{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","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":30786,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"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","trusted":true},"outputs":[],"execution_count":null},{"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# train.isnull().sum())\n# test.isnull().sum()\n# train.describe()\n# train['Class'].value_counts()\ntarget = train.pop('Class')\n\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,random_state=0)\n# X_tr.shape,X_val.shape,y_tr.shape,y_val.shape\n\nfrom sklearn.ensemble import RandomForestClassifier\nrf = RandomForestClassifier(class_weight='balanced',max_depth=3,random_state=0)\nrf.fit(X_tr,y_tr)\npred = rf.predict_proba(X_val)\n\n# 평가: roc-auc 평가지표\nfrom sklearn.metrics import roc_auc_score\nscore = roc_auc_score(y_val,pred[:,1])\nprint(score)\n\npred = rf.predict_proba(test)\nsumbit = pd.DataFrame({'id':test['id'],'Class':pred[:,1]})\nsumbit.to_csv('result.csv',index=False)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-24T12:25:34.519984Z","iopub.execute_input":"2024-11-24T12:25:34.520355Z","iopub.status.idle":"2024-11-24T12:26:05.850610Z","shell.execute_reply.started":"2024-11-24T12:25:34.520323Z","shell.execute_reply":"2024-11-24T12:26:05.849415Z"}},"outputs":[],"execution_count":null}]}