{"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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"data=pd.read_csv('/kaggle/input/quora-insincere-questions-classification/train.csv')\ndata.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#data[data['target']==1].head()\ndata['target'].value_counts()/data.shape[0]*100","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from wordcloud import WordCloud\nimport matplotlib.pyplot as plt\ninsincere_rows=data[data['target']==1]\nwc=WordCloud(background_color='white').generate(' '.join(insincere_rows['question_text']))\nplt.imshow(wc)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\ntrain,validate=train_test_split(data,test_size=0.3,random_state=1)\ntrain.shape,validate.shape\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import nltk\ndef clean_sentence(doc,stopwords,stemmer):\n    words=doc.split(' ')\n    words_clean=[stemmer.stem(word) for word in words if word not in stopwords]\n    return ' '.join(words_clean)\ndef clean_documents(docs_raw):\n    stopwords=nltk.corpus.stopwords.words('english')\n    stemmer=nltk.stem.PorterStemmer()\n    docs=docs_raw.str.lower().str.replace('[^a-z ]','' )\n    docs_clean=docs.apply(lambda doc:clean_sentence(doc,stopwords,stemmer))\n    return docs_clean\ntrain_docs_clean=clean_documents(train['question_text'])\ntrain_docs_clean.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.feature_extraction.text import CountVectorizer\nvectorizer=CountVectorizer(min_df=10).fit(train_docs_clean)\ndtm=vectorizer.transform(train_docs_clean)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dtm","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.tree import DecisionTreeClassifier\nmodel_df=DecisionTreeClassifier(max_depth=10).fit(dtm,train['target'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"validate_docs_clean=clean_documents(validate['question_text'])\ndtm_validate=vectorizer.transform(validate_docs_clean)\ndtm_validate","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"validate_pred=model_df.predict(dtm_validate)\nfrom sklearn.metrics import f1_score\nf1_score(validate['target'],validate_pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.naive_bayes import MultinomialNB\nmodel_nb=MultinomialNB().fit(dtm,train['target'])\nvalidate_pred=model_nb.predict(dtm_validate)\nf1_score(validate['target'],validate_pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test=pd.read_csv('/kaggle/input/quora-insincere-questions-classification/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"docs_clean=clean_documents(test['question_text'])\ndtm_test=vectorizer.transform(docs_clean)\ndtm_test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_pred=model_nb.predict(dtm_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission=pd.read_csv(\"/kaggle/input/quora-insincere-questions-classification/sample_submission.csv\")\nsample_submission","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission=pd.DataFrame({'qid':test['qid'],\n                        'prediction':test_pred})\nsubmission[['qid','prediction']].to_csv('submission.csv',index=False)\n","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":4}