{"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#https://code.google.com/archive/p/word2vec/\n# https://nlp.stanford.edu/projects/glove/\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.\nimport os\nprint(os.listdir(\"../input\"))\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"522d9790478f62193ea5c315372a2ab9cbe9b27f"},"cell_type":"markdown","source":"**Load packages and data**"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","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\nfrom sklearn.model_selection import GridSearchCV, StratifiedKFold\nfrom sklearn.metrics import f1_score, roc_auc_score, precision_score, recall_score\n\nfrom keras.preprocessing.text import Tokenizer\nfrom keras.preprocessing.sequence import pad_sequences\nfrom keras.layers import Dense, Input, CuDNNLSTM, Embedding, Dropout, Activation, CuDNNGRU, Conv1D\nfrom keras.layers import Bidirectional, GlobalMaxPool1D, GlobalMaxPooling1D, GlobalAveragePooling1D\nfrom keras.layers import Input, Embedding, Dense, Conv2D, MaxPool2D, concatenate\nfrom keras.layers import Reshape, Flatten, Concatenate, Dropout, SpatialDropout1D\nfrom keras.optimizers import Adam\nfrom keras.models import Model\nfrom keras import backend as K\nfrom keras.engine.topology import Layer\nfrom keras import initializers, regularizers, constraints, optimizers, layers\nfrom keras.layers import concatenate\nfrom keras.callbacks import *","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"embed_size = 300 # how big is each word vector\nmax_features = 61000 # how many unique words to use (i.e num rows in embedding vector)\nmaxlen = 70 # max number of words in a question to use","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train=pd.read_csv(\"../input/train.csv\")\n# Class count\ncount_class_0, count_class_1 = train.target.value_counts()\n\n# Divide by class\ndf_class_0 = train[train['target'] == 0]\ndf_class_1 = train[train['target'] == 1]\ndf_class_0_under = df_class_0.sample(count_class_1)\ntrain = pd.concat([df_class_0_under, df_class_1], axis=0)\n\nprint('Random under-sampling:')\nprint(train.target.value_counts())\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['question_text']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from collections import defaultdict\nfrom nltk.corpus import stopwords\nfrom nltk import WordNetLemmatizer\nimport re\ndef get_symbols_in_one(data):\n    symbols=[]\n    for text in data:\n        s=re.findall(r'\\W+',str(text))\n        symbols.extend(s),\n    return set(symbols)\n#Symbols presnet in the dataset\nfinal_symbols=get_symbols_in_one(train[\"question_text\"].values)\n\ndef clean_tag(x):\n    if '[math]' in x:\n        x=re.sub('\\[math\\].*?math\\]','MATH EQUATION',x)\n    if 'http' in x or 'www' in x:\n        x=re.sub('(?:(?:https?|ftp):\\/\\/)?[\\w/\\-?=%.]+\\.[\\w/\\-?=%.]+', 'URL', x)\n    return x\ndef clean_tag(x):\n    if '[math]' in x:\n        x=re.sub('\\[math\\].*?math\\]','MATH EQUATION',x)\n    if 'http' in x or 'www' in x:\n        x=re.sub('(?:(?:https?|ftp):\\/\\/)?[\\w/\\-?=%.]+\\.[\\w/\\-?=%.]+', 'URL', x)\n    return x\npuncts = [',', '.', '\"', ':', ')', '(', '-', '!', '?', '|', ';', \"'\", '$', '&', '/', '[', ']', '>', '%', '=', '#', '*', '+', '\\\\', \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, f' {punct} ')\n  return x\n\nmispell_dict = {'colour': 'color', 'centre': 'center', 'favourite': 'favorite', 'travelling': 'traveling', 'counselling': 'counseling', 'theatre': 'theater', \n                'cancelled': 'canceled', 'labour': 'labor', 'organisation': 'organization', \n                'wwii': 'world war 2', 'citicise': 'criticize', 'youtu ': 'youtube ', 'Qoura': 'Quora', \n                'sallary': 'salary', 'Whta': 'What', 'narcisist': 'narcissist', 'howdo': 'how do', 'whatare': 'what are', 'howcan': 'how can',\n                'howmuch': 'how much', 'howmany': 'how many', 'whydo': 'why do', 'doI': 'do I', 'theBest': 'the best', 'howdoes': 'how does',\n                'mastrubation': 'masturbation', 'mastrubate': 'masturbate', \"mastrubating\": 'masturbating', 'pennis': 'penis', \n                'Etherium': 'bitcoin', 'narcissit': 'narcissist', 'bigdata': 'big data', '2k17': '2017', '2k18': '2018', 'qouta': 'quota', 'exboyfriend': 'ex boyfriend',\n                'airhostess': 'air hostess', \"whst\": 'what', 'watsapp': 'whatsapp',\n                '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',\n                