by Andrew Trask
In [1]:
def pretty_print_review_and_label(i):
print(labels[i] + "\t:\t" + reviews[i][:80] + "...")
g = open('reviews.txt','r') # What we know!
reviews = list(map(lambda x:x[:-1],g.readlines()))
g.close()
g = open('labels.txt','r') # What we WANT to know!
labels = list(map(lambda x:x[:-1].upper(),g.readlines()))
g.close()
In [2]:
len(reviews)
Out[2]:
25000
In [3]:
reviews[0]
Out[3]:
'bromwell high is a cartoon comedy . it ran at the same time as some other programs about school life such as teachers . my 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 [4]:
labels[0]
Out[4]:
'POSITIVE'
In [5]:
print("labels.txt \t : \t reviews.txt\n")
pretty_print_review_and_label(2137)
pretty_print_review_and_label(12816)
pretty_print_review_and_label(6267)
pretty_print_review_and_label(21934)
pretty_print_review_and_label(5297)
pretty_print_review_and_label(4998)
labels.txt : reviews.txt
NEGATIVE : this movie is terrible but it has some good effects . ...
POSITIVE : adrian pasdar is excellent is this film . he makes a fascinating woman . ...
NEGATIVE : comment this movie is impossible . is terrible very improbable bad interpretat...
POSITIVE : excellent episode movie ala pulp fiction . days suicides . it doesnt get more...
NEGATIVE : if you haven t seen this it s terrible . it is pure trash . i saw this about ...
POSITIVE : this schiffer guy is a real genius the movie is of excellent quality and both e...
In [6]:
from collections import Counter
import numpy as np
In [7]:
positive_counts = Counter()
negative_counts = Counter()
total_counts = Counter()
In [8]:
for i in range(len(reviews)):
if(labels[i] == 'POSITIVE'):
for word in reviews[i].split(" "):
positive_counts[word] += 1
total_counts[word] += 1
else:
for word in reviews[i].split(" "):
negative_counts[word] += 1
total_counts[word] += 1
In [9]:
positive_counts.most_common()
Out[9]:
[('', 550468),
('the', 173324),
('.', 159654),
('and', 89722),
('a', 83688),
('of', 76855),
('to', 66746),
('is', 57245),
('in', 50215),
('br', 49235),
('it', 48025),
('i', 40743),
('that', 35630),
('this', 35080),
('s', 33815),
('as', 26308),
('with', 23247),
('for', 22416),
('was', 21917),
('film', 20937),
('but', 20822),
('movie', 19074),
('his', 17227),
('on', 17008),
('you', 16681),
('he', 16282),
('are', 14807),
('not', 14272),
('t', 13720),
('one', 13655),
('have', 12587),
('be', 12416),
('by', 11997),
('all', 11942),
('who', 11464),
('an', 11294),
('at', 11234),
('from', 10767),
('her', 10474),
('they', 9895),
('has', 9186),
('so', 9154),
('like', 9038),
('about', 8313),
('very', 8305),
('out', 8134),
('there', 8057),
('she', 7779),
('what', 7737),
('or', 7732),
('good', 7720),
('more', 7521),
('when', 7456),
('some', 7441),
('if', 7285),
('just', 7152),
('can', 7001),
('story', 6780),
('time', 6515),
('my', 6488),
('great', 6419),
('well', 6405),
('up', 6321),
('which', 6267),
('their', 6107),
('see', 6026),
('also', 5550),
('we', 5531),
('really', 5476),
('would', 5400),
('will', 5218),
('me', 5167),
('had', 5148),
('only', 5137),
('him', 5018),
('even', 4964),
('most', 4864),
('other', 4858),
('were', 4782),
('first', 4755),
('than', 4736),
('much', 4685),
('its', 4622),
('no', 4574),
('into', 4544),
('people', 4479),
('best', 4319),
('love', 4301),
('get', 4272),
('how', 4213),
('life', 4199),
('been', 4189),
('because', 4079),
('way', 4036),
('do', 3941),
('made', 3823),
('films', 3813),
('them', 3805),
('after', 3800),
('many', 3766),
('two', 3733),
('too', 3659),
('think', 3655),
('movies', 3586),
('characters', 3560),
('character', 3514),
('don', 3468),
('man', 3460),
('show', 3432),
('watch', 3424),
('seen', 3414),
('then', 3358),
('little', 3341),
('still', 3340),
('make', 3303),
('could', 3237),
('never', 3226),
('being', 3217),
('where', 3173),
('does', 3069),
('over', 3017),
('any', 3002),
('while', 2899),
('know', 2833),
('did', 2790),
('years', 2758),
('here', 2740),
('ever', 2734),
('end', 2696),
('these', 2694),
('such', 2590),
('real', 2568),
('scene', 2567),
('back', 2547),
('those', 2485),
('though', 2475),
('off', 2463),
('new', 2458),
('your', 2453),
('go', 2440),
('acting', 2437),
('plot', 2432),
('world', 2429),
('scenes', 2427),
('say', 2414),
('through', 2409),
('makes', 2390),
('better', 2381),
('now', 2368),
('work', 2346),
('young', 2343),
('old', 2311),
('ve', 2307),
('find', 2272),
('both', 2248),
('before', 2177),
('us', 2162),
('again', 2158),
('series', 2153),
('quite', 2143),
('something', 2135),
('cast', 2133),
('should', 2121),
('part', 2098),
('always', 2088),
('lot', 2087),
('another', 2075),
('actors', 2047),
('director', 2040),
('family', 2032),
('between', 2016),
('own', 2016),
('m', 1998),
('may', 1997),
('same', 1972),
('role', 1967),
('watching', 1966),
('every', 1954),
('funny', 1953),
('doesn', 1935),
('performance', 1928),
('few', 1918),
('bad', 1907),
('look', 1900),
('re', 1884),
('why', 1855),
('things', 1849),
('times', 1832),
('big', 1815),
('however', 1795),
('actually', 1790),
('action', 1789),
('going', 1783),
('bit', 1757),
('comedy', 1742),
('down', 1740),
('music', 1738),
('must', 1728),
('take', 1709),
('saw', 1692),
('long', 1690),
('right', 1688),
('fun', 1686),
('fact', 1684),
('excellent', 1683),
('around', 1674),
('didn', 1672),
('without', 1671),
('thing', 1662),
('thought', 1639),
('got', 1635),
('each', 1630),
('day', 1614),
('feel', 1597),
('seems', 1596),
('come', 1594),
('done', 1586),
('beautiful', 1580),
('especially', 1572),
('played', 1571),
('almost', 1566),
('want', 1562),
('yet', 1556),
('give', 1553),
('pretty', 1549),
('last', 1543),
('since', 1519),
('different', 1504),
('although', 1501),
('gets', 1490),
('true', 1487),
('interesting', 1481),
('job', 1470),
('enough', 1455),
('our', 1454),
('shows', 1447),
('horror', 1441),
('woman', 1439),
('tv', 1400),
('probably', 1398),
('father', 1395),
('original', 1393),
('girl', 1390),
('point', 1379),
('plays', 1378),
('wonderful', 1372),
('far', 1358),
('course', 1358),
('john', 1350),
('rather', 1340),
('isn', 1328),
('ll', 1326),
('later', 1324),
('dvd', 1324),
('whole', 1310),
('war', 1310),
('d', 1307),
('found', 1306),
('away', 1306),
('screen', 1305),
('nothing', 1300),
('year', 1297),
('once', 1296),
('hard', 1294),
('together', 1280),
('set', 1277),
('am', 1277),
('having', 1266),
('making', 1265),
('place', 1263),
('might', 1260),
('comes', 1260),
('sure', 1253),
('american', 1248),
('play', 1245),
('kind', 1244),
('perfect', 1242),
('takes', 1242),
('performances', 1237),
('himself', 1230),
('worth', 1221),
('everyone', 1221),
('anyone', 1214),
('actor', 1203),
('three', 1201),
('wife', 1196),
('classic', 1192),
('goes', 1186),
('ending', 1178),
('version', 1168),
('star', 1149),
('enjoy', 1146),
('book', 1142),
('nice', 1132),
('everything', 1128),
('during', 1124),
('put', 1118),
('seeing', 1111),
('least', 1102),
('house', 1100),
('high', 1095),
('watched', 1094),
('loved', 1087),
('men', 1087),
('night', 1082),
('anything', 1075),
('believe', 1071),
('guy', 1071),
('top', 1063),
('amazing', 1058),
('hollywood', 1056),
('looking', 1053),
('main', 1044),
('definitely', 1043),
('gives', 1031),
('home', 1029),
('seem', 1028),
('episode', 1023),
('audience', 1020),
('sense', 1020),
('truly', 1017),
('special', 1011),
('second', 1009),
('short', 1009),
('fan', 1009),
('mind', 1005),
('human', 1001),
('recommend', 999),
('full', 996),
('black', 995),
('help', 991),
('along', 989),
('trying', 987),
('small', 986),
('death', 985),
('friends', 981),
('remember', 974),
('often', 970),
('said', 966),
('favorite', 962),
('heart', 959),
('early', 957),
('left', 956),
('until', 955),
('script', 954),
('let', 954),
('maybe', 937),
('today', 936),
('live', 934),
('less', 934),
('moments', 933),
('others', 929),
('brilliant', 926),
('shot', 925),
('liked', 923),
('become', 916),
('won', 915),
('used', 910),
('style', 907),
('mother', 895),
('lives', 894),
('came', 893),
('stars', 890),
('cinema', 889),
('looks', 885),
('perhaps', 884),
('read', 882),
('enjoyed', 879),
('boy', 875),
('drama', 873),
('highly', 871),
('given', 870),
('playing', 867),
('use', 864),
('next', 859),
('women', 858),
('fine', 857),
('effects', 856),
('kids', 854),
('entertaining', 853),
('need', 852),
('line', 850),
('works', 848),
('someone', 847),
('mr', 836),
('simply', 835),
('picture', 833),
('children', 833),
('face', 831),
('keep', 831),
('friend', 831),
('dark', 830),
('overall', 828),
('certainly', 828),
('minutes', 827),
('wasn', 824),
('history', 822),
('finally', 820),
('couple', 816),
('against', 815),
('son', 809),
('understand', 808),
('lost', 807),
('michael', 805),
('else', 801),
('throughout', 798),
('fans', 797),
('city', 792),
('reason', 789),
('written', 787),
('production', 787),
('several', 784),
('school', 783),
('based', 781),
('rest', 781),
('try', 780),
('dead', 776),
('hope', 775),
('strong', 768),
('white', 765),
('tell', 759),
('itself', 758),
('half', 753),
('person', 749),
('sometimes', 746),
('past', 744),
('start', 744),
('genre', 743),
('beginning', 739),
('final', 739),
('town', 738),
('art', 734),
('humor', 732),
('game', 732),
('yes', 731),
('idea', 731),
('late', 730),
('becomes', 729),
('despite', 729),
('able', 726),
('case', 726),
('money', 723),
('child', 721),
('completely', 721),
('side', 719),
('camera', 716),
('getting', 714),
('instead', 712),
('soon', 702),
('under', 700),
