{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\n\nimport matplotlib.pyplot as plt\nimport matplotlib\n%matplotlib inline\n\nimport seaborn as sns\nsns.set()\n\nimport lightgbm as lgb\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import mean_squared_error","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"../input/gstoreextractedjson/train_cleaned.csv\", \n                    dtype={\"fullVisitorId\": \"str\", \"sessionId\": \"str\"}, \n                    parse_dates=[\"date\"])\ntest = pd.read_csv(\"../input/gstoreextractedjson/test_cleaned.csv\", \n                    dtype={\"fullVisitorId\": \"str\", \"sessionId\": \"str\"}, \n                    parse_dates=[\"date\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"9deef1ca601366382c3644c1ad436877a884544b"},"cell_type":"code","source":"for i in train.columns:\n    if train[str(i)].dtypes == object:\n        print(i)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"c9360fa6f90794b84080295cabf5aa7950fab6b4"},"cell_type":"code","source":"sum(train['totals.pageviews'] == 1), sum(train['totals.transactionRevenue'][train['totals.pageviews'] == 1]) ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"59ab4d815e14b8c17433a7f7ee9ec479a653ef27"},"cell_type":"code","source":"sum(train['totals.bounces'] == 1), sum(train['totals.transactionRevenue'][train['totals.bounces'] == 1]) ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f8065bc4b6b55d8c5280a3173e83a168af567b82"},"cell_type":"code","source":"idx_tr = train['totals.pageviews'] == 1\ntrain['totals.bounces'][idx_tr] = 1\nidx_t = test['totals.pageviews'] == 1\ntest['totals.bounces'][idx_t] = 1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"af267f9b4b49167702eb735ddd951d4b2776abdf"},"cell_type":"code","source":"train['ratioPageHits'] = train['totals.pageviews']/train['totals.hits']\ntest['ratioPageHits'] = test['totals.pageviews']/test['totals.hits']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"26b2d54f3086e646be97eb2ddc1ac561c39ab482"},"cell_type":"code","source":"train['visitStartTime'] = pd.to_datetime(train['visitStartTime'], unit='s')\ntest['visitStartTime'] = pd.to_datetime(test['visitStartTime'], unit='s')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"353b2041dfbc2016258183efa78ca0eae226da5e"},"cell_type":"code","source":"train[\"weekday\"] = train[\"date\"].dt.dayofweek\ntest[\"weekday\"] = test[\"date\"].dt.dayofweek\ntrain[\"month\"] = train[\"date\"].dt.month\ntest[\"month\"] = test[\"date\"].dt.month\ntrain['sessionHourOfDay'] = train['visitStartTime'].dt.hour\ntest['sessionHourOfDay'] = test['visitStartTime'].dt.hour","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ae95e8c2a5a3f7513656a8645f1d62b36378c509"},"cell_type":"code","source":"set(train.columns).difference(set(test.columns))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ba9f4433cf37178001ebe3a79fc4b7d605a05827"},"cell_type":"code","source":"# split the train dataset into train and valid based on time\n'''\nX_train = train[train[\"date\"]<=pd.Timestamp(2017,5,31)]\nX_val = train[train[\"date\"]>pd.Timestamp(2017,5,31)]\ny_train = np.log1p(X_train[\"totals.transactionRevenue\"].values)\ny_val = np.log1p(X_val[\"totals.transactionRevenue\"].values)\n'''","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"14f7937964dbc8cc5eae8fc1d215dc75bfd8ac7d"},"cell_type":"code","source":"not_train_cl = [\n    'fullVisitorId',\n    'sessionId', \n    'visitId',\n    'visitStartTime',\n    'totals.transactionRevenue',\n    'transaction',\n    'date'\n]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"23611e68fab1484010adc531217fb0951096f2fb"},"cell_type":"code","source":"features = list(set(train.columns).difference(set(not_train_cl)))\nfeatures","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d1327afe6a7e2cbdb016dfe780986ac378b64089"},"cell_type":"code","source":"target = train.loc[:,'totals.transactionRevenue'].values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"42b29d6bc9bfbcdaf18da6364bc85f9c6170f7db"},"cell_type":"code","source":"X_train, X_val, y_train, y_val = train_test_split(train[features], target, test_size=0.2, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a8a050bb3aa6652a1e325a28c34f5c485b94c942"},"cell_type":"code","source":"def rmse(y_true, y_pred):\n    return round(np.sqrt(mean_squared_error(y_true, y_pred)), 5)\n\ndef run_lgb(X_train, y_train, X_val, y_val, X_test):\n    data_train = lgb.Dataset(X_train, label=y_train)\n    data_val = lgb.Dataset(X_val, label=y_val)\n    param = {\n         'objective':'regression',\n         'metric': 'rmse',\n         'learning_rate':0.005,\n         'num_leaves':40,\n         'min_data_in_leaf':150,\n         'max_depth':10,\n         'bagging_fraction':0.6,\n         'feature_fraction':0.6,\n         'bagging_frequency': 6,\n         'verbosity':-1,\n         'random_state': 42}\n    model = lgb.train(param, data_train, valid_sets=[data_train, data_val], num_boost_round=5000, early_stopping_rounds=100,\n                  verbose_eval=200)\n    pred_y_test = model.predict(X_test, num_iteration=model.best_iteration)\n    \n    return pred_y_test, model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7d53090e78df45e6ec0a7dfd7c7e6b53c12813f4"},"cell_type":"code","source":"pred_test, model = run_lgb(X_train, y_train, X_val, y_val, test[features])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"5f5147b6c1ec3ea892f95ab5b9c1bb295a5fc467"},"cell_type":"code","source":"pred_test[pred_test<0]=0\nsubmission = test[['fullVisitorId']].copy()\nsubmission.loc[:,'PredictedLogRevenue'] = pred_test\ngrouped_test = submission[['fullVisitorId', 'PredictedLogRevenue']].groupby('fullVisitorId').sum().reset_index()\ngrouped_test.to_csv(\"submit.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"531c2d4623df431c34af33751066c82cda44e602"},"cell_type":"code","source":"","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}