{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"raw","source":"","metadata":{}},{"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\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 read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_kg_hide-output":true,"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import gc\nimport os\nimport joblib\nimport numpy as np\nimport pandas as pd\nfrom xgboost import XGBClassifier\nfrom catboost import CatBoostClassifier\nfrom lightgbm import LGBMClassifier\nfrom sklearn.svm import SVC\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.model_selection import KFold\nfrom imblearn.over_sampling import ADASYN","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = [pd.read_csv(f'../input/data-preparation/train{i}.csv') for i in range(1,8)]\ntrain = pd.concat(train)\ntrain = train[train['target']!=-1]\ntrain.reset_index(inplace = True, drop = True)\ntrain.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.target.value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ada = ADASYN(sampling_strategy='minority', random_state=420, n_neighbors=5)\nFEATURES = [i for i in train.columns if i not in ['id', 'target']]\nX_gen, y_gen = ada.fit_resample(train[FEATURES], train['target'])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"new_train = pd.concat([X_gen, y_gen], axis=1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.ensemble import VotingClassifier\n\nmodel_lgbm = LGBMClassifier(n_estimators = 40000)\nmodel_cat = CatBoostClassifier(iterations=25, learning_rate=0.5)\nmodel_xgb = XGBClassifier()\nmodel_rf = RandomForestClassifier()\n\n#model = VotingClassifier(estimators=[('lgbm', model_lgbm), ('cat', model_cat),('xgb',model_xgb),(\"rf\",model_rf)], voting='soft')\n# model.fit(X_train,y_train)\n# model.score(X_test,y_test)\n\n\nFEATURES = [i for i in new_train.columns if i not in ['target']]\nskf = KFold(n_splits = 5, shuffle = True, random_state = 42)\noof = np.zeros((len(new_train),))\npredictions = []\ntest_indexs = []\nfor fold,(train_idx, valid_idx) in enumerate(skf.split(new_train, new_train['target'] )):\n    X_train = new_train.loc[train_idx, FEATURES]\n    y_train = new_train.loc[train_idx, 'target']\n    X_val = new_train.loc[valid_idx, FEATURES]\n    y_val = new_train.loc[valid_idx, 'target']\n    #model = model)  \n    model_lgbm.fit(X_train,y_train,eval_set=[(X_val,y_val)])\n    model_cat.fit(X_train,y_train,eval_set=[(X_val,y_val)])\n    model_xgb.fit(X_train,y_train,eval_set=[(X_val,y_val)])\n    #model_rf.fit(X_train,y_train,eval_set=[(X_val,y_val)])\n    \n    joblib.dump(model_lgbm,\"LGBM\"+'_'+str(fold)+'.pkl')\n    joblib.dump(model_cat,\"CAT\"+'_'+str(fold)+'.pkl')\n    joblib.dump(model_xgb,\"XGB\"+'_'+str(fold)+'.pkl')\n    #joblib.dump(model_rf,\"RF\"+'_'+str(fold)+'.pkl')\n\n    for j, model in enumerate([model_lgbm, model_cat, model_xgb]):\n        preds = []\n        for i in range(1,81):\n            test = pd.read_csv(f'../input/g2net-prepare-features/test{i}.csv')\n            preds += [i[1] for i in model.predict_proba(test[FEATURES])]\n            if(j == 0):\n                test_indexs += test['id'].tolist()\n            del test\n            gc.collect()\n        predictions.append(np.array(preds))\n        del preds\n        gc.collect()\n\npredictions = np.average(predictions, axis = 0)\nsub = pd.DataFrame(list(zip(test_indexs, predictions)), columns = ['id','target'])\nsub = sub.groupby('id').mean().reset_index()\nsub.to_csv('submission.csv', index = False)\nsub.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}