('viewer', 699),
('age', 697),
('days', 696),
('stories', 696),
('felt', 694),
('simple', 694),
('roles', 693),
('video', 688),
('name', 683),
('either', 683),
('doing', 677),
('turns', 674),
('wants', 671),
('close', 671),
('title', 669),
('wrong', 668),
('went', 666),
('james', 665),
('evil', 659),
('budget', 657),
('episodes', 657),
('relationship', 655),
('fantastic', 653),
('piece', 653),
('david', 651),
('turn', 648),
('murder', 646),
('parts', 645),
('brother', 644),
('absolutely', 643),
('head', 643),
('experience', 642),
('eyes', 641),
('sex', 638),
('direction', 637),
('called', 637),
('directed', 636),
('lines', 634),
('behind', 633),
('sort', 632),
('actress', 631),
('lead', 630),
('oscar', 628),
('including', 627),
('example', 627),
('known', 625),
('musical', 625),
('chance', 621),
('score', 620),
('already', 619),
('feeling', 619),
('hit', 619),
('voice', 615),
('moment', 612),
('living', 612),
('low', 610),
('supporting', 610),
('ago', 609),
('themselves', 608),
('reality', 605),
('hilarious', 605),
('jack', 604),
('told', 603),
('hand', 601),
('quality', 600),
('moving', 600),
('dialogue', 600),
('song', 599),
('happy', 599),
('matter', 598),
('paul', 598),
('light', 594),
('future', 593),
('entire', 592),
('finds', 591),
('gave', 589),
('laugh', 587),
('released', 586),
('expect', 584),
('fight', 581),
('particularly', 580),
('cinematography', 579),
('police', 579),
('whose', 578),
('type', 578),
('sound', 578),
('view', 573),
('enjoyable', 573),
('number', 572),
('romantic', 572),
('husband', 572),
('daughter', 572),
('documentary', 571),
('self', 570),
('superb', 569),
('modern', 569),
('took', 569),
('robert', 569),
('mean', 566),
('shown', 563),
('coming', 561),
('important', 560),
('king', 559),
('leave', 559),
('change', 558),
('somewhat', 555),
('wanted', 555),
('tells', 554),
('events', 552),
('run', 552),
('career', 552),
('country', 552),
('heard', 550),
('season', 550),
('greatest', 549),
('girls', 549),
('etc', 547),
('care', 546),
('starts', 545),
('english', 542),
('killer', 541),
('tale', 540),
('guys', 540),
('totally', 540),
('animation', 540),
('usual', 539),
('miss', 535),
('opinion', 535),
('easy', 531),
('violence', 531),
('songs', 530),
('british', 528),
('says', 526),
('realistic', 525),
('writing', 524),
('writer', 522),
('act', 522),
('comic', 521),
('thriller', 519),
('television', 517),
('power', 516),
('ones', 515),
('kid', 514),
('york', 513),
('novel', 513),
('alone', 512),
('problem', 512),
('attention', 509),
('involved', 508),
('kill', 507),
('extremely', 507),
('seemed', 506),
('hero', 505),
('french', 505),
('rock', 504),
('stuff', 501),
('wish', 499),
('begins', 498),
('taken', 497),
('sad', 497),
('ways', 496),
('richard', 495),
('knows', 494),
('atmosphere', 493),
('similar', 491),
('surprised', 491),
('taking', 491),
('car', 491),
('george', 490),
('perfectly', 490),
('across', 489),
('team', 489),
('eye', 489),
('sequence', 489),
('room', 488),
('due', 488),
('among', 488),
('serious', 488),
('powerful', 488),
('strange', 487),
('order', 487),
('cannot', 487),
('b', 487),
('beauty', 486),
('famous', 485),
('happened', 484),
('tries', 484),
('herself', 484),
('myself', 484),
('class', 483),
('four', 482),
('cool', 481),
('release', 479),
('anyway', 479),
('theme', 479),
('opening', 478),
('entertainment', 477),
('slow', 475),
('ends', 475),
('unique', 475),
('exactly', 475),
('easily', 474),
('level', 474),
('o', 474),
('red', 474),
('interest', 472),
('happen', 471),
('crime', 470),
('viewing', 468),
('sets', 467),
('memorable', 467),
('stop', 466),
('group', 466),
('problems', 463),
('dance', 463),
('working', 463),
('sister', 463),
('message', 463),
('knew', 462),
('mystery', 461),
('nature', 461),
('bring', 460),
('believable', 459),
('thinking', 459),
('brought', 459),
('mostly', 458),
('disney', 457),
('couldn', 457),
('society', 456),
('lady', 455),
('within', 455),
('blood', 454),
('parents', 453),
('upon', 453),
('viewers', 453),
('meets', 452),
('form', 452),
('peter', 452),
('tom', 452),
('usually', 452),
('soundtrack', 452),
('local', 450),
('certain', 448),
('follow', 448),
('whether', 447),
('possible', 446),
('emotional', 445),
('killed', 444),
('above', 444),
('de', 444),
('god', 443),
('middle', 443),
('needs', 442),
('happens', 442),
('flick', 442),
('masterpiece', 441),
('period', 440),
('major', 440),
('named', 439),
('haven', 439),
('particular', 438),
('th', 438),
('earth', 437),
('feature', 437),
('stand', 436),
('words', 435),
('typical', 435),
('elements', 433),
('obviously', 433),
('romance', 431),
('jane', 430),
('yourself', 427),
('showing', 427),
('brings', 426),
('fantasy', 426),
('guess', 423),
('america', 423),
('unfortunately', 422),
('huge', 422),
('indeed', 421),
('running', 421),
('talent', 420),
('stage', 419),
('started', 418),
('leads', 417),
('sweet', 417),
('japanese', 417),
('poor', 416),
('deal', 416),
('incredible', 413),
('personal', 413),
('fast', 412),
('became', 410),
('deep', 410),
('hours', 409),
('giving', 408),
('nearly', 408),
('dream', 408),
('clearly', 407),
('turned', 407),
('obvious', 406),
('near', 406),
('cut', 405),
('surprise', 405),
('era', 404),
('body', 404),
('hour', 403),
('female', 403),
('five', 403),
('note', 399),
('learn', 398),
('truth', 398),
('except', 397),
('feels', 397),
('match', 397),
('tony', 397),
('filmed', 394),
('clear', 394),
('complete', 394),
('street', 393),
('eventually', 393),
('keeps', 393),
('older', 393),
('lots', 393),
('buy', 392),
('william', 391),
('stewart', 391),
('fall', 390),
('joe', 390),
('meet', 390),
('unlike', 389),
('talking', 389),
('shots', 389),
('rating', 389),
('difficult', 389),
('dramatic', 388),
('means', 388),
('situation', 386),
('wonder', 386),
('present', 386),
('appears', 386),
('subject', 386),
('comments', 385),
('general', 383),
('sequences', 383),
('lee', 383),
('points', 382),
('earlier', 382),
('gone', 379),
('check', 379),
('suspense', 378),
('recommended', 378),
('ten', 378),
('third', 377),
('business', 377),
('talk', 375),
('leaves', 375),
('beyond', 375),
('portrayal', 374),
('beautifully', 373),
('single', 372),
('bill', 372),
('plenty', 371),
('word', 371),
('whom', 370),
('falls', 370),
('scary', 369),
('non', 369),
('figure', 369),
('battle', 369),
('using', 368),
('return', 368),
('doubt', 367),
('add', 367),
('hear', 366),
('solid', 366),
('success', 366),
('jokes', 365),
('oh', 365),
('touching', 365),
('political', 365),
('hell', 364),
('awesome', 364),
('boys', 364),
('sexual', 362),
('recently', 362),
('dog', 362),
('please', 361),
('wouldn', 361),
('straight', 361),
('features', 361),
('forget', 360),
('setting', 360),
('lack', 360),
('married', 359),
('mark', 359),
('social', 357),
('interested', 356),
('adventure', 356),
('actual', 355),
('terrific', 355),
('sees', 355),
('brothers', 355),
('move', 354),
('call', 354),
('various', 353),
('theater', 353),
('dr', 353),
('animated', 352),
('western', 351),
('baby', 350),
('space', 350),
('leading', 348),
('disappointed', 348),
('portrayed', 346),
('aren', 346),
('screenplay', 345),
('smith', 345),
('towards', 344),
('hate', 344),
('noir', 343),
('outstanding', 342),
('decent', 342),
('kelly', 342),
('directors', 341),
('journey', 341),
('none', 340),
('looked', 340),
('effective', 340),
('storyline', 339),
('caught', 339),
('sci', 339),
('fi', 339),
('cold', 339),
('mary', 339),
('rich', 338),
('charming', 338),
('popular', 337),
('rare', 337),
('manages', 337),
('harry', 337),
('spirit', 336),
('appreciate', 335),
('open', 335),
('moves', 334),
('basically', 334),
('acted', 334),
('inside', 333),
('boring', 333),
('century', 333),
('mention', 333),
('deserves', 333),
('subtle', 333),
('pace', 333),
('familiar', 332),
('background', 332),
('ben', 331),
('creepy', 330),
('supposed', 330),
('secret', 329),
('die', 328),
('jim', 328),
('question', 327),
('effect', 327),
('natural', 327),
('impressive', 326),
('rate', 326),
('language', 326),
('saying', 325),
('intelligent', 325),
('telling', 324),
('realize', 324),
('material', 324),
('scott', 324),
('singing', 323),
('dancing', 322),
('visual', 321),
('adult', 321),
('imagine', 321),
('kept', 320),
('office', 320),
('uses', 319),
('pure', 318),
('wait', 318),
('stunning', 318),
('review', 317),
('previous', 317),
('copy', 317),
('seriously', 317),
('reading', 316),
('create', 316),
('hot', 316),
('created', 316),
('magic', 316),
('somehow', 316),
('stay', 315),
('attempt', 315),
('escape', 315),
('crazy', 315),
('air', 315),
('frank', 315),
('hands', 314),
('filled', 313),
('expected', 312),
('average', 312),
('surprisingly', 312),
('complex', 311),
('quickly', 310),
('successful', 310),
('studio', 310),
('plus', 309),
('male', 309),
('co', 307),
('images', 306),
('casting', 306),
('following', 306),
('minute', 306),
('exciting', 306),
('members', 305),
('follows', 305),
('themes', 305),
('german', 305),
('reasons', 305),
('e', 305),
('touch', 304),
('edge', 304),
('free', 304),
('cute', 304),
('genius', 304),
('outside', 303),
('reviews', 302),
('admit', 302),
('ok', 302),
('younger', 302),
('fighting', 301),
('odd', 301),
('master', 301),
('recent', 300),
('thanks', 300),
('break', 300),
('comment', 300),
('apart', 299),
('emotions', 298),
('lovely', 298),
('begin', 298),
('doctor', 297),
('party', 297),
('italian', 297),
('la', 296),
('missed', 296),
...]
