{"cells":[{"metadata":{"_uuid":"7cb82a6d1f008fcc568ee87245b751c2a4167f1c"},"cell_type":"markdown","source":"                                                Elo Merchant Category Recommendation\n![image.png](attachment:image.png)\n\n","attachments":{"image.png":{"image/png":"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"}}},{"metadata":{"_uuid":"d6b831a0448f351dbe6dd95b98366a08f1fd10dd"},"cell_type":"markdown","source":"Elo is a pure domestic card brand in Brazil and only allows for transactions in Brazilian Real currency. Elo results from a partnership of three of the largest banks in Brazil: Banco do Brasil, Bradesco and CAIXA. The Elo brand supports credit, debit, and prepaid card transactions. More than 50 million Elo cards have been issued to date. The Elo credit card supports so-called 'installments' that allows the shopper to spread their payments for online purchases over a certain period of time. Cielo, one of the largest merchant acquirers in Brazil, allows ecommerce merchants to accept Elo in their online store. Most of the Brazilian and international Payment Service Providers are connected to Cielo to allow its customer to accept Elo online. Please find below all Payment Service Providers that enable merchants to accept Elo in their webshop.\n\n\nThe competition circulates around the loyalty of customers and the precise prediction of the same is the main judging criteria.\n\nThe notebook here comprises of basic Exploratory Data Analysis and then some deep dive into particular customer transactions and then the final prediction of the loyalty score on basis of the various features from the different datasets in consideration"},{"metadata":{"_uuid":"ad6bf43c8bc6d7b78f8d055384c670430452c17c"},"cell_type":"markdown","source":"Importing Libraries"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"from sklearn import model_selection, preprocessing, metrics\nfrom sklearn.metrics import mean_squared_error\nfrom sklearn.model_selection import train_test_split\nfrom pandas import get_dummies\nimport lightgbm as lgb\nimport plotly.graph_objs as go\nimport plotly.offline as py\nimport xgboost as xgb\nimport matplotlib.pyplot as plt\nimport pandas_profiling as pp\nimport pandas as pd\nimport numpy as np\nimport matplotlib\nimport warnings\nimport sklearn\nimport scipy\nimport numpy\nimport json\nimport sys\nimport csv\n\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d7ed73971418d48d08bd579b0978c0053a926c82"},"cell_type":"code","source":"#Loading Train and Test Data\ndf_train = pd.read_csv('../input/train.csv', parse_dates=[\"first_active_month\"] )\ndf_test = pd.read_csv('../input/test.csv' ,parse_dates=[\"first_active_month\"] )\ndf_merchants=pd.read_csv('../input/merchants.csv')\ndf_new_merchant_transactions=pd.read_csv('../input/new_merchant_transactions.csv')\ndf_historical_transactions = pd.read_csv(\"../input/historical_transactions.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a43817cd33d20571e01653e7d717a7a49d452425"},"cell_type":"code","source":"sample_submission = pd.read_csv(\"../input/sample_submission.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"dad1ee03d61a146113fdf28df75a8cbe41572b71"},"cell_type":"code","source":"sample_submission.head()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"88d2678a86ab4131d0a7a4489044934eaf0b759a"},"cell_type":"markdown","source":"* The final recommendation is the above target value or the loyalty score for the Elo Platform."