'ryzen':'cpu','whattsapp':'whatsapp',\n                'undertale':'adventure','zenfone':'smartphone','cryptocurencies':'cryptocurrencies','koinex':'bitcoin','zebpay':'bitcoin',\n                'binance':'bitcoin','whtsapp':'whatsapp',\n                'reactjs':'framework','bittrex':'bitcoin','bitconnect':'bitcoin','bitfinex':'bitcoin',\n                'yourquote':'your quote','whyis':'why is','jiophone':'smartphone',\n                'dogecoin':'bitcoin','onecoin':'bitcoin','poloniex':'bitcoin','7700k':'cpu','angular2':'framework',\n                'segwit2x':'bitcoin','hashflare':'bitcoin','940mx':'gpu',\n                'openai':'framework','hashflare':'bitcoin','1050ti':'gpu','nearbuy':'near buy','freebitco':'bitcoin',\n                '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',}\ndef correction_mispell(x):\n    word=x.split()\n    for i in range(0,len(word)):\n        if mispell_dict.get(word[i]) is not None:\n            word[i]=mispell_dict.get(word[i])\n        elif mispell_dict.get(word[i].lower()) is not None:\n            word[i]=mispell_dict.get(word[i].lower)\n        word=\" \".join(word)\n        return word\ncontraction_mapping = {\"We'd\": \"We had\", \"That'd\": \"That had\", \"AREN'T\": \"Are not\", \"HADN'T\": \"Had not\", \n                       \"Could've\": \"Could have\", \"LeT's\": \"Let us\", \"How'll\": \"How will\", \"They'll\": \"They will\", \n                       \"DOESN'T\": \"Does not\", \"HE'S\": \"He has\", \"O'Clock\": \"Of the clock\", \"Who'll\": \"Who will\", \"What'S\": \"What is\", \n                       \"Ain't\": \"Am not\", \"WEREN'T\": \"Were not\", \"Y'all\": \"You all\", \"Y'ALL\": \"You all\", \"Here's\": \"Here is\", \"It'd\": \"It had\", \n                       \"Should've\": \"Should have\", \"I'M\": \"I am\", \"ISN'T\": \"Is not\", \"Would've\": \"Would have\", \"He'll\": \"He will\", \n                       \"DON'T\": \"Do not\", \"She'd\": \"She had\", \"WOULDN'T\": \"Would not\", \"She'll\": \"She will\", \"IT's\": \"It is\",\n                       \"There'd\": \"There had\", \"It'll\": \"It will\", \"You'll\": \"You will\", \"He'd\": \"He had\", \"What'll\": \"What will\", \"Ma'am\": \"Madam\",\n                       \"CAN'T\": \"Can not\", \"THAT'S\": \"That is\", \"You've\": \"You have\", \"She's\": \"She is\", \"Weren't\": \"Were not\", \n                       \"They've\": \"They have\", \"Couldn't\": \"Could not\", \"When's\": \"When is\", \"Haven't\": \"Have not\", \"We'll\": \"We will\", \n                       \"That's\": \"That is\", \"We're\": \"We are\", \"They're\": \"They' are\", \"You'd\": \"You would\", \"How'd\": \"How did\", \n                       \"What're\": \"What are\", \"Hasn't\": \"Has not\", \"Wasn't\": \"Was not\", \"Won't\": \"Will not\", \"There's\": \"There is\", \n                       \"Didn't\": \"Did not\", \"Doesn't\": \"Does not\", \"You're\": \"You are\", \"He's\": \"He is\", \"SO's\": \"So is\", \"We've\": \"We have\", \n                       \"Who's\": \"Who is\", \"Wouldn't\": \"Would not\", \"Why's\": \"Why is\", \"WHO's\": \"Who is\", \"Let's\": \"Let us\", \"How's\": \"How is\", \n                       \"Can't\": \"Can not\", \"Where's\": \"Where is\", \"They'd\": \"They had\", \"Don't\": \"Do not\", \"Shouldn't\":\"Should not\",\n                       \"Aren't\":\"Are not\", \"ain't\": \"is not\", \"What's\": \"What is\", \"It's\": \"It is\", \"Isn't\":\"Is not\", \"aren't\": \"are not\",\n                       \"can't\": \"cannot\", \"'cause\": \"because\", \"could've\": \"could have\", \"couldn't\": \"could not\", \"didn't\": \"did not\",  \n                       \"doesn't\": \"does not\", \"don't\": \"do not\", \"hadn't\": \"had not\", \"hasn't\": \"has not\", \"haven't\": \"have not\", \n                       \"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\", \n                       \"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\",\n                       \"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\",\n                       \"i've\": \"i have\", \"isn't\": \"is not\", \"it'd\": \"it would\", \"it'd've\": \"it would have\", \"it'll\": \"it will\", \n                       \"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\",\n                       \"mightn't\": \"might not\",\"mightn't've\": \"might not have\", \"must've\": \"must