{"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)\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom wordcloud import WordCloud, STOPWORDS\n#from tqdm import tqdm\n#tqdm.pandas()\nimport warnings\nwarnings.filterwarnings('ignore')\nimport gc\nfrom nltk.tokenize import TweetTokenizer\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.feature_extraction.text import TfidfVectorizer\nfrom sklearn.model_selection import cross_val_score\n# Input data files are available in the \"../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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_df=pd.read_csv('../input/quora-insincere-questions-classification/train.csv')\ntest_df=pd.read_csv('../input/quora-insincere-questions-classification/test.csv')\ntest_df['target']=None\ndf = pd.concat([train_df, test_df],axis=0, join='outer')\ntest_df.drop('target',axis=1, inplace=True)\nprint(f'Train shape:{train_df.shape}\\nTest shape:{test_df.shape}\\nTotal df shape:{df.shape}\\n')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df['new_question_text'] = df['question_text'].map(lambda x: x.lower() if isinstance(x,str) else x)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cloud_stop = set(STOPWORDS)\ncloud = WordCloud(background_color='white', stopwords=cloud_stop).generate(df['new_question_text'].str.cat(sep=', '))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(15,20))\nplt.imshow(cloud, interpolation=\"bilinear\")\nplt.axis(\"off\")\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(x='target', data=train_df, palette='RdBu')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tokenizer = TweetTokenizer().tokenize\nvect = TfidfVectorizer(tokenizer=tokenizer, ngram_range=(1,3),max_df=0.3)\nvect.fit(df['question_text'].values)\nvect_train = vect.transform(train_df['question_text'])\nvect_test = vect.transform(test_df['question_text'])\nvect_y = train_df['target']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"logreg = LogisticRegression(class_weight='balanced',n_jobs=-1,C=10)\nscores= cross_val_score(logreg, vect_train, vect_y, scoring='f1_macro',n_jobs=-1, cv=3)\nprint(f'Cross_Val\\nScore:{np.mean(scores)} +/- {np.std(scores)}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"logreg.fit(vect_train, vect_y)\npred = logreg.predict_proba(vect_test)\n#print(pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df['prediction'] = np.argmax(pred,axis=1)\ntest_df.drop('question_text',axis=1, inplace=True)\ntest_df.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}