},{"metadata":{"_uuid":"7dfeeee4e31b8d55b6ddcd61772fe97e7dbc9141"},"cell_type":"markdown","source":"**Pandas Profiling package has been used below for taking the profile report of the datasets**"},{"metadata":{"trusted":true,"_uuid":"b9fce84331c3d7a0afa4cce9d9fc120cbaa6e4b1","scrolled":true},"cell_type":"code","source":"pp.ProfileReport(df_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"5c01a742f2f468d65ede948398296d50871cf423"},"cell_type":"code","source":"pp.ProfileReport(df_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"6e9b30594cac3ae9ff4f34bc951b78f08f572989"},"cell_type":"code","source":"pp.ProfileReport(df_merchants)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"58592030995908d679dbc26fb1db3a69e29cf47b"},"cell_type":"code","source":"pp.ProfileReport(df_new_merchant_transactions)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"8d01d3ed4725d4a790848cbdc392534c80c6df7b"},"cell_type":"code","source":"#Missing Data Analysis on train set\ntotal = df_train.isnull().sum().sort_values(ascending = False)\npercent = (df_train.isnull().sum()/df_train.isnull().count()*100).sort_values(ascending = False)\nmissing_data  = pd.concat([total, percent], axis=1, keys=['Total', 'Percentage'])\nmissing_data.head(20)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d4f88bf4134e9085e37f15eaa52b672fc22f9cca"},"cell_type":"code","source":"#Missing Data Analysis on test set\ntotal = df_test.isnull().sum().sort_values(ascending = False)\npercent = (df_test.isnull().sum()/df_test.isnull().count()*100).sort_values(ascending = False)\nmissing_data  = pd.concat([total, percent], axis=1, keys=['Total', 'Percentage'])\nmissing_data.head(20)","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-output":true,"_uuid":"6e9ee9d6034be9c058211d339b33f216913a6c36"},"cell_type":"markdown","source":"The above analysis signifies that there are no missing values in the train and test set"},{"metadata":{"trusted":true,"_uuid":"afc321625d177a9f79ff84b0c043ec20b7f35804"},"cell_type":"code","source":"df_train.target.plot.hist()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"7a0a9553685bb80890e3b069d548ba710bf8f638"},"cell_type":"markdown","source":"The above plot signifies that most of the values of the target variable are between -9 to +9 .\n\nThere is an outlier value around -30"},{"metadata":{"trusted":true,"_uuid":"cd90adeb38b5891a53f22307fffcb04d56ca07d9"},"cell_type":"code","source":"# Code reference from https://www.kaggle.com/sudalairajkumar/simple-exploration-notebook-elo\n# SRK - Simple Exploration Notebook\n\nimport seaborn as sns\n\ncnt_srs = df_train['first_active_month'].dt.date.value_counts()\ncnt_srs = cnt_srs.sort_index()\nplt.figure(figsize=(14,6))\nsns.barplot(cnt_srs.index, cnt_srs.values, alpha=0.8, color='green')\nplt.xticks(rotation='vertical')\nplt.xlabel('First active month', fontsize=12)\nplt.ylabel('Number of cards', fontsize=12)\nplt.title(\"First active month count in train set\")\nplt.show()\n\ncnt_srs = df_test['first_active_month'].dt.date.value_counts()\ncnt_srs = cnt_srs.sort_index()\nplt.figure(figsize=(14,6))\nsns.barplot(cnt_srs.index, cnt_srs.values, alpha=0.8, color='green')\nplt.xticks(rotation='vertical')\nplt.xlabel('First active month', fontsize=12)\nplt.ylabel('Number of cards', fontsize=12)\nplt.title(\"First active month count in test set\")\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"10359e43998e7362ff1fb80feecdd31297a00592","scrolled":false},"cell_type":"code","source":"df_train.corr()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"e34a8586a40fa03eb39747f9a8c84e48099e33ec"},"cell_type":"markdown","source":"*** From the above correlation matrix , it is apparent that the features have very less correlation with target value.