have\", \"mustn't\": \"must not\", \n                       \"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\", \n                       \"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\",\n                       \"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\", \n                       \"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\",\n                       \"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\",\n                       \"they'd've\": \"they would have\", \"they'll\": \"they will\", \"they'll've\": \"they will have\", \"they're\": \"they are\", \"they've\": \"they have\", \n                       \"to've\": \"to have\", \"wasn't\": \"was not\", \"we'd\": \"we would\", \"we'd've\": \"we would have\", \n                       \"we'll\": \"we will\", \"we'll've\": \"we will have\", \"we're\": \"we are\", \"we've\": \"we have\", \"weren't\": \"were not\", \n                       \"what'll\": \"what will\", \"what'll've\": \"what will have\", \"what're\": \"what are\",  \"what's\": \"what is\", \"what've\": \"what have\", \n                       \"when's\": \"when is\", \"when've\": \"when have\", \"where'd\": \"where did\", \"where's\": \"where is\", \"where've\": \"where have\", \"who'll\": \"who will\", \n                       \"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\", \n                       \"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\", \n                       \"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\", \n                       \"you'd've\": \"you would have\",\n                       \"you'll\": \"you will\", \"you'll've\": \"you will have\", \"you're\": \"you are\", \"you've\": \"you have\" }\ndef clear_other_contradiction(x):\n    special=[\"’\", \"‘\", \"´\", \"`\"]\n    for s in special:\n        x=x.replace(s,\"'\")\n    x = ' '.join([contraction_mapping[n] if n in contraction_mapping else n for n in x.split(\" \")])\n    return x\nlemmatizer = WordNetLemmatizer()\ndef lemma_text(x):\n  x = x.split()\n  x = [lemmatizer.lemmatize(word) for word in x]\n  x = ' '.join(x)\n\n  return x\ndef data_cleaning(x):\n    clean_tag(x)\n    clean_punct(x)\n    correction_mispell(x)\n    clear_other_contradiction(x)\n    lemma_text(x)\n    return x\ntrain['question_text']=train['question_text'].apply(lambda x:data_cleaning(x))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.tail()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"embed_size = 300 # how big is each word vector\nmax_features = 61000 # how many unique words to use (i.e num rows in embedding vector)\nmaxlen = 70 # max number of words in a question to use\ndef load_and_prec():\n    print(\"Entered\")\n    train_df,test_df, = train_test_split(train,test_size=0.20, random_state=2018)\n\n    ## fill up the missing values\n    train_X = train_df[\"question_text\"].fillna(\"_##_\").values\n    test_X = test_df[\"question_text\"].fillna(\"_##_\").values\n\n    ## Tokenize the sentences\n    tokenizer = Tokenizer(num_words=max_features)\n    tokenizer.fit_on_texts(list(train_X))\n    train_X = tokenizer.texts_to_sequences(train_X)\n    test_X = tokenizer.texts_to_sequences(test_X)\n\n    ## Pad the sentences \n    train_X = pad_sequences(train_X, maxlen=maxlen)\n    test_X = pad_sequences(test_X, maxlen=maxlen)\n\n    ## Get the target values\n    train_y = train_df['target'].values\n    test_y=test_df['target'].values\n    \n    #shuffling the data\n    np.random.seed(2018)\n    trn_idx = np.random.permutation(len(train_X))\n\n    train_X = train_X[trn_idx]\n    train_y = train_y[trn_idx]\n    return train_X, test_X, train_y, test_y,tokenizer.word_index\ntrain_X, test_X, train_y,test_y, word_index = load_and_prec() ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train_X.shape)\nprint(test_X.shape)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"dba1893c267a1e7536bbf720636647d85c7e349c"},"cell_type":"markdown","source":"**Load embeddings**"},{"metadata":{"trusted":true,"_uuid":"a662716cc5fbbcc0c84019a87c52332ed8912e8d"},"cell_type":"code","source":"def load_glove(word_index):\n    EMBEDDING_FILE = '../input/embeddings/glove.840B.300d/glove.840B.300d.txt'\n    def get_coefs(word,*arr): return word, np.asarray(arr, dtype='float32')\n    embeddings_index = dict(get_coefs(*o.split(\" \")) for o in open(EMBEDDING_FILE))\n\n    all_embs = np.stack(embeddings_index.values())\n    emb_mean,emb_std = all_embs.mean(), all_embs.std()\n    embed_size = all_embs.shape[1]\n\n    # word_index = tokenizer.word_index\n    nb_words = min(max_features, len(word_index))\n    embedding_matrix = np.random.normal(emb_mean, emb_std, (nb_words, embed_size))\n    for word, i in word_index.items():\n        if i >= max_features: continue\n        embedding_vector = embeddings_index.get(word)\n        if embedding_vector is not None: embedding_matrix[i] = embedding_vector\n            \n    return embedding_matrix \n    \ndef load_fasttext(word_index):    \n    EMBEDDING_FILE = '../input/embeddings/wiki-news-300d-1M/wiki-news-300d-1M.vec'\n    def get_coefs(word,*arr): return word, np.asarray(arr, dtype='float32')\n    embeddings_index = dict(get_coefs(*o.split(\" \")) for o in open(EMBEDDING_FILE) if len(o)>100)\n\n    all_embs = np.stack(embeddings_index.values())\n    emb_mean,emb_std = all_embs.mean(), all_embs.std()\n    embed_size = all_embs.shape[1]\n\n    # word_index = tokenizer.word_index\n    nb_words = min(max_features, len(word_index))\n    embedding_matrix = np.random.normal(emb_mean, emb_std, (nb_words, embed_size))\n    for word, i in word_index.items():\n        if i >= max_features: continue\n        embedding_vector = embeddings_index.get(word)\n        if embedding_vector is not None: embedding_matrix[i] = embedding_vector\n\n    return embedding_matrix\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"5a676c3a275514a3351edf306e02d832a5f39317"},"cell_type":"markdown","source":"**Attention layer**"},{"metadata":{"trusted":true,"_uuid":"84e00df2c7b94205f5588af503f62412c48f46f3"},"cell_type":"code","source":"#https://blog.keras.io/using-pre-trained-word-embeddings-in-a-keras-model.html\n#https://arxiv.org/abs/1706.03762\n#https://arxiv.org/abs/1409.0473\n\nclass Attention(Layer):\n    def __init__(self, step_dim,\n                 W_regularizer=None, b_regularizer=None,\n                 W_constraint=None, b_constraint=None,\n                 bias=True, **kwargs):\n        self.supports_masking = True\n        self.init = initializers.get('glorot_uniform')\n\n        self.W_regularizer = regularizers.get(W_regularizer)\n        self.b_regularizer = regularizers.get(b_regularizer)\n\n        self.W_constraint = constraints.get(W_constraint)\n        self.b_constraint = constraints.get(b_constraint)\n\n        self.bias = bias\n        self.step_dim = step_dim\n        self.features_dim = 0\n        super(Attention, self).__init__(**kwargs)\n\n    def build(self, input_shape):\n        assert len(input_shape) == 3\n\n        self.W = self.add_weight((input_shape[-1],),\n                                 initializer=self.init,\n                                 name='{}_W'.format(self.name),\n                                 regularizer=self.W_regularizer,\n                                 constraint=self.W_constraint)\n        self.features_dim = input_shape[-1]\n\n        if self.bias:\n            self.b = self.add_weight((input_shape[1],),\n                                     initializer='zero',\n                                     name='{}_b'.format(self.name),\n                                     regularizer=self.b_regularizer,\n                                     constraint=self.b_constraint)\n        else:\n            self.b = None\n\n        self.built = True\n\n    def compute_mask(self, input, input_mask=None):\n        return None\n\n    def call(self, x, mask=None):\n        features_dim = self.features_dim\n        step_dim = self.step_dim\n\n        eij = K.reshape(K.dot(K.reshape(x, (-1, features_dim)),\n                        K.reshape(self.W, (features_dim, 1))), (-1, step_dim))\n\n        if self.bias:\n            eij += self.b\n\n        eij = K.tanh(eij)\n\n        a = K.exp(eij)\n\n        if mask is not None:\n            a *= K.cast(mask, K.floatx())\n\n        a /= K.cast(K.sum(a, axis=1, keepdims=True) + K.epsilon(), K.floatx())\n\n        a = K.expand_dims(a)\n        weighted_input = x * a\n        return K.sum(weighted_input, axis=1)\n\n    def compute_output_shape(self, input_shape):\n        return input_shape[0],  self.features_dim","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"34bc6b787e54f497bbceb6e76553a1166740c5a2"},"cell_type":"markdown","source":"**F1 score and CLR**"},{"metadata":{"trusted":true,"_uuid":"d3c6f9010fe9db1885297a5457b6fa77f56d2b71"},"cell_type":"code","source":"class CyclicLR(Callback):\n    print(\"Cyclic CLR called\")\n    \"\"\"This callback implements a cyclical learning rate policy (CLR).