{"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":30804,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Data Preprocessing","metadata":{}},{"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/jane-street-real-time-market-data-forecasting/lags.parquet/date_id=0/part-0.parquet'):\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},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\n\n# Path to the .parquet file\nfile_path = \"/kaggle/input/jane-street-real-time-market-data-forecasting/train.parquet/partition_id=0/part-0.parquet\"\n\n# Read the .parquet file into a DataFrame\ndata = pd.read_parquet(file_path)\ndata_no7 = data.drop('responder_7',axis=1)\ndata_no7= data_no7.drop('responder_8',axis=1)\n\n# Convert the DataFrame to a NumPy array\ndata_np = data.to_numpy()\n\n# Check the shape and content of the NumPy array\n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-06T14:04:47.353889Z","iopub.execute_input":"2024-12-06T14:04:47.354711Z","iopub.status.idle":"2024-12-06T14:04:50.038027Z","shell.execute_reply.started":"2024-12-06T14:04:47.354651Z","shell.execute_reply":"2024-12-06T14:04:50.036280Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"data_no7.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-06T14:05:14.852507Z","iopub.execute_input":"2024-12-06T14:05:14.854100Z","iopub.status.idle":"2024-12-06T14:05:14.886586Z","shell.execute_reply.started":"2024-12-06T14:05:14.854040Z","shell.execute_reply":"2024-12-06T14:05:14.884587Z"}},"outputs":[],"execution_count":null}]}