012.1428577.019.06.014.00000010.017.06.018.2857149.030.06.06.0-3.428223-0.685645-0.656738-0.7270510.000835-46.567662-51.620605-40.21484413.0146550.586868-0.009391-0.010240-0.0079785.590580e-071.08594251.07.2857142059.02111.0189.0240.035.035.00.250000-19.685591-1.199011-0.141246-1.4724560.307432141.3214290.993451-0.7857142.0-4.00.42857154.03.0416679.00.102041-0.364548-0.394195-0.015694-84.682611-104.544370-10.028476-0.016977-0.020739-0.001989-0.460074-5.9468220.077365
1235980.0107120.0113850.01028392.04.00.9854660.0001161.0473990.0001240.9460210.00011255-30.0127530.584441-0.727268-0.5456860.0573823.239906140.06.02.6923082.6093510.5822761.519505e+091.510240e+090-3-1.6181820.9811450.103818717070.5090910.254545-0.03739760.1090911392.527273551.00000020.03636410555546.9272731121113.98181810211628.7090911522117.8909092311111-16.993578-0.3268000.194814-0.7272680.060701-38.456761-50.90877141.495320286.3581783.250926-0.007743-0.0103900.0082321.150697e-053.2251761071.945455212322308.0115.09.0-4.4714840.800000-0.724609-0.4968320.2400692.91669316.06.01.7777782.9444442.3475801.524675e+091.521050e+092.01.01.3333330.2500000.85714371.070.070.6666670.250000-0.8571433.00.33333328.03.1111119.01.00.00.0000000.00.09.09.02.03.3333333.04.06.013.3333338.021.06.013.11111111.017.07.019.5555565.031.07.08.0-4.730273-0.5255860.133333-0.7246090.087627-35.067632-51.44726656.8000001205.8812072.911573-0.007039-0.0102060.0112684.780327e-052.92097441.04.5555562063.02105.0133.0175.064.064.00.163636-34.484237-1.0425181.384441-1.4518780.148986141.1757581.002235-0.2848482.0-2.00.036364156.04.47008512.00.114286-0.221053-0.2332210.115370-73.524393-102.35603798.295320-0.014783-0.0205950.019499-0.569482-23.4111850.024325
1236010.0106100.0113850.010283153.03.01.6233130.0000691.7418700.0000741.5732740.00006736-24.0039210.263851-0.740431-0.6667760.0309134.77230139.03.01.0833330.1357144.7146291.518770e+091.506421e+090-5-2.7500001.9071430.073225717070.7777780.177778-1.395122130.3611111193.305556310.861111210.58333310363668.2500001121415.5000000231733.7500001511814.0833333301112-23.492498-0.6525690.263851-0.7404310.039292-47.216353-52.57062718.469536154.6688844.740836-0.009416-0.0104290.0037696.185196e-064.7966261423.9444442132227525.0168.05.0-2.1169920.800000-0.740723-0.4233980.4679152.23375314.010.02.80000016.2000002.2360681.524587e+091.520114e+092.01.01.4000000.3000000.60858171.070.070.6000000.300000-0.6085811.00.2000008.01.6000005.01.03.00.6000001.00.05.05.02.03.4000003.04.04.015.8000004.022.05.013.0000009.017.05.015.2000003.024.04.04.0-2.836992-0.5673980.080000-0.7407230.131171-29.767344-52.59130956.8000002342.6665492.234109-0.006023-0.0105820.0112689.347708e-052.23274851.010.2000002064.02116.0183.0235.041.041.00.138889-26.120913-1.0901741.063851-1.4811540.088194141.3777780.997488-1.3500002.0-4.01.18333353.03.88333313.00.358974-0.492847-0.2807320.081835-76.983697-105.16193675.269536-0.015439-0.0210100.015037-0.149929-12.2092160.012280
1236020.0107120.0141660.010283396.01.04.2417900.0000275.6098950.0000364.0720030.000026514-319.0511060.800000-0.745105-0.6207220.0836693.868569594.010.01.1601560.6396626.7082331.517383e+091.484563e+090-12-4.8463049.307715-0.114157727171.6984440.211031-0.8673361590.30933915793.0719844990.97081700.00000000514514127.2198441121814.5038910234829.4824901523115.9980541312963-323.048961-0.6309550.800000-0.7451050.055988-44.492556-53.61507557.600000431.2881813.870888-0.008660-0.0104940.0111111.624012e-053.8632493790.7373542148252815.0395.013.0-8.375977-0.418945-0.740723-0.6443060.0146321.23688813.01.01.0000000.0000000.0000001.521740e+091.517842e+092.01.01.6923080.230769-0.94621272.071.071.9230770.076923-3.6055512.00.15384633.02.53846213.01.00.00.0000000.00.013.013.02.02.6923082.03.07.014.6153859.021.06.09.2307696.012.010.010.7692312.022.06.08.0-8.375977-0.644306-0.418945-0.7407230.014632-46.335374-53.332031-30.16406275.3268621.233767-0.008959-0.010288-0.0058192.845282e-061.23617645.03.4615382097.02142.0400.0445.0527.0527.00.025292-327.427083-1.2650280.381055-1.4858270.026253143.6215211.003133-3.1539962.0-11.00.000000607.02.16015611.00.021886-0.539419-0.5856190.034641-90.827931-106.94710627.435938-0.017620-0.0207820.005292-1.513947-2287.2500470.000662
