{"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,"scrolled":true},"cell_type":"code","source":"train = pd.read_csv('../input/train.csv').fillna(' ')\ntrain_text = train.question_text\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"6c87e4557b7f06508a9f7847d28be01c5d85d2b9"},"cell_type":"code","source":"test = pd.read_csv('../input/test.csv').fillna(' ')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"904aa6431a685522ab2d77f9b6737cb1d7eb417b"},"cell_type":"code","source":"test_text = test.question_text\nall_text = pd.concat([train_text, test_text])\n#print(train_df.columns)\n#print(train_df.question_text)\n#print(train_df.shape)\n#for x in train_df:\n#    print(x)\nfrom sklearn.feature_extraction.text import TfidfVectorizer\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import cross_val_score\n#def createDTM(messages):\n#    vect = TfidfVectorizer()\n#    dtm = vect.fit_transform(messages) # create DTM\n    \n    # create pandas dataframe of DTM\n#    return pd.DataFrame(dtm.toarray(), columns=vect.get_feature_names()) \n#messages = train_text.question_text\n#createDTM(messages)\nclass_names = ['target']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ccf131482f0f8a98e86ec9cb3c3ecaad9ccff5d3"},"cell_type":"code","source":"word_vectorizer = TfidfVectorizer(\n    sublinear_tf=True,\n    strip_accents='unicode',\n    analyzer='word',\n    token_pattern=r'\\w{1,}',\n    stop_words='english',\n    ngram_range=(1, 1),\n    max_features=10000)\nword_vectorizer.fit(all_text)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"60d52a5954cbee0b42b9d11ec495412c54e47556"},"cell_type":"code","source":"train_word_features = word_vectorizer.transform(train_text)\ntest_word_features = word_vectorizer.transform(test_text)\nscores = []\nsubmission = pd.DataFrame.from_dict({'id': test['qid']})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d128fbf75203572721f94eb427dd0ab72d355270"},"cell_type":"code","source":"for class_name in class_names:\n    train_target = train[class_name]\n    classifier = LogisticRegression(C=0.1, solver='sag')\n\n    cv_score = np.mean(cross_val_score(classifier, train_word_features, train_target, cv=3, scoring='roc_auc'))\n    scores.append(cv_score)\n    print('CV score for class {} is {}'.format(class_name, cv_score))\n\n    classifier.fit(train_word_features, train_target)\n    submission[class_name] = classifier.predict_proba(test_word_features)[:, 1]\n\nprint('Total CV score is {}'.format(np.mean(scores)))\n\nsubmission.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2f6d96938b1f25627fb2f611f63a492b67240f38"},"cell_type":"code","source":"print(word_vectorizer.vocabulary_)","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}