In [10]:
pos_neg_ratios = Counter()
for term,cnt in list(total_counts.most_common()):
if(cnt > 100):
pos_neg_ratio = positive_counts[term] / float(negative_counts[term]+1)
pos_neg_ratios[term] = pos_neg_ratio
for word,ratio in pos_neg_ratios.most_common():
if(ratio > 1):
pos_neg_ratios[word] = np.log(ratio)
else:
pos_neg_ratios[word] = -np.log((1 / (ratio+0.01)))
In [11]:
# words most frequently seen in a review with a "POSITIVE" label
pos_neg_ratios.most_common()
Out[11]:
[('edie', 4.6913478822291435),
('paulie', 4.0775374439057197),
('felix', 3.1527360223636558),
('polanski', 2.8233610476132043),
('matthau', 2.8067217286092401),
('victoria', 2.6810215287142909),
('mildred', 2.6026896854443837),
('gandhi', 2.5389738710582761),
('flawless', 2.451005098112319),
('superbly', 2.2600254785752498),
('perfection', 2.1594842493533721),
('astaire', 2.1400661634962708),
('captures', 2.0386195471595809),
('voight', 2.0301704926730531),
('wonderfully', 2.0218960560332353),
('powell', 1.9783454248084671),
('brosnan', 1.9547990964725592),
('lily', 1.9203768470501485),
('bakshi', 1.9029851043382795),
('lincoln', 1.9014583864844796),
('refreshing', 1.8551812956655511),
('breathtaking', 1.8481124057791867),
('bourne', 1.8478489358790986),
('lemmon', 1.8458266904983307),
('delightful', 1.8002701588959635),
('flynn', 1.7996646487351682),
('andrews', 1.7764919970972666),
('homer', 1.7692866133759964),
('beautifully', 1.7626953362841438),
('soccer', 1.7578579175523736),
('elvira', 1.7397031072720019),
('underrated', 1.7197859696029656),
('gripping', 1.7165360479904674),
('superb', 1.7091514458966952),
('delight', 1.6714733033535532),
('welles', 1.6677068205580761),
('sadness', 1.663505133704376),
('sinatra', 1.6389967146756448),
('touching', 1.637217476541176),
('timeless', 1.62924053973028),
('macy', 1.6211339521972916),
('unforgettable', 1.6177367152487956),
('favorites', 1.6158688027643908),
('stewart', 1.6119987332957739),
('sullivan', 1.6094379124341003),
('extraordinary', 1.6094379124341003),
('hartley', 1.6094379124341003),
('brilliantly', 1.5950491749820008),
('friendship', 1.5677652160335325),
('wonderful', 1.5645425925262093),
('palma', 1.5553706911638245),
('magnificent', 1.54663701119507),
('finest', 1.5462590108125689),
('jackie', 1.5439233053234738),
('ritter', 1.5404450409471491),
('tremendous', 1.5184661342283736),
('freedom', 1.5091151908062312),
('fantastic', 1.5048433868558566),
('terrific', 1.5026699370083942),
('noir', 1.493925025312256),
('sidney', 1.493925025312256),
('outstanding', 1.4910053152089213),
('pleasantly', 1.4894785973551214),
('mann', 1.4894785973551214),
('nancy', 1.488077055429833),
('marie', 1.4825711915553104),
('marvelous', 1.4739999415389962),
('excellent', 1.4647538505723599),
('ruth', 1.4596256342054401),
('stanwyck', 1.4412101187160054),
('widmark', 1.4350845252893227),
('splendid', 1.4271163556401458),
('chan', 1.423108334242607),
('exceptional', 1.4201959127955721),
('tender', 1.410986973710262),
('gentle', 1.4078005663408544),
('poignant', 1.4022947024663317),
('gem', 1.3932148039644643),
('amazing', 1.3919815802404802),
('chilling', 1.3862943611198906),
('fisher', 1.3862943611198906),
('davies', 1.3862943611198906),
('captivating', 1.3862943611198906),
('darker', 1.3652409519220583),
('april', 1.3499267169490159),
('kelly', 1.3461743673304654),
('blake', 1.3418425985490567),
('overlooked', 1.329135947279942),
('ralph', 1.32818673031261),
('bette', 1.3156767939059373),
('hoffman', 1.3150668518315229),
('cole', 1.3121863889661687),
('shines', 1.3049487216659381),
('powerful', 1.2999662776313934),
('notch', 1.2950456896547455),
('remarkable', 1.2883688239495823),
('pitt', 1.286210902562908),
('winters', 1.2833463918674481),
('vivid', 1.2762934659055623),
('gritty', 1.2757524867200667),
('giallo', 1.2745029551317739),
('portrait', 1.2704625455947689),
('innocence', 1.2694300209805796),
('psychiatrist', 1.2685113254635072),
('favorite', 1.2668956297860055),
('ensemble', 1.2656663733312759),
('stunning', 1.2622417124499117),
('burns', 1.259880436264232),
('garbo', 1.258954938743289),
('barbara', 1.2580400255962119),
('philip', 1.2527629684953681),
('panic', 1.2527629684953681),
('holly', 1.2527629684953681),
('carol', 1.2481440226390734),
('perfect', 1.246742480713785),
('appreciated', 1.2462482874741743),
('favourite', 1.2411123512753928),
('journey', 1.2367626271489269),
('rural', 1.235471471385307),
('bond', 1.2321436812926323),
('builds', 1.2305398317106577),
('brilliant', 1.2287554137664785),
('brooklyn', 1.2286654169163074),
('von', 1.225175011976539),
('recommended', 1.2163953243244932),
('unfolds', 1.2163953243244932),
('daniel', 1.20215296760895),
('perfectly', 1.1971931173405572),
('crafted', 1.1962507582320256),
('prince', 1.1939224684724346),
('troubled', 1.192138346678933),
('consequences', 1.1865810616140668),
('haunting', 1.1814999484738773),
('cinderella', 1.180052620608284),
('alexander', 1.1759989522835299),
('emotions', 1.1753049094563641),
('boxing', 1.1735135968412274),
('subtle', 1.1734135017508081),
('curtis', 1.1649873576129823),
('rare', 1.1566438362402944),
('loved', 1.1563661500586044),
('daughters', 1.1526795099383853),
('courage', 1.1438688802562305),
('dentist', 1.1426722784621401),
('highly', 1.1420208631618658),
('nominated', 1.1409146683587992),
('tony', 1.1397491942285991),
('draws', 1.1325138403437911),
('everyday', 1.1306150197542835),
('contrast', 1.1284652518177909),
('cried', 1.1213405397456659),
('fabulous', 1.1210851445201684),
('ned', 1.120591195386885),
('fay', 1.120591195386885),
('emma', 1.1184149159642893),
('sensitive', 1.113318436057805),
('smooth', 1.1089750757036563),
('dramas', 1.1080910326226534),
('today', 1.1050431789984001),
('helps', 1.1023091505494358),
('inspiring', 1.0986122886681098),
('jimmy', 1.0937696641923216),
('awesome', 1.0931328229034842),
('unique', 1.0881409888008142),
('tragic', 1.0871835928444868),
('intense', 1.0870514662670339),
('stellar', 1.0857088838322018),
('rival', 1.0822184788924332),
('provides', 1.0797081340289569),
('depression', 1.0782034170369026),
('shy', 1.0775588794702773),
('carrie', 1.076139432816051),
('blend', 1.0753554265038423),
('hank', 1.0736109864626924),
('diana', 1.0726368022648489),
('adorable', 1.0726368022648489),
('unexpected', 1.0722255334949147),
('achievement', 1.0668635903535293),
('bettie', 1.0663514264498881),
('happiness', 1.0632729222228008),
('glorious', 1.0608719606852626),
('davis', 1.0541605260972757),
('terrifying', 1.0525211814678428),
('beauty', 1.050410186850232),
('ideal', 1.0479685558493548),
('fears', 1.0467872208035236),
('hong', 1.0438040521731147),
('seasons', 1.0433496099930604),
('fascinating', 1.0414538748281612),
('carries', 1.0345904299031787),
('satisfying', 1.0321225473992768),
('definite', 1.0319209141694374),
('touched', 1.0296194171811581),
('greatest', 1.0248947127715422),
('creates', 1.0241097613701886),
('aunt', 1.023388867430522),
('walter', 1.022328983918479),
('spectacular', 1.0198314108149955),
('portrayal', 1.0189810189761024),
('ann', 1.0127808528183286),
('enterprise', 1.0116009116784799),
('musicals', 1.0096648026516135),
('deeply', 1.0094845087721023),
('incredible', 1.0061677561461084),
('mature', 1.0060195018402847),
('triumph', 0.99682959435816731),
('margaret', 0.99682959435816731),
('navy', 0.99493385919326827),
('harry', 0.99176919305006062),
('lucas', 0.990398704027877),
('sweet', 0.98966110487955483),
('joey', 0.98794672078059009),
('oscar', 0.98721905111049713),
('balance', 0.98649499054740353),
('warm', 0.98485340331145166),
('ages', 0.98449898190068863),
('guilt', 0.98082925301172619),
('glover', 0.98082925301172619),
('carrey', 0.98082925301172619),
('learns', 0.97881108885548895),
('unusual', 0.97788374278196932),
('sons', 0.97777581552483595),
('complex', 0.97761897738147796),
('essence', 0.97753435711487369),
('brazil', 0.9769153536905899),
('widow', 0.97650959186720987),
('solid', 0.97537964824416146),
('beautiful', 0.97326301262841053),
('holmes', 0.97246100334120955),
('awe', 0.97186058302896583),
('vhs', 0.97116734209998934),
('eerie', 0.97116734209998934),
('lonely', 0.96873720724669754),
('grim', 0.96873720724669754),
('sport', 0.96825047080486615),
('debut', 0.96508089604358704),
('destiny', 0.96343751029985703),
('thrillers', 0.96281074750904794),
('tears', 0.95977584381389391),
('rose', 0.95664202739772253),
('feelings', 0.95551144502743635),
('ginger', 0.95551144502743635),
('winning', 0.95471810900804055),
('stanley', 0.95387344302319799),
('cox', 0.95343027882361187),
('paris', 0.95278479030472663),
('heart', 0.95238806924516806),
('hooked', 0.95155887071161305),
('comfortable', 0.94803943018873538),
('mgm', 0.94446160884085151),
('masterpiece', 0.94155039863339296),
('themes', 0.94118828349588235),
('danny', 0.93967118051821874),
('anime', 0.93378388932167222),
('perry', 0.93328830824272613),
('joy', 0.93301752567946861),
('lovable', 0.93081883243706487),
('mysteries', 0.92953595862417571),
('hal', 0.92953595862417571),
('louis', 0.92871325187271225),
('charming', 0.92520609553210742),
('urban', 0.92367083917177761),
('allows', 0.92183091224977043),
('impact', 0.91815814604895041),
('italy', 0.91629073187415511),
('gradually', 0.91629073187415511),
('lifestyle', 0.91629073187415511),
('spy', 0.91289514287301687),
('treat', 0.91193342650519937),
('subsequent', 0.91056005716517008),
('kennedy', 0.90981821736853763),
