{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv(r'/kaggle/input/coleridgeinitiative-show-us-the-data/train.csv')\ntrain.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for i in list(train.columns):\n    print(i, ' ', train[i].nunique())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train[train['Id'] == 'f8b03c87-9d1a-4f20-b76b-cb6c69d447b2']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#pub_title vs Ids\npub_titl_ids = {}\nfor titl in list(train['pub_title'].unique()):\n    if train[train['pub_title']==titl]['Id'].nunique() > 1:\n        pub_titl_ids[titl]= list(set(train[train['pub_title']==titl]['Id']))\n\npub_titl_ids","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#dataset_title vs dataset_label\ntitl_lab = {}\nfor titl in list(train['dataset_title'].unique()):\n    if train[train['dataset_title']==titl]['dataset_label'].nunique() > 1:\n        titl_lab[titl]= list(set(train[train['dataset_title']==titl]['dataset_label']))\n\ntitl_lab","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['dataset_title'].value_counts().nlargest(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['dataset_label'].value_counts().nlargest(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import json \nf = open(r'/kaggle/input/coleridgeinitiative-show-us-the-data/train/f8b03c87-9d1a-4f20-b76b-cb6c69d447b2.json')\njs1 = json.load(f)\n\n#for i in range(len(js1)):\n#    print(i, ' ', js1[i]['section_title'])\nprint(js1)","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}