\nFeature 3 has the least correlation as it is closest to 0 and the Feature_1 and Feature_2 have a little negative correlation**"},{"metadata":{"_uuid":"48463435548385016be6bfcf6fc8ec525086c6c6"},"cell_type":"markdown","source":"Only Feature 2 and Feature 1 are being converted to numerical values as Feature 3 will not impact the target score much because of negative correlation"},{"metadata":{"trusted":true,"_uuid":"a7f9b90bf2f408bf4cc2c5084a648e9a6058aa68","scrolled":true},"cell_type":"code","source":"df_train = pd.get_dummies(df_train, columns=['feature_1', 'feature_3'])\ndf_test = pd.get_dummies(df_test, columns=['feature_1', 'feature_3'])\ndf_train.head()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"cbdc95185fb3cd61291d858f7a275f4cf9a94848"},"cell_type":"markdown","source":"**Basic EDA on Historical and New_merchant files**"},{"metadata":{"_uuid":"28a57c429e34dacb7a2b99649968e05f826774fa"},"cell_type":"markdown","source":"Top 10 cards with highest number of transactions in historical dataset"},{"metadata":{"trusted":true,"scrolled":true,"_uuid":"88a0288bfdc63d17ca5ea51f77b2a37f0390e36e"},"cell_type":"code","source":"df_card_history  = df_historical_transactions['card_id'].value_counts().head(10)\ndf_card_history","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"1f3550c0b20767486bc2399a576483a677a3a722"},"cell_type":"code","source":"df_card_history_authorized  = df_historical_transactions['authorized_flag'].value_counts()\ndf_card_history_authorized","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"df255fd667dbf66a2b7dcea7dc19657c9e643291"},"cell_type":"code","source":"df_non_authorized = df_historical_transactions[df_historical_transactions['authorized_flag'] == \"N\"]\ndf_non_authorized","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a5059e68a4fd1725939b60d824f77c0e6800754e","scrolled":false},"cell_type":"code","source":"df_card_unauth  = df_non_authorized['card_id'].value_counts()\ndf_card_unauth.head(10)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"b16c6f883ab76605e9598a1d189b9d8415262d13"},"cell_type":"markdown","source":"The below 2 card_ids have the most unauthorized transactions\n\n\n**C_ID_5ea401d358 ** --------- \n** C_ID_3d3dfdc692  **"},{"metadata":{"trusted":true,"_uuid":"e10d068796dc97522f3faf3fdeb683ee5c3d2c18","scrolled":true},"cell_type":"code","source":"df_card_1_unauth= df_non_authorized[df_non_authorized['card_id']==\"C_ID_5ea401d358\"]\ndf_card_2_unauth = df_non_authorized[df_non_authorized['card_id']==\"C_ID_3d3dfdc692\"]","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"caf8fee38b71c1ae0b23c373e960bcae98c92344"},"cell_type":"markdown","source":"Below are the findings for the merchants where these cards have done the  most unauthorized transactions"},{"metadata":{"trusted":true,"scrolled":false,"_uuid":"b3d83752cf92bdb4b6bba467ced4c03dc843679b"},"cell_type":"code","source":"df_card_1_merch = df_card_1_unauth['merchant_id'].value_counts()\ndf_card_1_merch.head(10)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"66d50e03c1275d271274f4afcecf51bc01ce6a97"},"cell_type":"markdown","source":"\"C_ID_5ea401d358\" has the most unauthorized transactions at \" M_ID_9fa00da7b2 \"    "},{"metadata":{"trusted":true,"_uuid":"26a1cd69b75cffefa067bb353a26adb5a5a5030b"},"cell_type":"code","source":"df_card_1_merch = df_card_2_unauth['merchant_id'].value_counts()\ndf_card_1_merch.head(10)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"dc617abf2dae42cfc1f85524feafafa3492b9261"},"cell_type":"markdown","source":"\"C_ID_3d3dfdc692\" has the most unauthorized transactions at  \"M_ID_79692349d6\"    "},{"metadata":{"_uuid":"ebd748fb800b8c6f8ad49ee6889637fbb14720d2"},"cell_type":"markdown","source":"**Top 10 cards with highest number of transactions in new merchant transactions dataset**"},{"metadata":{"trusted":true,"scrolled":false,"_uuid":"69b3c02ebe3bb7f16ec4f45e2f3af43103cd5cfb"},"cell_type":"code","source":"df_card_new  = df_new_merchant_transactions['card_id'].value_counts().head(10)\ndf_card_new","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":false,"_uuid":"7b89dc7af427c26477489a72cc8bd9e9baccadcb"},"cell_type":"code","source":"df_non_authorized = df_new_merchant_transactions[df_new_merchant_transactions['authorized_flag'] == \"N\"]\ndf_non_authorized","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"460494a5ea80befefae0b8080acc260b5f292d44"},"cell_type":"markdown","source":"***All