('loving', 0.90967549275543591),
('surprising', 0.90937028902958128),
('quiet', 0.90648673177753425),
('winter', 0.90624039602065365),
('reveals', 0.90490540964902977),
('raw', 0.90445627422715225),
('funniest', 0.90078654533818991),
('pleased', 0.89994159387262562),
('norman', 0.89994159387262562),
('thief', 0.89874642222324552),
('season', 0.89827222637147675),
('secrets', 0.89794159320595857),
('colorful', 0.89705936994626756),
('highest', 0.8967461358011849),
('compelling', 0.89462923509297576),
('danes', 0.89248008318043659),
('castle', 0.88967708335606499),
('kudos', 0.88889175768604067),
('great', 0.88810470901464589),
('baseball', 0.88730319500090271),
('subtitles', 0.88730319500090271),
('bleak', 0.88730319500090271),
('winner', 0.88643776872447388),
('tragedy', 0.88563699078315261),
('todd', 0.88551907320740142),
('nicely', 0.87924946019380601),
('arthur', 0.87546873735389985),
('essential', 0.87373111745535925),
('gorgeous', 0.8731725250935497),
('fonda', 0.87294029100054127),
('eastwood', 0.87139541196626402),
('focuses', 0.87082835779739776),
('enjoyed', 0.87070195951624607),
('natural', 0.86997924506912838),
('intensity', 0.86835126958503595),
('witty', 0.86824103423244681),
('rob', 0.8642954367557748),
('worlds', 0.86377269759070874),
('health', 0.86113891179907498),
('magical', 0.85953791528170564),
('deeper', 0.85802182375017932),
('lucy', 0.85618680780444956),
('moving', 0.85566611005772031),
('lovely', 0.85290640004681306),
('purple', 0.8513711857748395),
('memorable', 0.84801189112086062),
('sings', 0.84729786038720367),
('craig', 0.84342938360928321),
('modesty', 0.84342938360928321),
('relate', 0.84326559685926517),
('episodes', 0.84223712084137292),
('strong', 0.84167135777060931),
('smith', 0.83959811108590054),
('tear', 0.83704136022001441),
('apartment', 0.83333115290549531),
('princess', 0.83290912293510388),
('disagree', 0.83290912293510388),
('kung', 0.83173334384609199),
('adventure', 0.83150561393278388),
('columbo', 0.82667857318446791),
('jake', 0.82667857318446791),
('adds', 0.82485652591452319),
('hart', 0.82472353834866463),
('strength', 0.82417544296634937),
('realizes', 0.82360006895738058),
('dave', 0.8232003088081431),
('childhood', 0.82208086393583857),
('forbidden', 0.81989888619908913),
('tight', 0.81883539572344199),
('surreal', 0.8178506590609026),
('manager', 0.81770990320170756),
('dancer', 0.81574950265227764),
('studios', 0.81093021621632877),
('con', 0.81093021621632877),
('miike', 0.80821651034473263),
('realistic', 0.80807714723392232),
('explicit', 0.80792269515237358),
('kurt', 0.8060875917405409),
('traditional', 0.80535917116687328),
('deals', 0.80535917116687328),
('holds', 0.80493858654806194),
('carl', 0.80437281567016972),
('touches', 0.80396154690023547),
('gene', 0.80314807577427383),
('albert', 0.8027669055771679),
('abc', 0.80234647252493729),
('cry', 0.80011930011211307),
('sides', 0.7995275841185171),
('develops', 0.79850769621777162),
('eyre', 0.79850769621777162),
('dances', 0.79694397424158891),
('oscars', 0.79633141679517616),
('legendary', 0.79600456599965308),
('hearted', 0.79492987486988764),
('importance', 0.79492987486988764),
('portraying', 0.79356592830699269),
('impressed', 0.79258107754813223),
('waters', 0.79112758892014912),
('empire', 0.79078565012386137),
('edge', 0.789774016249017),
('jean', 0.78845736036427028),
('environment', 0.78845736036427028),
('sentimental', 0.7864791203521645),
('captured', 0.78623760362595729),
('styles', 0.78592891401091158),
('daring', 0.78592891401091158),
('frank', 0.78275933924963248),
('tense', 0.78275933924963248),
('backgrounds', 0.78275933924963248),
('matches', 0.78275933924963248),
('gothic', 0.78209466657644144),
('sharp', 0.7814397877056235),
('achieved', 0.78015855754957497),
('court', 0.77947526404844247),
('steals', 0.7789140023173704),
('rules', 0.77844476107184035),
('colors', 0.77684619943659217),
('reunion', 0.77318988823348167),
('covers', 0.77139937745969345),
('tale', 0.77010822169607374),
('rain', 0.7683706017975328),
('denzel', 0.76804848873306297),
('stays', 0.76787072675588186),
('blob', 0.76725515271366718),
('maria', 0.76214005204689672),
('conventional', 0.76214005204689672),
('fresh', 0.76158434211317383),
('midnight', 0.76096977689870637),
('landscape', 0.75852993982279704),
('animated', 0.75768570169751648),
('titanic', 0.75666058628227129),
('sunday', 0.75666058628227129),
('spring', 0.7537718023763802),
('cagney', 0.7537718023763802),
('enjoyable', 0.75246375771636476),
('immensely', 0.75198768058287868),
('sir', 0.7507762933965817),
('nevertheless', 0.75067102469813185),
('driven', 0.74994477895307854),
('performances', 0.74883252516063137),
('memories', 0.74721440183022114),
('nowadays', 0.74721440183022114),
('simple', 0.74641420974143258),
('golden', 0.74533293373051557),
('leslie', 0.74533293373051557),
('lovers', 0.74497224842453125),
('relationship', 0.74484232345601786),
('supporting', 0.74357803418683721),
('che', 0.74262723782331497),
('packed', 0.7410032017375805),
('trek', 0.74021469141793106),
('provoking', 0.73840377214806618),
('strikes', 0.73759894313077912),
('depiction', 0.73682224406260699),
('emotional', 0.73678211645681524),
('secretary', 0.7366322924996842),
('influenced', 0.73511137965897755),
('florida', 0.73511137965897755),
('germany', 0.73288750920945944),
('brings', 0.73142936713096229),
('lewis', 0.73129894652432159),
('elderly', 0.73088750854279239),
('owner', 0.72743625403857748),
('streets', 0.72666987259858895),
('henry', 0.72642196944481741),
('portrays', 0.72593700338293632),
('bears', 0.7252354951114458),
('china', 0.72489587887452556),
('anger', 0.72439972406404984),
('society', 0.72433010799663333),
('available', 0.72415741730250549),
('best', 0.72347034060446314),
('bugs', 0.72270598280148979),
('magic', 0.71878961117328299),
('delivers', 0.71846498854423513),
('verhoeven', 0.71846498854423513),
('jim', 0.71783979315031676),
('donald', 0.71667767797013937),
('endearing', 0.71465338578090898),
('relationships', 0.71393795022901896),
('greatly', 0.71256526641704687),
('charlie', 0.71024161391924534),
('brad', 0.71024161391924534),
('simon', 0.70967648251115578),
('effectively', 0.70914752190638641),
('march', 0.70774597998109789),
('atmosphere', 0.70744773070214162),
('influence', 0.70733181555190172),
('genius', 0.706392407309966),
('emotionally', 0.70556970055850243),
('ken', 0.70526854109229009),
('identity', 0.70484322032313651),
('sophisticated', 0.70470800296102132),
('dan', 0.70457587638356811),
('andrew', 0.70329955202396321),
('india', 0.70144598337464037),
('roy', 0.69970458110610434),
('surprisingly', 0.6995780708902356),
('sky', 0.69780919366575667),
('romantic', 0.69664981111114743),
('match', 0.69566924999265523),
('meets', 0.69314718055994529),
('cowboy', 0.69314718055994529),
('wave', 0.69314718055994529),
('bitter', 0.69314718055994529),
('patient', 0.69314718055994529),
('stylish', 0.69314718055994529),
('britain', 0.69314718055994529),
('affected', 0.69314718055994529),
('beatty', 0.69314718055994529),
('love', 0.69198533541937324),
('paul', 0.68980827929443067),
('andy', 0.68846333124751902),
('performance', 0.68797386327972465),
('patrick', 0.68645819240914863),
('unlike', 0.68546468438792907),
('brooks', 0.68433655087779044),
('refuses', 0.68348526964820844),
('award', 0.6824518914431974),
('complaint', 0.6824518914431974),
('ride', 0.68229716453587952),
('dawson', 0.68171848473632257),
('luke', 0.68158635815886937),
('wells', 0.68087708796813096),
('france', 0.6804081547825156),
('sports', 0.68007509899259255),
('handsome', 0.68007509899259255),
('directs', 0.67875844310784572),
('rebel', 0.67875844310784572),
('greater', 0.67605274720064523),
('dreams', 0.67599410133369586),
('effective', 0.67565402311242806),
('interpretation', 0.67479804189174875),
('works', 0.67445504754779284),
('brando', 0.67445504754779284),
('noble', 0.6737290947028437),
('paced', 0.67314651385327573),
('le', 0.67067432470788668),
('master', 0.67015766233524654),
('h', 0.6696166831497512),
('rings', 0.66904962898088483),
('easy', 0.66895995494594152),
('city', 0.66820823221269321),
('sunshine', 0.66782937257565544),
('succeeds', 0.66647893347778397),
('relations', 0.664159643686693),
('england', 0.66387679825983203),
('glimpse', 0.66329421741026418),
('aired', 0.66268797307523675),
('sees', 0.66263163663399482),
('both', 0.66248336767382998),
('definitely', 0.66199789483898808),
('imaginative', 0.66139848224536502),
('appreciate', 0.66083893732728749),
('tricks', 0.66071190480679143),
('striking', 0.66071190480679143),
('carefully', 0.65999497324304479),
('complicated', 0.65981076029235353),
('perspective', 0.65962448852130173),
('trilogy', 0.65877953705573755),
('future', 0.65834665141052828),
('lion', 0.65742909795786608),
('douglas', 0.65540685257709819),
('victor', 0.65540685257709819),
('inspired', 0.65459851044271034),
('marriage', 0.65392646740666405),
('demands', 0.65392646740666405),
('father', 0.65172321672194655),
('page', 0.65123628494430852),
('instant', 0.65058756614114943),
('era', 0.6495567444850836),
('ruthless', 0.64934455790155243),
('saga', 0.64934455790155243),
('joan', 0.64891392558311978),
('joseph', 0.64841128671855386),
('workers', 0.64829661439459352),
('fantasy', 0.64726757480925168),
('distant', 0.64551913157069074),
('accomplished', 0.64551913157069074),
('manhattan', 0.64435701639051324),
('personal', 0.64355023942057321),
