{"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":"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":"2021-12-28T22:16:34.790690Z","iopub.execute_input":"2021-12-28T22:16:34.791026Z","iopub.status.idle":"2021-12-28T22:16:34.802410Z","shell.execute_reply.started":"2021-12-28T22:16:34.790991Z","shell.execute_reply":"2021-12-28T22:16:34.801546Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pathlib\nos.getcwd()\ndf = pd.read_csv('../input/talkingdata-adtracking-fraud-detection/train.csv')\n# pathlib.Path().resolve()\n# pathlib.Path().parent.resolve()\n# pathlib.Path().absolute()\nprint (len(df))\ndf.head()\n","metadata":{"execution":{"iopub.status.busy":"2021-12-28T22:16:38.280685Z","iopub.execute_input":"2021-12-28T22:16:38.281292Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from catboost import CatBoostClassifier   #, Pool\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import roc_auc_score\n\nX = df.drop(columns=[\"is_attributed\", \"click_time\", \"attributed_time\"])\ny = df[\"is_attributed\"]\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.7, random_state=42)\n\ncb = CatBoostClassifier(n_estimators=200,\n                       loss_function=\"Logloss\", eval_metric=\"AUC\",\n                       depth=3, task_type='CPU',\n                       random_state=42,\n                       verbose=200, auto_class_weights=\"Balanced\")\n\ncb.fit(X_train, y_train, cat_features = [\"ip\", \"app\", \"device\", \"os\"], plot=True)","metadata":{"execution":{"iopub.status.busy":"2021-12-28T21:42:18.803499Z","iopub.status.idle":"2021-12-28T21:42:18.803979Z","shell.execute_reply.started":"2021-12-28T21:42:18.803717Z","shell.execute_reply":"2021-12-28T21:42:18.803740Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred = cb.predict(X_test, prediction_type=\"Probability\")\n\nroc_auc_score(y_pred[:, 1], y_test)","metadata":{"execution":{"iopub.status.busy":"2021-12-28T21:42:18.805745Z","iopub.status.idle":"2021-12-28T21:42:18.806064Z","shell.execute_reply.started":"2021-12-28T21:42:18.805900Z","shell.execute_reply":"2021-12-28T21:42:18.805917Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del (df, X_train, X_test, y_train, y_test, X, y)","metadata":{"execution":{"iopub.status.busy":"2021-12-28T21:42:18.807916Z","iopub.status.idle":"2021-12-28T21:42:18.808777Z","shell.execute_reply.started":"2021-12-28T21:42:18.808483Z","shell.execute_reply":"2021-12-28T21:42:18.808513Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample = pd.read_csv(\"/input/talkingdata-adtracking-fraud-detection/sample_submission.csv\")\n\nsample.head()","metadata":{"execution":{"iopub.status.busy":"2021-12-28T21:42:18.810128Z","iopub.status.idle":"2021-12-28T21:42:18.811228Z","shell.execute_reply.started":"2021-12-28T21:42:18.810926Z","shell.execute_reply":"2021-12-28T21:42:18.810958Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test = pd.read_csv(\"/kaggle/input/ad-tracking-fraud-detection/test.csv\")\n\npreds_to_publish = cb.predict(test, prediction_type=\"Probability\")","metadata":{"execution":{"iopub.status.busy":"2021-12-28T21:42:18.812472Z","iopub.status.idle":"2021-12-28T21:42:18.812944Z","shell.execute_reply.started":"2021-12-28T21:42:18.812689Z","shell.execute_reply":"2021-12-28T21:42:18.812714Z"},"trusted":true},"execution_count":null,"outputs":[]}]}