{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport datetime\nfrom sklearn.preprocessing import MinMaxScaler, Imputer\n\ntrain = pd.read_csv(\"../input/train.csv\")\ntest = pd.read_csv(\"../input/test.csv\")\n\ntrain['first_active_month'] = pd.to_datetime(train['first_active_month'])\ntest['first_active_month'] = pd.to_datetime(test['first_active_month'])\ntrain['elapsed_time'] = (datetime.date(2018, 2, 1) - train['first_active_month'].dt.date).dt.days\ntest['elapsed_time'] = (datetime.date(2018, 2, 1) - test['first_active_month'].dt.date).dt.days\n\ntarget = train['target']\ntrain = train.drop(['target', 'first_active_month'], axis=1)\ntest = test.drop('first_active_month', axis=1)\n\nimputer = Imputer(strategy='median')\nscaler = MinMaxScaler(feature_range=(0, 1))\ncard_ids = test['card_id'].values\ntrain = train.drop('card_id', axis= 1)\ntest = test.drop('card_id', axis = 1)\n# Fit on the training data\nimputer.fit(train)\n\n# Transform both training and testing data\ntrain = imputer.transform(train)\ntest = imputer.transform(test)\n\n# Repeat with the scaler\nscaler.fit(train)\ntrain = scaler.transform(train)\ntest = scaler.transform(test)\n\nimport lightgbm as lgb\nfrom sklearn.model_selection import train_test_split\n\n\ntrain = pd.DataFrame(train)\ntest = pd.DataFrame(test)\n\ntrain.info()\n\ntrain.head()\n\ntest.head()\n\n\n\ntrain[[0, 1, 2]] = train[[0, 1, 2]].astype('category')\ntest[[0, 1, 2]] = test[[0, 1, 2]].astype('category')\n\ntrain.info()\n\nX_tr, X_val, y_tr, y_val = train_test_split(train, target)\n\n\n\nlgb_train = lgb.Dataset(X_tr, y_tr)\nlgb_val = lgb.Dataset(X_val, y_val)\n\nparams ={\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': 0,\n        'seed':int(2**1),\n        'bagging_seed':int(2**1),\n        'drop_seed':int(2**1)\n        }\n\nlgbm_model = lgb.train(params, train_set = lgb_train, valid_sets = lgb_val)\n\n\n\npredictions = lgbm_model.predict(test)\n\n# Writing output to file\nsubm = pd.DataFrame()\nsubm['card_id'] = card_ids\nsubm['target'] = predictions\nsubm.to_csv('subLGBM.csv', index = False)","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"subm.head()","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}