{"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":false,"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","execution":{"iopub.status.busy":"2024-05-28T14:42:15.574739Z","iopub.execute_input":"2024-05-28T14:42:15.575685Z","iopub.status.idle":"2024-05-28T14:42:16.030871Z","shell.execute_reply.started":"2024-05-28T14:42:15.575640Z","shell.execute_reply":"2024-05-28T14:42:16.029988Z"},"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\")","metadata":{"execution":{"iopub.status.busy":"2024-05-28T14:42:19.279406Z","iopub.execute_input":"2024-05-28T14:42:19.279833Z","iopub.status.idle":"2024-05-28T14:42:22.164222Z","shell.execute_reply.started":"2024-05-28T14:42:19.279800Z","shell.execute_reply":"2024-05-28T14:42:22.163045Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 분류 : 신용카드 사기 거래 탐지\n# V1~V28 : PCA로 얻은 주성분, Time : 각 거래와 첫 거래 사이의 경과시간, Amount : 거래금액\n# Class : 응답변수(사기거래 1, 정상거래 0)\n\nfrom sklearn.ensemble import RandomForestClassifier\n\n# 입력 특성과 타겟 변수 분리\nX_train = train.drop(['id', 'Class'], axis=1)\ny_train = train['Class']\nX_test = test.drop(['id'], axis=1)\n\n# 모델 학습\nmodel = RandomForestClassifier()\nmodel.fit(X_train, y_train)\n\n# 테스트 데이터에 대한 예측\ny_pred = model.predict(X_test)\n\n# 제출 파일 생성\nsubmission = pd.DataFrame({'id' : test['id'], 'Class' : y_pred})\nsubmission.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2024-05-28T14:42:25.241222Z","iopub.execute_input":"2024-05-28T14:42:25.241602Z","iopub.status.idle":"2024-05-28T14:45:22.135301Z","shell.execute_reply.started":"2024-05-28T14:42:25.241572Z","shell.execute_reply":"2024-05-28T14:45:22.134286Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}