the transactions in the New Merchant transactions are authorized transactions. **"},{"metadata":{"_uuid":"23c9cd8238de0493c5dd5e1a73349d87238db816"},"cell_type":"markdown","source":"Moving on to the Historical and new merchant transactions table\nThe most interesting feature in transactions table seems to be the `purchase_amount`for a particular card_id \n\nIdeally the values should have been positive , but because the values have been normalized the data is different from expectation . Also,there should have been some integers in it's distribution which is obviously not the case here!"},{"metadata":{"_uuid":"46bf9db8eed4725aff831c940d813ae4681dc27c"},"cell_type":"markdown","source":""},{"metadata":{"trusted":true,"_uuid":"b8bbcce2a5cc81839d16c171534a2d0cb1ba03c0"},"cell_type":"code","source":"df_new_merchant_transactions.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":true,"_uuid":"52993cecb1adde9334a1d9bd5da803d739aacfb4"},"cell_type":"code","source":"df_new_merchant_transactions['purchase_amount_integer'] = df_new_merchant_transactions.purchase_amount.apply(lambda x: x == np.round(x))\nprint(df_new_merchant_transactions.groupby('purchase_amount_integer')['card_id'].count())","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"15935db8f1c77542146cb81fb785d56e62dc00fc"},"cell_type":"markdown","source":"The above code depicts that none of the purchase amount values are integers. \n\nSome modification is required to make the data consistent which can then be consumed in the model for better predictions.\n\nThe below code snippet has been referenced from :\nhttps://www.kaggle.com/raddar/towards-de-anonymizing-the-data-some-insights"},{"metadata":{"trusted":true,"_uuid":"a3305fb81efc8b38a945ddbda2f931db93032bef"},"cell_type":"code","source":"df_new_merchant_transactions['purchase_amount_new'] = np.round(df_new_merchant_transactions['purchase_amount'] / 0.00150265118 + 497.06,8)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"c514d9aa3ae37daa3e9f3722a68ea937f41a5370"},"cell_type":"code","source":"#rounding off two decimal places\ndf_new_merchant_transactions['purchase_amount_new'] = np.round(df_new_merchant_transactions['purchase_amount'] / 0.00150265118 + 497.06,2)\n\ndf_new_merchant_transactions['purchase_amount_integer'] = df_new_merchant_transactions.purchase_amount_new.apply(lambda x: x == np.round(x))\nprint(df_new_merchant_transactions.groupby('purchase_amount_integer')['card_id'].count())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":false,"_uuid":"ef11fded0b94f1d3f435d685e33c313929a1d7b6"},"cell_type":"code","source":"df_new_merchant_transactions.groupby('purchase_amount_new')['card_id'].count().reset_index(name='count').sort_values('count',ascending=False).head(100)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"bb325a16227758333880b2d76497217c4a24147b"},"cell_type":"markdown","source":"Since the above data has some **integer values** and some  with \"** 0.55 and 0.99 **\" after the decimal places, henceforth the \"**purchase amount**\" can be considered as the money spent on the transaction\n"},{"metadata":{"_uuid":"6c5747bd4133420ec02a10268ef611ac903cb06d"},"cell_type":"markdown","source":"* Converting the categorical data to numerical values with the help of **get_dummies** function from the pandas library\n\n* Since there are only 2 levels in **authorized flag** and **category_1** , henceforth they have been mapped to binary values"},{"metadata":{"trusted":true,"_uuid":"47c7d52a6dc9fddf32f571e74916da801e72f295"},"cell_type":"code","source":"df_historical_transactions = pd.get_dummies(df_historical_transactions, columns=['category_2', 'category_3'])\ndf_historical_transactions['authorized_flag'] = df_historical_transactions['authorized_flag'].map({'Y': 1, 'N': 0})\ndf_historical_transactions['category_1'] = df_historical_transactions['category_1'].map({'Y': 1, 'N': 0})\n\ndf_historical_transactions.