1236030.0080580.0113850.01028392.04.00.7413810.0000881.0473990.0001240.9460210.000112216-129.9236770.800000-0.746156-0.6014990.0474683.895862303.012.01.4292453.0044495.0510631.519817e+091.511038e+090-3-1.0138890.925388-0.541660717070.5370370.249785-0.149597440.2037046042.7962962080.962963680.3148151021621644.5972221122014.8101850231618.3750001523116.2314811312131-124.920284-0.5892470.605478-0.7461560.045124-42.419349-52.97710856.800000236.0996863.902824-0.008530-0.0105840.0114299.552742e-063.8833101010.4675932120222117.0119.044.0-28.175598-0.122375-0.745605-0.6403550.0143072.49784560.06.01.3636361.4926003.3383341.525102e+091.520376e+092.01.01.5454550.253700-0.18908271.070.070.5681820.251057-0.28511217.00.386364149.03.38636444.01.02.00.0454551.00.044.044.02.03.5454553.04.013.015.68181810.023.09.013.61363610.018.023.016.7727271.030.017.022.0-27.019533-0.614080-0.020396-0.7456050.032833-45.185240-52.937988-8.68866071.4640222.474673-0.009075-0.010519-0.0017242.873274e-062.50740754.01.2272732058.02113.0125.0180.0260.0260.00.203704-158.099275-1.2418530.677625-1.4917620.216863141.1052191.0004420.5315662.0-2.00.360269363.02.79288218.00.198020-0.435535-0.4446490.037646-87.604589-105.91509748.111340-0.017605-0.0211030.009705-17.567780-397.8550180.044156
1236050.0080580.0113850.010283276.02.02.2241420.0000293.1421980.0000412.8380620.00003789-46.2856200.800000-0.746878-0.5200630.0889052.315573173.012.01.9659094.3321582.6995071.519758e+091.496256e+090-9-4.0898886.219101-0.129187717070.5280900.252043-0.114476160.1797752212.483146830.93258430.033708108989108.0224721121815.1910110232633.0561801522215.7303371311826-43.745371-0.4971060.133333-0.7468780.071913-36.664948-52.28144156.000000440.7530572.314891-0.007377-0.0106700.0114291.794239e-052.3144422723.0561802120239230.0302.020.0-10.5151250.800000-0.729004-0.5257560.1333472.98836022.05.01.2222220.8888894.2426411.525023e+091.519895e+092.01.01.7000000.221053-0.94530071.070.070.4500000.2605260.2176878.00.40000075.03.75000020.01.02.00.1000001.00.020.020.02.03.7000003.04.011.013.1500008.022.07.014.2000009.017.014.016.4500001.029.010.015.0-10.846836-0.6026020.160000-0.7290040.045259-36.975860-51.75927756.800000665.2543872.998082-0.007476-0.0102680.0112682.673913e-052.97702859.02.9500002059.02119.0304.0363.0109.0109.00.224719-56.800744-1.0458191.600000-1.4758820.227179140.9780900.998893-2.3898882.0-8.00.133708195.03.18813117.00.127168-0.291286-0.3280350.094118-73.640808-104.040718112.800000-0.014853-0.0209370.022696-2.985131-58.4082200.051108
1236060.0131450.0113850.011428215.03.02.8260920.0000612.4477260.0000532.4569170.00005354-13.5887740.800000-0.742415-0.2516440.4289190.91620194.05.01.8076921.6485671.2415791.519856e+091.499732e+090-7-5.1111115.7987420.876313717070.7962960.165269-1.51373960.1111111312.425926440.814815340.62963010545487.3333331121511.8148150221729.9629631502115.314815231912-21.404541-0.4116260.400000-0.7424150.168139-17.814047-52.71038756.8000002151.4969160.916009-0.003555-0.0106060.0114298.551966e-050.9163142324.2962962119235210.0242.05.0-1.9565430.423340-0.628418-0.3913090.2080122.21945516.012.03.20000024.2000002.2360681.523882e+091.519986e+092.01.01.2000000.2000002.23606871.071.071.0000000.0000000.0000002.00.40000017.03.4000005.01.01.00.2000001.00.05.05.02.03.2000003.04.02.011.60000010.012.04.011.0000009.016.05.09.2000002.016.03.03.0-2.344604-0.4689210.035278-0.6284180.080064-27.782910-44.61767630.0571291048.5893772.219455-0.005511-0.0088510.0059634.126407e-052.21945545.09.0000002073.02118.0244.0289.059.059.00.092593-15.545317-0.6429531.223340-1.3708330.143982141.7962961.002877-3.9111112.0-6.00.829630110.05.00769217.00.170213-0.141321-0.1283930.071961-45.596957-97.32806286.857129-0.009066-0.0194570.017391-0.137785-10.3648620.013293
