{"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\n#print(os.listdir(\"../input\"))\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","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 wordcloud import WordCloud\nimport matplotlib.pyplot as plt\ninsincere_rows = data[data.target == 0]\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 = .3, random_state = 1)\ntrain.shape, validate.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"type(train['question_text'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import nltk\ndef clean_sentance(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_sentance(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\nvactorizer = CountVectorizer(min_df = 10).fit(train_docs_clean)\ndtm = vactorizer.transform(train_docs_clean)","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 = vactorizer.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":39,"outputs":[{"output_type":"execute_result","execution_count":39,"data":{"text/plain":"0.5425968470252713"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"test =pd.read_csv('../input/test.csv')\ntest.head()","execution_count":41,"outputs":[{"output_type":"execute_result","execution_count":41,"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":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>qid</th>\n      <th>question_text</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>0000163e3ea7c7a74cd7</td>\n      <td>Why do so many women become so rude and arroga...</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>00002bd4fb5d505b9161</td>\n      <td>When should I apply for RV college of engineer...</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>00007756b4a147d2b0b3</td>\n      <td>What is it really like to be a nurse practitio...</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>000086e4b7e1c7146103</td>\n      <td>Who are entrepreneurs?</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>0000c4c3fbe8785a3090</td>\n      <td>Is education really making good people nowadays?</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"docs_clean = clean_documents(test.question_text)\ndtm_test = vactorizer.transform(docs_clean)\ndtm_test","execution_count":42,"outputs":[{"output_type":"execute_result","execution_count":42,"data":{"text/plain":"<375806x19550 sparse matrix of type '<class 'numpy.int64'>'\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":43,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission = pd.read_csv('../input/sample_submission.csv')\nsubmission = pd.DataFrame({'qid': test['qid'],\n                          'prediction': test_pred})\nsubmission[['qid','prediction']].to_csv('submission.csv',index = False)","execution_count":44,"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}