{"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_minor":4,"nbformat":4,"cells":[{"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 20GB 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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = pd.read_csv('/kaggle/input/quora-insincere-questions-classification/train.csv')\ndata.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data['target'].nunique()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data['target'].unique()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data['target'].value_counts() / data.shape[0] * 100","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data.isna().sum()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from gensim.parsing.porter import PorterStemmer\nfrom gensim.parsing import remove_stopwords\nstemmer = PorterStemmer()\n\n# Text cleaning\ndocs = data['question_text'].str.lower() # lower case conversion\ndocs = docs.str.replace('[^a-z\\s]', '') # removal of special characters\ndocs = pd.Series(stemmer.stem_documents(docs)) # Identifying root form of the word\ndocs = docs.apply(remove_stopwords) # Removing stop words\ndocs.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer\n\ntrain_x, validate_x, train_y, validate_y = train_test_split(docs,\n                                                    data['target'],\n                                                    test_size=0.2,\n                                                    random_state=1)\n\nvectorizer = CountVectorizer(min_df=20).fit(train_x)\nvocab = vectorizer.get_feature_names()\ntrain_dtm = vectorizer.transform(train_x)\nvalidate_dtm = vectorizer.transform(validate_x)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.naive_bayes import MultinomialNB\nfrom sklearn.metrics import accuracy_score, f1_score\nmodel_nb = MultinomialNB().fit(train_dtm, train_y)\n\nvalidate_y_pred = model_nb.predict(validate_dtm)\nprint(accuracy_score(validate_y, validate_y_pred))\nprint(f1_score(validate_y, validate_y_pred, pos_label=1))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test = pd.read_csv('/kaggle/input/quora-insincere-questions-classification/test.csv')\ntest_docs = test['question_text'].str.lower() # lower case conversion\ntest_docs = test_docs.str.replace('[^a-z\\s]', '') # removal of special characters\ntest_docs = pd.Series(stemmer.stem_documents(test_docs)) # Identifying root form of the word\ntest_docs = test_docs.apply(remove_stopwords) # Removing stop words\ntest_docs.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_dtm = vectorizer.transform(test_docs)\ntest_y_pred = model_nb.predict(test_dtm)\ntest['prediction'] = test_y_pred","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample = pd.read_csv('/kaggle/input/quora-insincere-questions-classification/sample_submission.csv')\nsample.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test[['qid', 'prediction']].to_csv('submission.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}