{"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\n%matplotlib inline\nimport warnings\nwarnings.filterwarnings('ignore')\n\nimport os\nimport csv\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport string\nimport re\nimport nltk\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom PIL import Image\nfrom wordcloud import WordCloud","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 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\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data = pd.read_csv('../input/quora-insincere-questions-classification/train.csv')\ntest_data = pd.read_csv('../input/quora-insincere-questions-classification/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Dimensions of Training Dataset : \", train_data.shape)\nprint(\"Dimensions of Test Dataset : \", test_data.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(x=\"target\", data=train_data, palette=\"Set1\")\nplt.title('Target Count')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"num_questions = len(train_data['qid'])\nnum_sincere_questions = len(train_data.qid[train_data['target'] == 0])\nnum_insincere_questions = len(train_data.qid[train_data['target'] == 1])\nprint(\"Number of Sincere questions in the training set : \", num_sincere_questions)\nprint(\"Number of Insincere questions in the training set : \", num_insincere_questions)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"values = [train_data[train_data['target']==0].shape[0], train_data[train_data['target']==1].shape[0]]\nlabels = ['Sincere Questions', 'Insincere Questions']\n\nplt.pie(values, labels=labels, autopct='%1.1f%%', shadow=True)\nplt.title('Target Distribution')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(num_sincere_questions/num_questions * 100, 'percent of training data questions are sincere')\nprint(num_insincere_questions/num_questions * 100, 'percent of training data questions are insincere')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.isnull().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.duplicated(subset = [\"question_text\", \"qid\", \"target\"]).any()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"nltk.download('wordnet')\nnltk.download('punkt')\nnltk.download('stopwords')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data['freq_qid'] = train_data.groupby('qid')['qid'].transform('count') \ntrain_data['qlen'] = train_data['question_text'].str.len() \ntrain_data['n_words'] = train_data['question_text'].apply(lambda row: len(row.split(\" \")))\ntrain_data['numeric_words'] = train_data['question_text'].apply(lambda row: sum(c.isdigit() for c in row))\ntrain_data['sp_char_words'] = train_data['question_text'].str.findall(r'[^a-zA-Z0–9 ]').str.len()\ntrain_data['char_words'] = train_data['question_text'].apply(lambda row: len(str(row)))\ntrain_data['unique_words'] = train_data['question_text'].apply(lambda row: len(set(str(row).split())))\n\ntrain_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data['freq_qid'] = test_data.groupby('qid')['qid'].transform('count') \ntest_data['qlen'] = test_data['question_text'].str.len() \ntest_data['n_words'] = test_data['question_text'].apply(lambda row: len(row.split(\" \")))\ntest_data['numeric_words'] = test_data['question_text'].apply(lambda row: sum(c.isdigit() for c in