{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"data = pd.concat([\n       pd.read_csv(\"../input/pageviews/pageviews.csv\", parse_dates=[\"FEC_EVENT\"]),\n       pd.read_csv(\"../input/pageviews_complemento/pageviews_complemento.csv\", parse_dates=[\"FEC_EVENT\"])\n])\ndata","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test = []\nfor c in data.drop([\"USER_ID\", \"FEC_EVENT\"], axis=1).columns:\n    print(\"haciendo\", c)\n    temp = pd.crosstab(data.USER_ID, data[c])\n    temp.columns = [c + \"_\" + str(v) for v in temp.columns]\n    X_test.append(temp.apply(lambda x: x / x.sum(), axis=1))\nX_test = pd.concat(X_test, axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = data[data.FEC_EVENT.dt.month < 10]\nX_train = []\nfor c in data.drop([\"USER_ID\", \"FEC_EVENT\"], axis=1).columns:\n    print(\"haciendo\", c)\n    temp = pd.crosstab(data.USER_ID, data[c])\n    temp.columns = [c + \"_\" + str(v) for v in temp.columns]\n    X_train.append(temp.apply(lambda x: x / x.sum(), axis=1))\nX_train = pd.concat(X_train, axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"features = list(set(X_train.columns).intersection(set(X_test.columns)))\nX_train = X_train[features]\nX_test = X_test[features]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_prev = pd.read_csv(\"../input/conversiones/conversiones.csv\")\ny_train = pd.Series(0, index=X_train.index)\nidx = set(y_prev[y_prev.mes >= 10].USER_ID.unique()).intersection(\n        set(X_train.index))\ny_train.loc[list(idx)] = 1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from lightgbm import LGBMClassifier\nfrom sklearn import model_selection\nfrom sklearn.metrics import roc_auc_score\n\nfi = []\ntest_probs = []\ni = 0\nfor train_idx, valid_idx in model_selection.KFold(n_splits=10, shuffle=True).split(X_train):\n    i += 1\n    Xt = X_train.iloc[train_idx]\n    yt = y_train.loc[X_train.index].iloc[train_idx]\n\n    Xv = X_train.iloc[valid_idx]\n    yv = y_train.loc[X_train.index].iloc[valid_idx]\n\n    learner = LGBMClassifier(n_estimators=10000)\n    learner.fit(Xt, yt,  early_stopping_rounds=10, eval_metric=\"auc\",\n                eval_set=[(Xt, yt), (Xv, yv)])\n    \n    test_probs.append(pd.Series(learner.predict_proba(X_test)[:, -1],\n                                index=X_test.index, name=\"fold_\" + str(i)))\n    fi.append(pd.Series(learner.feature_importances_ / learner.feature_importances_.sum(), index=Xt.columns))\n\ntest_probs = pd.concat(test_probs, axis=1).mean(axis=1)\ntest_probs.index.name=\"USER_ID\"\ntest_probs.name=\"SCORE\"\ntest_probs.to_csv(\"benchmark.zip\", header=True, compression=\"zip\")\nfi = pd.concat(fi, axis=1).mean(axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.listdir(\"./\")","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}