('meeting', 0.64313675998528386),
('individual', 0.64313675998528386),
('pushing', 0.64313675998528386),
('pleasant', 0.64250344774119039),
('brave', 0.64185388617239469),
('william', 0.64083139119578469),
('hudson', 0.64077919504262937),
('friendly', 0.63949446706762514),
('eccentric', 0.63907995928966954),
('awards', 0.63875310849414646),
('jack', 0.63838309514997038),
('seeking', 0.63808740337691783),
('divorce', 0.63757732940513456),
('colonel', 0.63757732940513456),
('jane', 0.63443957973316734),
('keeping', 0.63414883979798953),
('gives', 0.63383568159497883),
('ted', 0.63342794585832296),
('animation', 0.63208692379869902),
('progress', 0.6317782341836532),
('larger', 0.63127177684185776),
('concert', 0.63127177684185776),
('nation', 0.6296337748376194),
('albeit', 0.62739580299716491),
('adapted', 0.62613647027698516),
('discovers', 0.62542900650499444),
('classic', 0.62504956428050518),
('segment', 0.62335141862440335),
('morgan', 0.62303761437291871),
('mouse', 0.62294292188669675),
('impressive', 0.62211140744319349),
('artist', 0.62168821657780038),
('ultimate', 0.62168821657780038),
('griffith', 0.62117368093485603),
('drew', 0.62082651898031915),
('emily', 0.62082651898031915),
('moved', 0.6197197120051281),
('families', 0.61903920840622351),
('profound', 0.61903920840622351),
('innocent', 0.61851219917136446),
('versions', 0.61730910416844087),
('eddie', 0.61691981517206107),
('criticism', 0.61651395453902935),
('nature', 0.61594514653194088),
('recognized', 0.61518563909023349),
('sexuality', 0.61467556511845012),
('contract', 0.61400986000122149),
('brian', 0.61344043794920278),
('remembered', 0.6131044728864089),
('determined', 0.6123858239154869),
('offers', 0.61207935747116349),
('pleasure', 0.61195702582993206),
('washington', 0.61180154110599294),
('images', 0.61159731359583758),
('games', 0.61067095873570676),
('academy', 0.60872983874736208),
('fashioned', 0.60798937221963845),
('melodrama', 0.60749173598145145),
('rough', 0.60613580357031549),
('charismatic', 0.60613580357031549),
('peoples', 0.60613580357031549),
('dealing', 0.60517840761398811),
('fine', 0.60496962268013299),
('tap', 0.60391604683200273),
('trio', 0.60157998703445481),
('russell', 0.60120968523425966),
('figures', 0.60077386042893011),
('ward', 0.60005675749393339),
('shine', 0.59911823091166894),
('brady', 0.59911823091166894),
('job', 0.59845562125168661),
('satisfied', 0.59652034487087369),
('river', 0.59637962862495086),
('brown', 0.595773016534769),
('believable', 0.59566072133302495),
('always', 0.59470710774669278),
('bound', 0.59470710774669278),
('hall', 0.5933967777928858),
('cook', 0.5916777203950857),
('claire', 0.59136448625000293),
('broadway', 0.59033768669372433),
('anna', 0.58778666490211906),
('peace', 0.58628403501758408),
('visually', 0.58539431926349916),
('morality', 0.58525821854876026),
('falk', 0.58525821854876026),
('growing', 0.58466653756587539),
('experiences', 0.58314628534561685),
('stood', 0.58314628534561685),
('touch', 0.58122926435596001),
('lives', 0.5810976767513224),
('kubrick', 0.58066919713325493),
('timing', 0.58047401805583243),
('expressions', 0.57981849525294216),
('struggles', 0.57981849525294216),
('authentic', 0.57848427223980559),
('helen', 0.57763429343810091),
('pre', 0.57700753064729182),
('quirky', 0.5753641449035618),
('young', 0.57531672344534313),
('inner', 0.57454143815209846),
('mexico', 0.57443087372056334),
('clint', 0.57380042292737909),
('sisters', 0.57286101468544337),
('realism', 0.57226528899949558),
('french', 0.5720692490067093),
('personalities', 0.5720692490067093),
('surprises', 0.57113222999698177),
('adventures', 0.57113222999698177),
('overcome', 0.5697681593994407),
('timothy', 0.56953322459276867),
('tales', 0.56909453188996639),
('war', 0.56843317302781682),
('civil', 0.5679840376059393),
('countries', 0.56737779327091187),
('streep', 0.56710645966458029),
('tradition', 0.56685345523565323),
('oliver', 0.56673325570428668),
('australia', 0.56580775818334383),
('understanding', 0.56531380905006046),
('players', 0.56509525370004821),
('knowing', 0.56489284503626647),
('rogers', 0.56421349718405212),
('suspenseful', 0.56368911332305849),
('variety', 0.56368911332305849),
('true', 0.56281525180810066),
('jr', 0.56220982311246936),
('psychological', 0.56108745854687891),
('sent', 0.55961578793542266),
('grand', 0.55961578793542266),
('branagh', 0.55961578793542266),
('reminiscent', 0.55961578793542266),
('performing', 0.55961578793542266),
('wealth', 0.55961578793542266),
('overwhelming', 0.55961578793542266),
('odds', 0.55961578793542266),
('brothers', 0.55891181043362848),
('howard', 0.55811089675600245),
('david', 0.55693122256475369),
('generation', 0.55628799784274796),
('grow', 0.55612538299565417),
('survival', 0.55594605904646033),
('mainstream', 0.55574731115750231),
('dick', 0.55431073570572953),
('charm', 0.55288175575407861),
('kirk', 0.55278982286502287),
('twists', 0.55244729845681018),
('gangster', 0.55206858230003986),
('jeff', 0.55179306225421365),
('family', 0.55116244510065526),
('tend', 0.55053307336110335),
('thanks', 0.55049088015842218),
('world', 0.54744234723432639),
('sutherland', 0.54743536937855164),
('life', 0.54695514434959924),
('disc', 0.54654370636806993),
('bug', 0.54654370636806993),
('tribute', 0.5455111817538808),
('europe', 0.54522705048332309),
('sacrifice', 0.54430155296238014),
('color', 0.54405127139431109),
('superior', 0.54333490233128523),
('york', 0.54318235866536513),
('pulls', 0.54266622962164945),
('jackson', 0.54232429082536171),
('hearts', 0.54232429082536171),
('enjoy', 0.54124285135906114),
('redemption', 0.54056759296472823),
('madness', 0.540384426007535),
('stands', 0.5389965007326869),
('trial', 0.5389965007326869),
('greek', 0.5389965007326869),
('hamilton', 0.5389965007326869),
('each', 0.5388212312554177),
('faithful', 0.53773307668591508),
('received', 0.5372768098531604),
('documentaries', 0.53714293208336406),
('jealous', 0.53714293208336406),
('different', 0.53709860682460819),
('describes', 0.53680111016925136),
('shorts', 0.53596159703753288),
('brilliance', 0.53551823635636209),
('mountains', 0.53492317534505118),
('share', 0.53408248593025787),
('dealt', 0.53408248593025787),
('providing', 0.53329847961804933),
('explore', 0.53329847961804933),
('series', 0.5325809226575603),
('fellow', 0.5323318289869543),
('loves', 0.53062825106217038),
('revolution', 0.53062825106217038),
('olivier', 0.53062825106217038),
('roman', 0.53062825106217038),
('century', 0.53002783074992665),
('musical', 0.52966871156747064),
('heroic', 0.52925932545482868),
('approach', 0.52806743020049673),
('ironically', 0.52806743020049673),
('temple', 0.52806743020049673),
('moves', 0.5279372642387119),
('gift', 0.52702030968597136),
('julie', 0.52609309589677911),
('tells', 0.52415107836314001),
('radio', 0.52394671172868779),
('uncle', 0.52354439617376536),
('union', 0.52324814376454787),
('deep', 0.52309571635780505),
('reminds', 0.52157841554225237),
('famous', 0.52118841080153722),
('jazz', 0.52053443789295151),
('dennis', 0.51987545928590861),
('epic', 0.51919387343650736),
('adult', 0.519167695083386),
('shows', 0.51915322220375304),
('performed', 0.5191244265806858),
('demons', 0.5191244265806858),
('discovered', 0.51879379341516751),
('eric', 0.51879379341516751),
('youth', 0.5185626062681431),
('human', 0.51851411224987087),
('tarzan', 0.51813827061227724),
('ourselves', 0.51794309153485463),
('wwii', 0.51758240622887042),
('passion', 0.5162164724008671),
('desire', 0.51607497965213445),
('pays', 0.51581316527702981),
('dirty', 0.51557622652458857),
('fox', 0.51557622652458857),
('sympathetic', 0.51546600332249293),
('symbolism', 0.51546600332249293),
('attitude', 0.51530993621331933),
('appearances', 0.51466440007315639),
('jeremy', 0.51466440007315639),
('fun', 0.51439068993048687),
('south', 0.51420972175023116),
('arrives', 0.51409894911095988),
('present', 0.51341965894303732),
('com', 0.51326167856387173),
('smile', 0.51265880484765169),
('alan', 0.51082562376599072),
('ring', 0.51082562376599072),
('visit', 0.51082562376599072),
('fits', 0.51082562376599072),
('provided', 0.51082562376599072),
('carter', 0.51082562376599072),
('aging', 0.51082562376599072),
('countryside', 0.51082562376599072),
('begins', 0.51015650363396647),
('success', 0.50900578704900468),
('japan', 0.50900578704900468),
('accurate', 0.50895471583017893),
('proud', 0.50800474742434931),
('daily', 0.5075946031845443),
('karloff', 0.50724780241810674),
('atmospheric', 0.50724780241810674),
('recently', 0.50714914903668207),
('fu', 0.50704490092608467),
('horrors', 0.50656122497953315),
('finding', 0.50637127341661037),
('lust', 0.5059356384717989),
('hitchcock', 0.50574947073413001),
('among', 0.50334004951332734),
('viewing', 0.50302139827440906),
('investigation', 0.50262885656181222),
('shining', 0.50262885656181222),
('duo', 0.5020919437972361),
('cameron', 0.5020919437972361),
('finds', 0.50128303100539795),
('contemporary', 0.50077528791248915),
('genuine', 0.50046283673044401),
('frightening', 0.49995595152908684),
('plays', 0.49975983848890226),
('age', 0.49941323171424595),
('position', 0.49899116611898781),
('continues', 0.49863035067217237),
('roles', 0.49839716550752178),
('james', 0.49837216269470402),
('individuals', 0.49824684155913052),
('brought', 0.49783842823917956),
('hilarious', 0.49714551986191058),
