{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport seaborn as sns","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/talkingdata-adtracking-fraud-detection/train.csv', skiprows=150000000, nrows=50000000)\ntrain_count = len(train)\n\npred = pd.read_csv('/kaggle/input/talkingdata-adtracking-fraud-detection/test.csv')\npred_id = pred['click_id']\npred = pred.drop(['click_id'], axis=1)\n\ndf = pd.concat([train, pred])\ndf.isnull().sum()\n\nprint(\"Train Samples:\",len(train))\nprint(\"Eval Samples:\",len(pred))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}