{"cells":[{"metadata":{"_uuid":"6df55b542f152882e00385a0f73198f4e3bc4316"},"cell_type":"markdown","source":"**FEEL FREE TO UPVOTE**  （＾ｖ＾）"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport datetime\nimport gc\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport lightgbm as lgb\nfrom sklearn.model_selection import StratifiedKFold\nfrom sklearn.metrics import mean_squared_error\nimport time\nimport warnings\nwarnings.filterwarnings('ignore')\nnp.random.seed(4590)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_new_columns(name,aggs):\n    return [name + '_' + k + '_' + agg for k in aggs.keys() for agg in aggs[k]]","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"df_train = pd.read_csv('../input/elo-merchant-category-recommendation/train.csv')\ndf_test = pd.read_csv('../input/elo-merchant-category-recommendation/test.csv')\ndf_hist_trans = pd.read_csv('../input/elo-merchant-category-recommendation/historical_transactions.csv')\ndf_new_merchant_trans = pd.read_csv('../input/elo-merchant-category-recommendation/new_merchant_transactions.csv')\ndf_merchants = pd.read_csv('../input/elo-merchant-category-recommendation/merchants.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"gdf = df_hist_trans.groupby(\"card_id\")\nprint(type(gdf))\ngdf = gdf.agg({'merchant_category_id':['min']}).reset_index()\nprint(type(gdf))\ngdf.columns = [\"card_id\", \"merchant_category_id\"]\ndf_train = pd.merge(df_train, gdf, on=\"card_id\", how=\"left\")\ndf_test = pd.merge(df_test, gdf, on=\"card_id\", how=\"left\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"gdf = df_hist_trans.groupby(\"card_id\")\nprint(type(gdf))\ngdf = gdf.agg({'merchant_category_id':['max']}).reset_index()\nprint(type(gdf))\ngdf.columns = [\"card_id\", \"max_merchant_category_id\"]\ndf_train = pd.merge(df_train, gdf, on=\"card_id\", how=\"left\")\ndf_test = pd.merge(df_test, gdf, on=\"card_id\", how=\"left\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"71f89a3b8a93b2f2feb2cd0a45f860cde33687be"},"cell_type":"code","source":"for df in [df_hist_trans,df_new_merchant_trans]:\n    df['category_2'].fillna(1.0,inplace=True)\n    df['category_3'].fillna('A',inplace=True)\n    df['merchant_id'].fillna('M_ID_00a6ca8a8a',inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"690ba01a38f524e9345b419200f588f937bc067a"},"cell_type":"code","source":"for df in [df_hist_trans,df_new_merchant_trans]:\n    df['purchase_date'] = pd.to_datetime(df['purchase_date'])\n    df['year'] = df['purchase_date'].dt.year\n    df['weekofyear'] = df['purchase_date'].dt.weekofyear\n    df['month'] = df['purchase_date'].dt.month\n    df['dayofweek'] = df['purchase_date'].dt.dayofweek\n    df['weekend'] = (df.purchase_date.dt.weekday >=5).astype(int)\n    df['hour'] = df['purchase_date'].dt.hour\n    df['authorized_flag'] = df['authorized_flag'].map({'Y':1, 'N':0})\n    df['category_1'] = df['category_1'].map({'Y':1, 'N':0}) \n    #https://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/73244\n    df['month_diff'] = ((datetime.datetime.today() - df['purchase_date']).dt.days)//30\n    df['month_diff'] += df['month_lag']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f7f5625db40db4395374991124fb796c9decd60b"},"cell_type":"code","source":"aggs = {}\nfor col in ['month','hour','weekofyear','dayofweek','year','subsector_id','merchant_id','merchant_category_id']:\n    aggs[col] = ['nunique']\naggs['purchase_amount'] = ['sum','max','min','mean','var']\naggs['installments'] = ['sum','max','min','mean','var']\naggs['purchase_date'] = ['max','min']\naggs['month_lag'] = ['max','min','mean','var']\naggs['month_diff'] = ['mean']\naggs['weekend'] = ['sum', 'mean']\naggs['category_1'] = ['sum', 'mean']\naggs['card_id'] = ['size']\n\nfor col in ['category_2','category_3']:\n    df_new_merchant_trans[col+'_mean'] = df_new_merchant_trans.groupby([col])['purchase_amount'].transform('mean')\n    aggs[col+'_mean'] = ['mean']\n    \nnew_columns = get_new_columns('new_hist',aggs)\ndf_hist_trans_group = df_new_merchant_trans.groupby('card_id').agg(aggs)\ndf_hist_trans_group.columns = new_columns\ndf_hist_trans_group.reset_index(drop=False,inplace=True)\ndf_hist_trans_group['new_hist_purchase_date_diff'] = (df_hist_trans_group['new_hist_purchase_date_max'] - df_hist_trans_group['new_hist_purchase_date_min']).dt.days\ndf_hist_trans_group['new_hist_purchase_date_average'] = df_hist_trans_group['new_hist_purchase_date_diff']/df_hist_trans_group['new_hist_card_id_size']\ndf_hist_trans_group['new_hist_purchase_date_uptonow'] = (datetime.datetime.today() - df_hist_trans_group['new_hist_purchase_date_max']).dt.days\ndf_train = df_train.merge(df_hist_trans_group,on='card_id',how='left')\ndf_test = df_test.merge(df_hist_trans_group,on='card_id',how='left')\ndel df_hist_trans_group;gc.collect()\ndel df_new_merchant_trans;gc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ddf1d5bb0ade2b22b0f072c208c1506ea64503ea"},"cell_type":"code","source":"aggs = {}\nfor col in ['month','hour','weekofyear','dayofweek','year','subsector_id','merchant_id','merchant_category_id']:\n    aggs[col] = ['nunique']\n\naggs['purchase_amount'] = ['sum','max','min','mean','var']\naggs['installments'] = ['sum','max','min','mean','var']\naggs['purchase_date'] = ['max','min']\naggs['month_lag'] = ['max','min','mean','var']\naggs['month_diff'] = ['mean']\naggs['authorized_flag'] = ['sum', 'mean']\naggs['weekend'] = ['sum', 'mean']\naggs['category_1'] = ['sum', 'mean']\naggs['card_id'] = ['size']\n\nfor col in ['category_2','category_3']:\n    df_hist_trans[col+'_mean'] = df_hist_trans.groupby([col])['purchase_amount'].transform('mean')\n    aggs[col+'_mean'] = ['mean']    \n\nnew_columns = get_new_columns('hist',aggs)\ndf_hist_trans_group = df_hist_trans.groupby('card_id').agg(aggs)\ndf_hist_trans_group.columns = new_columns\ndf_hist_trans_group.reset_index(drop=False,inplace=True)\ndf_hist_trans_group['hist_purchase_date_diff'] = (df_hist_trans_group['hist_purchase_date_max'] - df_hist_trans_group['hist_purchase_date_min']).dt.days\ndf_hist_trans_group['hist_purchase_date_average'] = df_hist_trans_group['hist_purchase_date_diff']/df_hist_trans_group['hist_card_id_size']\ndf_hist_trans_group['hist_purchase_date_uptonow'] = (datetime.datetime.today() - df_hist_trans_group['hist_purchase_date_max']).dt.days\ndf_train = df_train.merge(df_hist_trans_group,on='card_id',how='left')\ndf_test = df_test.merge(df_hist_trans_group,on='card_id',how='left')\ndel df_hist_trans_group;gc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a075cc90ab1322829e4fad3ff39fce307c5db93c"},"cell_type":"code","source":"del df_hist_trans;gc.collect()\n#del df_new_merchant_trans;gc.collect()#清理内存-\ndf_train.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import Imputer\nimp = Imputer(missing_values='NaN', strategy='most_frequent', axis=0)\ndf_merchants['avg_sales_lag3']=imp.fit(pd.DataFrame(df_merchants['avg_sales_lag3'].values.reshape(-1,1))).transform(pd.DataFrame(df_merchants['avg_sales_lag3'].values.reshape(-1,1)))\ndf_merchants['avg_sales_lag6']=imp.fit(pd.DataFrame(df_merchants['avg_sales_lag6'].values.reshape(-1,1))).transform(pd.DataFrame(df_merchants['avg_sales_lag6'].values.reshape(-1,1)))\ndf_merchants['avg_sales_lag12']=imp.fit(pd.DataFrame(df_merchants['avg_sales_lag12'].values.reshape(-1,1))).transform(pd.DataFrame(df_merchants['avg_sales_lag12'].values.reshape(-1,1)))\ndf_merchants['category_2']=imp.fit(pd.DataFrame(df_merchants['category_2'].values.reshape(-1,1))).transform(pd.DataFrame(df_merchants['category_2'].values.reshape(-1,1)))\ndf_merchants.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"aggs={}\nfor col in ['avg_sales_lag3','avg_purchases_lag3','active_months_lag3','avg_sales_lag6','avg_purchases_lag6','active_months_lag6','avg_sales_lag12','avg_purchases_lag12','active_months_lag12','numerical_1','numerical_2']:\n    aggs[col]= ['mean']\n    \nnew_columns= get_new_columns('merchants',aggs)\ndf_merchants_group = df_merchants.groupby('merchant_category_id').agg(aggs)\ndf_merchants_group.columns = new_columns\ndf_merchants_group.reset_index(drop=False,inplace=True)\ndf_train=df_train.merge(df_merchants_group,on='merchant_category_id',how='left')\ndf_test=df_test.merge(df_merchants_group.reset_index(),on='merchant_category_id',how='left')\ndf_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_merchants['max_merchant_category_id']=df_merchants['merchant_category_id']\n#df_test['max_merchant_category_id']=df_test['merchant_category_id']\n\naggs={}\nfor