1236210.0106100.0113850.010283245.02.02.5994230.0000432.7892700.0000462.5192950.00004262-39.123627-0.115794-0.737892-0.6310260.0109482.304651120.05.01.9354841.3072451.1498201.509376e+091.496312e+090-4-2.1451611.699894-0.089070757474.7096770.209413-0.946935190.3064521953.145161430.69354800.00000000626257.8548396101212.2096770181732.27419422442216.4354841301015-27.946076-0.450743-0.028949-0.7378920.057592-47.130465-54.778397-8.68457360.1802532.343068-0.008449-0.009972-0.0015441.997562e-062.2535551512.435484224023920.0151.06.0-3.779785-0.499023-0.708008-0.6299640.0055581.1749367.03.01.7500000.9166670.8545631.511654e+091.509494e+091.01.01.0000000.0000000.00000075.074.074.6666670.266667-0.9682462.00.33333319.03.1666676.01.01.00.1666671.00.06.06.01.011.00000011.011.04.08.0000000.018.03.045.16666744.047.05.010.3333331.026.03.05.0-1.839193-0.459798-0.166341-0.7080080.071578-47.033610-53.100586-37.42675830.8494131.087096-0.008438-0.009440-0.0066541.008353e-061.24261525.04.1666672214.02239.0153.0178.068.068.00.096774-42.903412-1.260990-0.614818-1.4459000.096611149.3763440.999424-1.1451611.0-3.00.166667127.03.6854848.00.058333-0.337822-0.342151-0.076852-94.164075-107.878983-46.111330-0.016887-0.019412-0.008198-0.303733-32.4678810.009355
\n

37198 rows × 191 columns

\n
"},"metadata":{}}]},{"cell_type":"code","source":"test = test.assign(newFeature1=(train['days_feature_2_ratio'] + train['days_feature_1_ratio']) / 2,\n newFeature2=(train['days_feature_1'] + train['days_feature_3']) / 2,\n newFeature3=(train['days_feature_2'] + train['days_feature_3']) / 2,\n newFeature4=(train['days_feature_2_ratio'] + train['days_feature_3_ratio']) / 2,\n newFeature5=(train['days_feature_1_ratio'] + train['days_feature_3_ratio']) / 2,\n newFeature6=(train['hist_purchase_amount_min'] + train['hist_purchase_amount_mean']) / 2,\n newFeature7=(train['hist_installments_mean'] + train['hist_installments_skew']) / 2,\n newFeature8=(train['hist_purchase_date_max'] + train['hist_purchase_date_min']) / 2,\n newFeature9=(train['hist_month_lag_mean'] + train['hist_month_lag_skew']) / 2,\n newFeature10=(train['hist_authorized_flag_sum'] + train['hist_category_1_sum']) / 2,\n newFeature11=(train['hist_card_id_size'] + train['hist_card_id_count']) / 2,\n newFeature12=(train['hist_month_max'] + train['hist_hour_nunique']) / 2,\n newFeature13=(train['hist_hour_max'] + train['hist_hour_min']) / 2,\n newFeature14=(train['hist_weekofyear_nunique'] + train['hist_weekofyear_mean']) / 2,\n newFeature15=(train['hist_weekofyear_mean'] + train['hist_day_mean']) / 2,\n newFeature16=(train['hist_amount_month_ratio_mean'] + train['hist_amount_month_ratio_min']) / 2,\n newFeature17=(train['hist_purchase_date_uptonow'] + train['hist_purchase_date_uptomin']) / 2,\n newFeature18=(train['hist_CLV'] + train['duration_mean']) / 2,\n newFeature19=(train['duration_max'] + train['duration_min']) / 2\n )","metadata":{"execution":{"iopub.status.busy":"2023-12-19T12:49:03.074628Z","iopub.execute_input":"2023-12-19T12:49:03.074875Z","iopub.status.idle":"2023-12-19T12:49:03.201163Z","shell.execute_reply.started":"2023-12-19T12:49:03.074836Z","shell.execute_reply":"2023-12-19T12:49:03.199973Z"},"trusted":true},"execution_count":35,"outputs":[]},{"cell_type":"markdown","source":"Apply