{"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\"))\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":"import pandas as pd\nimport numpy as np\nfrom sklearn.feature_extraction.text import TfidfVectorizer\nfrom sklearn.linear_model.logistic import LogisticRegression","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b324e1ab1ca5ef772547a78ef32b23783a6c14ab"},"cell_type":"code","source":"df = pd.read_csv('../input/train.csv')\ntest=pd.read_csv(\"../input/test.csv\")\nid=df.qid\ntext=df.question_text\ntestxt=test.question_text\nans=df.target\nid1=test.qid","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"0841d187acc46b58eab75855c4d0977c81e1c195"},"cell_type":"code","source":"vect=TfidfVectorizer(stop_words='english')\nX_train=vect.fit_transform(text)\nX_test=vect.transform(testxt)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"92be4af5b5fae3a6b32e630465bf5847b89468cb"},"cell_type":"code","source":"clas=LogisticRegression()\nclas.fit(X_train, ans)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"cdaf338de2dceaff64a351a274702dd83de8dd86"},"cell_type":"code","source":"f=clas.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"1991e237bb116c2ecf48016ebcf2a0defff04369"},"cell_type":"code","source":"sub = pd.DataFrame()\nsub['qid'] = id1\nsub['prediction'] = f\nsub.to_csv('submission.csv',index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"19b96baad642efcc4badf8fb636cd5585c65a050"},"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}