

In [1]:

    
from theano.sandbox import cuda









    



WARNING (theano.sandbox.cuda): The cuda backend is deprecated and will be removed in the next release (v0.10).  Please switch to the gpuarray backend. You can get more information about how to switch at this URL:
 https://github.com/Theano/Theano/wiki/Converting-to-the-new-gpu-back-end%28gpuarray%29

Using gpu device 0: Tesla K80 (CNMeM is disabled, cuDNN 5103)



In [2]:

    
import utils; reload(utils)
from utils import *









    



Using Theano backend.

Setup data



In [3]:

    
from keras.datasets import imdb



In [5]:

    
idx = imdb.get_word_index()









    



Downloading data from https://s3.amazonaws.com/text-datasets/imdb_word_index.pkl



In [6]:

    
idx









    Out[6]:





{'fawn': 34701,
 'tsukino': 52006,
 'nunnery': 52007,
 'sonja': 16816,
 'vani': 63951,
 'woods': 1408,
 'spiders': 16115,
 'hanging': 2345,
 'woody': 2289,
 'trawling': 52008,
 "hold's": 52009,
 'comically': 11307,
 'localized': 40830,
 'disobeying': 30568,
 "'royale": 52010,
 "harpo's": 40831,
 'canet': 52011,
 'aileen': 19313,
 'acurately': 52012,
 "diplomat's": 52013,
 'rickman': 25242,
 'arranged': 6746,
 'rumbustious': 52014,
 'familiarness': 52015,
 "spider'": 52016,
 'hahahah': 68804,
 "wood'": 52017,
 'transvestism': 40833,
 "hangin'": 34702,
 'bringing': 2338,
 'seamier': 40834,
 'wooded': 34703,
 'bravora': 52018,
 'grueling': 16817,
 'wooden': 1636,
 'wednesday': 16818,
 "'prix": 52019,
 'altagracia': 34704,
 'circuitry': 52020,
 'crotch': 11585,
 'busybody': 57766,
 "tart'n'tangy": 52021,
 'burgade': 14129,
 'thrace': 52023,
 "tom's": 11038,
 'snuggles': 52025,
 'francesco': 29114,
 'complainers': 52027,
 'templarios': 52125,
 '272': 40835,
 '273': 52028,
 'zaniacs': 52130,
 '275': 34706,
 'consenting': 27631,
 'snuggled': 40836,
 'inanimate': 15492,
 'uality': 52030,
 'bronte': 11926,
 'errors': 4010,
 'dialogs': 3230,
 "yomada's": 52031,
 "madman's": 34707,
 'dialoge': 30585,
 'usenet': 52033,
 'videodrome': 40837,
 "kid'": 26338,
 'pawed': 52034,
 "'girlfriend'": 30569,
 "'pleasure": 52035,
 "'reloaded'": 52036,
 "kazakos'": 40839,
 'rocque': 52037,
 'mailings': 52038,
 'brainwashed': 11927,
 'mcanally': 16819,
 "tom''": 52039,
 'kurupt': 25243,
 'affiliated': 21905,
 'babaganoosh': 52040,
 "noe's": 40840,
 'quart': 40841,
 'kids': 359,
 'uplifting': 5034,
 'controversy': 7093,
 'kida': 21906,
 'kidd': 23379,
 "error'": 52041,
 'neurologist': 52042,
 'spotty': 18510,
 'cobblers': 30570,
 'projection': 9878,
 'fastforwarding': 40842,
 'sters': 52043,
 "eggar's": 52044,
 'etherything': 52045,
 'gateshead': 40843,
 'airball': 34708,
 'unsinkable': 25244,
 'stern': 7180,
 "cervi's": 52046,
 'dnd': 40844,
 'dna': 11586,
 'insecurity': 20598,
 "'reboot'": 52047,
 'trelkovsky': 11037,
 'jaekel': 52048,
 'sidebars': 52049,
 "sforza's": 52050,
 'distortions': 17633,
 'mutinies': 52051,
 'sermons': 30602,
 '7ft': 40846,
 'boobage': 52052,
 "o'bannon's": 52053,
 'populations': 23380,
 'chulak': 52054,
 'mesmerize': 27633,
 'quinnell': 52055,
 'yahoo': 10307,
 'meteorologist': 52057,
 'beswick': 42577,
 'boorman': 15493,
 'voicework': 40847,
 "ster'": 52058,
 'blustering': 22922,
 'hj': 52059,
 'intake': 27634,
 'morally': 5621,
 'jumbling': 40849,
 'bowersock': 52060,
 "'porky's'": 52061,
 'gershon': 16821,
 'ludicrosity': 40850,
 'coprophilia': 52062,
 'expressively': 40851,
 "india's": 19500,
 "post's": 34710,
 'wana': 52063,
 'wang': 5283,
 'wand': 30571,
 'wane': 25245,
 'edgeways': 52321,
 'titanium': 34711,
 'pinta': 40852,
 'want': 178,
 'pinto': 30572,
 'whoopdedoodles': 52065,
 'tchaikovsky': 21908,
 'travel': 2103,
 "'victory'": 52066,
 'copious': 11928,
 'gouge': 22433,
 "chapters'": 52067,
 'barbra': 6702,
 'uselessness': 30573,
 "wan'": 52068,
 'assimilated': 27635,
 'petiot': 16116,
 'most\xc2\x85and': 52069,
 'dinosaurs': 3930,
 'wrong': 352,
 'seda': 52070,
 'stollen': 52071,
 'sentencing': 34712,
 'ouroboros': 40853,
 'assimilates': 40854,
 'colorfully': 40855,
 'glenne': 27636,
 'dongen': 52072,
 'subplots': 4760,
 'kiloton': 52073,
 'chandon': 23381,
 "effect'": 34713,
 'snugly': 27637,
 'kuei': 40856,
 'welcomed': 9092,
 'dishonor': 30071,
 'concurrence': 52075,
 'stoicism': 23382,
 "guys'": 14896,
 "beroemd'": 52077,
 'butcher': 6703,
 "melfi's": 40857,
 'aargh': 30623,
 'playhouse': 20599,
 'wickedly': 11308,
 'fit': 1180,
 'labratory': 52078,
 'lifeline': 40859,
 'screaming': 1927,
 'fix': 4287,
 'cineliterate': 52079,
 'fic': 52080,
 'fia': 52081,
 'fig': 34714,
 'fmvs': 52082,
 'fie': 52083,
 'reentered': 52084,
 'fin': 30574,
 'doctresses': 52085,
 'fil': 52086,
 'zucker': 12606,
 'ached': 31931,
 'counsil': 52088,
 'paterfamilias': 52089,
 'songwriter': 13885,
 'shivam': 34715,
 'hurting': 9654,
 'effects': 299,
 'slauther': 52090,
 "'flame'": 52091,
 'sommerset': 52092,
 'interwhined': 52093,
 'whacking': 27638,
 'bartok': 52094,
 'barton': 8775,
 'frewer': 21909,
 "fi'": 52095,
 'ingrid': 6192,
 'stribor': 30575,
 'approporiately': 52096,
 'wobblyhand': 52097,
 'tantalisingly': 52098,
 'ankylosaurus': 52099,
 'parasites': 17634,
 'childen': 52100,
 "jenkins'": 52101,
 'metafiction': 52102,
 'golem': 17635,
 'indiscretion': 40860,
 "reeves'": 23383,
 "inamorata's": 57781,
 'brittannica': 52104,
 'adapt': 7916,
 "russo's": 30576,
 'guitarists': 48246,
 'abbott': 10553,
 'abbots': 40861,
 'lanisha': 17649,
 'magickal': 40863,
 'mattter': 52105,
 "'willy": 52106,
 'pumpkins': 34716,
 'stuntpeople': 52107,
 'estimate': 30577,
 'ugghhh': 40864,
 'gameplay': 11309,
 "wern't": 52108,
 "n'sync": 40865,
 'sickeningly': 16117,
 'chiara': 40866,
 'disturbed': 4011,
 'portmanteau': 40867,
 'ineffectively': 52109,
 "duchonvey's": 82143,
 "nasty'": 37519,
 'purpose': 1285,
 'lazers': 52112,
 'lightened': 28105,
 'kaliganj': 52113,
 'popularism': 52114,
 "damme's": 18511,
 'stylistics': 30578,
 'mindgaming': 52115,
 'spoilerish': 46449,
 "'corny'": 52117,
 'boerner': 34718,
 'olds': 6792,
 'bakelite': 52118,
 'renovated': 27639,
 'forrester': 27640,
 "lumiere's": 52119,
 'gaskets': 52024,
 'needed': 884,
 'smight': 34719,
 'master': 1297,
 "edie's": 25905,
 'seeber': 40868,
 'hiya': 52120,
 'fuzziness': 52121,
 'genesis': 14897,
 'rewards': 12607,
 'enthrall': 30579,
 "'about": 40869,
 "recollection's": 52122,
 'mutilated': 11039,
 'fatherlands': 52123,
 "fischer's": 52124,
 'positively': 5399,
 '270': 34705,
 'ahmed': 34720,
 'zatoichi': 9836,
 'bannister': 13886,
 'anniversaries': 52127,
 "helm's": 30580,
 "'work'": 52128,
 'exclaimed': 34721,
 "'unfunny'": 52129,
 '274': 52029,
 'feeling': 544,
 "wanda's": 52131,
 'dolan': 33266,
 '278': 52133,
 'peacoat': 52134,
 'brawny': 40870,
 'mishra': 40871,
 'worlders': 40872,
 'protags': 52135,
