{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":80687,"databundleVersionId":8672016,"sourceType":"competition"}],"dockerImageVersionId":30698,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"- 이 코드는 완벽하지 않아요\n- roc-auc 평가지표일 때 predict과 predict_proba를 비교해보세요\n- 검증데이터를 사용해보세요!","metadata":{}},{"cell_type":"code","source":"import pandas as pd\ntrain = pd.read_csv(\"/kaggle/input/big-data-analytics-certification-kr-2024-2/train.csv\")\ntest = pd.read_csv(\"/kaggle/input/big-data-analytics-certification-kr-2024-2/test.csv\")\n# display(train.head(5))\n# test.head(5)\n\ntrain['Class'].value_counts() # 0: 170523, 1: 360\ntarget = train.pop('Class')\ntrain.drop('id', axis=1, inplace=True)\nid = test.pop('id')\n# display(test.info())\n\n# Min-Max Scaling\nfrom sklearn.preprocessing import MinMaxScaler\nscaler = MinMaxScaler()\ncols = train.columns\nfor col in cols:\n    train[col] = scaler.fit_transform(train[[col]])\n    test[col] = scaler.transform(test[[col]])\n# display(train.head(5))\n\n# 훈련 \n# 훈련 - 검증 데이터 분류\nfrom sklearn.model_selection import train_test_split\nX_tr, X_val, y_tr, y_val = train_test_split(train, target, test_size=0.2,\n                                           random_state=2024)\nprint(X_tr.shape, X_val.shape, y_tr.shape, y_val.shape)\n\n# 모델훈련\nfrom sklearn.ensemble import RandomForestClassifier\n\nmodel = RandomForestClassifier(random_state=2024)\nmodel.fit(X_tr, y_tr)\n\npred_proba = model.predict_proba(X_val)\npred_proba\nfrom sklearn.metrics import roc_auc_score\nscore = roc_auc_score(y_val, pred_proba[:,1])\nscore\n\ntest_pred = model.predict_proba(test)\npd.DataFrame({\n    'id': id,\n    'Class': test_pred[:,1]\n}).to_csv('submission.csv', index=False)\n\npd.read_csv('submission.csv')","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-05-28T03:53:08.551775Z","iopub.execute_input":"2024-05-28T03:53:08.552186Z","iopub.status.idle":"2024-05-28T03:55:19.180401Z","shell.execute_reply.started":"2024-05-28T03:53:08.552157Z","shell.execute_reply":"2024-05-28T03:55:19.179239Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"execution":{"iopub.status.busy":"2024-05-28T03:25:52.327291Z","iopub.execute_input":"2024-05-28T03:25:52.327698Z","iopub.status.idle":"2024-05-28T03:25:53.382410Z","shell.execute_reply.started":"2024-05-28T03:25:52.327669Z","shell.execute_reply":"2024-05-28T03:25:53.381320Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}