{"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\nos.listdir('/kaggle/input/coleridgeinitiative-show-us-the-data')\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":{},"cell_type":"markdown","source":"# 1. Data Exploration"},{"metadata":{"trusted":true},"cell_type":"code","source":"traindf=pd.read_csv('/kaggle/input/coleridgeinitiative-show-us-the-data/train.csv')\nprint(traindf.shape)\ntraindf.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Columns description\n1. id (publication id) - note that there are multiple rows for some training documents, indicating multiple mentioned datasets\n1. pub_title -  publication title (a small number of publications have the same title)\n1. dataset_title - the title of the dataset that is mentioned within the publication\n1. dataset_label - a portion of the text that indicates the dataset\n1. cleaned_label - the dataset_label, as passed through the clean_text function from the Evaluation page\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub_df=pd.read_csv('/kaggle/input/coleridgeinitiative-show-us-the-data/sample_submission.csv')\nprint(sample_sub_df.shape)\nsample_sub_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(traindf['dataset_title'].unique())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(traindf['dataset_label'].unique())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(traindf['cleaned_label'].unique())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"cleaned_label and dataset_label values looks similar and number of unique values are same too, cross verifying it"},{"metadata":{"trusted":true},"cell_type":"code","source":"traindf['cleaned_label'].equals(traindf['dataset_label'].str.lower())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"cleaned_label and dataset_label values are not same"},{"metadata":{},"cell_type":"markdown","source":"Picking up couple of json file and analyzing them"},{"metadata":{"trusted":true},"cell_type":"code","source":"import json\nwith open('../input/coleridgeinitiative-show-us-the-data/train/0007f880-0a9b-492d-9a58-76eb0b0e0bd7.json') as f:\n    sample = json.load(f)\n    \n    \njsondf= pd.json_normalize(sample)\njsondf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with open('../input/coleridgeinitiative-show-us-the-data/train/0008656f-0ba2-4632-8602-3017b44c2e90.json') as f:\n    sample = json.load(f)\n    \n    \njsondf= pd.json_normalize(sample)\njsondf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}