 'skullcap': 52136,
 'dastagir': 57596,
 'affairs': 5622,
 'wholesome': 7799,
 'hymen': 52137,
 'paramedics': 25246,
 'unpersons': 52138,
 'heavyarms': 52139,
 'affaire': 52140,
 'coulisses': 52141,
 'hymer': 40873,
 'kremlin': 52142,
 'shipments': 30581,
 'pixilated': 52143,
 "'00s": 30582,
 'diminishing': 18512,
 'cinematic': 1357,
 'resonates': 14898,
 'simplify': 40874,
 "nature'": 40875,
 'temptresses': 40876,
 'reverence': 16822,
 'resonated': 19502,
 'dailey': 34722,
 '2\xc2\x85': 52144,
 'treize': 27641,
 'majo': 52145,
 'kiya': 21910,
 'woolnough': 52146,
 'thanatos': 39797,
 'sandoval': 35731,
 'dorama': 40879,
 "o'shaughnessy": 52147,
 'tech': 4988,
 'fugitives': 32018,
 'teck': 30583,
 "'e'": 76125,
 'doesn\xe2\x80\x99t': 40881,
 'purged': 52149,
 'saying': 657,
 "martians'": 41095,
 'norliss': 23418,
 'dickey': 27642,
 'dicker': 52152,
 "'sependipity": 52153,
 'padded': 8422,
 'ordell': 57792,
 "sturges'": 40882,
 'independentcritics': 52154,
 'tempted': 5745,
 "atkinson's": 34724,
 'hounded': 25247,
 'apace': 52155,
 'clicked': 15494,
 "'humor'": 30584,
 "martino's": 17177,
 "'supporting": 52156,
 'warmongering': 52032,
 "zemeckis's": 34725,
 'lube': 21911,
 'shocky': 52157,
 'plate': 7476,
 'plata': 40883,
 'sturgess': 40884,
 "nerds'": 40885,
 'plato': 20600,
 'plath': 34726,
 'platt': 40886,
 'mcnab': 52159,
 'clumsiness': 27643,
 'altogether': 3899,
 'massacring': 42584,
 'bicenntinial': 52160,
 'skaal': 40887,
 'droning': 14360,
 'lds': 8776,
 'jaguar': 21912,
 "cale's": 34727,
 'nicely': 1777,
 'mummy': 4588,
 "lot's": 18513,
 'patch': 10086,
 'kerkhof': 50202,
 "leader's": 52161,
 "'movie": 27644,
 'uncomfirmed': 52162,
 'heirloom': 40888,
 'wrangle': 47360,
 'emotion\xc2\x85': 52163,
 "'stargate'": 52164,
 'pinoy': 40889,
 'conchatta': 40890,
 'broeke': 41128,
 'advisedly': 40891,
 "barker's": 17636,
 'descours': 52166,
 'lots': 772,
 'lotr': 9259,
 'irs': 9879,
 'lott': 52167,
 'xvi': 40892,
 'irk': 34728,
 'irl': 52168,
 'ira': 6887,
 'belzer': 21913,
 'irc': 52169,
 'ire': 27645,
 'requisites': 40893,
 'discipline': 7693,
 'lyoko': 52961,
 'extend': 11310,
 'nature': 873,
 "'dickie'": 52170,
 'optimist': 40894,
 'lapping': 30586,
 'superficial': 3900,
 'vestment': 52171,
 'extent': 2823,
 'tendons': 52172,
 "heller's": 52173,
 'quagmires': 52174,
 'miyako': 52175,
 'moocow': 20601,
 "coles'": 52176,
 'lookit': 40895,
 'ravenously': 52177,
 'levitating': 40896,
 'perfunctorily': 52178,
 'lookin': 30587,
 "lot'": 40898,
 'lookie': 52179,
 'fearlessly': 34870,
 'libyan': 52181,
 'fondles': 40899,
 'gopher': 35714,
 'wearying': 40901,
 "nz's": 52182,
 'minuses': 27646,
 'puposelessly': 52183,
 'shandling': 52184,
 'decapitates': 31268,
 'humming': 11929,
 "'nother": 40902,
 'smackdown': 21914,
 'underdone': 30588,
 'frf': 40903,
 'triviality': 52185,
 'fro': 25248,
 'bothers': 8777,
 "'kensington": 52186,
 'much': 73,
 'muco': 34730,
 'wiseguy': 22615,
 "richie's": 27648,
 'tonino': 40904,
 'unleavened': 52187,
 'fry': 11587,
 "'tv'": 40905,
 'toning': 40906,
 'obese': 14361,
 'sensationalized': 30589,
 'spiv': 40907,
 'spit': 6259,
 'arkin': 7364,
 'charleton': 21915,
 'jeon': 16823,
 'boardroom': 21916,
 'doubts': 4989,
 'spin': 3084,
 'hepo': 53083,
 'wildcat': 27649,
 'venoms': 10584,
 'misconstrues': 52191,
 'mesmerising': 18514,
 'misconstrued': 40908,
 'rescinds': 52192,
 'prostrate': 52193,
 'majid': 40909,
 'climbed': 16479,
 'canoeing': 34731,
 'majin': 52195,
 'animie': 57804,
 'sylke': 40910,
 'conditioned': 14899,
 'waddell': 40911,
 '3\xc2\x85': 52196,
 'hyperdrive': 41188,
 'conditioner': 34732,
 'bricklayer': 53153,
 'hong': 2576,
 'memoriam': 52198,
 'inventively': 30592,
 "levant's": 25249,
 'portobello': 20638,
 'remand': 52200,
 'mummified': 19504,
 'honk': 27650,
 'spews': 19505,
 'visitations': 40912,
 'mummifies': 52201,
 'cavanaugh': 25250,
 'zeon': 23385,
 "jungle's": 40913,
 'viertel': 34733,
 'frenchmen': 27651,
 'torpedoes': 52202,
 'schlessinger': 52203,
 'torpedoed': 34734,
 'blister': 69876,
 'cinefest': 52204,
 'furlough': 34735,
 'mainsequence': 52205,
 'mentors': 40914,
 'academic': 9094,
 'stillness': 20602,
 'academia': 40915,
 'lonelier': 52206,
 'nibby': 52207,
 "losers'": 52208,
 'cineastes': 40916,
 'corporate': 4449,
 'massaging': 40917,
 'bellow': 30593,
 'absurdities': 19506,
 'expetations': 53241,
 'nyfiken': 40918,
 'mehras': 75638,
 'lasse': 52209,
 'visability': 52210,
 'militarily': 33946,
 "elder'": 52211,
 'gainsbourg': 19023,
 'hah': 20603,
 'hai': 13420,
 'haj': 34736,
 'hak': 25251,
 'hal': 4311,
 'ham': 4892,
 'duffer': 53259,
 'haa': 52213,
 'had': 66,
 'advancement': 11930,
 'hag': 16825,
 "hand'": 25252,
 'hay': 13421,
 'mcnamara': 20604,
 "mozart's": 52214,
 'duffel': 30731,
 'haq': 30594,
 'har': 13887,
 'has': 44,
 'hat': 2401,
 'hav': 40919,
 'haw': 30595,
 'figtings': 52215,
 'elders': 15495,
 'underpanted': 52216,
 'pninson': 52217,
 'unequivocally': 27652,
 "barbara's": 23673,
 "bello'": 52219,
 'indicative': 12997,
 'yawnfest': 40920,
 'hexploitation': 52220,
 "loder's": 52221,
 'sleuthing': 27653,
 "justin's": 32622,
 "'ball": 52222,
 "'summer": 52223,
 "'demons'": 34935,
 "mormon's": 52225,
 "laughton's": 34737,
 'debell': 52226,
 'shipyard': 39724,
 'unabashedly': 30597,
 'disks': 40401,
 'crowd': 2290,
 'crowe': 10087,
 "vancouver's": 56434,
 'mosques': 34738,
 'crown': 6627,
 'culpas': 52227,
 'crows': 27654,
 'surrell': 53344,
 'flowless': 52229,
 'sheirk': 52230,
 "'three": 40923,
 "peterson'": 52231,
 'ooverall': 52232,
 'perchance': 40924,
 'bottom': 1321,
 'chabert': 53363,
 'sneha': 52233,
 'inhuman': 13888,
 'ichii': 52234,
 'ursla': 52235,
 'completly': 30598,
 'moviedom': 40925,
 'raddick': 52236,
 'brundage': 51995,
 'brigades': 40926,
 'starring': 1181,
 "'goal'": 52237,
 'caskets': 52238,
 'willcock': 52239,
 "threesome's": 52240,
 "mosque'": 52241,
 "cover's": 52242,
 'spaceships': 17637,
 'anomalous': 40927,
 'ptsd': 27655,
 'shirdan': 52243,
 'obscenity': 21962,
 'lemmings': 30599,
 'duccio': 30600,
 "levene's": 52244,
 "'gorby'": 52245,
 "teenager's": 25255,
 'marshall': 5340,
 'honeymoon': 9095,
 'shoots': 3231,
 'despised': 12258,
 'okabasho': 52246,
 'fabric': 8289,
 'cannavale': 18515,
 'raped': 3537,
 "tutt's": 52247,
 'grasping': 17638,
 'despises': 18516,
 "thief's": 40928,
 'rapes': 8926,
 'raper': 52248,
 "eyre'": 27656,
 'walchek': 52249,
 "elmo's": 23386,
 'perfumes': 40929,
 'spurting': 21918,
 "exposition'\xc2\x85": 52250,
 'denoting': 52251,
 'thesaurus': 34740,
 "shoot'": 40930,
 'bonejack': 49759,
 'simpsonian': 52253,
 'hebetude': 30601,
 "hallow's": 34741,
 'desperation\xc2\x85': 52254,
 'incinerator': 34742,
 'congratulations': 10308,
 'humbled': 52255,
 "else's": 5924,
 'trelkovski': 40845,