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"e06100c8b56a7d83ad83136239c70b7d93993ef1"},"cell_type":"code","source":"df_historical_transactions['purchase_amount_integer'] = df_historical_transactions.purchase_amount.apply(lambda x: x == np.round(x))\nprint(df_historical_transactions.groupby('purchase_amount_integer')['card_id'].count())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"e16058769f38ff549ee72f1c3a62fa036e339837"},"cell_type":"code","source":"#df_historical_transactions['purchase_amount_new'] = np.round(df_historical_transactions['purchase_amount'] / 0.00150265118 + 497.06,8)\ndf_historical_transactions['purchase_amount_new'] = np.round(df_historical_transactions['purchase_amount'] / 0.00150265118 + 497.06,2)\ndf_historical_transactions['purchase_amount_integer'] = df_historical_transactions.purchase_amount_new.apply(lambda x: x == np.round(x))\nprint(df_historical_transactions.groupby('purchase_amount_integer')['card_id'].count())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"040c44cc7b7be5861f797dbb79a45b8766991406"},"cell_type":"code","source":"df_historical_transactions.groupby('purchase_amount_new')['card_id'].count().reset_index(name='count').sort_values('count',ascending=False).head(100)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"b527389430b026a30604600f17935a4284975df2"},"cell_type":"markdown","source":"Since the above data too has some **integer values** and some  with \"**.50 and 0.99**\" after the decimal places, henceforth the \"**purchase amount**\" can be confirmed as the money spent on the transaction\n"},{"metadata":{"trusted":true,"_uuid":"b29ea76b6062fbf4340cc6f84b4b2ab236164b4b"},"cell_type":"code","source":"del df_historical_transactions['purchase_amount_integer']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ef01c6a5d5873ef7814d0ed5803d3ed0e9e8e801"},"cell_type":"code","source":"df_historical_transactions.dtypes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"4d33ce41a7e790077747815cebec06dd545bed10"},"cell_type":"code","source":"\ndef aggregate_transactions(trans, prefix):  \n    trans.loc[:, 'purchase_date'] = pd.DatetimeIndex(trans['purchase_date']).\\\n                                      astype(np.int64) * 1e-9\n    \n    agg_func = {\n        'authorized_flag': ['sum', 'mean'],\n        'category_1': ['mean'],\n        'category_2_1.0': ['mean'],\n        'category_2_2.0': ['mean'],\n        'category_2_3.0': ['mean'],\n        'category_2_4.0': ['mean'],\n        'category_2_5.0': ['mean'],\n        'category_3_A': ['mean'],\n        'category_3_B': ['mean'],\n        'category_3_C': ['mean'],\n        'merchant_id': ['nunique'],\n        'purchase_amount_new': ['sum', 'mean', 'max', 'min', 'std'],\n        'installments': ['sum', 'mean', 'max', 'min', 'std'],\n        'purchase_date': [np.ptp],\n        'month_lag': ['min', 'max']\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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"709b97b711cd68221946fad436f5181bac62b13b"},"cell_type":"code","source":"###### Aggregate transaction function on the historical transaction ######\n\nimport gc\nmerch_hist = aggregate_transactions(df_historical_transactions, prefix='hist_')\n\ndel df_historical_transactions\ngc.collect()\ndf_train = pd.merge(df_train, merch_hist, on='card_id',how='left')\ndf_test = pd.merge(df_test, merch_hist, on='card_id',how='left')\n\ndel merch_hist\ngc.collect()\ndf_train.head()\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"e1eaf20a6401181371aa37c00bf2ef851b101439"},"cell_type":"markdown","source":"* Similar to the historical transaction dataset, the categorical variables from the new merchant dataset are also converted with the below