{"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":{"trusted":true},"cell_type":"code","source":"from gensim.parsing.preprocessing import remove_stopwords\nfrom gensim.parsing.porter import PorterStemmer\n\nstemmer = PorterStemmer()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = pd.read_csv('/kaggle/input/quora-insincere-questions-classification/test.csv')\ntest.head()","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/quora-insincere-questions-classification/train.csv').sample(100000)\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# docs will be a pandas series\ndef clean_documents(docs):\n    stemmer = PorterStemmer()\n    docs_clean = docs.str.lower()\n    docs_clean = docs_clean.str.replace('[^a-z\\s]', '')\n    docs_clean = docs_clean.apply(lambda doc: remove_stopwords(doc))\n    docs_clean = pd.Series(stemmer.stem_documents(docs_clean), index=docs.index)\n    return docs_clean","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_cleaned = clean_documents(train['question_text'])\ntrain_cleaned.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom sklearn.naive_bayes import MultinomialNB\nfrom sklearn.metrics import accuracy_score, f1_score\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_x, validate_x, train_y, validate_y = train_test_split(train_cleaned,\n                                                           train['target'],\n                                                           test_size=0.2,\n                                                           random_state=1)\ntrain_x.shape, validate_x.shape, train_y.shape, validate_y.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.feature_extraction.text import CountVectorizer\n\nvectorizer = CountVectorizer(min_df=2,stop_words='english',).fit(train_x)\nvocab = vectorizer.get_feature_names()\ntrain_dtm = vectorizer.transform(train_x)\nvalidate_dtm = vectorizer.transform(validate_x)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#df_train_dtm = pd.DataFrame(train_dtm.toarray(), columns=vocab, index=train_x.index)\n#df_validate_dtm = pd.DataFrame(validate_dtm.toarray(), columns=vocab, index=validate_x.index)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"nb_model = MultinomialNB().fit(train_dtm, train_y)\npred_validate_y = pd.Series(nb_model.predict(validate_dtm), index=validate_y.index)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(accuracy_score(validate_y, pred_validate_y))\nprint(f1_score(validate_y, pred_validate_y))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_docs = clean_documents(test['question_text'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_dtm = vectorizer.transform(test_docs)\n#df_test_dtm = pd.DataFrame(test_dtm.toarray(), index=test_docs.index, columns=vocab)\npred_test_y = pd.Series(nb_model.predict(test_dtm))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample = pd.read_csv('/kaggle/input/quora-insincere-questions-classification/sample_submission.csv')\nsample.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.DataFrame({\n    'qid': test['qid'],\n    'prediction': pred_test_y\n})\nsubmission.to_csv('submission.csv', index=False)","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}