{"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 5GB 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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import pandas as pd\ndata=pd.read_csv(\"../input/stackoverflow-tag-prediction/data.csv\")\ndata.drop(columns=['Unnamed: 0','Id'],axis=1,inplace=True)\ndata","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def strip_html(sentence):\n    compiled=re.compile(r\"<.*?>\")\n    cleaned_sentence=re.sub(compiled,\" \",str(sentence))\n    return cleaned_sentence\nimport re\nfrom nltk.tokenize import word_tokenize\nfrom nltk.corpus import stopwords\nfrom nltk.stem.snowball import SnowballStemmer\nsentences=[]\nstemmer=SnowballStemmer(\"english\")\nstop_words = set(stopwords.words('english'))\nstart=0\nend=1000000\nfrom datetime import datetime\nstart_time = datetime.now()\nfor i,j in zip(data.iloc[start:end,0],data.iloc[start:end,1]):\n    sentence=str(i)+\" \"+str(j)\n    sentence=re.sub(r\"<code>(.*?)</code>\",\" \",sentence)# removes all the code\n    sentence=strip_html(sentence.encode('utf-8'))\n    sentence=re.sub(r\"[^A-Za-z]\",\" \",sentence)\n    words=word_tokenize(sentence.lower())\n    sentence=\" \".join(str(stemmer.stem(i)) for i in words if i not in stop_words and( len(i)!=1 or i=='c'))\n    sentences.append(sentence)\nprint(datetime.now()-start_time)\nimport pickle as pkl\nwith open('data1.txt','wb') as fh:\n    pkl.dump(sentences,fh)","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}