code snippet with the help of **get_dummies** function from the pandas library\n\n* Since there are only 2 levels in **authorized flag** and **category_1** , henceforth they have been mapped to binary values"},{"metadata":{"trusted":true,"_uuid":"91fc0bc9bb78c59d4b67072273c58c80a9efbfdd"},"cell_type":"code","source":"df_new_merchant_transactions = pd.get_dummies(df_new_merchant_transactions, columns=['category_2', 'category_3'])\ndf_new_merchant_transactions['authorized_flag'] = df_new_merchant_transactions['authorized_flag'].map({'Y': 1, 'N': 0})\ndf_new_merchant_transactions['category_1'] = df_new_merchant_transactions['category_1'].map({'Y': 1, 'N': 0})\n\ndf_new_merchant_transactions.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"61c3dd35607a7c47c41afa61cb4d9769dd964aa2"},"cell_type":"code","source":"######Aggregate transaction function on the new merchant transaction ######\n\nmerch_new = aggregate_transactions(df_new_merchant_transactions, prefix='new_')\ndel df_new_merchant_transactions\ngc.collect()\ndf_train = pd.merge(df_train, merch_new, on='card_id',how='left')\ndf_test = pd.merge(df_test, merch_new, on='card_id',how='left')\n\ndel merch_new\ngc.collect()\ndf_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"c21cb1f6e6bb7b63d5b56a42f7d389d99871af19"},"cell_type":"code","source":"###### Dropping 3 columns ######\n\ntarget = df_train['target']\ndrops = ['card_id', 'first_active_month', 'target']\nuse_cols = [c for c in df_train.columns if c not in drops]\nfeatures = list(df_train[use_cols].columns)\ndf_train[features].head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"282f55c18c6addab664eaa3e084ed451a5ca6f8e","scrolled":true},"cell_type":"code","source":"print(df_train[features].shape)\nprint(df_test[features].shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b345f504bc78590d5f9b744cdb5c660ff312ded4"},"cell_type":"code","source":"df_train.corr()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8ea1548059259f47c2506cd98613ad98d2edd41b"},"cell_type":"markdown","source":"Cross-validation is a resampling procedure used to evaluate machine learning models on a limited data sample.\n\nThe general procedure is as follows:\n1. Shuffle the dataset randomly.\n2. Split the dataset into k groups\n3. For each unique group:\n    1. Take the group as a hold out or test data set\n    2. Take the remaining groups as a training data set\n    3. Fit a model on the training set and evaluate it on the test set\n4. Retain the evaluation score and discard the model\n5. Summarize the skill of the model using the sample of model evaluation scores\n\n\nReferences: https://machinelearningmastery.com/k-fold-cross-validation/"},{"metadata":{"trusted":true,"_uuid":"859bbca03cef0ad4929ee7c7ed055e4cff1f66eb"},"cell_type":"code","source":"#### Utilizing KFold Cross Validator ####\n\nfrom sklearn.model_selection import KFold","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"231c4bb475defee64da912a6b8df4f7106fce279"},"cell_type":"markdown","source":"Light GBM is a gradient boosting framework that uses tree based learning algorithm.\n\nLight GBM grows tree vertically while other algorithm grows trees horizontally meaning that Light GBM grows tree leaf-wise while other algorithm grows level-wise. It will choose the leaf with max delta loss to grow. When growing the same leaf, Leaf-wise algorithm can reduce more loss than a level-wise algorithm.