{"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":"from sklearn.feature_extraction.text import TfidfVectorizer\ndf = pd.read_csv('../input/train.csv')\ndf.replace([np.NaN],[''],inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"813a3fc5bdd407ca312dd15db691f4b50711edc4"},"cell_type":"code","source":"X=df['question_text']\ny=df['target']\ndf['question_text'] = df['question_text'].str.replace(\"[^a-zA-Z#]\", \" \")\ntrain=df.question_text\ntest=df.target","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"bb70ed45a317a3a6d885225f194cb914ece2f493"},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train, X_test, y_train, y_test = train_test_split(df['question_text'], df['target'], random_state = 0)\n\nvect = TfidfVectorizer(min_df = 5).fit(X_train)\nX_train_vectorized = vect.transform(X_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"e7a2364f14c88e21b6f79483f21ad810c1869fdd"},"cell_type":"code","source":"from sklearn.linear_model import LogisticRegression\nmodel = LogisticRegression()\nmodel.fit(X_train_vectorized, y_train)\npredictions = model.predict(vect.transform(X_test))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"67ce2b4a916bc7ab0325419aa493b898a7cc06da"},"cell_type":"code","source":"from sklearn.metrics import roc_auc_score\nprint('AUC: ', roc_auc_score(y_test, predictions))\nprint(model.predict(vect.transform(['Has the United States become the largest dictatorship in the world'])))","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}