 "rape'": 52256,
 "'chapters'": 59386,
 '1600s': 52257,
 'martian': 7253,
 'nicest': 25256,
 'eyred': 52259,
 'passenger': 9457,
 'disgrace': 6041,
 'moderne': 52260,
 'barrymore': 5120,
 'yankovich': 52261,
 'moderns': 40931,
 'studliest': 52262,
 'bedsheet': 52263,
 'decapitation': 14900,
 'slurring': 52264,
 "'nunsploitation'": 52265,
 "'character'": 34743,
 'cambodia': 9880,
 'rebelious': 52266,
 'pasadena': 27657,
 'crowne': 40932,
 "'bedchamber": 52267,
 'conjectural': 52268,
 'appologize': 52269,
 'halfassing': 52270,
 'paycheque': 57816,
 'palms': 20606,
 "'islands": 52271,
 'hawked': 40933,
 'palme': 21919,
 'conservatively': 40934,
 'larp': 64007,
 'palma': 5558,
 'smelling': 21920,
 'aragorn': 12998,
 'hawker': 52272,
 'hawkes': 52273,
 'explosions': 3975,
 'loren': 8059,
 "pyle's": 52274,
 'shootout': 6704,
 "mike's": 18517,
 "driscoll's": 52275,
 'cogsworth': 40935,
 "britian's": 52276,
 'childs': 34744,
 "portrait's": 52277,
 'chain': 3626,
 'whoever': 2497,
 'puttered': 52278,
 'childe': 52279,
 'maywether': 52280,
 'chair': 3036,
 "rance's": 52281,
 'machu': 34745,
 'ballet': 4517,
 'grapples': 34746,
 'summerize': 76152,
 'freelance': 30603,
 "andrea's": 52283,
 '\xc2\x91very': 52284,
 'coolidge': 45879,
 'mache': 18518,
 'balled': 52285,
 'grappled': 40937,
 'macha': 18519,
 'underlining': 21921,
 'macho': 5623,
 'oversight': 19507,
 'machi': 25257,
 'verbally': 11311,
 'tenacious': 21922,
 'windshields': 40938,
 'paychecks': 18557,
 'jerk': 3396,
 "good'": 11931,
 'prancer': 34748,
 'prances': 21923,
 'olympus': 52286,
 'lark': 21924,
 'embark': 10785,
 'gloomy': 7365,
 'jehaan': 52287,
 'turaqui': 52288,
 "child'": 20607,
 'locked': 2894,
 'pranced': 52289,
 'exact': 2588,
 'unattuned': 52290,
 'minute': 783,
 'skewed': 16118,
 'hodgins': 40940,
 'skewer': 34749,
 'think\xc2\x85': 52291,
 'rosenstein': 38765,
 'helmit': 52292,
 'wrestlemanias': 34750,
 'hindered': 16826,
 "martha's": 30604,
 'cheree': 52293,
 "pluckin'": 52294,
 'ogles': 40941,
 'heavyweight': 11932,
 'aada': 82190,
 'chopping': 11312,
 'strongboy': 61534,
 'hegemonic': 41342,
 'adorns': 40942,
 'xxth': 41346,
 'nobuhiro': 34751,
 'capit\xc3\xa3es': 52298,
 'kavogianni': 52299,
 'antwerp': 13422,
 'celebrated': 6538,
 'roarke': 52300,
 'baggins': 40943,
 'cheeseburgers': 31270,
 'matras': 52301,
 "nineties'": 52302,
 "'craig'": 52303,
 'celebrates': 12999,
 'unintentionally': 3383,
 'drafted': 14362,
 'climby': 52304,
 '303': 52305,
 'oldies': 18520,
 'climbs': 9096,
 'honour': 9655,
 'plucking': 34752,
 '305': 30074,
 'address': 5514,
 'menjou': 40944,
 "'freak'": 42592,
 'dwindling': 19508,
 'benson': 9458,
 'white\xe2\x80\x99s': 52307,
 'shamelessness': 40945,
 'impacted': 21925,
 'upatz': 52308,
 'cusack': 3840,
 "flavia's": 37567,
 'effette': 52309,
 'influx': 34753,
 'boooooooo': 52310,
 'dimitrova': 52311,
 'houseman': 13423,
 'bigas': 25259,
 'boylen': 52312,
 'phillipenes': 52313,
 'fakery': 40946,
 "grandpa's": 27658,
 'darnell': 27659,
 'undergone': 19509,
 'handbags': 52315,
 'perished': 21926,
 'pooped': 37778,
 'vigour': 27660,
 'opposed': 3627,
 'etude': 52316,
 "caine's": 11799,
 'doozers': 52317,
 'photojournals': 34754,
 'perishes': 52318,
 'constrains': 34755,
 'migenes': 40948,
 'consoled': 30605,
 'alastair': 16827,
 'wvs': 52319,
 'ooooooh': 52320,
 'approving': 34756,
 'consoles': 40949,
 'disparagement': 52064,
 'futureistic': 52322,
 'rebounding': 52323,
 "'date": 52324,
 'gregoire': 52325,
 'rutherford': 21927,
 'americanised': 34757,
 'novikov': 82196,
 'following': 1042,
 'munroe': 34758,
 "morita'": 52326,
 'christenssen': 52327,
 'oatmeal': 23106,
 'fossey': 25260,
 'livered': 40950,
 'listens': 13000,
 "'marci": 76164,
 "otis's": 52330,
 'thanking': 23387,
 'maude': 16019,
 'extensions': 34759,
 'ameteurish': 52332,
 "commender's": 52333,
 'agricultural': 27661,
 'convincingly': 4518,
 'fueled': 17639,
 'mahattan': 54014,
 "paris's": 40952,
 'vulkan': 52336,
 'stapes': 52337,
 'odysessy': 52338,
 'harmon': 12259,
 'surfing': 4252,
 'halloran': 23494,
 'unbelieveably': 49580,
 "'offed'": 52339,
 'quadrant': 30607,
 'inhabiting': 19510,
 'nebbish': 34760,
 'forebears': 40953,
 'skirmish': 34761,
 'ocassionally': 52340,
 "'resist": 52341,
 'impactful': 21928,
 'spicier': 52342,
 'touristy': 40954,
 "'football'": 52343,
 'webpage': 40955,
 'exurbia': 52345,
 'jucier': 52346,
 'professors': 14901,
 'structuring': 34762,
 'jig': 30608,
 'overlord': 40956,
 'disconnect': 25261,
 'sniffle': 82201,
 'slimeball': 40957,
 'jia': 40958,
 'milked': 16828,
 'banjoes': 40959,
 'jim': 1237,
 'workforces': 52348,
 'jip': 52349,
 'rotweiller': 52350,
 'mundaneness': 34763,
 "'ninja'": 52351,
 "dead'": 11040,
 "cipriani's": 40960,
 'modestly': 20608,
 "professor'": 52352,
 'shacked': 40961,
 'bashful': 34764,
 'sorter': 23388,
 'overpowering': 16120,
 'workmanlike': 18521,
 'henpecked': 27662,
 'sorted': 18522,
 "j\xc5\x8db's": 52354,
 "'always": 52355,
 "'baptists": 34765,
 'dreamcatchers': 52356,
 "'silence'": 52357,
 'hickory': 21929,
 'fun\xc2\x97yet': 52358,
 'breakumentary': 52359,
 'didn': 15496,
 'didi': 52360,
 'pealing': 52361,
 'dispite': 40962,
 "italy's": 25262,
 'instability': 21930,
 'quarter': 6539,
 'quartet': 12608,
 'padm\xc3\xa9': 52362,
 "'bleedmedry": 52363,
 'pahalniuk': 52364,
 'honduras': 52365,
 'bursting': 10786,
 "pablo's": 41465,
 'irremediably': 52367,
 'presages': 40963,
 'bowlegged': 57832,
 'dalip': 65183,
 'entering': 6260,
 'newsradio': 76172,
 'presaged': 54150,
 "giallo's": 27663,
 'bouyant': 40964,
 'amerterish': 52368,
 'rajni': 18523,
 'leeves': 30610,
 'macauley': 34767,
 'seriously': 612,
 'sugercoma': 52369,
 'grimstead': 52370,
 "'fairy'": 52371,
 'zenda': 30611,
 "'twins'": 52372,
 'realisation': 17640,
 'highsmith': 27664,
 'raunchy': 7817,
 'incentives': 40965,
 'flatson': 52374,
 'snooker': 35097,
 'crazies': 16829,
 'crazier': 14902,
 'grandma': 7094,
 'napunsaktha': 52375,
 'workmanship': 30612,
 'reisner': 52376,
 "sanford's": 61306,
 '\xc2\x91do\xc3\xb1a': 52377,
 'modest': 6108,
 "everything's": 19153,
 'hamer': 40966,
 "couldn't'": 52379,
 'quibble': 13001,
 'socking': 52380,
 'tingler': 21931,
 'gutman': 52381,
 'lachlan': 40967,
 'tableaus': 52382,
 'headbanger': 52383,
 'spoken': 2847,
 'cerebrally': 34768,
 "'road": 23490,
 'tableaux': 21932,
 "proust's": 40968,
 'periodical': 40969,
 "shoveller's": 52385,
 'tamara': 25263,
 'affords': 17641,
 'concert': 3249,
 "yara's": 87955,
 'someome': 52386,
 'lingering': 8424,
 "abraham's": 41511,
 'beesley': 34769,
 'cherbourg': 34770,
 'kagan': 28624,
 'snatch': 9097,
 "miyazaki's": 9260,
 'absorbs': 25264,
 "koltai's": 40970,
 'tingled': 64027,
 'crossroads': 19511,
 'rehab': 16121,
 'falworth': 52389,
 'sequals': 52390,
 ...}