\n\nLight GBM works this way\n![image.png](attachment:image.png)\n\nOther algorithms works this way\n![image.png](attachment:image.png)\n\n\nReferences : https://medium.com/@pushkarmandot/https-medium-com-pushkarmandot-what-is-lightgbm-how-to-implement-it-how-to-fine-tune-the-parameters-60347819b7fc\n\n","attachments":{"image.png":{"image/png":"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"}}},{"metadata":{"trusted":true,"_uuid":"c390df670bdf85404511e24c21bc93dce03aa43c"},"cell_type":"code","source":"###LGB model detals for different parameters referenced from  the below notebook\n####https://www.kaggle.com/peterhurford/you-re-going-to-want-more-categories-lb-3-737\n\nparam = {'num_leaves': 50,\n         'min_data_in_leaf': 30, \n         'objective':'regression',\n         'max_depth': -1,\n         'learning_rate': 0.005,\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\n################# 5  fold cross validation #################\n\n\n### Splitting the dataset into 5 folds for validation\nfolds = KFold(n_splits=5, shuffle=True, random_state=15)\noof_5 = np.zeros(len(df_train))\npredictions = np.zeros(len(df_test))\n\n\n\nfor fold_, (trn_idx, val_idx) in enumerate(folds.split(df_train.values, target.values)):\n    print('-')\n    print(\"Fold {}\".format(fold_ + 1))\n    trn_data = lgb.Dataset(df_train.iloc[trn_idx][features], label=target.iloc[trn_idx])\n    val_data = lgb.Dataset(df_train.iloc[val_idx][features], label=target.iloc[val_idx])\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=100)\n    oof_5[val_idx] = clf.predict(df_train.iloc[val_idx][features], num_iteration=clf.best_iteration)\n    predictions += clf.predict(df_test[features], num_iteration=clf.best_iteration) / folds.n_splits","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"09fe8137e8a5bceca746525c3b0373e850acc3d4"},"cell_type":"markdown","source":"**Calculating the mean squared error with the help light gradient booster model**"},{"metadata":{"trusted":true,"_uuid":"8fc4415470849eec828438b238243eee377e8459"},"cell_type":"code","source":"print('5 Fold Cross Validation - lgb - ', np.sqrt(mean_squared_error(oof_5, target)))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":false,"_uuid":"d7d9b4649fdd56d88d4735f9207753b8b3c15f50"},"cell_type":"code","source":"###LGB model detals for different parameters referenced from  the below notebook\n####https://www.kaggle.com/peterhurford/you-re-going-to-want-more-categories-lb-3-737\n\nparam = {'num_leaves': 50,\n         'min_data_in_leaf': 30, \n         'objective':'regression',\n         'max_depth': -1,\n         'learning_rate': 0.005,\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\n\n\n################# 10  fold cross validation #################\n\n\n\n### Splitting the dataset into 10 folds for validation\nfolds = KFold(n_splits=10, shuffle=True, random_state=15)\noof_10 = np.zeros(len(df_train))\npredictions = np.zeros(len(df_test))\n\n\n\nfor fold_, (trn_idx, val_idx) in enumerate(folds.split(df_train.values, target.values)):\n    print('-')\n    print(\"Fold {}\".format(fold_ + 1))\n    trn_data = lgb.Dataset(df_train.iloc[trn_idx][features], label=target.iloc[trn_idx])\n    val_data = lgb.Dataset(df_train.iloc[val_idx][features], label=target.iloc[val_idx])\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=100)\n    oof_10[val_idx] = clf.predict(df_train.iloc[val_idx][features], num_iteration=clf.best_iteration)\n    predictions += clf.predict(df_test[features], num_iteration=clf.best_iteration) / folds.n_splits","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"54899ee27ef2807d4111c11b9290c888ed6df041"},"cell_type":"code","source":"print('10 Fold Cross Validation - lgb - ', np.sqrt(mean_squared_error(oof_10, target)))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2c1bd3d0600a0a1c3a8501ae7a0b633c5d9ca8a9"},"cell_type":"code","source":"sub_df = pd.read_csv('../input/sample_submission.csv')\nsub_df[\"target\"] =  predictions #0.5 * predictions_lgb + 0.5 * predictions_xgb\nsub_df.to_csv(\"submission.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":true,"_uuid":"425ce733fad63b005bbef571fbb7b5ae8a7e47bd"},"cell_type":"code","source":"sub_df.tail(5)","execution_count":null,"outputs":[]}],"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}