{"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":84493,"databundleVersionId":9871156,"sourceType":"competition"}],"dockerImageVersionId":30786,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import pandas as pd\n\n# Replace 'your_file.parquet' with the path to your Parquet file\ndf = pd.read_parquet('/kaggle/input/jane-street-real-time-market-data-forecasting/train.parquet/partition_id=0/part-0.parquet')\npd.set_option('display.max_columns', None)\n# Display the first few rows\ndf[:100].to_csv('output_head.csv', index=False) ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-04T10:44:44.365291Z","iopub.execute_input":"2024-11-04T10:44:44.365764Z","iopub.status.idle":"2024-11-04T10:44:45.658467Z","shell.execute_reply.started":"2024-11-04T10:44:44.365719Z","shell.execute_reply":"2024-11-04T10:44:45.657312Z"}},"outputs":[],"execution_count":19},{"cell_type":"code","source":"empty_count = df['feature_43'].isna().sum()\nempty_count","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-04T10:30:24.510585Z","iopub.execute_input":"2024-11-04T10:30:24.511069Z","iopub.status.idle":"2024-11-04T10:30:24.522917Z","shell.execute_reply.started":"2024-11-04T10:30:24.511023Z","shell.execute_reply":"2024-11-04T10:30:24.521677Z"}},"outputs":[{"execution_count":17,"output_type":"execute_result","data":{"text/plain":"38328"},"metadata":{}}],"execution_count":17},{"cell_type":"markdown","source":"The whole coloumn is empty, same with feature 1,2,3,4,26,31\n","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}