('brutal', 0.49681488669639234),
('appropriate', 0.49643688631389105),
('dance', 0.49581998314812048),
('league', 0.49578774640145024),
('helping', 0.49578774640145024),
('answers', 0.49578774640145024),
('stunts', 0.49561620510246196),
('traveling', 0.49532143723002542),
('thoroughly', 0.49414593456733524),
('depicted', 0.49317068852726992),
('combination', 0.49247648509779424),
('honor', 0.49247648509779424),
('differences', 0.49247648509779424),
('fully', 0.49213349075383811),
('tracy', 0.49159426183810306),
('battles', 0.49140753790888908),
('possibility', 0.49112055268665822),
('romance', 0.4901589869574316),
('initially', 0.49002249613622745),
('happy', 0.4898997500608791),
('crime', 0.48977221456815834),
('singing', 0.4893852925281213),
('especially', 0.48901267837860624),
('shakespeare', 0.48754793889664511),
('hugh', 0.48729512635579658),
('detail', 0.48609484250827351),
('julia', 0.48550781578170082),
('san', 0.48550781578170082),
('guide', 0.48550781578170082),
('desperation', 0.48550781578170082),
('companion', 0.48550781578170082),
('strongly', 0.48460242866688824),
('necessary', 0.48302334245403883),
('humanity', 0.48265474679929443),
('drama', 0.48221998493060503),
('nonetheless', 0.48183808689273838),
('intrigue', 0.48183808689273838),
('warming', 0.48183808689273838),
('cuba', 0.48183808689273838),
('planned', 0.47957308026188628),
('pictures', 0.47929937011921681),
('broadcast', 0.47849024312305422),
('nine', 0.47803580094299974),
('settings', 0.47743860773325364),
('history', 0.47732966933780852),
('ordinary', 0.47725880012690741),
('trade', 0.47692407209030935),
('official', 0.47608267532211779),
('primary', 0.47608267532211779),
('episode', 0.47529620261150429),
('role', 0.47520268270188676),
('spirit', 0.47477690799839323),
('grey', 0.47409361449726067),
('ways', 0.47323464982718205),
('cup', 0.47260441094579297),
('piano', 0.47260441094579297),
('familiar', 0.47241617565111949),
('sinister', 0.47198579044972683),
('reveal', 0.47171449364936496),
('max', 0.47150852042515579),
('dated', 0.47121648567094482),
('losing', 0.47000362924573563),
('discovery', 0.47000362924573563),
('vicious', 0.47000362924573563),
('genuinely', 0.46871413841586385),
('hatred', 0.46734051182625186),
('mistaken', 0.46702300110759781),
('dream', 0.46608972992459924),
('challenge', 0.46608972992459924),
('crisis', 0.46575733836428446),
('photographed', 0.46488852857896512),
('critics', 0.46430560813109778),
('bird', 0.46430560813109778),
('machines', 0.46430560813109778),
('born', 0.46411383518967209),
('detective', 0.4636633473511525),
('higher', 0.46328467899699055),
('remains', 0.46262352194811296),
('inevitable', 0.46262352194811296),
('soviet', 0.4618180446592961),
('ryan', 0.46134556650262099),
('african', 0.46112595521371813),
('smaller', 0.46081520319132935),
('techniques', 0.46052488529119184),
('information', 0.46034171833399862),
('deserved', 0.45999798712841444),
('lynch', 0.45953232937844013),
('spielberg', 0.45953232937844013),
('cynical', 0.45953232937844013),
('tour', 0.45953232937844013),
('francisco', 0.45953232937844013),
('struggle', 0.45911782160048453),
('language', 0.45902121257712653),
('visual', 0.45823514408822852),
('warner', 0.45724137763188427),
('social', 0.45720078250735313),
('reality', 0.45719346885019546),
('hidden', 0.45675840249571492),
('breaking', 0.45601738727099561),
('sometimes', 0.45563021171182794),
('modern', 0.45500247579345005),
('surfing', 0.45425527227759638),
('popular', 0.45410691533051023),
('surprised', 0.4534409399850382),
('follows', 0.45245361754408348),
('keeps', 0.45234869400701483),
('john', 0.4520909494482197),
('mixed', 0.45198512374305722),
('defeat', 0.45198512374305722),
('justice', 0.45142724367280018),
('treasure', 0.45083371313801535),
('presents', 0.44973793178615257),
('years', 0.44919197032104968),
('chief', 0.44895022004790319),
('shadows', 0.44802472252696035),
('closely', 0.44701411102103689),
('segments', 0.44701411102103689),
('lose', 0.44658335503763702),
('caine', 0.44628710262841953),
('caught', 0.44610275383999071),
('hamlet', 0.44558510189758965),
('chinese', 0.44507424620321018),
('welcome', 0.44438052435783792),
('birth', 0.44368632092836219),
('represents', 0.44320543609101143),
('puts', 0.44279106572085081),
('visuals', 0.44183275227903923),
('fame', 0.44183275227903923),
('closer', 0.44183275227903923),
('web', 0.44183275227903923),
('criminal', 0.4412745608048752),
('minor', 0.4409224199448939),
('jon', 0.44086703515908027),
('liked', 0.44074991514020723),
('restaurant', 0.44031183943833246),
('de', 0.43983275161237217),
('flaws', 0.43983275161237217),
('searching', 0.4393666597838457),
('rap', 0.43891304217570443),
('light', 0.43884433018199892),
('elizabeth', 0.43872232986464682),
('marry', 0.43861731542506488),
('learned', 0.43825493093115531),
('controversial', 0.43825493093115531),
('oz', 0.43825493093115531),
('slowly', 0.43785660389939979),
('comedic', 0.43721380642274466),
('wayne', 0.43721380642274466),
('thrilling', 0.43721380642274466),
('bridge', 0.43721380642274466),
('married', 0.43658501682196887),
('nazi', 0.4361020775700542),
('murder', 0.4353180712578455),
('physical', 0.4353180712578455),
('johnny', 0.43483971678806865),
('michelle', 0.43445264498141672),
('wallace', 0.43403848055222038),
('comedies', 0.43395706390247063),
('silent', 0.43395706390247063),
('played', 0.43387244114515305),
('international', 0.43363598507486073),
('vision', 0.43286408229627887),
('intelligent', 0.43196704885367099),
('shop', 0.43078291609245434),
('also', 0.43036720209769169),
('levels', 0.4302451371066513),
('miss', 0.43006426712153217),
('movement', 0.4295626596872249),
...]
In [12]:
# words most frequently seen in a review with a "NEGATIVE" label
list(reversed(pos_neg_ratios.most_common()))[0:30]
Out[12]:
[('boll', -4.0778152602708904),
('uwe', -3.9218753018711578),
('seagal', -3.3202501058581921),
('unwatchable', -3.0269848170580955),
('stinker', -2.9876839403711624),
('mst', -2.7753833211707968),
('incoherent', -2.7641396677532537),
('unfunny', -2.5545257844967644),
('waste', -2.4907515123361046),
('blah', -2.4475792789485005),
('horrid', -2.3715779644809971),
('pointless', -2.3451073877136341),
('atrocious', -2.3187369339642556),
('redeeming', -2.2667790015910296),
('prom', -2.2601040980178784),
('drivel', -2.2476029585766928),
('lousy', -2.2118080125207054),
('worst', -2.1930856334332267),
('laughable', -2.172468615469592),
('awful', -2.1385076866397488),
('poorly', -2.1326133844207011),
('wasting', -2.1178155545614512),
('remotely', -2.111046881095167),
('existent', -2.0024805005437076),
('boredom', -1.9241486572738005),
('miserably', -1.9216610938019989),
('sucks', -1.9166645809588516),
('uninspired', -1.9131499212248517),
('lame', -1.9117232884159072),
('insult', -1.9085323769376259)]
In [13]:
from IPython.display import Image
review = "This was a horrible, terrible movie."
Image(filename='sentiment_network.png')
Out[13]:
In [14]:
review = "The movie was excellent"
Image(filename='sentiment_network_pos.png')
Out[14]:
In [15]:
vocab = set(total_counts.keys())
vocab_size = len(vocab)
print(vocab_size)
74074
In [16]:
list(vocab)
Out[16]:
['',
'lupe',
'bleibtreu',
'industrious',
'manges',
'sanfrancisco',
'dreamcast',
'dysfuntional',
'catholique',
'hippolyte',
'genuinely',
'voucher',
'stupednous',
'macroscopic',
'aunt',
'balu',
'string',
'personified',
'corpulent',
'leat',
'chap',
'sistematski',
'dawns',
'generalities',
'restrict',
'winfrey',
'instituting',
'escreve',
'canals',
'rivet',
'rose',
'roxann',
'cultivated',
'hummers',
'proclamation',
'screecher',
'limbo',
'backer',
'nekhron',
'tit',
'blueray',
'registrar',
'tripped',
'dougray',
'karima',
'titillation',
'anika',
'buck',
'hildy',
'supervise',
'unplugged',
'trended',
'skyrockets',
'rearrange',
'william',
'flounced',
'ger',
'numerical',
'castlebeck',
'prabhats',
'firms',
'dearz',
'constrains',
'kimi',
'lelouch',
'cleveland',
'mellon',
'matondkar',
'elektra',
'gobbling',
'mesa',
'detained',
'kaboud',
'ali',
'shrieks',
'ithot',
'borges',
'specify',
'dismaying',
'sealing',
'hugely',
'socioty',
'moolah',
'threaten',
'galley',
'grasp',
'whereby',
'dumbstuck',
'fervor',
'formations',
'suspenders',
'rrhs',
'forefather',
'storymode',
'campos',
'katzelmacher',
'philosophized',
'politburo',
'coopers',
'whoosing',
'dp',
'sevencard',
'johannesburg',
'oliveira',
'passer',
'occupy',
'pooling',
'segment',
'duping',
'delineate',
'reeeeeaally',
'irrelevancy',
'campsite',
'backers',
'emote',
'psychotherapists',
'trucking',
'qi',
'smurfettes',
'woodie',
'rgv',
'glories',
'music',
'destines',
'een',
'crudity',
'mosntres',
'methodists',
'bohemia',
'stuccoed',
'gel',
'imprisoning',
'sartana',
'ut',
'enfant',
'downsides',
'nozzle',
'foop',
'vow',
'underwhelmed',
'mungle',
'amati',
'reforging',
'placido',
'slayed',
'aggh',
'amillenialist',
'surroundings',
'sanest',
'banally',
'warbling',
'leung',
'oppressive',
'carrols',
'mastercard',
'hedrin',
'logically',
'destroyers',
'spades',
'disagree',
'bunce',
'uproar',
'atheism',
'dinaggioi',
'farscape',
'asylums',
'tritely',
'klein',
'commences',
'urgency',
'gretta',
'jordi',
'rickles',
'garca',
'hille',
'duhllywood',
'kundera',
'rubberized',
'murkier',
'lightfoot',
'roladex',
'macmurray',
'hamminess',
'disneyish',
'zyuranger',
'snyapses',
'introduction',
'qualms',
'grooms',
'galaxies',
'showy',
'wallis',
'bereaving',
'launchpad',
'momentary',
'terminal',
'subset',
