{"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)\nfrom sklearn.model_selection import train_test_split\n# from sklearn.linear_model import LinearRegression\n# from sklearn.ensemble import RandomForestRegressor\nimport catboost\nfrom catboost import CatBoostRegressor\n\nimport pickle \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\ndef analiseModData(df):\n    df.dropna(axis=0, inplace=True)\n    df = df.drop(['Id', 'matchId','matchType', 'matchDuration',\n                  'teamKills', 'rankPoints', 'winPoints','roadKills',\n                  'swimDistance', 'kills', 'killPoints', 'maxPlace'], axis=1)\n    \n    dictValueCounts ={}\n    GroupValueCount = df['groupId'].value_counts()\n    dictValueCounts = dict(zip(GroupValueCount.index.tolist(), GroupValueCount.tolist()))\n    df['groupId'].update(df['groupId'].map(dictValueCounts))   \n    del dictValueCounts, GroupValueCount     \n    return df  \n\ndef linModel(dataTrain):\n    modTrain = analiseModData(dataTrain)\n    (trainData,\n     testData,\n     trainLabel,\n     testLabel) = train_test_split(modTrain.drop('winPlacePerc', axis=1),\n                              modTrain[\"winPlacePerc\"],\n                              test_size=0.3,\n                              random_state=1234126)\n    \n#     linReg = LinearRegression()\n#     rfr = RandomForestRegressor()\n#     rfr.fit(trainData, trainLabel)\n    cbr = CatBoostRegressor()\n    cbr.fit(trainData, trainLabel)\n\n\n#     linReg.fit(trainData, trainLabel)\n    del trainData, trainLabel, testData, testLabel, modTrain  \n    with open(\"pickle_lin_model.pkl\", 'wb') as file:  \n        pickle.dump(cbr, file)\n\n    return cbr\n\n\ndef prdict(test):\n    import pickle\n    testd = analiseModData(test)\n    with open('pickle_lin_model.pkl', 'rb') as file:  \n        pickle_lin_model = pickle.load(file)\n    \n    preds = pickle_lin_model.predict(testd)\n    del testd\n    return preds\ndataTrain = pd.read_csv('../input/pubg-finish-placement-prediction/train_V2.csv')\n# train = pd.read_csv('../input/mytrain/my_train_6670.csv')\ntest = pd.read_csv('../input/pubg-finish-placement-prediction/test_V2.csv')\nid_value = test.Id\nmyModel = linModel(dataTrain)\npreds = prdict(test)\n\nsubmission = pd.DataFrame(\n    {'id': id_value, 'winPlacePerc': preds},\n    columns=['id', 'winPlacePerc'])\ndel id_value, preds, dataTrain, test, myModel\nsubmission.to_csv('submission3.csv', index=False)\n\n    \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":"","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}