\n    The method cycles the learning rate between two boundaries with\n    some constant frequency, as detailed in this paper (https://arxiv.org/abs/1506.01186).\n    The amplitude of the cycle can be scaled on a per-iteration or \n    per-cycle basis.\n    This class has three built-in policies, as put forth in the paper.\n    \"triangular\":\n        A basic triangular cycle w/ no amplitude scaling.\n    \"triangular2\":\n        A basic triangular cycle that scales initial amplitude by half each cycle.\n    \"exp_range\":\n        A cycle that scales initial amplitude by gamma**(cycle iterations) at each \n        cycle iteration.\n    For more detail, please see paper.\n    \n    # Example\n        ```python\n            clr = CyclicLR(base_lr=0.001, max_lr=0.006,\n                                step_size=2000., mode='triangular')\n            model.fit(X_train, Y_train, callbacks=[clr])\n        ```\n    \n    Class also supports custom scaling functions:\n        ```python\n            clr_fn = lambda x: 0.5*(1+np.sin(x*np.pi/2.))\n            clr = CyclicLR(base_lr=0.001, max_lr=0.006,\n                                step_size=2000., scale_fn=clr_fn,\n                                scale_mode='cycle')\n            model.fit(X_train, Y_train, callbacks=[clr])\n        ```    \n    # Arguments\n        base_lr: initial learning rate which is the\n            lower boundary in the cycle.\n        max_lr: upper boundary in the cycle. Functionally,\n            it defines the cycle amplitude (max_lr - base_lr).\n            The lr at any cycle is the sum of base_lr\n            and some scaling of the amplitude; therefore \n            max_lr may not actually be reached depending on\n            scaling function.\n        step_size: number of training iterations per\n            half cycle. Authors suggest setting step_size\n            2-8 x training iterations in epoch.\n        mode: one of {triangular, triangular2, exp_range}.\n            Default 'triangular'.\n            Values correspond to policies detailed above.\n            If scale_fn is not None, this argument is ignored.\n        gamma: constant in 'exp_range' scaling function:\n            gamma**(cycle iterations)\n        scale_fn: Custom scaling policy defined by a single\n            argument lambda function, where \n            0 <= scale_fn(x) <= 1 for all x >= 0.\n            mode paramater is ignored \n        scale_mode: {'cycle', 'iterations'}.\n            Defines whether scale_fn is evaluated on \n            cycle number or cycle iterations (training\n            iterations since start of cycle). Default is 'cycle'.\n    \"\"\"\n    def __init__(self, base_lr=0.001, max_lr=0.006, step_size=2000., mode='triangular',\n                 gamma=1., scale_fn=None, scale_mode='cycle'):\n        super(CyclicLR, self).__init__()\n\n        self.base_lr = base_lr\n        self.max_lr = max_lr\n        self.step_size = step_size\n        self.mode = mode\n        self.gamma = gamma\n        if scale_fn == None:\n            if self.mode == 'triangular':\n                self.scale_fn = lambda x: 1.\n                self.scale_mode = 'cycle'\n            elif self.mode == 'triangular2':\n                self.scale_fn = lambda x: 1/(2.**(x-1))\n                self.scale_mode = 'cycle'\n            elif self.mode == 'exp_range':\n                self.scale_fn = lambda x: gamma**(x)\n                self.scale_mode = 'iterations'\n        else:\n            self.scale_fn = scale_fn\n            self.scale_mode = scale_mode\n        self.clr_iterations = 0.\n        self.trn_iterations = 0.\n        self.history = {}\n\n        self._reset()\n\n    def _reset(self, new_base_lr=None, new_max_lr=None,\n               new_step_size=None):\n        \"\"\"Resets cycle iterations.\n        Optional boundary/step size adjustment.\n        \"\"\"\n        if new_base_lr != None:\n            self.base_lr = new_base_lr\n        if new_max_lr != None:\n            self.max_lr = new_max_lr\n        if new_step_size != None:\n            self.step_size = new_step_size\n        self.clr_iterations = 0.