{"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":30732,"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},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"execution":{"iopub.status.busy":"2024-06-07T05:16:04.259476Z","iopub.execute_input":"2024-06-07T05:16:04.259841Z","iopub.status.idle":"2024-06-07T05:16:11.058268Z","shell.execute_reply.started":"2024-06-07T05:16:04.259810Z","shell.execute_reply":"2024-06-07T05:16:11.057163Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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')\ntrain.head()\ntest.head()\n# train.info()\n# test.info()\ntarget = train.pop('Class')\ntrain = train.drop('id',axis=1)\ntest_id = test.pop('id')\n\n# object컬럼 없음\n# train_test_split\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=2024)\nx_tr.shape,x_val.shape,y_tr.shape,y_val.shape\n\n# 랜덤 포래스트 \nfrom sklearn.ensemble import RandomForestClassifier\nrf = RandomForestClassifier()\nrf.fit(x_tr,y_tr)\npred = rf.predict_proba(x_val)[:,1]\n\n# 평가 라이브러리\nfrom sklearn.metrics import roc_auc_score\nroc_auc_score(y_val,pred)","metadata":{"execution":{"iopub.status.busy":"2024-06-07T05:22:31.409229Z","iopub.execute_input":"2024-06-07T05:22:31.409612Z","iopub.status.idle":"2024-06-07T05:24:48.492805Z","shell.execute_reply.started":"2024-06-07T05:22:31.409583Z","shell.execute_reply":"2024-06-07T05:24:48.491650Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}