{"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":9870407,"sourceType":"competition"}],"dockerImageVersionId":30786,"isInternetEnabled":true,"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":"2024-10-16T20:33:22.053969Z","iopub.execute_input":"2024-10-16T20:33:22.054409Z","iopub.status.idle":"2024-10-16T20:33:23.650829Z","shell.execute_reply.started":"2024-10-16T20:33:22.054363Z","shell.execute_reply":"2024-10-16T20:33:23.649393Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# numpy\nimport numpy as np\n\n# pandas stuff\nimport pandas as pd\npd.set_option('display.max_rows', None)\npd.set_option('display.max_columns', None)\n\n# plotting stuff\nfrom pandas.plotting import lag_plot\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport plotly.express as px\nimport plotly.graph_objects as go\ncolorMap = sns.light_palette(\"blue\", as_cmap=True)\n#plt.rcParams.update({'font.size': 12})\n\n\n# install dabl\n!pip install dabl > /dev/null\nimport dabl\n# install datatable\n!pip install datatable > /dev/null\nimport datatable as dt\n\n# misc\nimport missingno as msno\n\n# system\nimport warnings\nwarnings.filterwarnings('ignore')\n# for the image import\nimport os\nfrom IPython.display import Image\n# garbage collector to keep RAM in check\nimport gc  ","metadata":{"execution":{"iopub.status.busy":"2024-10-16T20:35:11.620494Z","iopub.execute_input":"2024-10-16T20:35:11.621127Z","iopub.status.idle":"2024-10-16T20:40:43.485884Z","shell.execute_reply.started":"2024-10-16T20:35:11.621081Z","shell.execute_reply":"2024-10-16T20:40:43.484787Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!wc -l ../input/jane-street-market-prediction/train.csv","metadata":{"execution":{"iopub.status.busy":"2024-10-16T21:03:39.998660Z","iopub.execute_input":"2024-10-16T21:03:39.999821Z","iopub.status.idle":"2024-10-16T21:03:41.169045Z","shell.execute_reply.started":"2024-10-16T21:03:39.999766Z","shell.execute_reply":"2024-10-16T21:03:41.167688Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n\ntrain_data_datatable = dt.fread('../input/jane-street-market-prediction/train.csv')","metadata":{"execution":{"iopub.status.busy":"2024-10-16T21:03:43.991186Z","iopub.execute_input":"2024-10-16T21:03:43.991704Z","iopub.status.idle":"2024-10-16T21:03:44.576469Z","shell.execute_reply.started":"2024-10-16T21:03:43.991652Z","shell.execute_reply":"2024-10-16T21:03:44.575325Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n\ntrain_data = train_data_datatable.to_pandas()","metadata":{"execution":{"iopub.status.busy":"2024-10-16T21:04:14.134465Z","iopub.execute_input":"2024-10-16T21:04:14.134919Z","iopub.status.idle":"2024-10-16T21:04:14.159712Z","shell.execute_reply.started":"2024-10-16T21:04:14.134877Z","shell.execute_reply":"2024-10-16T21:04:14.158520Z"},"trusted":true},"execution_count":null,"outputs":[]}]}