{"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":"2022-08-17T13:05:56.224142Z","iopub.execute_input":"2022-08-17T13:05:56.225595Z","iopub.status.idle":"2022-08-17T13:05:56.262649Z","shell.execute_reply.started":"2022-08-17T13:05:56.225477Z","shell.execute_reply":"2022-08-17T13:05:56.261398Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 1 Here we are Going to do EDA on the whole dataset of nyra_2019_complete set","metadata":{}},{"cell_type":"markdown","source":"# Using Simple two lines by means of pandas Profiling, same can be done using dataprep too, please do explore and let me know about it.","metadata":{}},{"cell_type":"code","source":"!pip install pandas-profiling","metadata":{"execution":{"iopub.status.busy":"2022-08-17T13:06:55.329974Z","iopub.execute_input":"2022-08-17T13:06:55.330461Z","iopub.status.idle":"2022-08-17T13:07:09.038760Z","shell.execute_reply.started":"2022-08-17T13:06:55.330422Z","shell.execute_reply":"2022-08-17T13:07:09.037098Z"},"_kg_hide-input":true,"_kg_hide-output":true,"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas_profiling as pp","metadata":{"execution":{"iopub.status.busy":"2022-08-17T13:09:12.776492Z","iopub.execute_input":"2022-08-17T13:09:12.777318Z","iopub.status.idle":"2022-08-17T13:09:15.607942Z","shell.execute_reply.started":"2022-08-17T13:09:12.777140Z","shell.execute_reply":"2022-08-17T13:09:15.606173Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = pd.read_csv('/kaggle/input/big-data-derby-2022/nyra_tracking_table.csv')","metadata":{"execution":{"iopub.status.busy":"2022-08-17T13:12:44.833620Z","iopub.execute_input":"2022-08-17T13:12:44.834210Z","iopub.status.idle":"2022-08-17T13:12:51.966649Z","shell.execute_reply.started":"2022-08-17T13:12:44.834159Z","shell.execute_reply":"2022-08-17T13:12:51.965035Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"profile = pp.ProfileReport(df)\n#profile.to_file(\"output.html\")","metadata":{"execution":{"iopub.status.busy":"2022-08-17T13:13:08.386002Z","iopub.execute_input":"2022-08-17T13:13:08.386414Z","iopub.status.idle":"2022-08-17T13:13:08.394410Z","shell.execute_reply.started":"2022-08-17T13:13:08.386380Z","shell.execute_reply":"2022-08-17T13:13:08.393105Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"profile","metadata":{"execution":{"iopub.status.busy":"2022-08-17T13:13:17.674112Z","iopub.execute_input":"2022-08-17T13:13:17.674548Z","iopub.status.idle":"2022-08-17T13:15:53.721730Z","shell.execute_reply.started":"2022-08-17T13:13:17.674513Z","shell.execute_reply":"2022-08-17T13:15:53.720141Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Her we can see the complete set EDA, Some how i feel Dataprep looks much better than this,....\n# Let me know the feedback ,,,this is work in progress","metadata":{}},{"cell_type":"markdown","source":"","metadata":{}}]}