In [7]:

    
idx2word = {v:k for k,v in idx.iteritems()}



In [8]:

    
idx2word









    Out[8]:





{1: 'the',
 2: 'and',
 3: 'a',
 4: 'of',
 5: 'to',
 6: 'is',
 7: 'br',
 8: 'in',
 9: 'it',
 10: 'i',
 11: 'this',
 12: 'that',
 13: 'was',
 14: 'as',
 15: 'for',
 16: 'with',
 17: 'movie',
 18: 'but',
 19: 'film',
 20: 'on',
 21: 'not',
 22: 'you',
 23: 'are',
 24: 'his',
 25: 'have',
 26: 'he',
 27: 'be',
 28: 'one',
 29: 'all',
 30: 'at',
 31: 'by',
 32: 'an',
 33: 'they',
 34: 'who',
 35: 'so',
 36: 'from',
 37: 'like',
 38: 'her',
 39: 'or',
 40: 'just',
 41: 'about',
 42: "it's",
 43: 'out',
 44: 'has',
 45: 'if',
 46: 'some',
 47: 'there',
 48: 'what',
 49: 'good',
 50: 'more',
 51: 'when',
 52: 'very',
 53: 'up',
 54: 'no',
 55: 'time',
 56: 'she',
 57: 'even',
 58: 'my',
 59: 'would',
 60: 'which',
 61: 'only',
 62: 'story',
 63: 'really',
 64: 'see',
 65: 'their',
 66: 'had',
 67: 'can',
 68: 'were',
 69: 'me',
 70: 'well',
 71: 'than',
 72: 'we',
 73: 'much',
 74: 'been',
 75: 'bad',
 76: 'get',
 77: 'will',
 78: 'do',
 79: 'also',
 80: 'into',
 81: 'people',
 82: 'other',
 83: 'first',
 84: 'great',
 85: 'because',
 86: 'how',
 87: 'him',
 88: 'most',
 89: "don't",
 90: 'made',
 91: 'its',
 92: 'then',
 93: 'way',
 94: 'make',
 95: 'them',
 96: 'too',
 97: 'could',
 98: 'any',
 99: 'movies',
 100: 'after',
 101: 'think',
 102: 'characters',
 103: 'watch',
 104: 'two',
 105: 'films',
 106: 'character',
 107: 'seen',
 108: 'many',
 109: 'being',
 110: 'life',
 111: 'plot',
 112: 'never',
 113: 'acting',
 114: 'little',
 115: 'best',
 116: 'love',
 117: 'over',
 118: 'where',
 119: 'did',
 120: 'show',
 121: 'know',
 122: 'off',
 123: 'ever',
 124: 'does',
 125: 'better',
 126: 'your',
 127: 'end',
 128: 'still',
 129: 'man',
 130: 'here',
 131: 'these',
 132: 'say',
 133: 'scene',
 134: 'while',
 135: 'why',
 136: 'scenes',
 137: 'go',
 138: 'such',
 139: 'something',
 140: 'through',
 141: 'should',
 142: 'back',
 143: "i'm",
 144: 'real',
 145: 'those',
 146: 'watching',
 147: 'now',
 148: 'though',
 149: "doesn't",
 150: 'years',
 151: 'old',
 152: 'thing',
 153: 'actors',
 154: 'work',
 155: '10',
 156: 'before',
 157: 'another',
 158: "didn't",
 159: 'new',
 160: 'funny',
 161: 'nothing',
 162: 'actually',
 163: 'makes',
 164: 'director',
 165: 'look',
 166: 'find',
 167: 'going',
 168: 'few',
 169: 'same',
 170: 'part',
 171: 'again',
 172: 'every',
 173: 'lot',
 174: 'cast',
 175: 'us',
 176: 'quite',
 177: 'down',
 178: 'want',
 179: 'world',
 180: 'things',
 181: 'pretty',
 182: 'young',
 183: 'seems',
 184: 'around',
 185: 'got',
 186: 'horror',
 187: 'however',
 188: "can't",
 189: 'fact',
 190: 'take',
 191: 'big',
 192: 'enough',
 193: 'long',
 194: 'thought',
 195: "that's",
 196: 'both',
 197: 'between',
 198: 'series',
 199: 'give',
 200: 'may',
 201: 'original',
 202: 'own',
 203: 'action',
 204: "i've",
 205: 'right',
 206: 'without',
 207: 'always',
 208: 'times',
 209: 'comedy',
 210: 'point',
 211: 'gets',
 212: 'must',
 213: 'come',
 214: 'role',
 215: "isn't",
 216: 'saw',
 217: 'almost',
 218: 'interesting',
 219: 'least',
 220: 'family',
 221: 'done',
 222: "there's",
 223: 'whole',
 224: 'bit',
 225: 'music',
 226: 'script',
 227: 'far',
 228: 'making',
 229: 'guy',
 230: 'anything',
 231: 'minutes',
 232: 'feel',
 233: 'last',
 234: 'since',
 235: 'might',
 236: 'performance',
 237: "he's",
 238: '2',
 239: 'probably',
 240: 'kind',
 241: 'am',
 242: 'away',
 243: 'yet',
 244: 'rather',
 245: 'tv',
 246: 'worst',
 247: 'girl',
 248: 'day',
 249: 'sure',
 250: 'fun',
 251: 'hard',
 252: 'woman',
 253: 'played',
 254: 'each',
 255: 'found',
 256: 'anyone',
 257: 'having',
 258: 'although',
 259: 'especially',
 260: 'our',
 261: 'believe',
 262: 'course',
 263: 'comes',
 264: 'looking',
 265: 'screen',
 266: 'trying',
 267: 'set',
 268: 'goes',
 269: 'looks',
 270: 'place',
 271: 'book',
 272: 'different',
 273: 'put',
 274: 'ending',
 275: 'money',
 276: 'maybe',
 277: 'once',
 278: 'sense',
 279: 'reason',
 280: 'true',
 281: 'actor',
 282: 'everything',
 283: "wasn't",
 284: 'shows',
 285: 'dvd',
 286: 'three',
 287: 'worth',
 288: 'year',
 289: 'job',
 290: 'main',
 291: 'someone',
 292: 'together',
 293: 'watched',
 294: 'play',
 295: 'american',
 296: 'plays',
 297: '1',
 298: 'said',
 299: 'effects',
 300: 'later',
 301: 'takes',
 302: 'instead',
 303: 'seem',
 304: 'beautiful',
 305: 'john',
 306: 'himself',
 307: 'version',
 308: 'audience',
 309: 'high',
 310: 'house',
 311: 'night',
 312: 'during',
 313: 'everyone',
 314: 'left',
 315: 'special',
 316: 'seeing',
 317: 'half',
 318: 'excellent',
 319: 'wife',
 320: 'star',
 321: 'shot',
 322: 'war',
 323: 'idea',
 324: 'nice',
 325: 'black',
 326: 'less',
 327: 'mind',
 328: 'simply',
 329: 'read',
 330: 'second',
 331: 'else',
 332: "you're",
 333: 'father',
 334: 'fan',
 335: 'poor',
 336: 'help',
 337: 'completely',
 338: 'death',
 339: '3',
 340: 'used',
 341: 'home',
 342: 'either',
 343: 'short',
 344: 'line',
 345: 'given',
 346: 'men',
 347: 'top',
 348: 'dead',
 349: 'budget',
 350: 'try',
 351: 'performances',
 352: 'wrong',