row))\ntest_data['sp_char_words'] = test_data['question_text'].str.findall(r'[^a-zA-Z0–9 ]').str.len()\ntest_data['char_words'] = test_data['question_text'].apply(lambda row: len(str(row)))\ntest_data['unique_words'] = test_data['question_text'].apply(lambda row: len(set(str(row).split())))\n\ntest_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"puncts=[',', '.', '\"', ':', ')', '(', '-', '!', '?', '|', ';', \"'\", '$', '&', '/', '[', ']', '>', '%', '=', '#', '*', '+', '\\\\', \n        '•', '~', '@', '£', '·', '_', '{', '}', '©', '^', '®', '`', '<', '→', '°', '€', '™', '›', '♥', '←', '×', '§', '″', '′', \n        '█', '…', '“', '★', '”', '–', '●', '►', '−', '¢', '¬', '░', '¡', '¶', '↑', '±', '¿', '▾', '═', '¦', '║', '―', '¥', '▓', \n        '—', '‹', '─', '▒', '：', '⊕', '▼', '▪', '†', '■', '’', '▀', '¨', '▄', '♫', '☆', '¯', '♦', '¤', '▲', '¸', '⋅', '‘', '∞', \n        '∙', '）', '↓', '、', '│', '（', '»', '，', '♪', '╩', '╚', '・', '╦', '╣', '╔', '╗', '▬', '❤', '≤', '‡', '√', '◄', '━', \n        '⇒', '▶', '≥', '╝', '♡', '◊', '。', '✈', '≡', '☺', '✔', '↵', '≈', '✓', '♣', '☎', '℃', '◦', '└', '‟', '～', '！', '○', \n        '◆', '№', '♠', '▌', '✿', '▸', '⁄', '□', '❖', '✦', '．', '÷', '｜', '┃', '／', '￥', '╠', '↩', '✭', '▐', '☼', '☻', '┐', \n        '├', '«', '∼', '┌', '℉', '☮', '฿', '≦', '♬', '✧', '〉', '－', '⌂', '✖', '･', '◕', '※', '‖', '◀', '‰', '\\x97', '↺', \n        '∆', '┘', '┬', '╬', '،', '⌘', '⊂', '＞', '〈', '⎙', '？', '☠', '⇐', '▫', '∗', '∈', '≠', '♀', '♔', '˚', '℗', '┗', '＊', \n        '┼', '❀', '＆', '∩', '♂', '‿', '∑', '‣', '➜', '┛', '⇓', '☯', '⊖', '☀', '┳', '；', '∇', '⇑', '✰', '◇', '♯', '☞', '´', \n        '↔', '┏', '｡', '◘', '∂', '✌', '♭', '┣', '┴', '┓', '✨', '\\xa0', '˜', '❥', '┫', '℠', '✒', '［', '∫', '\\x93', '≧', '］', \n        '\\x94', '∀', '♛', '\\x96', '∨', '◎', '↻', '⇩', '＜', '≫', '✩', '✪', '♕', '؟', '₤', '☛', '╮', '␊', '＋', '┈', '％', \n        '╋', '▽', '⇨', '┻', '⊗', '￡', '।', '▂', '✯', '▇', '＿', '➤', '✞', '＝', '▷', '△', '◙', '▅', '✝', '∧', '␉', '☭', \n        '┊', '╯', '☾', '➔', '∴', '\\x92', '▃', '↳', '＾', '׳', '➢', '╭', '➡', '＠', '⊙', '☢', '˝', '∏', '„', '∥', '❝', '☐', \n        '▆', '╱', '⋙', '๏', '☁', '⇔', '▔', '\\x91', '➚', '◡', '╰', '\\x85', '♢', '˙', '۞', '✘', '✮', '☑', '⋆', 'ⓘ', '❒', \n        '☣', '✉', '⌊', '➠', '∣', '❑', '◢', 'ⓒ', '\\x80', '〒', '∕', '▮', '⦿', '✫', '✚', '⋯', '♩', '☂', '❞', '‗', '܂', '☜', \n        '‾', '✜', '╲', '∘', '⟩', '＼', '⟨', '·', '✗', '♚', '∅', 'ⓔ', '◣', '͡', '‛', '❦', '◠', '✄', '❄', '∃', '␣', '≪', '｢', \n        '≅', '◯', '☽', '∎', '｣', '❧', '̅', 'ⓐ', '↘', '⚓', '▣', '˘', '∪', '⇢', '✍', '⊥', '＃', '⎯', '↠', '۩', '☰', '◥', \n        '⊆', '✽', '⚡', '↪', '❁', '☹', '◼', '☃', '◤', '❏', 'ⓢ', '⊱', '➝', '̣', '✡', '∠', '｀', '▴', '┤', '∝', '♏', 'ⓐ', \n        '✎', ';', '␤', '＇', '❣', '✂', '✤', 'ⓞ', '☪', '✴', '⌒', '˛', '♒', '＄', '✶', '▻', 'ⓔ', '◌', '◈', '❚', '❂', '￦', \n        '◉', '╜', '̃', '✱', '╖', '❉', 'ⓡ', '↗', 'ⓣ', '♻', '➽', '׀', '✲', '✬', '☉', '▉', '≒', '☥', '⌐', '♨', '✕', 'ⓝ', \n        '⊰', '❘', '＂', '⇧', '̵', '➪', '▁', '▏', '⊃', 'ⓛ', '‚', '♰', '́', '✏', '⏑', '̶', 'ⓢ', '⩾', '￠', '❍', '≃', '⋰', '♋', \n        '､', '̂', '❋', '✳', 'ⓤ', '╤', '▕', '⌣', '✸', '℮', '⁺', '▨', '╨', 'ⓥ', '♈', '❃', '☝', '✻', '⊇', '≻', '♘', '♞', \n        '◂', '✟', '⌠', '✠', '☚', '✥', '❊', 'ⓒ', '⌈', '❅', 'ⓡ', '♧', 'ⓞ', '▭', '❱', 'ⓣ', '∟', '☕', '♺', '∵', '⍝', 'ⓑ', \n        '✵', '✣', '٭', '♆', 