{"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":"train=pd.read_csv('/kaggle/input/facebook-recruiting-iii-keyword-extraction/Train.zip')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.shape\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train1=train.iloc[1:50000,:]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train1.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train1.isnull().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y=train1.Tags\nx=train1.drop('Tags',axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del train1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import re","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def check(x):\n    s=re.sub('<[^>]*>','',x)\n    s=re.sub('[^\\w\\s]','',s)\n    return s","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x1=x.Body.apply(check)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x.Body=x1\ndel x1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"xtr,xte,ytr,yte=train_test_split(x,y,test_size=.20,random_state=20)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ct=CountVectorizer()\ntf=TfidfVectorizer()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ct.fit_transform(xtr,ytr)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pickle","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}