 353: 'classic',
 354: 'boring',
 355: 'enjoy',
 356: 'need',
 357: 'rest',
 358: 'use',
 359: 'kids',
 360: 'hollywood',
 361: 'low',
 362: 'production',
 363: 'until',
 364: 'along',
 365: 'full',
 366: 'friends',
 367: 'camera',
 368: 'truly',
 369: 'women',
 370: 'awful',
 371: 'video',
 372: 'next',
 373: 'tell',
 374: 'remember',
 375: 'couple',
 376: 'stupid',
 377: 'start',
 378: 'stars',
 379: 'perhaps',
 380: 'sex',
 381: 'mean',
 382: 'came',
 383: 'recommend',
 384: 'let',
 385: 'moments',
 386: 'wonderful',
 387: 'episode',
 388: 'understand',
 389: 'small',
 390: 'face',
 391: 'terrible',
 392: 'playing',
 393: 'school',
 394: 'getting',
 395: 'written',
 396: 'doing',
 397: 'often',
 398: 'keep',
 399: 'early',
 400: 'name',
 401: 'perfect',
 402: 'style',
 403: 'human',
 404: 'definitely',
 405: 'gives',
 406: 'others',
 407: 'itself',
 408: 'lines',
 409: 'live',
 410: 'become',
 411: 'dialogue',
 412: 'person',
 413: 'lost',
 414: 'finally',
 415: 'piece',
 416: 'head',
 417: 'case',
 418: 'felt',
 419: 'yes',
 420: 'liked',
 421: 'supposed',
 422: 'title',
 423: "couldn't",
 424: 'absolutely',
 425: 'white',
 426: 'against',
 427: 'boy',
 428: 'picture',
 429: 'sort',
 430: 'worse',
 431: 'certainly',
 432: 'went',
 433: 'entire',
 434: 'waste',
 435: 'cinema',
 436: 'problem',
 437: 'hope',
 438: 'entertaining',
 439: "she's",
 440: 'mr',
 441: 'overall',
 442: 'evil',
 443: 'called',
 444: 'loved',
 445: 'based',
 446: 'oh',
 447: 'several',
 448: 'fans',
 449: 'mother',
 450: 'drama',
 451: 'beginning',
 452: 'killer',
 453: 'lives',
 454: '5',
 455: 'direction',
 456: 'care',
 457: 'already',
 458: 'becomes',
 459: 'laugh',
 460: 'example',
 461: 'friend',
 462: 'dark',
 463: 'despite',
 464: 'under',
 465: 'seemed',
 466: 'throughout',
 467: '4',
 468: 'turn',
 469: 'unfortunately',
 470: 'wanted',
 471: "i'd",
 472: '\xc2\x96',
 473: 'children',
 474: 'final',
 475: 'fine',
 476: 'history',
 477: 'amazing',
 478: 'sound',
 479: 'guess',
 480: 'heart',
 481: 'totally',
 482: 'lead',
 483: 'humor',
 484: 'writing',
 485: 'michael',
 486: 'quality',
 487: "you'll",
 488: 'close',
 489: 'son',
 490: 'guys',
 491: 'wants',
 492: 'works',
 493: 'behind',
 494: 'tries',
 495: 'art',
 496: 'side',
 497: 'game',
 498: 'past',
 499: 'able',
 500: 'b',
 501: 'days',
 502: 'turns',
 503: 'child',
 504: "they're",
 505: 'hand',
 506: 'flick',
 507: 'enjoyed',
 508: 'act',
 509: 'genre',
 510: 'town',
 511: 'favorite',
 512: 'soon',
 513: 'kill',
 514: 'starts',
 515: 'sometimes',
 516: 'car',
 517: 'gave',
 518: 'run',
 519: 'late',
 520: 'eyes',
 521: 'actress',
 522: 'etc',
 523: 'directed',
 524: 'horrible',
 525: "won't",
 526: 'viewer',
 527: 'brilliant',
 528: 'parts',
 529: 'self',
 530: 'themselves',
 531: 'hour',
 532: 'expect',
 533: 'thinking',
 534: 'stories',
 535: 'stuff',
 536: 'girls',
 537: 'obviously',
 538: 'blood',
 539: 'decent',
 540: 'city',
 541: 'voice',
 542: 'highly',
 543: 'myself',
 544: 'feeling',
 545: 'fight',
 546: 'except',
 547: 'slow',
 548: 'matter',
 549: 'type',
 550: 'anyway',
 551: 'kid',
 552: 'roles',
 553: 'killed',
 554: 'heard',
 555: 'god',
 556: 'age',
 557: 'says',
 558: 'moment',
 559: 'took',
 560: 'leave',
 561: 'writer',
 562: 'strong',
 563: 'cannot',
 564: 'violence',
 565: 'police',
 566: 'hit',
 567: 'stop',
 568: 'happens',
 569: 'particularly',
 570: 'known',
 571: 'involved',
 572: 'happened',
 573: 'extremely',
 574: 'daughter',
 575: 'obvious',
 576: 'told',
 577: 'chance',
 578: 'living',
 579: 'coming',
 580: 'lack',
 581: 'alone',
 582: 'experience',
 583: "wouldn't",
 584: 'including',
 585: 'murder',
 586: 'attempt',
 587: 's',
 588: 'please',
 589: 'james',
 590: 'happen',
 591: 'wonder',
 592: 'crap',
 593: 'ago',
 594: 'brother',
 595: "film's",
 596: 'gore',
 597: 'none',
 598: 'complete',
 599: 'interest',
 600: 'score',
 601: 'group',
 602: 'cut',
 603: 'simple',
 604: 'save',
 605: 'ok',
 606: 'hell',
 607: 'looked',
 608: 'career',
 609: 'number',
 610: 'song',
 611: 'possible',
 612: 'seriously',
 613: 'annoying',
 614: 'shown',
 615: 'exactly',
 616: 'sad',
 617: 'running',
 618: 'musical',
 619: 'serious',
 620: 'taken',
 621: 'yourself',
 622: 'whose',
 623: 'released',
 624: 'cinematography',
 625: 'david',
 626: 'scary',
 627: 'ends',
 628: 'english',
 629: 'hero',
 630: 'usually',
 631: 'hours',
 632: 'reality',
 633: 'opening',
 634: "i'll",
 635: 'across',
 636: 'today',
 637: 'jokes',
 638: 'light',
 639: 'hilarious',
 640: 'somewhat',
 641: 'usual',
 642: 'started',
 643: 'cool',
 644: 'ridiculous',
 645: 'body',
 646: 'relationship',
 647: 'view',
 648: 'level',
 649: 'opinion',
 650: 'change',
 651: 'happy',
 652: 'middle',
 653: 'taking',
 654: 'wish',
 655: 'husband',
 656: 'finds',
 657: 'saying',
 658: 'order',
 659: 'talking',
 660: 'ones',
 661: 'documentary',
 662: 'shots',
 663: 'huge',
 664: 'novel',
 665: 'female',
 666: 'mostly',
 667: 'robert',
 668: 'power',
 669: 'episodes',
 670: 'room',
 671: 'important',
 672: 'rating',
 673: 'talent',
 674: 'five',
 675: 'major',
 676: 'turned',
 677: 'strange',
 678: 'word',