'trustworthiness',
'nakamura',
'elba',
'ebenezer',
'kookily',
'atmosphere',
'flaunting',
'tapestries',
'plum',
'shaaadaaaap',
'barrister',
'disliked',
'clavier',
'hood',
'lin',
'veen',
'occultist',
'ruffalo',
'filaments',
'gs',
'arent',
'cabell',
'causes',
'eally',
'maiko',
'luske',
'matchpoint',
'oscillators',
'bashers',
'stupidily',
'melania',
'tessier',
'solids',
'sinclair',
'ogles',
'jack',
'baaaaaaaaaaad',
'ladiesman',
'hinders',
'constructive',
'neverending',
'scrabbles',
'tor',
'poem',
'montag',
'persuasive',
'dechifered',
'manjit',
'illudere',
'university',
'graaf',
'recruits',
'nowhere',
'scarecrow',
'frulein',
'flags',
'cliche',
'houses',
'intramural',
'phases',
'hasty',
'tinkly',
'arduno',
'massaccesi',
'admitting',
'waterfalls',
'corben',
'petroleum',
'qc',
'hangs',
'roves',
'acolytes',
'abetted',
'bruno',
'validation',
'heartbreak',
'wickerman',
'philedelphia',
'shrift',
'website',
'kahlua',
'webb',
'evened',
'munroe',
'mormondom',
'powerweight',
'bratwurst',
'heathen',
'desu',
'mccrea',
'pterodactyls',
'staphani',
'hicksville',
'caricature',
'raj',
'povich',
'wo',
'labyrinth',
'fatcheek',
'coyote',
'expressway',
'edina',
'mankin',
'rubrick',
'maids',
'fx',
'pond',
'dive',
'transcendant',
'strobing',
'counterculture',
'arsewit',
'hotbed',
'seediest',
'class',
'guile',
'pollack',
'divide',
'trotting',
'alltime',
'seftel',
'bushi',
'saskatoon',
'favre',
'escapeuntil',
'tortuously',
'immeasurable',
'filmation',
'doig',
'coulson',
'dater',
'taft',
'wk',
'pristine',
'anbuchelvan',
'nicco',
'unbalances',
'filthiness',
'barbarism',
'tableaux',
'walston',
'hillarious',
'knockoff',
'discplines',
'massey',
'mediation',
'autobiographic',
'geek',
'boldt',
'celled',
'manfredini',
'angrily',
'drifting',
'spouts',
'europa',
'faker',
'links',
'idolizes',
'cates',
'porcupine',
'outreach',
'pieczanski',
'seond',
'almoust',
'explosives',
'trannies',
'homepages',
'vlissingen',
'ufern',
'wing',
'girardot',
'sill',
'ailed',
'bolha',
'fartsys',
'givings',
'underplays',
'swarming',
'andrea',
'tonto',
'disciple',
'tila',
'licensure',
'odbray',
'rowland',
'chives',
'gozu',
'ronny',
'hoarding',
'unreachable',
'shizophrenic',
'mature',
'undestand',
'carafotes',
'hanna',
'sixty',
'expeditioners',
'haphazard',
'shops',
'acct',
'heartpounding',
'kailin',
'dime',
'crazes',
'britain',
'karma',
'brutalizing',
'espanol',
'zaniness',
'tampering',
'wiser',
'electrocute',
'nastier',
'journeying',
'highjly',
'adjustment',
'lecturing',
'tlb',
'duke',
'incurs',
'pertwee',
'denzell',
'devastatingly',
'vaude',
'billion',
'levi',
'coop',
'drippy',
'accustomed',
'cardella',
'translated',
'doubtfully',
'debtors',
'grue',
'moviestar',
'mellissa',
'clinkers',
'pudding',
'scrooges',
'setback',
'ecologic',
'rockabilly',
'sonego',
'affronting',
'etvorka',
'department',
'hawas',
'poker',
'hangers',
'chahine',
'dereks',
'unattuned',
'illigal',
'distanced',
'raver',
'wits',
'homerian',
'skank',
'brings',
'gem',
'sketchy',
'huddle',
'blyth',
'fly',
'chequered',
'anno',
'flatness',
'nomad',
'thematics',
'vigilant',
'suprise',
'instructions',
'levine',
'.',
'dorkiest',
'wrestlers',
'patrons',
'aphoristic',
'despondency',
'raubal',
'setpiece',
'suffers',
'psychiatry',
'nearby',
'finding',
'yippee',
'purposeful',
'kings',
'moderator',
'jaid',
'undr',
'oro',
'saturate',
'recognise',
'prowls',
'bypass',
'surpassing',
'characteriology',
'toon',
'matt',
'bests',
'northmen',
'conjure',
'jonesing',
'savages',
'warship',
'revamp',
'groupe',
'powering',
'tamest',
'massacrenot',
'creativity',
'transmissions',
'ornithologist',
'kenovic',
'terminatrix',
'gander',
'deplore',
'indianapolis',
'pavlov',
'fresnay',
'revealed',
'railways',
'marienbad',
'greystone',
'genndy',
'unfocused',
'pranked',
'huit',
'senegalese',
'everingham',
'lustreless',
'bamboo',
'decoff',
'filmometer',
'notebook',
'yegg',
'dressler',
'manpower',
'sods',
'lulu',
'unlicensed',
'caucasian',
'ghotst',
'pavelic',
'photowise',
'ironside',
'lifshitz',
'sith',
'reccomended',
'interleave',
'uncomprehensible',
'hirsh',
'stables',
'enthrall',
'capitulate',
'submit',
'flirtations',
'kiva',
'sara',
'wah',
'phycho',
'carvalho',
'affirm',
'birthmother',
'defensa',
'forton',
'dardis',
'stereos',
'wnk',
'zzzzzzzzzzzz',
'superwonderscope',
'kurta',
'soulless',
'klebb',
'dictatorial',
'dizzying',
'batouch',
'sportswriter',
'arrrghhhhhhs',
'dcors',
'loureno',
'busybody',
'oppikoppi',
'exhooker',
'pronounced',
'conaughey',
'icarus',
'regained',
'manjayegi',
'broadened',
'nashville',
'capitalise',
'narcissus',
'surprisingly',
'decry',
'sturgeon',
'madolyn',
'admittance',
'neweyes',
'spectecular',
'kaabee',
'napping',
'psychiatrist',
'miscegenation',
'diff',
'prescott',
'hypocritical',
'lwr',
'eeks',
'lennier',
'merman',
'incapacitated',
'strip',
'practice',
'untergang',
'falwell',
'adi',
'ahahahahahaaaaa',
'teen',
'heroes',
'reviled',
'outrageous',
'squatter',
'manoj',
'orlander',
'sadahiv',
'aleck',
'honkytonks',
'pulchritudinous',
'harbored',
'banquo',
'dupes',
'wedgie',
'catholiques',
'pedicab',
'compensate',
'popcorncoke',
'sociopathy',
'torme',
'raged',
'barely',
'ib',
'bethany',
'foolishly',
'deducts',
'hennenlotter',
'thence',
'afterwhile',
'negotiated',
'readable',
'hangar',
'nationalists',
'forces',
'orville',
'untangle',
'curves',
'skeptically',
'snakebite',
'logand',
'constructor',
'intensional',
'superfun',
'regime',
'demagogue',
'hafte',
'argeninean',
'strolls',
'languages',
'inbred',
'adjusted',
'bilge',
'karmas',
'chonopolisians',
'piglet',
'sebastiaans',
'preiti',
'bailout',
'kazuhiro',
'jaden',
'revision',
'shave',
'hears',
'dreamquest',
'portaraying',
'mannequin',
'rayed',
'incidentally',
'dodds',
'truax',
'farmani',
'headlining',
'holman',
'landholdings',
'tomboy',
'redemptions',
'krusty',
'girotti',
'decoder',
'amateuristic',
'cellmates',
'prostitutes',
'pupart',
'stubbed',
'fairly',
'sceptical',
'suzannes',
'eisley',
'discontentment',
'bergen',
'overpopulation',
'exeggcute',
'wippleman',
'keiko',
'youngs',
'jeanie',
'duncan',
'coixet',
'misfit',
'kurtz',
'jimi',
'frequents',
'sharpen',
'confide',
'programmes',
'watcheable',
'barem',
'lippmann',
'socio',
'burbling',
'brulier',
'glitchy',
'newberry',
'awareness',
'craze',
'rebuild',
'destroy',
'diet',
'krug',
'len',
'dde',
'umpf',
'rotary',
'sardine',
'desaturate',
'evanescence',
'suggestion',
'bohemian',
'rehman',
'osiric',
'desperateness',
'jerri',
'apolitical',
'understatedly',
'sturla',
'appendage',
'coexisted',
'ostracization',
'meld',
'mayan',
'pillars',
'syncopated',
'makes',
'eccentricity',
'bestbut',
'presidente',
'apparantly',
'hatching',
'babson',
'ossification',
'tolerant',
'dumbo',
'nationalities',
'vocalist',
'arduously',
'inexpensive',
'backtrack',
'ahahahahahhahahahahahahahahahhahahahahahahah',
'estes',
'expressiveness',
'sunroof',
'biographers',
'lisps',
'whiskey',
'romaro',
'expressively',
'kevnjeff',
'schizophrenia',
'swapping',
'marque',
'southron',
'myth',
'smothered',
'unrealness',
'hoosiers',
'mortis',
'roadrunner',
'cereals',
'follywood',
'shake',
'iraqis',
'outrageousness',
'ply',
'righto',
'eduction',
'mitch',
'condescended',
'sleek',
'janelle',
'flutters',
'tk',
'colette',
'profuse',
'grumbled',
'ont',
'tempts',
'foothold',
'ratcatcher',
'brutish',
'nipper',
'sydney',
'simulation',
'bonnevie',
'sedition',
'gulliver',
'filmhistory',
'harnesses',
'impressionists',
'handshakes',
'plopped',
'ornaments',
'lorri',
'peepers',
'balinese',
'heaving',
'tiglon',
'frogballs',
'meyerowitz',
'leverage',
'jacqui',
'tractor',
'selective',
'sphincter',
'warred',
'pinfold',
'rollan',
'survey',
'financially',
'tipoff',
'investment',
'shredding',
'wright',
'edie',
'paesan',
'couric',
'eurosleaze',
'dahlia',
'weathered',
'yasumi',
'feud',
'brusquely',
'castlevania',
'metamoprhis',
'soured',
'naefe',
'recalled',
'weensy',
'nighty',
'patted',
'menopuasal',
'childs',
'toucan',
'remembers',
'springit',
'elfort',
'mailed',
'spud',
'knockouts',
'coherent',
'ivan',
'sitter',
'poseidon',
'influx',
'escargot',
'wealth',
'goosier',
'dereliction',
'wada',
'shys',
'lawlessness',
'waldeman',
'blessedly',
'couplings',
'public',
'ahhhhhh',
'severin',
'shopkeeper',
'notches',
'metaphorical',
'peliky',
'weihenmeyer',
'poolguy',
'ogi',
'number',
'reccomend',
'herek',
'pomerantz',
'supersize',
'cup',
'stat',
'fluid',
'zasu',
'antartic',
'dass',
'cobern',
'transformers',
'anglos',
'bellamy',
'teletype',
'lessen',
'fatherland',
'appeased',
'clambake',
'yetians',
'dweeb',
'funicello',
'cele',
'km',
'embroidering',
'grayce',
'tait',
'neatly',
'itinerant',
'lack',
'sheeks',
'plainsman',
'metamorphis',
'zapar',
'quoters',
'romps',
'mckee',
'ingalls',
'stubly',
'tur',
'eritated',
'goodluck',
'fanfilm',
'matel',
'barabar',
'oy',
'dini',
'innsbruck',
'charton',
'clowes',
'sportsmen',
'predict',
'kusakari',
'lunceford',
'kish',
'fonterbras',
'fruitfully',
'behold',
'splaining',
'ordell',
'definatey',
'lve',
'shapeshifter',
'hairless',
'inroads',
'diabolic',
'sloooow',
'striesand',
'aag',
'siouxie',
'unbelievable',
'standards',
'slugging',
'barn',
'repressive',
'sportsmanship',
'circulating',
'duilio',
'ravensbrck',
'allowed',
'jir',
'tampax',
'wabbits',
'hindrance',
'macau',
'artificially',
'innuendo',
'boardwalk',
'counterweight',
'trainyard',
'alos',
'alejo',
'anglicised',
'unglued',
'surmounting',
'fruits',
'climates',
'blackmailing',
'kittredge',
...]
In [17]:
import numpy as np
layer_0 = np.zeros((1,vocab_size))
layer_0
Out[17]:
array([[ 0., 0., 0., ..., 0., 0., 0.]])
