{"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":"2022-08-01T22:33:03.557489Z","iopub.execute_input":"2022-08-01T22:33:03.558064Z","iopub.status.idle":"2022-08-01T22:33:03.565542Z","shell.execute_reply.started":"2022-08-01T22:33:03.558032Z","shell.execute_reply":"2022-08-01T22:33:03.564607Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# The Pandas Profiling lib can be very helpful to do initial explorations. ","metadata":{}},{"cell_type":"markdown","source":"## We just must be careful because it doesn't handle well large datasets (even with large amounts of memory).\n## There is a way around, though, just configure it by parts, separating interactions from missing and correlations, for example. It can be pretty handy!","metadata":{}},{"cell_type":"code","source":"from pandas_profiling import ProfileReport","metadata":{"execution":{"iopub.status.busy":"2022-08-01T22:33:03.566978Z","iopub.execute_input":"2022-08-01T22:33:03.567603Z","iopub.status.idle":"2022-08-01T22:33:03.575716Z","shell.execute_reply.started":"2022-08-01T22:33:03.567569Z","shell.execute_reply":"2022-08-01T22:33:03.574781Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"API and documentation: https://pandas-profiling.ydata.ai/docs/master/index.html","metadata":{}},{"cell_type":"code","source":"df = pd.read_csv('../input/tabular-playground-series-aug-2022/train.csv',index_col='id')","metadata":{"execution":{"iopub.status.busy":"2022-08-01T23:06:33.592565Z","iopub.execute_input":"2022-08-01T23:06:33.593079Z","iopub.status.idle":"2022-08-01T23:06:33.716320Z","shell.execute_reply.started":"2022-08-01T23:06:33.593041Z","shell.execute_reply":"2022-08-01T23:06:33.715347Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Disable samples, correlations, missing diagrams and duplicates at once\nr = ProfileReport(df,\n    samples=None,\n#     correlations=None,\ncorrelations={\"pearson\": {\"calculate\": True, \"threshold\": 0.8},\n              \"spearman\": {\"calculate\": False},\n              \"kendall\": {\"calculate\": False},\n              \"phi_k\": {\"calculate\": False},\n              \"cramers\": {\"calculate\": True}},                  \n#     missing_diagrams=None,\nmissing_diagrams={\n        \"bar\":True,\n        \"matrix\":True,\n        \"heatmap\": False,\n        \"dendrogram\": False,\n    },\n    duplicates=None,\n    interactions=None,\n)","metadata":{"execution":{"iopub.status.busy":"2022-08-01T23:06:35.603325Z","iopub.execute_input":"2022-08-01T23:06:35.603946Z","iopub.status.idle":"2022-08-01T23:06:35.616895Z","shell.execute_reply.started":"2022-08-01T23:06:35.603913Z","shell.execute_reply":"2022-08-01T23:06:35.615736Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"r.to_notebook_iframe()\n# the toggle details button reveals some more statistics","metadata":{"execution":{"iopub.status.busy":"2022-08-01T23:07:23.462519Z","iopub.execute_input":"2022-08-01T23:07:23.462895Z","iopub.status.idle":"2022-08-01T23:07:23.509018Z","shell.execute_reply.started":"2022-08-01T23:07:23.462866Z","shell.execute_reply":"2022-08-01T23:07:23.507857Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# THe Alerts section shows highly correlated features, high cardinality and missing values","metadata":{"execution":{"iopub.status.busy":"2022-08-01T23:09:18.071670Z","iopub.execute_input":"2022-08-01T23:09:18.072532Z","iopub.status.idle":"2022-08-01T23:09:18.076746Z","shell.execute_reply.started":"2022-08-01T23:09:18.072491Z","shell.execute_reply":"2022-08-01T23:09:18.075746Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}