{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np \nimport pandas as pd\nfrom nltk.tokenize import word_tokenize\nfrom sklearn.feature_extraction.text import TfidfVectorizer\nfrom nltk.corpus import stopwords\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.linear_model import SGDClassifier\nfrom sklearn.model_selection import cross_val_predict\nfrom sklearn.model_selection import StratifiedKFold\nfrom sklearn.metrics import roc_auc_score, classification_report, f1_score\nfrom sklearn.model_selection import GridSearchCV,RandomizedSearchCV,KFold\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"df  = pd.read_csv('../input/quora-insincere-questions-classification/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"vect = TfidfVectorizer()\nsklearn_tokenizer = vect.build_tokenizer()\nstop_words = set(stopwords.words(\"english\"))\ny = df.target.to_numpy()\nvect=TfidfVectorizer(tokenizer = sklearn_tokenizer,stop_words='english',ngram_range=(1, 1), norm='l2')\nclf=SGDClassifier(alpha=0.0001,epsilon=0.1, eta0=0.0,\n                               l1_ratio=0.1, learning_rate='optimal',\n                               loss='modified_huber', penalty='l2',class_weight =  'balanced')\npp = Pipeline([('vect',vect),('clf',clf )])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pp.fit(df.question_text.to_numpy(),y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df =  pd.read_csv('../input/quora-insincere-questions-classification/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df['prediction'] = pp.predict(test_df.question_text.to_numpy())\ntest_df[['qid','prediction']].to_csv(\"submission.csv\", index=False)","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":1}