 679: 'modern',
 680: 'call',
 681: 'apparently',
 682: 'disappointed',
 683: 'single',
 684: 'events',
 685: 'due',
 686: 'four',
 687: 'songs',
 688: 'basically',
 689: 'attention',
 690: '7',
 691: 'knows',
 692: 'clearly',
 693: 'supporting',
 694: 'knew',
 695: 'british',
 696: 'television',
 697: 'comic',
 698: 'non',
 699: 'fast',
 700: 'earth',
 701: 'country',
 702: 'future',
 703: 'cheap',
 704: 'class',
 705: 'thriller',
 706: '8',
 707: 'silly',
 708: 'king',
 709: 'problems',
 710: "aren't",
 711: 'easily',
 712: 'words',
 713: 'tells',
 714: 'miss',
 715: 'jack',
 716: 'local',
 717: 'sequence',
 718: 'bring',
 719: 'entertainment',
 720: 'paul',
 721: 'beyond',
 722: 'upon',
 723: 'whether',
 724: 'predictable',
 725: 'moving',
 726: 'similar',
 727: 'straight',
 728: 'romantic',
 729: 'sets',
 730: 'review',
 731: 'falls',
 732: 'oscar',
 733: 'mystery',
 734: 'enjoyable',
 735: 'needs',
 736: 'appears',
 737: 'talk',
 738: 'rock',
 739: 'george',
 740: 'giving',
 741: 'eye',
 742: 'richard',
 743: 'within',
 744: 'ten',
 745: 'animation',
 746: 'message',
 747: 'theater',
 748: 'near',
 749: 'above',
 750: 'dull',
 751: 'nearly',
 752: 'sequel',
 753: 'theme',
 754: 'points',
 755: "'",
 756: 'stand',
 757: 'mention',
 758: 'lady',
 759: 'bunch',
 760: 'add',
 761: 'feels',
 762: 'herself',
 763: 'release',
 764: 'red',
 765: 'team',
 766: 'storyline',
 767: 'surprised',
 768: 'ways',
 769: 'using',
 770: 'named',
 771: "haven't",
 772: 'lots',
 773: 'easy',
 774: 'fantastic',
 775: 'begins',
 776: 'actual',
 777: 'working',
 778: 'effort',
 779: 'york',
 780: 'die',
 781: 'hate',
 782: 'french',
 783: 'minute',
 784: 'tale',
 785: 'clear',
 786: 'stay',
 787: '9',
 788: 'elements',
 789: 'feature',
 790: 'among',
 791: 'follow',
 792: 'comments',
 793: 're',
 794: 'viewers',
 795: 'avoid',
 796: 'sister',
 797: 'showing',
 798: 'typical',
 799: 'editing',
 800: "what's",
 801: 'famous',
 802: 'tried',
 803: 'sorry',
 804: 'dialog',
 805: 'check',
 806: 'fall',
 807: 'period',
 808: 'season',
 809: 'form',
 810: 'certain',
 811: 'filmed',
 812: 'weak',
 813: 'soundtrack',
 814: 'means',
 815: 'buy',
 816: 'material',
 817: 'somehow',
 818: 'realistic',
 819: 'figure',
 820: 'crime',
 821: 'doubt',
 822: 'gone',
 823: 'peter',
 824: 'tom',
 825: 'kept',
 826: 'viewing',
 827: 't',
 828: 'general',
 829: 'leads',
 830: 'greatest',
 831: 'space',
 832: 'lame',
 833: 'suspense',
 834: 'dance',
 835: 'imagine',
 836: 'brought',
 837: 'third',
 838: 'atmosphere',
 839: 'hear',
 840: 'particular',
 841: 'sequences',
 842: 'whatever',
 843: 'parents',
 844: 'move',
 845: 'lee',
 846: 'indeed',
 847: 'learn',
 848: 'rent',
 849: 'de',
 850: 'eventually',
 851: 'note',
 852: 'deal',
 853: 'average',
 854: 'reviews',
 855: 'wait',
 856: 'forget',
 857: 'japanese',
 858: 'sexual',
 859: 'poorly',
 860: 'premise',
 861: 'okay',
 862: 'zombie',
 863: 'surprise',
 864: 'believable',
 865: 'stage',
 866: 'possibly',
 867: 'sit',
 868: "who's",
 869: 'decided',
 870: 'expected',
 871: "you've",
 872: 'subject',
 873: 'nature',
 874: 'became',
 875: 'difficult',
 876: 'free',
 877: 'killing',
 878: 'screenplay',
 879: 'truth',
 880: 'romance',
 881: 'dr',
 882: 'nor',
 883: 'reading',
 884: 'needed',
 885: 'question',
 886: 'leaves',
 887: 'street',
 888: '20',
 889: 'meets',
 890: 'hot',
 891: 'unless',
 892: 'begin',
 893: 'baby',
 894: 'superb',
 895: 'credits',
 896: 'imdb',
 897: 'otherwise',
 898: 'write',
 899: 'shame',
 900: "let's",
 901: 'situation',
 902: 'dramatic',
 903: 'memorable',
 904: 'directors',
 905: 'earlier',
 906: 'meet',
 907: 'disney',
 908: 'open',
 909: 'dog',
 910: 'badly',
 911: 'joe',
 912: 'male',
 913: 'weird',
 914: 'acted',
 915: 'forced',
 916: 'laughs',
 917: 'sci',
 918: 'emotional',
 919: 'older',
 920: 'realize',
 921: 'fi',
 922: 'dream',
 923: 'society',
 924: 'writers',
 925: 'interested',
 926: 'footage',
 927: 'forward',
 928: 'comment',
 929: 'crazy',
 930: 'deep',
 931: 'sounds',
 932: 'plus',
 933: 'beauty',
 934: 'whom',
 935: 'america',
 936: 'fantasy',
 937: 'directing',
 938: 'keeps',
 939: 'ask',
 940: 'development',
 941: 'features',
 942: 'air',
 943: 'quickly',
 944: 'mess',
 945: 'creepy',
 946: 'towards',
 947: 'perfectly',
 948: 'mark',
 949: 'worked',
 950: 'box',
 951: 'cheesy',
 952: 'unique',
 953: 'setting',
 954: 'hands',
 955: 'plenty',
 956: 'result',
 957: 'previous',
 958: 'brings',
 959: 'effect',
 960: 'e',
 961: 'total',
 962: 'personal',
 963: 'incredibly',
 964: 'rate',
 965: 'fire',
 966: 'monster',
 967: 'business',
 968: 'leading',
 969: 'apart',
 970: 'casting',
 971: 'admit',
 972: 'joke',
 973: 'powerful',
 974: 'appear',
 975: 'background',
 976: 'telling',
 977: 'girlfriend',
 978: 'meant',
 979: 'christmas',
 980: 'hardly',
 981: 'present',
 982: 'battle',
 983: 'potential',
 984: 'create',
 985: 'bill',
 986: 'break',
 987: 'pay',
 988: 'masterpiece',
 989: 'gay',
 990: 'political',
 991: 'return',
 992: 'dumb',
 993: 'fails',
 994: 'fighting',
 995: 'various',
 996: 'era',
 997: 'portrayed',
 998: 'co',
 999: 'cop',
 1000: 'secret',
 ...}



