{"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":"2022-08-11T03:44:45.020653Z","iopub.execute_input":"2022-08-11T03:44:45.021127Z","iopub.status.idle":"2022-08-11T03:44:45.056305Z","shell.execute_reply.started":"2022-08-11T03:44:45.021037Z","shell.execute_reply":"2022-08-11T03:44:45.055342Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = pd.read_csv(\"/kaggle/input/nlp-getting-started/train.csv\")","metadata":{"execution":{"iopub.status.busy":"2022-08-11T03:45:45.513737Z","iopub.execute_input":"2022-08-11T03:45:45.515297Z","iopub.status.idle":"2022-08-11T03:45:45.569237Z","shell.execute_reply.started":"2022-08-11T03:45:45.515242Z","shell.execute_reply":"2022-08-11T03:45:45.568080Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install dataprep","metadata":{"execution":{"iopub.status.busy":"2022-08-11T03:47:44.336142Z","iopub.execute_input":"2022-08-11T03:47:44.336665Z","iopub.status.idle":"2022-08-11T03:48:30.215216Z","shell.execute_reply.started":"2022-08-11T03:47:44.336629Z","shell.execute_reply":"2022-08-11T03:48:30.213664Z"},"_kg_hide-input":true,"_kg_hide-output":true,"jupyter":{"source_hidden":true,"outputs_hidden":true},"collapsed":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from dataprep.eda import create_report # Install the required libraries","metadata":{"execution":{"iopub.status.busy":"2022-08-11T03:48:30.218052Z","iopub.execute_input":"2022-08-11T03:48:30.218545Z","iopub.status.idle":"2022-08-11T03:48:33.335271Z","shell.execute_reply.started":"2022-08-11T03:48:30.218494Z","shell.execute_reply":"2022-08-11T03:48:33.334034Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"tweet_eda = create_report(df) # Create a instance for the report ","metadata":{"execution":{"iopub.status.busy":"2022-08-11T03:49:09.505876Z","iopub.execute_input":"2022-08-11T03:49:09.506427Z","iopub.status.idle":"2022-08-11T03:49:14.883240Z","shell.execute_reply.started":"2022-08-11T03:49:09.506387Z","shell.execute_reply":"2022-08-11T03:49:14.882019Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\"Show details\" in the below tab can show different plot, Box,pie,stats and many more just in one single shot\nthere are many libraries like this...\"pandas profilin\",Lux,D-tale, and sweetviz\"","metadata":{}},{"cell_type":"code","source":"tweet_eda # Finally EDA for the whole data set","metadata":{"execution":{"iopub.status.busy":"2022-08-11T03:49:23.126038Z","iopub.execute_input":"2022-08-11T03:49:23.126569Z","iopub.status.idle":"2022-08-11T03:49:23.347757Z","shell.execute_reply.started":"2022-08-11T03:49:23.126525Z","shell.execute_reply":"2022-08-11T03:49:23.345800Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Please let me know your comment and thank you","metadata":{}},{"cell_type":"markdown","source":"","metadata":{}}]}