{"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","scrolled":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_csv('../input/coleridgeinitiative-show-us-the-data/train.csv')\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ss = pd.read_csv('../input/coleridgeinitiative-show-us-the-data/sample_submission.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ss","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train[train.Id == '000e04d6-d6ef-442f-b070-4309493221ba'].pub_title","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train[train.Id == '000e04d6-d6ef-442f-b070-4309493221ba']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.Id.describe()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import json\ndef clean_text(txt):\n    return re.sub('[^A-Za-z0-9]+', ' ', str(txt).lower()).strip()\nset_of_data = set()\nfor data_name in train[\"cleaned_label\"]:\n    set_of_data.add(data_name.strip())\nlen(set_of_data)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"prefix_test = \"../input/coleridgeinitiative-show-us-the-data/test\"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_path = []\nfor dirname, _, filenames in os.walk(prefix_test):\n    for filename in filenames:\n        # print(os.path.join(dirname, filename))\n        test_path.append(os.path.join(dirname, filename))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_path","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pub_list = []\npub_id = []\nfor p in test_path:\n    with open(p, \"r\") as f:\n        pub = json.loads(f.read())\n        pub_list.append(pub)\n        pub_id.append(p.split(\"/\")[-1].split(\".\")[0])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pub_id","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df1 = DataFrame.from_dict(pub_list[], orient='columns', dtype=None, columns=None)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pub_list[0]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}