{"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)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\ndata=pd.read_csv('../input/train.csv')\ndata.shape\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data[data['target']==1].head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data['target'].value_counts()/data.shape[0]*100 # Highly imbalanced data","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 # Splitting for train and validation\ntrain,validate=train_test_split(data,test_size=0.3,random_state=1)\ntrain.shape,validate.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import nltk\n\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)\n\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\n\ntrain_docs_clean=clean_documents(train['question_text'])\ntrain_docs_clean.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Convert to document matrix\n\nfrom 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":"total_values= 914285*19550 # Sparcity is 99.96%\nnon_zer_values=5406880\nnon_zer_values/total_values *100\n(total_values-non_zer_values)/total_values*100 ","execution_count":29,"outputs":[{"output_type":"execute_result","execution_count":29,"data":{"text/plain":"99.96975048787652"},"metadata":{}}]},{"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":30,"outputs":[{"output_type":"execute_result","execution_count":30,"data":{"text/plain":"<391837x19550 sparse matrix of type ''\n\twith 2313528 stored elements in Compressed Sparse Row format>"},"metadata":{}}]},{"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":31,"outputs":[{"output_type":"execute_result","execution_count":31,"data":{"text/plain":"0.26105845181674564"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"f1 score for Decision tree is 0.261"},{"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":32,"outputs":[{"output_type":"execute_result","execution_count":32,"data":{"text/plain":"0.5425968470252713"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"f1 score for MultinomialNB is 0.542"},{"metadata":{"trusted":true},"cell_type":"code","source":"test=pd.read_csv('../input/test.csv')\ntest.head()","execution_count":33,"outputs":[{"output_type":"execute_result","execution_count":33,"data":{"text/plain":" qid question_text\n0 0000163e3ea7c7a74cd7 Why do so many women become so rude and arroga...\n1 00002bd4fb5d505b9161 When should I apply for RV college of engineer...\n2 00007756b4a147d2b0b3 What is it really like to be a nurse practitio...\n3 000086e4b7e1c7146103 Who are entrepreneurs?\n4 0000c4c3fbe8785a3090 Is education really making good people nowadays?","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
qidquestion_text
00000163e3ea7c7a74cd7Why do so many women become so rude and arroga...
100002bd4fb5d505b9161When should I apply for RV college of engineer...
200007756b4a147d2b0b3What is it really like to be a nurse practitio...
3000086e4b7e1c7146103Who are entrepreneurs?
40000c4c3fbe8785a3090Is education really making good people nowadays?
\n
"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"docs_clean=clean_documents(test['question_text'])\ndtm_test=vectorizer.transform(docs_clean)\ndtm_test","execution_count":34,"outputs":[{"output_type":"execute_result","execution_count":34,"data":{"text/plain":"<375806x19550 sparse matrix of type ''\n\twith 2220720 stored elements in Compressed Sparse Row format>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_pred=model_nb.predict(dtm_test)","execution_count":35,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission=pd.read_csv('../input/sample_submission.csv')\nsample_submission.head()","execution_count":37,"outputs":[{"output_type":"execute_result","execution_count":37,"data":{"text/plain":" qid prediction\n0 0000163e3ea7c7a74cd7 0\n1 00002bd4fb5d505b9161 0\n2 00007756b4a147d2b0b3 0\n3 000086e4b7e1c7146103 0\n4 0000c4c3fbe8785a3090 0","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
qidprediction
00000163e3ea7c7a74cd70
100002bd4fb5d505b91610
200007756b4a147d2b0b30
3000086e4b7e1c71461030
40000c4c3fbe8785a30900
\n
"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission=pd.DataFrame({'qid':test['qid'],'prediction':test_pred})\nsubmission[['qid','prediction']].to_csv('submission.csv',index=False)","execution_count":38,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}