In [9]:

    
imdv_reviews_file = get_file('imdb_full.pkl',
                            origin='https://s3.amazonaws.com/text-datasets/imdb_full.pkl',
                            md5_hash='d091312047c43cf9e4e38fef92437263')









    



Downloading data from https://s3.amazonaws.com/text-datasets/imdb_full.pkl



In [11]:

    
(x_train, labels_train), (x_test, labels_test) = pickle.load(open(imdv_reviews_file, 'rb'))



In [12]:

    
x_train



In [13]:

    
' '.join([idx2word[o] for o in x_train[0]])









    Out[13]:





"bromwell high is a cartoon comedy it ran at the same time as some other programs about school life such as teachers my 35 years in the teaching profession lead me to believe that bromwell high's satire is much closer to reality than is teachers the scramble to survive financially the insightful students who can see right through their pathetic teachers' pomp the pettiness of the whole situation all remind me of the schools i knew and their students when i saw the episode in which a student repeatedly tried to burn down the school i immediately recalled at high a classic line inspector i'm here to sack one of your teachers student welcome to bromwell high i expect that many adults of my age think that bromwell high is far fetched what a pity that it isn't"



In [14]:

    
labels_train









    Out[14]:





[1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 ...]



In [15]:

    
# reduce the vocabulary size by setting rare words to max index
vocab_size = 5000
training_data = [np.array([i if i<vocab_size-1 else vocab_size-1 for i in s]) for s in x_train]



In [16]:

    
test_data = [np.array([i if i<vocab_size-1 else vocab_size-1 for i in s]) for s in x_test]



In [17]:

    
# pad with zero (or truncate) each sentence to make consistent length
training_data = sequence.pad_sequences(training_data, maxlen=500, value=0)
test_data = sequence.pad_sequences(test_data, maxlen=500, value=0)



In [18]:

    
training_data.shape









    Out[18]:





(25000, 500)

Single hidden layer



In [20]:

    
model = Sequential([
    Embedding(vocab_size, 32, input_length=500),
    Flatten(),
    Dense(100, activation='relu'),
    Dropout(0.7),
    Dense(1, activation='sigmoid')
])



In [21]:

    
model.compile(loss='binary_crossentropy', optimizer=Adam(), metrics=['accuracy'])



In [22]:

    
model.summary()









    



____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
embedding_1 (Embedding)          (None, 500, 32)       160000      embedding_input_1[0][0]          
____________________________________________________________________________________________________
flatten_1 (Flatten)              (None, 16000)         0           embedding_1[0][0]                
____________________________________________________________________________________________________
dense_1 (Dense)                  (None, 100)           1600100     flatten_1[0][0]                  
____________________________________________________________________________________________________
dropout_1 (Dropout)              (None, 100)           0           dense_1[0][0]                    
____________________________________________________________________________________________________
dense_2 (Dense)                  (None, 1)             101         dropout_1[0][0]                  
====================================================================================================
Total params: 1,760,201
Trainable params: 1,760,201
Non-trainable params: 0
____________________________________________________________________________________________________



In [23]:

    
model.fit(training_data, labels_train, validation_data=(test_data, labels_test),
         nb_epoch=2, batch_size=64, verbose=2)









    



Train on 25000 samples, validate on 25000 samples
Epoch 1/2
4s - loss: 0.4547 - acc: 0.7615 - val_loss: 0.2951 - val_acc: 0.8740
Epoch 2/2
4s - loss: 0.1930 - acc: 0.9291 - val_loss: 0.3148 - val_acc: 0.8702






    Out[23]:





<keras.callbacks.History at 0x7f1bedc04b10>

CNN

A CNN is likely to work better, since it is designed to take advantage of ordered data. We'll need to use 1D CNN, since it is a sequence of words.



In [24]:

    
conv1 = Sequential([
    Embedding(vocab_size, 32, input_length=500, dropout=0.2),
    Dropout(0.2),
    Convolution1D(64, 5, border_mode='same', activation='relu'),
    Dropout(0.2),
    MaxPooling1D(),
    Flatten(),
    Dense(100, activation='relu'),
    Dropout(0.7),
    Dense(1, activation='sigmoid')
])



In [25]:

    
conv1.compile(loss='binary_crossentropy',
             optimizer=Adam(),
             metrics=['accuracy'])



In [26]:

    
conv1.summary()









    



____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
embedding_2 (Embedding)          (None, 500, 32)       160000      embedding_input_2[0][0]          
____________________________________________________________________________________________________
dropout_2 (Dropout)              (None, 500, 32)       0           embedding_2[0][0]                
____________________________________________________________________________________________________
convolution1d_1 (Convolution1D)  (None, 500, 64)       10304       dropout_2[0][0]                  
____________________________________________________________________________________________________
dropout_3 (Dropout)              (None, 500, 64)       0           convolution1d_1[0][0]            
____________________________________________________________________________________________________
maxpooling1d_1 (MaxPooling1D)    (None, 250, 64)       0           dropout_3[0][0]                  
____________________________________________________________________________________________________
flatten_2 (Flatten)              (None, 16000)         0           maxpooling1d_1[0][0]             
____________________________________________________________________________________________________
dense_3 (Dense)                  (None, 100)           1600100     flatten_2[0][0]                  
____________________________________________________________________________________________________
dropout_4 (Dropout)              (None, 100)           0           dense_3[0][0]                    
____________________________________________________________________________________________________
dense_4 (Dense)                  (None, 1)             101         dropout_4[0][0]                  
====================================================================================================
Total params: 1,770,505
Trainable params: 1,770,505
Non-trainable params: 0
____________________________________________________________________________________________________



In [28]:

    
conv1.fit(training_data, labels_train, validation_data=(test_data, labels_test),
         nb_epoch=4, batch_size=64, verbose=2)









    



Train on 25000 samples, validate on 25000 samples
Epoch 1/4
18s - loss: 0.5018 - acc: 0.7199 - val_loss: 0.2975 - val_acc: 0.8798
Epoch 2/4
18s - loss: 0.2993 - acc: 0.8797 - val_loss: 0.2604 - val_acc: 0.8946
Epoch 3/4
18s - loss: 0.2575 - acc: 0.8981 - val_loss: 0.2582 - val_acc: 0.8940
Epoch 4/4
18s - loss: 0.2424 - acc: 0.9050 - val_loss: 0.2617 - val_acc: 0.8928