col in ['avg_sales_lag3','avg_purchases_lag3','active_months_lag3','avg_sales_lag6','avg_purchases_lag6','active_months_lag6','avg_sales_lag12','avg_purchases_lag12','active_months_lag12','numerical_1','numerical_2']:\n    aggs[col]= ['mean']\n    \nnew_columns= get_new_columns('max_merchants',aggs)\ndf_merchants_group = df_merchants.groupby('max_merchant_category_id').agg(aggs)\ndf_merchants_group.columns = new_columns\ndf_merchants_group.reset_index(drop=False,inplace=True)\ndf_train=df_train.merge(df_merchants_group,on='max_merchant_category_id',how='left')\ndf_test=df_test.merge(df_merchants_group.reset_index(),on='max_merchant_category_id',how='left')\ndf_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"6f3182aeac0c3bf7a061a1b9e25e859f25fee9b5"},"cell_type":"code","source":"df_train['outliers'] = 0\ndf_train.loc[df_train['target'] < -30, 'outliers'] = 1\ndf_train['outliers'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ce2082fc1fb0e3f8f7d27fc166aa7a8351b65504"},"cell_type":"code","source":"for df in [df_train,df_test]:\n    df['first_active_month'] = pd.to_datetime(df['first_active_month'])\n    df['dayofweek'] = df['first_active_month'].dt.dayofweek\n    df['weekofyear'] = df['first_active_month'].dt.weekofyear\n    df['month'] = df['first_active_month'].dt.month\n    df['elapsed_time'] = (datetime.datetime.today() - df['first_active_month']).dt.days\n    df['hist_first_buy'] = (df['hist_purchase_date_min'] - df['first_active_month']).dt.days\n    df['new_hist_first_buy'] = (df['new_hist_purchase_date_min'] - df['first_active_month']).dt.days\n    for f in ['hist_purchase_date_max','hist_purchase_date_min','new_hist_purchase_date_max',\\\n                     'new_hist_purchase_date_min']:\n        df[f] = df[f].astype(np.int64) * 1e-9\n    df['card_id_total'] = df['new_hist_card_id_size']+df['hist_card_id_size']\n    df['purchase_amount_total'] = df['new_hist_purchase_amount_sum']+df['hist_purchase_amount_sum']\n\nfor f in ['feature_1','feature_2','feature_3']:\n    order_label = df_train.groupby([f])['outliers'].mean()\n    df_train[f] = df_train[f].map(order_label)\n    df_test[f] = df_test[f].map(order_label)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"c4f20f27679889542acfd60d1f1ac381b201ac43"},"cell_type":"code","source":"df_train_columns = [c for c in df_train.columns if c not in ['card_id', 'first_active_month','target','outliers']]\ntarget = df_train['target']\ndel df_train['target']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"c9bbc95244978b519d94131907b547c2b6c94191"},"cell_type":"code","source":"param = {'num_leaves': 31,\n         'min_data_in_leaf': 27, \n         'objective':'regression',\n         'max_depth': -1,\n         'learning_rate': 0.015,\n         \"min_child_samples\": 50,\n         \"boosting\": \"gbdt\",\n         \"feature_fraction\": 0.9,\n         \"bagging_freq\": 1,\n         \"bagging_fraction\": 0.9 ,\n         \"bagging_seed\": 11,\n         \"metric\": 'rmse',\n         \"lambda_l1\": 0.1,\n         \"verbosity\": -1,\n         \"nthread\": 4,\n         \"random_state\": 4590}\nfolds = StratifiedKFold(n_splits=5, shuffle=True, random_state=4590)\noof = np.zeros(len(df_train))\npredictions = np.zeros(len(df_test))\nfeature_importance_df = pd.DataFrame()\n\nfor fold_, (trn_idx, val_idx) in enumerate(folds.split(df_train,df_train['outliers'].values)):\n    print(\"fold {}\".format(fold_))\n    trn_data = lgb.Dataset(df_train.iloc[trn_idx][df_train_columns], label=target.iloc[trn_idx])#, categorical_feature=categorical_feats)\n    val_data = lgb.Dataset(df_train.iloc[val_idx][df_train_columns], label=target.iloc[val_idx])#, categorical_feature=categorical_feats)\n\n    num_round = 10000\n    clf = lgb.train(param, trn_data, num_round, valid_sets = [trn_data, val_data], verbose_eval=200, early_stopping_rounds = 200)\n    oof[val_idx] = clf.predict(df_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(df_test[df_train_columns], num_iteration=clf.best_iteration) / folds.n_splits\n\nnp.sqrt(mean_squared_error(oof, target))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_without_outliers = pd.DataFrame({\"card_id\":df_test[\"card_id\"].values})\nmodel_without_outliers[\"target\"] = predictions","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#del df_train['outliers']\n#del df_train['target']\n#target = df_train['outliers']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"features = [c for c in df_train.columns if c not in ['card_id', 'first_active_month']]\ncategorical_feats = [c for c in features if 'feature_' in c]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"param = {'num_leaves': 31,\n         'min_data_in_leaf': 30, \n         'objective':'binary',\n         'max_depth': 6,\n         'learning_rate': 0.01,\n         \"boosting\": \"rf\",\n         \"feature_fraction\": 0.9,\n         \"bagging_freq\": 1,\n         \"bagging_fraction\": 0.9 ,\n         \"bagging_seed\": 11,\n         \"metric\": 'binary_logloss',\n         \"lambda_l1\": 0.1,\n         \"verbosity\": -1,\n         \"random_state\": 2333}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import StratifiedKFold, KFold\nfrom sklearn.metrics import mean_squared_error\nfrom sklearn.metrics import log_loss\n%%time\nfolds = KFold(n_splits=5, shuffle=True, random_state=15)\noof = np.zeros(len(df_train))\npredictions = np.zeros(len(df_test))\nfeature_importance_df = pd.DataFrame()\n\nstart = time.time()\n\n\nfor fold_, (trn_idx, val_idx) in enumerate(folds.split(df_train.values, target.values)):\n    print(\"fold n°{}\".format(fold_))\n    trn_data = lgb.Dataset(df_train.iloc[trn_idx][features], label=target.iloc[trn_idx], categorical_feature=categorical_feats)\n    val_data = lgb.Dataset(df_train.iloc[val_idx][features], label=target.iloc[val_idx], categorical_feature=categorical_feats)\n\n    num_round = 10000\n    clf = lgb.train(param, trn_data, num_round, valid_sets = [trn_data, val_data], verbose_eval=100, early_stopping_rounds = 200)\n    oof[val_idx] = clf.predict(df_train.iloc[val_idx][features], num_iteration=clf.best_iteration)\n    \n    fold_importance_df = pd.DataFrame()\n    fold_importance_df[\"feature\"] = features\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(df_test[features], num_iteration=clf.best_iteration) / folds.n_splits\n\nprint(\"CV score: {:<8.5f}\".format(log_loss(target, oof)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"### 'target' is the probability of whether an observation is an outlier\ndf_outlier_prob = pd.DataFrame({\"card_id\":df_test[\"card_id\"].values})\ndf_outlier_prob[\"target\"] = predictions\ndf_outlier_prob.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"outlier_id = pd.DataFrame(df_outlier_prob.sort_values(by='target',ascending = False).head(25000)['card_id'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"best_submission = pd.read_csv('../input/finaldata/submission_ashish.csv')\nmost_likely_liers = best_submission.merge(outlier_id,how='right')\nmost_likely_liers.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nfor card_id in most_likely_liers['card_id']:\n    model_without_outliers.loc[model_without_outliers['card_id']==card_id,'target']\\\n    = most_likely_liers.loc[most_likely_liers['card_id']==card_id,'target'].values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_without_outliers.to_csv(\"combining_submission.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"355e9c24949b8e5d677fe5a2f117228c3310dab6"},"cell_type":"code","source":"#sub_df = pd.DataFrame({\"card_id\":df_test[\"card_id\"].values})\n#sub_df[\"target\"] = predictions\n#sub_df.to_csv(\"submission.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"40b64481054fa71e692829c7039eccceb31b77fe"},"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\n#best_features = feature_importance_df.loc[feature_importance_df.Feature.isin(cols)]\n\n#plt.figure(figsize=(14,25))\n#sns.barplot(x=\"importance\",\n            #y=\"Feature\",\n            #data=best_features.sort_values(by=\"importance\",\n                                          # ascending=False))\n#plt.title('LightGBM Features (avg over folds)')\n#plt.tight_layout()\n#plt.savefig('lgbm_importances.png')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"58c9a5445698e42dfbd9548695290487a2ce171a"},"cell_type":"markdown","source":"**To be continued ...**"}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}