\n        \n    def clr(self):\n        cycle = np.floor(1+self.clr_iterations/(2*self.step_size))\n        x = np.abs(self.clr_iterations/self.step_size - 2*cycle + 1)\n        if self.scale_mode == 'cycle':\n            return self.base_lr + (self.max_lr-self.base_lr)*np.maximum(0, (1-x))*self.scale_fn(cycle)\n        else:\n            return self.base_lr + (self.max_lr-self.base_lr)*np.maximum(0, (1-x))*self.scale_fn(self.clr_iterations)\n        \n    def on_train_begin(self, logs={}):\n        logs = logs or {}\n\n        if self.clr_iterations == 0:\n            K.set_value(self.model.optimizer.lr, self.base_lr)\n        else:\n            K.set_value(self.model.optimizer.lr, self.clr())        \n            \n    def on_batch_end(self, epoch, logs=None):\n        \n        logs = logs or {}\n        self.trn_iterations += 1\n        self.clr_iterations += 1\n\n        self.history.setdefault('lr', []).append(K.get_value(self.model.optimizer.lr))\n        self.history.setdefault('iterations', []).append(self.trn_iterations)\n\n        for k, v in logs.items():\n            self.history.setdefault(k, []).append(v)\n        \n        K.set_value(self.model.optimizer.lr, self.clr())\n    \n\ndef f1(y_true, y_pred):\n    '''\n    metric from here \n    https://stackoverflow.com/questions/43547402/how-to-calculate-f1-macro-in-keras\n    '''\n    def recall(y_true, y_pred):\n        \"\"\"Recall metric.\n\n        Only computes a batch-wise average of recall.\n\n        Computes the recall, a metric for multi-label classification of\n        how many relevant items are selected.\n        \"\"\"\n        true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))\n        possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))\n        recall = true_positives / (possible_positives + K.epsilon())\n        return recall\n\n    def precision(y_true, y_pred):\n        \"\"\"Precision metric.\n\n        Only computes a batch-wise average of precision.\n\n        Computes the precision, a metric for multi-label classification of\n        how many selected items are relevant.\n        \"\"\"\n        true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))\n        predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))\n        precision = true_positives / (predicted_positives + K.epsilon())\n        return precision\n    precision = precision(y_true, y_pred)\n    recall = recall(y_true, y_pred)\n    return 2*((precision*recall)/(precision+recall+K.epsilon()))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"embedding_matrix_glove = load_glove(word_index)\nembedding_matrix_fast = load_fasttext(word_index)\nembedding_matrix = np.mean([embedding_matrix_glove,embedding_matrix_fast], axis = 0)\nnp.shape(embedding_matrix)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"99d03d2eb63600f1b222522616eab3fa35819f37"},"cell_type":"code","source":"\n#embedding_matrix_3 = load_para(word_index)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f0ea9b1468bd7cd3ceead2593c641900dc3a2a77"},"cell_type":"code","source":"## Simple average: http://aclweb.org/anthology/N18-2031\n## Unweighted DME in https://arxiv.org/pdf/1804.07983.pdf  \nembedding_matrix = np.mean([embedding_matrix_glove,embedding_matrix_fast], axis = 0)\nnp.shape(embedding_matrix)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"89b49b33d6204e1695888cf0a5fe683d4d37ef00"},"cell_type":"code","source":"def threshold_search(y_true, y_proba):\n    best_threshold = 0\n    best_score = 0\n    for threshold in np.arange(0.1, 0.501, 0.01):\n    #for threshold in [i * 0.01 for i in range(100)]:\n        threshold = np.round(threshold, 2)\n        #precision=precision_score(y_true=y_true, y_pred=y_proba > threshold)\n        #recall=recall_score(y_true=y_true, y_pred=y_proba > threshold)\n        score = f1_score(y_true=y_true, y_pred=y_proba > threshold)\n        print(\"F1 score at threshold {0} is {1} \".format(threshold,score))\n        if score > best_score:\n            best_threshold = threshold\n            best_score = score\n            recall=recall_score\n            precision=precision_score\n    search_result = {'threshold': best_threshold, 'f1': best_score}\n    print(\"Best thershold {0} and F1 score is {1} \".format(best_threshold,best_score))\n    return search_result","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def train_pred(model, train_X, train_y, val_X, val_y, epochs=2, callback=None):\n    for e in range(epochs):\n        model.fit(train_X, train_y, batch_size=512, epochs=1, validation_data=(val_X, val_y), callbacks = callback, verbose=0)\n        pred_val_y = model.predict([val_X], batch_size=1024, verbose=0)\n        best_score = metrics.f1_score(val_y, (pred_val_y >0.38).astype(int))\n        print(\"Epoch: \", e, \"-    Val F1 Score: {:.4f} \".format(best_score))\n    pred_test_y = model.predict([test_X], batch_size=1024, verbose=0)\n    print('=' * 60)\n    return pred_val_y, pred_test_y, best_score","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def model_lstm_atten1(embedding_matrix):    \n    inp = Input(shape=(maxlen,))\n    x = Embedding(max_features, embed_size, weights=[embedding_matrix], trainable=False)(inp)\n    x = SpatialDropout1D(0.1)(x)\n    x = Bidirectional(CuDNNLSTM(256, return_sequences=True))(x)\n    y = Bidirectional(CuDNNGRU(128, return_sequences=True))(x)\n    \n    atten_1 = Attention(maxlen)(x) # skip connect\n    atten_2 = Attention(maxlen)(y)\n    avg_pool = GlobalMaxPooling1D()(y)\n    max_pool = GlobalMaxPooling1D()(y)\n    \n    conc = concatenate([atten_1, atten_2, avg_pool, max_pool])\n    outp = Dense(1, activation=\"sigmoid\")(conc)    \n    model = Model(inputs=inp, outputs=outp)\n    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=[f1])\n    \n    return model\ndef model_lstm_atten(embedding_matrix):\n    inp = Input(shape=(maxlen,))\n    x = Embedding(max_features, embed_size, weights=[embedding_matrix], trainable=False)(inp)\n    x = SpatialDropout1D(0.1)(x)\n    x = Bidirectional(CuDNNLSTM(40, return_sequences=True))(x)\n    y = Bidirectional(CuDNNGRU(40, return_sequences=True))(x)    \n    atten_1 = Attention(maxlen)(x) # skip connect\n    atten_2 = Attention(maxlen)(y)\n    avg_pool = GlobalAveragePooling1D()(y)\n    max_pool = GlobalMaxPooling1D()(y)\n    conc = concatenate([atten_1, atten_2, avg_pool, max_pool])\n    conc = Dense(16, activation=\"relu\")(conc)\n    conc = Dropout(0.1)(conc)\n    outp = Dense(1, activation=\"sigmoid\")(conc)    \n    model = Model(inputs=inp, outputs=outp)\n    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=[f1])\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#with threshold 0.38\nDATA_SPLIT_SEED = 2018\nclr = CyclicLR(base_lr=0.001, max_lr=0.003,\n               step_size=300., mode='exp_range',\n               gamma=0.99994)\n\ntrain_meta = np.zeros(train_y.shape)\ntest_meta = np.zeros(test_X.shape[0])\nsplits = list(StratifiedKFold(n_splits=4, shuffle=True,random_state=DATA_SPLIT_SEED).split(train_X, train_y))\nfor idx, (train_idx, valid_idx) in enumerate(splits):\n        X_train = train_X[train_idx]\n        y_train = train_y[train_idx]\n        X_val = train_X[valid_idx]\n        y_val = train_y[valid_idx]\n        model = model_lstm_atten1(embedding_matrix)\n        pred_val_y, pred_test_y, best_score = train_pred(model, X_train, y_train, X_val, y_val, epochs = 4, callback = [clr])\n        train_meta[valid_idx] = pred_val_y.reshape(-1)\n        test_meta += pred_test_y.reshape(-1) / len(splits)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"threshold_search(y_true=train_y, y_proba=train_meta)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"threshold_search(y_true=test_y, y_proba=test_meta)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#lr_0.02\nDATA_SPLIT_SEED = 2018\nclr = CyclicLR(base_lr=0.001, max_lr=0.002,\n               step_size=300., mode='exp_range',\n               gamma=0.99994)\n\ntrain_meta = np.zeros(train_y.shape)\ntest_meta = np.zeros(test_X.shape[0])\nsplits = list(StratifiedKFold(n_splits=4, shuffle=True,random_state=DATA_SPLIT_SEED).split(train_X, train_y))\nfor idx, (train_idx, valid_idx) in enumerate(splits):\n        X_train = train_X[train_idx]\n        y_train = train_y[train_idx]\n        X_val = train_X[valid_idx]\n        y_val = train_y[valid_idx]\n        model = model_lstm_atten(embedding_matrix)\n        pred_val_y, pred_test_y, best_score = train_pred(model, X_train, y_train, X_val, y_val, epochs = 4, callback = [clr])\n        train_meta[valid_idx] = pred_val_y.reshape(-1)\n        test_meta += pred_test_y.reshape(-1) / len(splits)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"threshold_search(y_true=train_y, y_proba=train_meta)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"threshold_search(y_true=test_y, y_proba=test_meta)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nDATA_SPLIT_SEED = 2018\nclr = CyclicLR(base_lr=0.001, max_lr=0.004,\n               step_size=300., mode='exp_range',\n               