Light GBM Modelling Technique with Stratified K Folds enumerated on training set and outliers ","metadata":{"_uuid":"dac5e3fdfb1731d5b883ab2268f386cf61a869f7"}},{"cell_type":"code","source":"# increase_test","metadata":{"execution":{"iopub.status.busy":"2023-12-19T12:49:03.203655Z","iopub.execute_input":"2023-12-19T12:49:03.204286Z","iopub.status.idle":"2023-12-19T12:49:03.209966Z","shell.execute_reply.started":"2023-12-19T12:49:03.204219Z","shell.execute_reply":"2023-12-19T12:49:03.208783Z"},"trusted":true},"execution_count":36,"outputs":[]},{"cell_type":"code","source":"# Change in Hyper Parameters using kernel : https://www.kaggle.com/mfjwr1/simple-lightgbm-without-blending/output\nimport lightgbm as lgb\n\nfolds = StratifiedKFold(n_splits=5, shuffle = True, random_state=4950)\noof = np.zeros(len(train))\npredictions = np.zeros(len(test))\nfeature_importance_df = pd.DataFrame()\n\nfor fold_, (trn_idx, val_idx) in enumerate(folds.split(train.values, train['outliers'].values)):\n \n print(\"fold {}\".format(fold_))\n trn_data = lgb.Dataset(train.iloc[trn_idx][df_train_columns], label=target.iloc[trn_idx])\n val_data = lgb.Dataset(train.iloc[val_idx][df_train_columns], label=target.iloc[val_idx])\n\n param ={\n 'task': 'train',\n 'boosting': 'goss',\n 'objective': 'regression',\n 'metric': 'rmse',\n 'learning_rate': 0.01,\n 'subsample': 0.9855232997390695,\n 'max_depth': 7,\n 'top_rate': 0.9064148448434349,\n 'num_leaves': 63,\n 'min_child_weight': 41.9612869171337,\n 'other_rate': 0.0721768246018207,\n 'reg_alpha': 9.677537745007898,\n 'colsample_bytree': 0.5665320670155495,\n 'min_split_gain': 9.820197773625843,\n 'reg_lambda': 8.2532317400459,\n 'min_data_in_leaf': 21,\n 'verbose': -1,\n 'seed':int(2**fold_),\n 'bagging_seed':int(2**fold_),\n 'drop_seed':int(2**fold_)\n }\n \n num_round = 10000\n clf = lgb.train(param, trn_data, num_round, valid_sets = [trn_data, val_data], verbose_eval=-1, early_stopping_rounds = 200)\n oof[val_idx] = clf.predict(train.iloc[val_idx][df_train_columns], num_iteration=clf.best_iteration)\n \n fold_importance_df = pd.DataFrame()\n fold_importance_df[\"Feature\"] = df_train_columns\n fold_importance_df[\"importance\"] = clf.feature_importance()\n fold_importance_df[\"fold\"] = fold_ + 1\n feature_importance_df = pd.concat([feature_importance_df, fold_importance_df], axis=0)\n \n predictions += clf.predict(test[df_train_columns], num_iteration=clf.best_iteration) / folds.n_splits\n\n# np.sqrt(mean_squared_error(oof, target))\nmean_absolute_error(oof, target)","metadata":{"_uuid":"29d413b0cf270375808c3424410e71e07f71e15e","scrolled":true,"execution":{"iopub.status.busy":"2023-12-19T12:49:03.211949Z","iopub.execute_input":"2023-12-19T12:49:03.212274Z","iopub.status.idle":"2023-12-19T12:56:08.032769Z","shell.execute_reply.started":"2023-12-19T12:49:03.212213Z","shell.execute_reply":"2023-12-19T12:56:08.0306Z"},"trusted":true},"execution_count":37,"outputs":[{"name":"stdout","text":"fold 0\nTraining until validation scores don't improve for 200 rounds.\nEarly stopping, best iteration is:\n[847]\ttraining's rmse: 3.39771\tvalid_1's rmse: 3.65322\nfold 1\nTraining until validation scores don't improve for 200 rounds.\nEarly stopping, best iteration is:\n[1140]\ttraining's rmse: 3.35321\tvalid_1's rmse: 3.64809\nfold 2\nTraining until validation scores don't improve for 200 rounds.\nEarly stopping, best iteration is:\n[767]\ttraining's rmse: 3.40015\tvalid_1's rmse: 3.66149\nfold 3\nTraining until validation scores don't improve for 200 rounds.\nEarly stopping, best iteration is:\n[1120]\ttraining's rmse: 3.35631\tvalid_1's rmse: 3.6388\nfold 4\nTraining until validation scores don't improve for 200 rounds.\nEarly stopping, best iteration is:\n[1079]\ttraining's rmse: 3.36585\tvalid_1's rmse: 3.64906\n","output_type":"stream"},{"execution_count":37,"output_type":"execute_result","data":{"text/plain":"1.5668911764859201"},"metadata":{}}]},{"cell_type":"markdown","source":"Feature Importance - Stratified K Folds Technique","metadata":{"_uuid":"04426bf9e197bbef4aa7e13fa4dfeef14fad7fdc"}},{"cell_type":"code","source":"cols = (feature_importance_df[[\"Feature\", \"importance\"]]\n .groupby(\"Feature\")\n .mean()\n .sort_values(by=\"importance\", ascending=False)[:1000].index)\n\nbest_features = feature_importance_df.loc[feature_importance_df.Feature.isin(cols)]\n\nplt.figure(figsize=(14,25))\nsns.barplot(x=\"importance\",\n y=\"Feature\",\n data=best_features.sort_values(by=\"importance\",\n ascending=False))\nplt.title('LightGBM Features (avg over folds)')\nplt.tight_layout()\nplt.savefig('lgbm_importances.png')","metadata":{"_uuid":"f594383f5fb83246203ce54b4892592673e699ce","scrolled":true,"execution":{"iopub.status.busy":"2023-12-19T12:56:08.034594Z","iopub.execute_input":"2023-12-19T12:56:08.03512Z","iopub.status.idle":"2023-12-19T12:56:19.039191Z","shell.execute_reply.started":"2023-12-19T12:56:08.035062Z","shell.execute_reply":"2023-12-19T12:56:19.038089Z"},"trusted":true},"execution_count":38,"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}]},{"cell_type":"code","source":"features = [c for c in train.columns if c not in ['first_active_month', 'target', 'card_id', 'outliers',\n 'hist_purchase_date_max', 'hist_purchase_date_min', 'hist_card_id_size',\n 'new_purchase_date_max', 'new_purchase_date_min', 'new_card_id_size']]","metadata":{"_uuid":"4e4259f0bc335d4060f6d28ddc044617c9c7f94d","execution":{"iopub.status.busy":"2023-12-19T12:56:19.040709Z","iopub.execute_input":"2023-12-19T12:56:19.041033Z","iopub.status.idle":"2023-12-19T12:56:19.047147Z","shell.execute_reply.started":"2023-12-19T12:56:19.040971Z","shell.execute_reply":"2023-12-19T12:56:19.046276Z"},"trusted":true},"execution_count":39,"outputs":[]},{"cell_type":"markdown","source":"Apply Light GBM Modelling Technique with Repeated K Folds enumerated on training set and Target ","metadata":{"_uuid":"4b3d96a1354b5f37e7ba1a845428948cf7f8d1f9"}},{"cell_type":"code","source":"folds = RepeatedKFold(n_splits=5, n_repeats=2, random_state=4950)\noof_2 = np.zeros(len(train))\npredictions_2 = np.zeros(len(test))\nfeature_importance_df_2 = pd.DataFrame()\n\nfor fold_, (trn_idx, val_idx) in enumerate(folds.split(train.values, target.values)):\n \n print(\"fold {}\".format(fold_))\n trn_data = lgb.Dataset(train.iloc[trn_idx][features], label=target.iloc[trn_idx])\n val_data = lgb.Dataset(train.iloc[val_idx][features], label=target.iloc[val_idx])\n \n param ={\n 'task': 'train',\n 'boosting': 'goss',\n 'objective': 'regression',\n 'metric': 'rmse',\n 'learning_rate': 0.01,\n 'subsample': 0.9855232997390695,\n 'max_depth': 7,\n 'top_rate': 0.9064148448434349,\n 'num_leaves': 63,\n 'min_child_weight': 41.9612869171337,\n 'other_rate': 0.0721768246018207,\n 'reg_alpha': 9.677537745007898,\n 'colsample_bytree': 0.5665320670155495,\n 'min_split_gain': 9.820197773625843,\n 'reg_lambda': 8.2532317400459,\n 'min_data_in_leaf': 21,\n 'verbose': -1,\n 'seed':int(2**fold_),\n 'bagging_seed':int(2**fold_),\n 'drop_seed':int(2**fold_)\n }\n \n num_round = 10000\n clf_r = lgb.train(param, trn_data, num_round, valid_sets = [trn_data, val_data], verbose_eval=-1, early_stopping_rounds = 200)\n oof_2[val_idx] = clf_r.predict(train.iloc[val_idx][features], num_iteration=clf_r.best_iteration)\n \n fold_importance_df = pd.DataFrame()\n fold_importance_df[\"Feature\"] = features\n fold_importance_df[\"importance\"] = clf_r.feature_importance()\n fold_importance_df[\"fold\"] = fold_ + 1\n feature_importance_df_2 = pd.concat([feature_importance_df_2, fold_importance_df], axis=0)\n \n predictions_2 += clf_r.predict(test[features], num_iteration=clf_r.best_iteration) / (5 * 2)\n\nprint(\"CV score: {:<8.5f}\".format(mean_squared_error(oof_2, target)**0.5))","metadata":{"_uuid":"85f3d1c010115cd099839c8434fe37a9429d8696","execution":{"iopub.status.busy":"2023-12-19T12:56:19.048808Z","iopub.execute_input":"2023-12-19T12:56:19.049327Z","iopub.status.idle":"2023-12-19T13:00:09.507234Z","shell.execute_reply.started":"2023-12-19T12:56:19.049262Z","shell.execute_reply":"2023-12-19T13:00:09.449803Z"},"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":40,"outputs":[{"name":"stdout","text":"fold 0\nTraining until validation scores don't improve for 200 rounds.\nEarly stopping, best iteration is:\n[837]\ttraining's rmse: 3.39929\tvalid_1's rmse: 3.65729\nfold 1\nTraining until validation scores don't improve for 200 rounds.\nEarly stopping, best iteration is:\n[940]\ttraining's rmse: 3.34448\tvalid_1's rmse: 3.80083\nfold 2\nTraining until validation scores don't improve for 200 rounds.\nEarly stopping, best iteration is:\n[741]\ttraining's rmse: 3.43618\tvalid_1's rmse: 3.56001\nfold 3\nTraining until validation scores don't improve for 200 rounds.\n","output_type":"stream"},{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)","\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 34\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 35\u001b[0m \u001b[0mnum_round\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m10000\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 36\u001b[0;31m \u001b[0mclf_r\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlgb\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mparam\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtrn_data\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnum_round\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalid_sets\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mtrn_data\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mval_data\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mverbose_eval\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mearly_stopping_rounds\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m200\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 37\u001b[0m \u001b[0moof_2\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mval_idx\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mclf_r\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0miloc\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mval_idx\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mfeatures\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnum_iteration\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mclf_r\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbest_iteration\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 38\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/lightgbm/engine.py\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(params, train_set, num_boost_round, valid_sets, valid_names, fobj, feval, init_model, feature_name, categorical_feature, early_stopping_rounds, evals_result, verbose_eval, learning_rates, keep_training_booster, callbacks)\u001b[0m\n\u001b[1;32m 216\u001b[0m evaluation_result_list=None))\n\u001b[1;32m 217\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 218\u001b[0;31m \u001b[0mbooster\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfobj\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mfobj\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 219\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 220\u001b[0m \u001b[0mevaluation_result_list\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/lightgbm/basic.py\u001b[0m in \u001b[0;36mupdate\u001b[0;34m(self, train_set, fobj)\u001b[0m\n\u001b[1;32m 1800\u001b[0m _safe_call(_LIB.LGBM_BoosterUpdateOneIter(\n\u001b[1;32m 1801\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhandle\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1802\u001b[0;31m ctypes.byref(is_finished)))\n\u001b[0m\u001b[1;32m 1803\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__is_predicted_cur_iter\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;32mFalse\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0m_\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange_\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__num_dataset\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1804\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mis_finished\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalue\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mKeyboardInterrupt\u001b[0m: "],"ename":"KeyboardInterrupt","evalue":"","output_type":"error"}]},{"cell_type":"markdown","source":"Feature Importance - Repeated K Folds","metadata":{"_uuid":"e68611a4c9f1f1a042ddc5eedcfad33d89575b13"}},{"cell_type":"code","source":"cols = (feature_importance_df_2[[\"Feature\", \"importance\"]]\n .groupby(\"Feature\")\n .mean()\n .sort_values(by=\"importance\", ascending=False)[:1000].index)\n\nbest_features = feature_importance_df_2.loc[feature_importance_df_2.Feature.isin(cols)]\n\nplt.figure(figsize=(14,25))\nsns.barplot(x=\"importance\",\n y=\"Feature\",\n data=best_features.sort_values(by=\"importance\",\n ascending=False))\nplt.title('LightGBM Features (avg over folds)')\nplt.tight_layout()\nplt.savefig('lgbm_importances.png')","metadata":{"_uuid":"5e3ecdfbeb0d615801156a32ff14eade7e994950","scrolled":true,"execution":{"iopub.status.busy":"2023-12-19T13:00:09.451388Z","iopub.status.idle":"2023-12-19T13:00:09.452147Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Stacking the models together.","metadata":{"_uuid":"d83f9093cd718a2e72b3d9b84a02a8e72156c625"}},{"cell_type":"code","source":"from sklearn.linear_model import BayesianRidge\n\ntrain_stack = np.vstack([oof,oof_2]).transpose()\ntest_stack = np.vstack([predictions, predictions_2]).transpose()\n\nfolds_stack = RepeatedKFold(n_splits=5, n_repeats=1, random_state=4590)\noof_stack = np.zeros(train_stack.shape[0])\npredictions_3 = np.zeros(test_stack.shape[0])\n\nfor fold_, (trn_idx, val_idx) in enumerate(folds_stack.split(train_stack,target)):\n print(\"fold {}\".format(fold_))\n trn_data, trn_y = train_stack[trn_idx], target.iloc[trn_idx].values\n val_data, val_y = train_stack[val_idx], target.iloc[val_idx].values\n \n clf_3 = BayesianRidge()\n clf_3.fit(trn_data, trn_y)\n \n oof_stack[val_idx] = clf_3.predict(val_data)\n predictions_3 += clf_3.predict(test_stack) / 5\n \n# np.sqrt(mean_squared_error(target.values, oof_stack))\nmean_squared_error(target.values, oof_stack)","metadata":{"_uuid":"a65e5bb380bc06a3dcac649cc1168457d3c156a3","execution":{"iopub.status.busy":"2023-12-19T13:00:09.453091Z","iopub.status.idle":"2023-12-19T13:00:09.453791Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Final Predictions and Submission File.","metadata":{"_uuid":"d8b3c5b718779a1d5729e89a5341258c44de24e2"}},{"cell_type":"code","source":"sample_submission = pd.read_csv('../input/sample_submission.csv')\nsample_submission['target'] = predictions_3\nsample_submission.to_csv('submission_ashish_lgbm.csv', index=False)","metadata":{"_uuid":"e87474495a3b14a96345eb2773fce5564268d9ac","execution":{"iopub.status.busy":"2023-12-19T13:00:09.45479Z","iopub.status.idle":"2023-12-19T13:00:09.455314Z"},"trusted":true},"execution_count":null,"outputs":[]}]}