'ⓘ', '∶', '⚜', '◞', '்', '✹', '➥', '↕', '̳', '∷', '✋', '➧', '∋', '̿', 'ͧ', '┅', '⥤', '⬆', '⋱', \n        '☄', '↖', '⋮', '۔', '♌', 'ⓛ', '╕', '♓', '❯', '♍', '▋', '✺', '⭐', '✾', '♊', '➣', '▿', 'ⓑ', '♉', '⏠', '◾', '▹', \n        '⩽', '↦', '╥', '⍵', '⌋', '։', '➨', '∮', '⇥', 'ⓗ', 'ⓓ', '⁻', '⎝', '⌥', '⌉', '◔', '◑', '✼', '♎', '♐', '╪', '⊚', \n        '☒', '⇤', 'ⓜ', '⎠', '◐', '⚠', '╞', '◗', '⎕', 'ⓨ', '☟', 'ⓟ', '♟', '❈', '↬', 'ⓓ', '◻', '♮', '❙', '♤', '∉', '؛', \n        '⁂', 'ⓝ', '־', '♑', '╫', '╓', '╳', '⬅', '☔', '☸', '┄', '╧', '׃', '⎢', '❆', '⋄', '⚫', '̏', '☏', '➞', '͂', '␙', \n        'ⓤ', '◟', '̊', '⚐', '✙', '↙', '̾', '℘', '✷', '⍺', '❌', '⊢', '▵', '✅', 'ⓖ', '☨', '▰', '╡', 'ⓜ', '☤', '∽', '╘', \n        '˹', '↨', '♙', '⬇', '♱', '⌡', '⠀', '╛', '❕', '┉', 'ⓟ', '̀', '♖', 'ⓚ', '┆', '⎜', '◜', '⚾', '⤴', '✇', '╟', '⎛', \n        '☩', '➲', '➟', 'ⓥ', 'ⓗ', '⏝', '◃', '╢', '↯', '✆', '˃', '⍴', '❇', '⚽', '╒', '̸', '♜', '☓', '➳', '⇄', '☬', '⚑', \n        '✐', '⌃', '◅', '▢', '❐', '∊', '☈', '॥', '⎮', '▩', 'ு', '⊹', '‵', '␔', '☊', '➸', '̌', '☿', '⇉', '⊳', '╙', 'ⓦ', \n        '⇣', '｛', '̄', '↝', '⎟', '▍', '❗', '״', '΄', '▞', '◁', '⛄', '⇝', '⎪', '♁', '⇠', '☇', '✊', 'ி', '｝', '⭕', '➘', \n        '⁀', '☙', '❛', '❓', '⟲', '⇀', '≲', 'ⓕ', '⎥', '\\u06dd', 'ͤ', '₋', '̱', '̎', '♝', '≳', '▙', '➭', '܀', 'ⓖ', '⇛', '▊', \n        '⇗', '̷', '⇱', '℅', 'ⓧ', '⚛', '̐', '̕', '⇌', '␀', '≌', 'ⓦ', '⊤', '̓', '☦', 'ⓕ', '▜', '➙', 'ⓨ', '⌨', '◮', '☷', \n        '◍', 'ⓚ', '≔', '⏩', '⍳', '℞', '┋', '˻', '▚', '≺', 'ْ', '▟', '➻', '̪', '⏪', '̉', '⎞', '┇', '⍟', '⇪', '▎', '⇦', '␝', \n        '⤷', '≖', '⟶', '♗', '̴', '♄', 'ͨ', '̈', '❜', '̡', '▛', '✁', '➩', 'ா', '˂', '↥', '⏎', '⎷', '̲', '➖', '↲', '⩵', '̗', '❢', \n        '≎', '⚔', '⇇', '̑', '⊿', '̖', '☍', '➹', '⥊', '⁁', '✢']\n\ndef clean_punct(x):\n    for punct in puncts:\n        if punct in x:\n            x = x.replace(punct, '{}' .format(punct))\n    return x","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def clean_numbers(x):\n    if bool(re.search(r'\\d', x)):\n        x = re.sub('[0-9]{5,}', '#####', x)\n        x = re.sub('[0-9]{4}', '####', x)\n        x = re.sub('[0-9]{3}', '###', x)\n        x = re.sub('[0-9]{2}', '##', x)\n    return x","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"mispell_dict = {'colour': 'color', 'centre': 'center', 'favourite': 'favorite', 'travelling': 'traveling', 'counselling': 'counseling', 'theatre': 'theater', 'cancelled': 'canceled', 'labour': 'labor', 'organisation': 'organization', 'wwii': 'world war 2', 'citicise': 'criticize', 'youtu ': 'youtube ', 'Qoura': 'Quora', 'sallary': 'salary', 'Whta': 'What', 'narcisist': 'narcissist', 'howdo': 'how do', 'whatare': 'what are', 'howcan': 'how can', 'howmuch': 'how much', 'howmany': 'how many', 'whydo': 'why do', 'doI': 'do I', 'theBest': 'the best', 'howdoes': 'how does', 'mastrubation': 'masturbation', 'mastrubate': 'masturbate', \"mastrubating\": 'masturbating', 'pennis': 'penis', 'Etherium': 'bitcoin', 'narcissit': 'narcissist', 'bigdata': 'big data', '2k17': '2017', '2k18': '2018', 'qouta': 'quota', 'exboyfriend': 'ex boyfriend', 'airhostess': 'air hostess', \"whst\": 'what', 'watsapp': 'whatsapp', 'demonitisation': 'demonetization', 'demonitization': 'demonetization', 'demonetisation': 'demonetization', \n                'electroneum':'bitcoin','nanodegree':'degree','hotstar':'star','dream11':'dream','ftre':'fire','tensorflow':'framework','unocoin':'bitcoin',\n                'lnmiit':'limit','unacademy':'academy','altcoin':'bitcoin','altcoins':'bitcoin','litecoin':'bitcoin','coinbase':'bitcoin','cryptocurency':'cryptocurrency',\n                'simpliv':'simple','quoras':'quora','schizoids':'psychopath','remainers':'remainder','twinflame':'soulmate','quorans':'quora','brexit':'demonetized',\n                'iiest':'institute','dceu':'comics','pessat':'exam','uceed':'college','bhakts':'devotee','boruto':'anime',\n                'cryptocoin':'bitcoin','blockchains':'blockchain','fiancee':'fiance','redmi':'smartphone','oneplus':'smartphone','qoura':'quora','deepmind':'framework','ryzen':'cpu','whattsapp':'whatsapp',\n                'undertale':'adventure','zenfone':'smartphone','cryptocurencies':'cryptocurrencies','koinex':'bitcoin','zebpay':'bitcoin','binance':'bitcoin','whtsapp':'whatsapp',\n                'reactjs':'framework','bittrex':'bitcoin','bitconnect':'bitcoin','bitfinex':'bitcoin','yourquote':'your quote','whyis':'why is','jiophone':'smartphone',\n                'dogecoin':'bitcoin','onecoin':'bitcoin','poloniex':'bitcoin','7700k':'cpu','angular2':'framework','segwit2x':'bitcoin','hashflare':'bitcoin','940mx':'gpu',\n                'openai':'framework','hashflare':'bitcoin','1050ti':'gpu','nearbuy':'near buy','freebitco':'bitcoin','antminer':'bitcoin','filecoin':'bitcoin','whatapp':'whatsapp',\n                'empowr':'empower','1080ti':'gpu','crytocurrency':'cryptocurrency','8700k':'cpu','whatsaap':'whatsapp','g4560':'cpu','payymoney':'pay money',\n                'fuckboys':'fuck boys','intenship':'internship','zcash':'bitcoin','demonatisation':'demonetization','narcicist':'narcissist','mastuburation':'masturbation',\n                'trignometric':'trigonometric','cryptocurreny':'cryptocurrency','howdid':'how did','crytocurrencies':'cryptocurrencies','phycopath':'psychopath',\n                'bytecoin':'bitcoin','possesiveness':'possessiveness','scollege':'college','humanties':'humanities','altacoin':'bitcoin','demonitised':'demonetized',\n                'brasília':'brazilia','accolite':'accolyte','econimics':'economics','varrier':'warrier','quroa':'quora','statergy':'strategy','langague':'language',\n                'splatoon':'game','7600k':'cpu','gate2018':'gate 2018','in2018':'in 2018','narcassist':'narcissist','jiocoin':'bitcoin','hnlu':'hulu','7300hq':'cpu',\n                'weatern':'western','interledger':'blockchain','deplation':'deflation', 'cryptocurrencies':'cryptocurrency', 'bitcoin':'blockchain cryptocurrency',}\n\ndef _get_mispell(mispell_dict):\n    mispell_re = re.compile('(%s)' % '|'.join(mispell_dict.keys()))\n    return mispell_dict, mispell_re\n\nmispellings, mispellings_re = _get_mispell(mispell_dict)\ndef replace_typical_misspell(text):\n    def replace(match):\n        return mispellings[match.group(0)]\n    return mispellings_re.sub(replace, text)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"contraction_dict = {\"ain't\": \"is not\", \"aren't\": \"are not\",\"can't\": \"cannot\", \"'cause\": \"because\", \"could've\": \"could have\", \"couldn't\": \"could not\", \"didn't\": \"did not\",  \"doesn't\": \"does not\", \"don't\": \"do not\", \"hadn't\": \"had not\", \"hasn't\": \"has not\", \"haven't\": \"have not\", \"he'd\": \"he would\",\"he'll\": \"he will\", \"he's\": \"he is\", \"how'd\": \"how did\", \"how'd'y\": \"how do you\", \"how'll\": \"how will\", \"how's\": \"how is\",  \"I'd\": \"I would\", \"I'd've\": \"I would have\", \"I'll\": \"I will\", \"I'll've\": \"I will have\",\"I'm\": \"I am\", \"I've\": \"I have\", \"i'd\": \"i would\", \"i'd've\": \"i would have\", \"i'll\": \"i will\",  \"i'll've\": \"i will have\",\"i'm\": \"i am\", \"i've\": \"i have\", \"isn't\": \"is not\", \"it'd\": \"it would\", \"it'd've\": \"it would have\", \"it'll\": \"it will\", \"it'll've\": \"it will have\",\"it's\": \"it is\", \"let's\": \"let us\", \"ma'am\": \"madam\", \"mayn't\": \"may not\", \"might've\": \"might have\",\"mightn't\": \"might not\",\"mightn't've\": \"might not have\", \"must've\": \"must have\", \"mustn't\": \"must not\", \"mustn't've\": \"must not have\", \"needn't\": \"need not\", \"needn't've\": \"need not have\",\"o'clock\": \"of the clock\", \"oughtn't\": \"ought not\", \"oughtn't've\": \"ought not have\", \"shan't\": \"shall not\", \"sha'n't\": \"shall not\", \"shan't've\": \"shall not have\", \"she'd\": \"she would\", \"she'd've\": \"she would have\", \"she'll\": \"she will\", \"she'll've\": \"she will have\", \"she's\": \"she is\", \"should've\": \"should have\", \"shouldn't\": \"should not\", \"shouldn't've\": \"should not have\", \"so've\": \"so have\",\"so's\": \"so as\", \"this's\": \"this is\",\"that'd\": \"that would\", \"that'd've\": \"that would have\", \"that's\": \"that is\", \"there'd\": \"there would\", \"there'd've\": \"there would have\", \"there's\": \"there is\", \"here's\": \"here is\",\"they'd\": \"they would\", \"they'd've\": \"they would have\", \"they'll\": \"they will\", \"they'll've\": \"they will have\", \"they're\": \"they are\", \"they've\": \"they have\", \"to've\": \"to have\", \"wasn't\": \"was not\", \"we'd\": \"we would\", \"we'd've\": \"we would have\", \"we'll\": \"we will\", \"we'll've\": \"we will have\", \"we're\": \"we are\", \"we've\": \"we have\", \"weren't\": \"were not\", \"what'll\": \"what will\", \"what'll've\": \"what will have\", \"what're\": \"what are\",  \"what's\": \"what is\", \"what've\": \"what have\", \"when's\": \"when is\", \"when've\": \"when have\", \"where'd\": \"where did\", \"where's\": \"where is\", \"where've\": \"where have\", \"who'll\": \"who will\", \"who'll've\": \"who will have\", \"who's\": \"who is\", \"who've\": \"who have\", \"why's\": \"why is\", \"why've\": \"why have\", \"will've\": \"will have\", \"won't\": \"will not\", \"won't've\": \"will not have\", \"would've\": \"would have\", \"wouldn't\": \"would not\", \"wouldn't've\": \"would not have\", \"y'all\": \"you all\", \"y'all'd\": \"you all would\",\"y'all'd've\": \"you all would have\",\"y'all're\": \"you all are\",\"y'all've\": \"you all have\",\"you'd\": \"you would\", \"you'd've\": \"you would have\", \"you'll\": \"you will\", \"you'll've\": \"you will have\", \"you're\": \"you are\", \"you've\": \"you have\"}\n\ndef _get_contractions(contraction_dict):\n    contraction_re = re.compile('(%s)' % '|'.join(contraction_dict.keys()))\n    return contraction_dict, contraction_re\n\ncontractions, contractions_re = _get_contractions(contraction_dict)\n\ndef replace_contractions(text):\n    def replace(match):\n        return contractions[match.group(0)]\n    return contractions_re.sub(replace, text)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"stopword_list = nltk.corpus.stopwords.words('english')\ndef remove_stopwords(text, is_lower_case=True):\n    tokenizer = ToktokTokenizer()\n    tokens = tokenizer.tokenize(text)\n    tokens = [token.strip() for token in tokens]\n    if is_lower_case:\n        filtered_tokens = [token for token in tokens if token not in stopword_list]\n    else:\n        filtered_tokens = [token for token in tokens if token.lower() not in stopword_list]\n    filtered_text = ' '.join(filtered_tokens)\n    return filtered_text","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from nltk.stem import  SnowballStemmer\nfrom nltk.tokenize.toktok import ToktokTokenizer\ndef stem_text(text):\n    tokenizer = ToktokTokenizer()\n    stemmer = SnowballStemmer('english')\n    tokens = tokenizer.tokenize(text)\n    tokens = [token.strip() for token in tokens]\n    tokens = [stemmer.stem(token) for token in tokens]\n    return ' '.join(tokens)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from nltk.stem import WordNetLemmatizer\nfrom nltk.tokenize.toktok import ToktokTokenizer\nwordnet_lemmatizer = WordNetLemmatizer()\ndef lemma_text(text):\n    tokenizer = ToktokTokenizer()\n    tokens = tokenizer.tokenize(text)\n    tokens = [token.strip() for token in tokens]\n    tokens = [wordnet_lemmatizer.lemmatize(token) for token in tokens]\n    return ' '.join(tokens)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def clean_sentence(x):\n    x = x.lower()\n    x = clean_punct(x)\n    x = clean_numbers(x)\n    x = replace_typical_misspell(x)\n    x = remove_stopwords(x)\n    x = replace_contractions(x)\n    x = stem_text(x)\n    x = lemma_text(x)\n    x = x.replace(\"'\",\"\")\n    return x","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data['preprocessed_question_text'] = train_data['question_text'].apply(lambda x: clean_sentence(x))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.preprocessed_question_text.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data['preprocessed_question_text'] = test_data['question_text'].apply(lambda x: clean_sentence(x))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data.preprocessed_question_text.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def cloud(text, title, size = (10,7)):\n    # Processing Text\n    words_list = text.unique().tolist()\n    words = ' '.join(words_list)\n    \n    wordcloud = WordCloud(width=800, height=400,\n                          collocations=False\n                         ).generate(words)\n    \n    # Output Visualization\n    fig = plt.figure(figsize=size, dpi=80, facecolor='k',edgecolor='k')\n    plt.imshow(wordcloud,interpolation='bilinear')\n    plt.axis('off')\n    plt.title(title, fontsize=25,color='w')\n    plt.tight_layout(pad=0)\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cloud(train_data[train_data['target']==0]['question_text'], 'Sincere Questions On question_text')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cloud(train_data[train_data['target']==0]['preprocessed_question_text'], 'Sincere Questions On preprocessed_question_text')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cloud(train_data[train_data['target']==1]['question_text'], 'Insincere Questions On question_text')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cloud(train_data[train_data['target']==1]['preprocessed_question_text'], 'Insincere Questions On preprocessed_question_text')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os\nimport time\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom tqdm import tqdm\nimport math\nfrom sklearn.model_selection import train_test_split\nfrom sklearn import metrics\n\nfrom keras.preprocessing.text import Tokenizer\nfrom keras.preprocessing.sequence import pad_sequences\nfrom tensorflow.compat.v1.keras.layers import CuDNNGRU\nfrom keras.layers import Dense, Input, LSTM, Embedding, Dropout, Activation, Conv1D\nfrom keras.layers import Bidirectional, GlobalMaxPool1D\nfrom keras.models import Model\nfrom keras import initializers, regularizers, constraints, optimizers, layers","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"## split to train and val\ntrain_data, val_data = train_test_split(train_data, test_size=0.1, random_state=2018)\n\n## some config values \nembed_size = 300 # how big is each word vector\nmax_features = 50000 # how many unique words to use (i.e num rows in embedding vector)\nmaxlen = 100 # max number of words in a question to use\n\n## fill up the missing values\ntrain_X = train_data[\"question_text\"].fillna(\"_na_\").values\nval_X = val_data[\"question_text\"].fillna(\"_na_\").values\ntest_X = test_data[\"question_text\"].fillna(\"_na_\").values\n\n## Tokenize the sentences\ntokenizer = Tokenizer(num_words=max_features)\ntokenizer.fit_on_texts(list(train_X))\ntrain_X = tokenizer.texts_to_sequences(train_X)\nval_X = tokenizer.texts_to_sequences(val_X)\ntest_X = tokenizer.texts_to_sequences(test_X)\n\n## Pad the sentences \ntrain_X = pad_sequences(train_X, maxlen=maxlen)\nval_X = pad_sequences(val_X, maxlen=maxlen)\ntest_X = pad_sequences(test_X, maxlen=maxlen)\n\n## Get the target values\ntrain_y = train_data['target'].values\nval_y = val_data['target'].values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"inp = Input(shape=(maxlen,))\nx = Embedding(max_features, embed_size)(inp)\nx = Bidirectional(LSTM(64, return_sequences=True))(x)\nx = GlobalMaxPool1D()(x)\nx = Dense(16, activation=\"relu\")(x)\nx = Dropout(0.1)(x)\nx = Dense(1, activation=\"sigmoid\")(x)\nmodel = Model(inputs=inp, outputs=x)\nmodel.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n\nprint(model.summary())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(train_X, train_y, batch_size=512, epochs=2, validation_data=(val_X, val_y))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_noemb_val_y = model.predict([val_X], batch_size=1024, verbose=1)\nfor thresh in np.arange(0.1, 0.501, 0.01):\n    thresh = np.round(thresh, 2)\n    print(\"F1 score at threshold {0} is {1}\".format(thresh, metrics.f1_score(val_y, (pred_noemb_val_y>thresh).astype(int))))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_noemb_test_y = model.predict([test_X], batch_size=1024, verbose=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_noemb_test_y = (pred_noemb_test_y > 0.33).astype(int)\nout_df = pd.DataFrame({\"qid\":test_data[\"qid\"].values})\nout_df['prediction'] = pred_noemb_test_y\nout_df.to_csv(\"submission.csv\", index=False)\nprint('Successfully saved submission')\npred_noemb_test_y","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}