gamma=0.99994)\n\ntrain_meta = np.zeros(train_y.shape)\ntest_meta = np.zeros(test_X.shape[0])\nsplits = list(StratifiedKFold(n_splits=4, shuffle=True,random_state=DATA_SPLIT_SEED).split(train_X, train_y))\nfor idx, (train_idx, valid_idx) in enumerate(splits):\n        X_train = train_X[train_idx]\n        y_train = train_y[train_idx]\n        X_val = train_X[valid_idx]\n        y_val = train_y[valid_idx]\n        model = model_lstm_atten1(embedding_matrix)\n        pred_val_y, pred_test_y, best_score = train_pred(model, X_train, y_train, X_val, y_val, epochs = 4, callback = [clr])\n        train_meta[valid_idx] = pred_val_y.reshape(-1)\n        test_meta += pred_test_y.reshape(-1) / len(splits)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"threshold_search(y_true=train_y, y_proba=train_meta)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"threshold_search(y_true=test_y, y_proba=test_meta)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#with different number of k folds \nDATA_SPLIT_SEED = 2018\nclr = CyclicLR(base_lr=0.001, max_lr=0.003,\n               step_size=300., mode='exp_range',\n               gamma=0.99994)\n\ntrain_meta = np.zeros(train_y.shape)\ntest_meta = np.zeros(test_X.shape[0])\nsplits = list(StratifiedKFold(n_splits=7, shuffle=True,random_state=DATA_SPLIT_SEED).split(train_X, train_y))\nfor idx, (train_idx, valid_idx) in enumerate(splits):\n        X_train = train_X[train_idx]\n        y_train = train_y[train_idx]\n        X_val = train_X[valid_idx]\n        y_val = train_y[valid_idx]\n        model = model_lstm_atten1(embedding_matrix)\n        pred_val_y, pred_test_y, best_score = train_pred(model, X_train, y_train, X_val, y_val, epochs = 4, callback = [clr])\n        train_meta[valid_idx] = pred_val_y.reshape(-1)\n        test_meta += pred_test_y.reshape(-1) / len(splits)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"threshold_search(y_true=train_y, y_proba=train_meta)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"threshold_search(y_true=test_y, y_proba=test_meta)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#with different number of epochs \nDATA_SPLIT_SEED = 2018\nclr = CyclicLR(base_lr=0.001, max_lr=0.003,\n               step_size=300., mode='exp_range',\n               gamma=0.99994)\n\ntrain_meta = np.zeros(train_y.shape)\ntest_meta = np.zeros(test_X.shape[0])\nsplits = list(StratifiedKFold(n_splits=7, shuffle=True,random_state=DATA_SPLIT_SEED).split(train_X, train_y))\nfor idx, (train_idx, valid_idx) in enumerate(splits):\n        X_train = train_X[train_idx]\n        y_train = train_y[train_idx]\n        X_val = train_X[valid_idx]\n        y_val = train_y[valid_idx]\n        model = model_lstm_atten1(embedding_matrix)\n        pred_val_y, pred_test_y, best_score = train_pred(model, X_train, y_train, X_val, y_val, epochs = 6, callback = [clr])\n        train_meta[valid_idx] = pred_val_y.reshape(-1)\n        test_meta += pred_test_y.reshape(-1) / len(splits)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"threshold_search(y_true=train_y, y_proba=train_meta)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"threshold_search(y_true=test_y, y_proba=test_meta)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#with threshold 0.33\nclr = CyclicLR(base_lr=0.001, max_lr=0.003,\n               step_size=300., mode='exp_range',\n               gamma=0.99994)\n\ntrain_meta = np.zeros(train_y.shape)\ntest_meta = np.zeros(test_X.shape[0])\nsplits = list(StratifiedKFold(n_splits=4, shuffle=True,random_state=DATA_SPLIT_SEED).split(train_X, train_y))\nfor idx, (train_idx, valid_idx) in enumerate(splits):\n        X_train = train_X[train_idx]\n        y_train = train_y[train_idx]\n        X_val = train_X[valid_idx]\n        y_val = train_y[valid_idx]\n        model = model_lstm(embedding_matrix)\n        pred_val_y, pred_test_y, best_score = train_pred(model, X_train, y_train, X_val, y_val, epochs = 4, callback = [clr])\n        train_meta[valid_idx] = pred_val_y.reshape(-1)\n        test_meta += pred_test_y.reshape(-1) / len(splits)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"threshold_search(y_true=train_y, y_proba=train_meta)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"threshold_search(y_true=test_y, y_proba=test_meta)","execution_count":null,"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":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}