{"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 in \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 \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\nimport spacy\nfrom nltk.stem import WordNetLemmatizer\nnlp = spacy.load('en_core_web_sm')\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"df = pd.read_csv(\"../input/train.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"5e49d7ce71d367d6d1348e042aaa6102d711a1e0"},"cell_type":"code","source":"df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7c272eed919e1177a9ec7d561e0a5a8d692dc684"},"cell_type":"code","source":"df.drop('qid',1,inplace = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b2788daf6660e1c13e856240300a9b95b2057387"},"cell_type":"code","source":"lem = WordNetLemmatizer()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"8b1635abd5bb56e7f5fe823bd7cc923938dc428a"},"cell_type":"code","source":"def cleaning(text):\n    words = []\n    doc = nlp(text)\n    for token in doc:\n        if not token.is_punct:\n            words.append(lem.lemmatize(token.text))\n    return ' '.join(words)\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"e62910237e47fb595f6ce41d0baa230410d953be"},"cell_type":"code","source":"df['question_text'] = df['question_text'].apply(cleaning)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"5ee2005956e4aa8802302ea01d25bd114a651bb7"},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}