    Out[28]:





<keras.callbacks.History at 0x7f1be1f09e50>

CNN with Pre-trained vectors



In [30]:

    
def get_glove_dataset(dataset):
    """Download the requested glove dataset from files.fast.ai
    and return a location that can be passed to load_vectors.
    """
    # see wordvectors.ipynb for info on how these files were
    # generated from the original glove data.
    md5sums = {'6B.50d': '8e1557d1228decbda7db6dfd81cd9909',
               '6B.100d': 'c92dbbeacde2b0384a43014885a60b2c',
               '6B.200d': 'af271b46c04b0b2e41a84d8cd806178d',
               '6B.300d': '30290210376887dcc6d0a5a6374d8255'}
    glove_path = os.path.abspath('data/glove/results')
    %mkdir -p $glove_path
    return get_file(dataset,
                    'http://files.fast.ai/models/glove/' + dataset + '.tgz',
                    cache_subdir=glove_path,
                    md5_hash=md5sums.get(dataset, None),
                    untar=True)



In [31]:

    
def load_vectors(loc):
    return (load_array(loc+'.dat'),
        pickle.load(open(loc+'_words.pkl','rb')),
        pickle.load(open(loc+'_idx.pkl','rb')))



In [32]:

    
vecs, words, wordidx = load_vectors(get_glove_dataset('6B.50d'))









    



Untaring file...



In [33]:

    
def create_emb():
    n_fact = vecs.shape[1]
    emb = np.zeros((vocab_size, n_fact))

    for i in range(1,len(emb)):
        word = idx2word[i]
        if word and re.match(r"^[a-zA-Z0-9\-]*$", word):
            src_idx = wordidx[word]
            emb[i] = vecs[src_idx]
        else:
            # If we can't find the word in glove, randomly initialize
            emb[i] = normal(scale=0.6, size=(n_fact,))

    # This is our "rare word" id - we want to randomly initialize
    emb[-1] = normal(scale=0.6, size=(n_fact,))
    emb/=3
    return emb



In [34]:

    
emb = create_emb()



In [35]:

    
vocab_size









    Out[35]:





5000



In [37]:

    
model = Sequential([
    Embedding(vocab_size, 50, input_length=500, dropout=0.2, weights=[emb], trainable=False),
    Dropout(0.25),
    Convolution1D(64, 5, border_mode='same', activation='relu'),
    Dropout(0.25),
    MaxPooling1D(),
    Flatten(),
    Dense(100, activation='relu'),
    Dropout(0.7),
    Dense(1, activation='sigmoid')
])



In [38]:

    
model.compile(loss='binary_crossentropy',
             optimizer=Adam(),
             metrics=['accuracy'])



In [39]:

    
model.fit(training_data, labels_train, validation_data=(test_data, labels_test),
         nb_epoch=2, batch_size=64, verbose=2)









    



Train on 25000 samples, validate on 25000 samples
Epoch 1/2
16s - loss: 0.5855 - acc: 0.6865 - val_loss: 0.4858 - val_acc: 0.7889
Epoch 2/2
16s - loss: 0.4966 - acc: 0.7657 - val_loss: 0.4622 - val_acc: 0.8135






    Out[39]:





<keras.callbacks.History at 0x7f1bd5c9c7d0>



In [40]:

    
model.layers[0].trainable=True



In [41]:

    
model.optimizer.lr=1e-4



In [43]:

    
model.fit(training_data, labels_train, validation_data=(test_data, labels_test),
         nb_epoch=1, batch_size=64, verbose=2)









    



Train on 25000 samples, validate on 25000 samples
Epoch 1/1
16s - loss: 0.4733 - acc: 0.7782 - val_loss: 0.4509 - val_acc: 0.8048






    Out[43]:





<keras.callbacks.History at 0x7f1c097dcb90>

Multi-size CNNs

https://quid.com/feed/how-quid-uses-deep-learning-with-small-data



In [45]:

    
from keras.layers import Merge



In [46]:

    
graph_in = Input((vocab_size, 50))



In [47]:

    
convs = []
for fsz in range(3,6):
    x = Convolution1D(64, fsz, border_mode='same', activation='relu')(graph_in)
    x = MaxPooling1D()(x)
    x = Flatten()(x)
    convs.append(x)
out = Merge(mode='concat')(convs)
graph = Model(graph_in, out)



In [48]:

    
graph.summary()









    



____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
input_1 (InputLayer)             (None, 5000, 50)      0                                            
____________________________________________________________________________________________________
convolution1d_3 (Convolution1D)  (None, 5000, 64)      9664        input_1[0][0]                    
____________________________________________________________________________________________________
convolution1d_4 (Convolution1D)  (None, 5000, 64)      12864       input_1[0][0]                    
____________________________________________________________________________________________________
convolution1d_5 (Convolution1D)  (None, 5000, 64)      16064       input_1[0][0]                    
____________________________________________________________________________________________________
maxpooling1d_3 (MaxPooling1D)    (None, 2500, 64)      0           convolution1d_3[0][0]            
____________________________________________________________________________________________________
maxpooling1d_4 (MaxPooling1D)    (None, 2500, 64)      0           convolution1d_4[0][0]            
____________________________________________________________________________________________________
maxpooling1d_5 (MaxPooling1D)    (None, 2500, 64)      0           convolution1d_5[0][0]            
____________________________________________________________________________________________________
flatten_4 (Flatten)              (None, 160000)        0           maxpooling1d_3[0][0]             
____________________________________________________________________________________________________
flatten_5 (Flatten)              (None, 160000)        0           maxpooling1d_4[0][0]             
____________________________________________________________________________________________________
flatten_6 (Flatten)              (None, 160000)        0           maxpooling1d_5[0][0]             
____________________________________________________________________________________________________
merge_1 (Merge)                  (None, 480000)        0           flatten_4[0][0]                  
                                                                   flatten_5[0][0]                  
                                                                   flatten_6[0][0]                  
====================================================================================================
Total params: 38,592
Trainable params: 38,592
Non-trainable params: 0
____________________________________________________________________________________________________



In [49]:

    
emb = create_emb()



In [51]:

    
model = Sequential ([
    Embedding(vocab_size, 50, input_length=500, dropout=0.2, weights=[emb]),
    Dropout (0.2),
    graph,
    Dropout (0.5),
    Dense (100, activation="relu"),
    Dropout (0.7),
    Dense (1, activation='sigmoid')
    ])



In [52]:

    
model.summary()









    



____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
embedding_4 (Embedding)          (None, 500, 50)       250000      embedding_input_4[0][0]          
____________________________________________________________________________________________________
dropout_8 (Dropout)              (None, 500, 50)       0           embedding_4[0][0]                
____________________________________________________________________________________________________
model_1 (Model)                  multiple              38592       dropout_8[0][0]                  
____________________________________________________________________________________________________
dropout_9 (Dropout)              (None, 48000)         0           model_1[1][0]                    
____________________________________________________________________________________________________
dense_7 (Dense)                  (None, 100)           4800100     dropout_9[0][0]                  
____________________________________________________________________________________________________
dropout_10 (Dropout)             (None, 100)           0           dense_7[0][0]                    
____________________________________________________________________________________________________
dense_8 (Dense)                  (None, 1)             101         dropout_10[0][0]                 
====================================================================================================
Total params: 5,088,793
Trainable params: 5,088,793
Non-trainable params: 0
____________________________________________________________________________________________________



In [53]:

    
model.compile(loss='binary_crossentropy',
             optimizer=Adam(),
             metrics=['accuracy'])



In [55]:

    
model.fit(training_data, labels_train, validation_data=(test_data, labels_test),
         nb_epoch=2, batch_size=64, verbose=2)









    



Train on 25000 samples, validate on 25000 samples
Epoch 1/2
36s - loss: 0.4792 - acc: 0.7548 - val_loss: 0.3209 - val_acc: 0.8642
Epoch 2/2
35s - loss: 0.3117 - acc: 0.8733 - val_loss: 0.2712 - val_acc: 0.8948






    Out[55]:





<keras.callbacks.History at 0x7f1bd172c5d0>



In [ ]: