{"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_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"%matplotlib inline\nimport warnings\nwarnings.filterwarnings('ignore')\n\nimport numpy as np\nimport pandas as pd\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\nfrom subprocess import check_output\n\n%matplotlib inline\nimport plotly.offline as py\npy.init_notebook_mode(connected=True)\nimport plotly.graph_objs as go\nimport plotly.tools as tls\n\nimport os\nimport gc\nimport csv\nimport re\nimport string\nimport nltk\nfrom tqdm import tqdm\nfrom collections import Counter\nfrom wordcloud import WordCloud, STOPWORDS\nfrom scipy.sparse import hstack\nfrom IPython.display import Image\nfrom tqdm import tqdm_notebook\ntqdm_notebook().pandas()\n\nfrom nltk.corpus import stopwords\nfrom nltk.stem import PorterStemmer, SnowballStemmer, WordNetLemmatizer\nfrom nltk.stem.lancaster import LancasterStemmer\nfrom nltk.util import ngrams","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install distance\n!pip install bs4","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import distance\nfrom bs4 import BeautifulSoup","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**DATA OVERVIEW**\n* Train data consists of 1.3 million rows and 3 features in it.\n \n* -train.csv - the training set -test.csv - the test set -sample_submission.csv - A sample submission in the correct format -enbeddings\n \n* Size of train.csv:\n \n* No. of rows: 1.31M\n \n* No. of columns: 3\n* **Data fields**:\n* qid — unique question identifier\n \n* question_text — Quora question text\n \n* target — a question labeled “insincere” has a value of, 1 otherwise 0\n* **Evaluation**\n* As this dataset is highly imbalanced, we will use F1 score as a metric for this dataset.\n \n* Metric is F1 Score between the predicted and the observed targets. There are just two classes, but the positive class makes just over 6% of the total. So the target is highly imbalanced, which is why a metric such as F1 seems appropriate for this kind of problem as it considers both precision and recall of the test to compute the score","metadata":{}},{"cell_type":"code","source":"#Reading Data\ntrain = pd.read_csv(\"../input/quora-insincere-questions-classification/train.csv\")\ntest=pd.read_csv(\"../input/quora-insincere-questions-classification/test.csv\")\nprint(\"Number of train data points:\",train.shape[0])\nprint(\"Number of test data points:\",test.shape[0])\nprint(\"Shape of Train Data:\", train.shape)\nprint(\"Shape of Test Data:\", test.shape)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Distribution of data points among output classes**","metadata":{}},{"cell_type":"code","source":"train.groupby(\"target\")['qid'].count().plot.bar()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Check Percentage of Sincere and Insincere questions\nprint('~> Percentage of Sincere Questions (is_duplicate = 0):\\n   {}%'.format(100 - round(train['target'].mean()*100, 2)))\nprint('\\n~> Percentage of Insincere Questions (is_duplicate = 1):\\n   {}%'.format(round(train['target'].mean()*100, 2)))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# sns.boxplot(x=\"target\", y=\"question_text\", data=train)\n# plt.grid()\n# plt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Data Processing** \nThe text data is not entirely clean, thus we need to apply some data preprocessing techniques.\n* 1.Removing Punctuation\n* 2.Cleaning Numbers\n* 3.Correcting Misspelled Words\n* 4.Removing Contractions\n* 5.Removing Stopwords\n* 6.Stemming\n* 7.Lemmatization","metadata":{}},{"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","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Special Characters that were in the data; we’ll use replace to remove these characters\ndef clean_punct(x):\n    for punct in puncts:\n        if punct in x:\n            x = x.replace(punct, '{}' .format(punct))\n    return x","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Cleaning Numbers\ndef 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","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"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',}","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#replace misspelled words using a misspell mapping and regex functions.\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)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"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\"}","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Removing Contractions\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)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Stop words are a set of commonly used words in any language. For example, in English, “the”, “is” and “and” so we'll remove them \nstopword_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","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def preprocess(x):\n    x = str(x).lower()\n    x = x.replace(\",000,000\", \"m\").replace(\",000\", \"k\").replace(\"′\", \"'\").replace(\"’\", \"'\")\\\n                           .replace(\"%\", \" percent \").replace(\"₹\", \" rupee \").replace(\"$\", \" dollar \")\\\n                           .replace(\"€\", \" euro \").replace(\"'ll\", \" will\")\n    x = re.sub(r\"([0-9]+)000000\", r\"\\1m\", x)\n    x = re.sub(r\"([0-9]+)000\", r\"\\1k\", x)\n    \n    \n    porter = PorterStemmer()\n    pattern = re.compile('\\W')\n    \n    if type(x) == type(''):\n        x = re.sub(pattern, ' ', x)\n    \n    \n    if type(x) == type(''):\n        x = porter.stem(x)\n        example1 = BeautifulSoup(x)\n        x = example1.get_text()\n               \n    \n    return x","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#converting words to their base forms using crude Heuristic rules\n#For example, one rule could be to remove ’s’ from the end of any word, so that ‘cats’ becomes ‘cat’\nfrom 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)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#remove endings only if the base form is present in a dictionary.\nfrom 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)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#apply below given steps to clean the text on train and test data.\ndef 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 = preprocess(x)\n    x = stem_text(x)\n    x = lemma_text(x)\n    x = x.replace(\"'\",\"\")\n    return x","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train['preprocessed_question_text'] = train['question_text'].apply(lambda x: clean_sentence(x))\ntest['preprocessed_question_text'] = test['question_text'].apply(lambda x: clean_sentence(x))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import copy\nimport sys\nimport os \nimport pandas as pd\nimport numpy as np\nfrom tqdm import tqdm\nimport spacy\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport regex as re\nimport time\nimport warnings\nimport sqlite3\nfrom sqlalchemy import create_engine # database connection\nimport csv\nimport os\nwarnings.filterwarnings(\"ignore\")\nimport datetime as dt\nimport numpy as np\nfrom nltk.corpus import stopwords\nfrom sklearn.preprocessing import normalize\nimport seaborn as sns\nfrom sklearn.metrics import confusion_matrix\nfrom sklearn.metrics import accuracy_score, log_loss\nfrom sklearn.feature_extraction.text import TfidfVectorizer\nfrom collections import Counter\nfrom sklearn.svm import SVC\nfrom sklearn.model_selection import StratifiedKFold \nfrom collections import Counter, defaultdict\nfrom sklearn.naive_bayes import MultinomialNB\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.model_selection import GridSearchCV\nimport math\nfrom sklearn.metrics import normalized_mutual_info_score\n\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn.linear_model import SGDClassifier\nfrom mlxtend.classifier import StackingClassifier\n\nfrom sklearn import model_selection\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.metrics import precision_recall_curve, auc, roc_curve\nfrom sklearn.metrics import f1_score","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# small function to find threshold and find best f score - Eval metric of competition\ndef bestThresshold(y_train,train_preds):\n    tmp = [0,0,0] # idx, cur, max\n    delta = 0\n    for tmp[0] in tqdm(np.arange(0.1, 0.501, 0.01)):\n        tmp[1] = f1_score(y_train, np.array(train_preds)>tmp[0])\n        if tmp[1] > tmp[2]:\n            delta = tmp[0]\n            tmp[2] = tmp[1]\n    print('best threshold is {:.4f} with F1 score: {:.4f}'.format(delta, tmp[2]))\n    return tmp[2]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Function that splits X_train and y_train into train and validation data and trains the model as per the passed parameter\n\ndef model_train_cv(x_train,y_train,nfold,model_obj):\n    splits = list(StratifiedKFold(n_splits=nfold, shuffle=True, random_state = None).split(x_train, y_train))\n    x_train = x_train\n    y_train = np.array(y_train)\n    # matrix for the out-of-fold predictions\n    train_oof_preds = np.zeros((x_train.shape[0]))\n    for i, (train_idx, valid_idx) in enumerate(splits):\n\n        x_train_fold = x_train[train_idx.astype(int)]\n        y_train_fold = y_train[train_idx.astype(int)]\n        x_val_fold = x_train[valid_idx.astype(int)]\n        y_val_fold = y_train[valid_idx.astype(int)]\n\n        clf = copy.deepcopy(model_obj)\n        clf.fit(x_train_fold, y_train_fold)\n        valid_preds_fold = clf.predict_proba(x_val_fold)[:,1]\n\n        # storing OOF predictions\n        train_oof_preds[valid_idx] = valid_preds_fold\n    return train_oof_preds","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Term Frequency — Inverse Document Frequency (TF-IDF)******\n* Term Frequency (tf): gives us the frequency of the word in each document in the corpus. It is the ratio of number of times the word appears in a document compared to the total number of words in that document. It increases as the number of occurrences of that word within the document increases. Each document has its own tf.\n \n* Inverse Data Frequency (idf): used to calculate the weight of rare words across all documents in the corpus. The words that occur rarely in the corpus have a high IDF score. It is given by the equation below.\n \n","metadata":{}},{"cell_type":"code","source":"tfv = TfidfVectorizer(dtype=np.float32, min_df=3,  max_features=None, \n            strip_accents='unicode', analyzer='word',token_pattern=r'\\w{1,}',\n            ngram_range=(1, 3), use_idf=1,smooth_idf=1,sublinear_tf=1,\n            stop_words = 'english')\n\n# Fitting TF-IDF to both training and test sets (semi-supervised learning)\ntfv.fit(list(train.preprocessed_question_text.values) + list(test.preprocessed_question_text.values))\nX_train =  tfv.transform(train.preprocessed_question_text.values) \nX_test_tfv = tfv.transform(test.preprocessed_question_text.values)\ny_train = train.target.values\n\nprint(\"Number of data points in train data :\",X_train.shape, y_train.shape)\nprint(\"Number of data points in test data :\",X_test_tfv.shape)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Fitting a simple Logistic Regression on TF-IDF\ntrain_oof_preds = model_train_cv(X_train,y_train,5,LogisticRegression(C=1.0))\nf1 = bestThresshold(y_train,train_oof_preds)\nprint (\"F1 Score: %0.3f \" %f1 )\n\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}