In [18]:
from IPython.display import Image
Image(filename='sentiment_network.png')
Out[18]:
In [19]:
word2index = {}
for i,word in enumerate(vocab):
word2index[word] = i
word2index
Out[19]:
{'': 0,
'lupe': 1,
'bleibtreu': 2,
'industrious': 3,
'manges': 4,
'sanfrancisco': 5,
'dreamcast': 6,
'dysfuntional': 7,
'catholique': 8,
'hippolyte': 9,
'genuinely': 10,
'voucher': 11,
'stupednous': 12,
'macroscopic': 13,
'aunt': 14,
'balu': 15,
'string': 16,
'personified': 17,
'corpulent': 18,
'leat': 19,
'chap': 20,
'sistematski': 21,
'dawns': 22,
'generalities': 23,
'restrict': 24,
'winfrey': 25,
'instituting': 26,
'escreve': 27,
'canals': 28,
'rivet': 29,
'rose': 30,
'roxann': 31,
'cultivated': 32,
'hummers': 33,
'proclamation': 34,
'screecher': 35,
'limbo': 36,
'backer': 37,
'nekhron': 38,
'tit': 39,
'blueray': 40,
'registrar': 41,
'tripped': 42,
'dougray': 43,
'karima': 44,
'titillation': 45,
'anika': 46,
'buck': 47,
'hildy': 48,
'supervise': 49,
'unplugged': 50,
'trended': 51,
'skyrockets': 52,
'rearrange': 53,
'william': 54,
'flounced': 55,
'ger': 56,
'numerical': 57,
'castlebeck': 58,
'prabhats': 59,
'firms': 60,
'dearz': 61,
'constrains': 62,
'kimi': 63,
'lelouch': 64,
'cleveland': 65,
'mellon': 66,
'matondkar': 67,
'elektra': 68,
'gobbling': 69,
'mesa': 70,
'detained': 71,
'kaboud': 72,
'ali': 73,
'shrieks': 74,
'ithot': 75,
'borges': 76,
'specify': 77,
'dismaying': 78,
'sealing': 79,
'hugely': 80,
'socioty': 81,
'moolah': 82,
'threaten': 83,
'galley': 84,
'grasp': 85,
'whereby': 86,
'dumbstuck': 87,
'fervor': 88,
'formations': 89,
'suspenders': 90,
'rrhs': 91,
'forefather': 92,
'storymode': 93,
'campos': 94,
'katzelmacher': 95,
'philosophized': 96,
'politburo': 97,
'coopers': 98,
'whoosing': 99,
'dp': 100,
'sevencard': 101,
'johannesburg': 102,
'oliveira': 103,
'passer': 104,
'occupy': 105,
'pooling': 106,
'segment': 107,
'duping': 108,
'delineate': 109,
'reeeeeaally': 110,
'irrelevancy': 111,
'campsite': 112,
'backers': 113,
'emote': 114,
'psychotherapists': 115,
'trucking': 116,
'qi': 117,
'smurfettes': 118,
'woodie': 119,
'rgv': 120,
'glories': 121,
'music': 122,
'destines': 123,
'een': 124,
'crudity': 125,
'mosntres': 126,
'methodists': 127,
'bohemia': 128,
'stuccoed': 129,
'gel': 130,
'imprisoning': 131,
'sartana': 132,
'ut': 133,
'enfant': 134,
'downsides': 135,
'nozzle': 136,
'foop': 137,
'vow': 138,
'underwhelmed': 139,
'mungle': 140,
'amati': 141,
'reforging': 142,
'placido': 143,
'slayed': 144,
'aggh': 145,
'amillenialist': 146,
'surroundings': 147,
'sanest': 148,
'banally': 149,
'warbling': 150,
'leung': 151,
'oppressive': 152,
'carrols': 153,
'mastercard': 154,
'hedrin': 155,
'logically': 156,
'destroyers': 157,
'spades': 158,
'disagree': 159,
'bunce': 160,
'uproar': 161,
'atheism': 162,
'dinaggioi': 163,
'farscape': 164,
'asylums': 165,
'tritely': 166,
'klein': 167,
'commences': 168,
'urgency': 169,
'gretta': 170,
'jordi': 171,
'rickles': 172,
'garca': 173,
'hille': 174,
'duhllywood': 175,
'kundera': 176,
'rubberized': 177,
'murkier': 178,
'lightfoot': 179,
'roladex': 180,
'macmurray': 181,
'hamminess': 182,
'disneyish': 183,
'zyuranger': 184,
'snyapses': 185,
'introduction': 186,
'qualms': 187,
'grooms': 188,
'galaxies': 189,
'showy': 190,
'wallis': 191,
'bereaving': 192,
'launchpad': 193,
'momentary': 194,
'terminal': 195,
'subset': 196,
'trustworthiness': 197,
'nakamura': 198,
'elba': 199,
'ebenezer': 200,
'kookily': 201,
'atmosphere': 202,
'flaunting': 203,
'tapestries': 204,
'plum': 205,
'shaaadaaaap': 206,
'barrister': 207,
'disliked': 208,
'clavier': 209,
'hood': 210,
'lin': 211,
'veen': 212,
'occultist': 213,
'ruffalo': 214,
'filaments': 215,
'gs': 216,
'arent': 217,
'cabell': 218,
'causes': 219,
'eally': 220,
'maiko': 221,
'luske': 222,
'matchpoint': 223,
'oscillators': 224,
'bashers': 225,
'stupidily': 226,
'melania': 227,
'tessier': 228,
'solids': 229,
'sinclair': 230,
'ogles': 231,
'jack': 232,
'baaaaaaaaaaad': 233,
'ladiesman': 234,
'hinders': 235,
'constructive': 236,
'neverending': 237,
'scrabbles': 238,
'tor': 239,
'poem': 240,
'montag': 241,
'persuasive': 242,
'dechifered': 243,
'manjit': 244,
'illudere': 245,
'university': 246,
'graaf': 247,
'recruits': 248,
'nowhere': 249,
'scarecrow': 250,
'frulein': 251,
'flags': 252,
'cliche': 253,
'houses': 254,
'intramural': 255,
'phases': 256,
'hasty': 257,
'tinkly': 258,
'arduno': 259,
'massaccesi': 260,
'admitting': 261,
'waterfalls': 262,
'corben': 263,
'petroleum': 264,
'qc': 265,
'hangs': 266,
'roves': 267,
'acolytes': 268,
'abetted': 269,
'bruno': 270,
'validation': 271,
'heartbreak': 272,
'wickerman': 273,
'philedelphia': 274,
'shrift': 275,
'website': 276,
'kahlua': 277,
'webb': 278,
'evened': 279,
'munroe': 280,
'mormondom': 281,
'powerweight': 282,
'bratwurst': 283,
'heathen': 284,
'desu': 285,
'mccrea': 286,
'pterodactyls': 287,
'staphani': 288,
'hicksville': 289,
'caricature': 290,
'raj': 291,
'povich': 292,
'wo': 293,
'labyrinth': 294,
'fatcheek': 295,
'coyote': 296,
'expressway': 297,
'edina': 298,
'mankin': 299,
'rubrick': 300,
'maids': 301,
'fx': 302,
'pond': 303,
'dive': 304,
'transcendant': 305,
'strobing': 306,
'counterculture': 307,
'arsewit': 308,
'hotbed': 309,
'seediest': 310,
'class': 311,
'guile': 312,
'pollack': 313,
'divide': 314,
'trotting': 315,
'alltime': 316,
'seftel': 317,
'bushi': 318,
'saskatoon': 319,
'favre': 320,
'escapeuntil': 321,
'tortuously': 322,
'immeasurable': 323,
'filmation': 324,
'doig': 325,
'coulson': 326,
'dater': 327,
'taft': 328,
'wk': 329,
'pristine': 330,
'anbuchelvan': 331,
'nicco': 332,
'unbalances': 333,
'filthiness': 334,
'barbarism': 335,
'tableaux': 336,
'walston': 337,
'hillarious': 338,
'knockoff': 339,
'discplines': 340,
'massey': 341,
'mediation': 342,
'autobiographic': 343,
'geek': 344,
'boldt': 345,
'celled': 346,
'manfredini': 347,
'angrily': 348,
'drifting': 349,
'spouts': 350,
'europa': 351,
'faker': 352,
'links': 353,
'idolizes': 354,
'cates': 355,
'porcupine': 356,
'outreach': 357,
'pieczanski': 358,
'seond': 359,
'almoust': 360,
'explosives': 361,
'trannies': 362,
'homepages': 363,
'vlissingen': 364,
'ufern': 365,
'wing': 366,
'girardot': 367,
'sill': 368,
'ailed': 369,
'bolha': 370,
'fartsys': 371,
'givings': 372,
'underplays': 373,
'swarming': 374,
'andrea': 375,
'tonto': 376,
'disciple': 377,
'tila': 378,
'licensure': 379,
'odbray': 380,
'rowland': 381,
'chives': 382,
'gozu': 383,
'ronny': 384,
'hoarding': 385,
'unreachable': 386,
'shizophrenic': 387,
'mature': 388,
'undestand': 389,
'carafotes': 390,
'hanna': 391,
'sixty': 392,
'expeditioners': 393,
'haphazard': 394,
'shops': 395,
'acct': 396,
'heartpounding': 397,
'kailin': 398,
'dime': 399,
'crazes': 400,
'britain': 401,
'karma': 402,
'brutalizing': 403,
'espanol': 404,
'zaniness': 405,
'tampering': 406,
'wiser': 407,
'electrocute': 408,
'nastier': 409,
'journeying': 410,
'highjly': 411,
'adjustment': 412,
'lecturing': 413,
'tlb': 414,
'duke': 415,
'incurs': 416,
'pertwee': 417,
'denzell': 418,
'devastatingly': 419,
'vaude': 420,
'billion': 421,
'levi': 422,
'coop': 423,
'drippy': 424,
'accustomed': 425,
'cardella': 426,
'translated': 427,
'doubtfully': 428,
'debtors': 429,
'grue': 430,
'moviestar': 431,
'mellissa': 432,
'clinkers': 433,
'pudding': 434,
'scrooges': 435,
'setback': 436,
'ecologic': 437,
'rockabilly': 438,
'sonego': 439,
'affronting': 440,
'etvorka': 441,
'department': 442,
'hawas': 443,
'poker': 444,
'hangers': 445,
'chahine': 446,
'dereks': 447,
'unattuned': 448,
'illigal': 449,
'distanced': 450,
'raver': 451,
'wits': 452,
'homerian': 453,
'skank': 454,
'brings': 455,
'gem': 456,
'sketchy': 457,
'huddle': 458,
'blyth': 459,
'fly': 460,
'chequered': 461,
'anno': 462,
'flatness': 463,
'nomad': 464,
'thematics': 465,
'vigilant': 466,
'suprise': 467,
'instructions': 468,
'levine': 469,
'.': 470,
'dorkiest': 471,
'wrestlers': 472,
'patrons': 473,
'aphoristic': 474,
'despondency': 475,
'raubal': 476,
'setpiece': 477,
'suffers': 478,
'psychiatry': 479,
'nearby': 480,
'finding': 481,
'yippee': 482,
'purposeful': 483,
'kings': 484,
'moderator': 485,
'jaid': 486,
'undr': 487,
'oro': 488,
'saturate': 489,
'recognise': 490,
'prowls': 491,
'bypass': 492,
'surpassing': 493,
'characteriology': 494,
'toon': 495,
'matt': 496,
'bests': 497,
'northmen': 498,
'conjure': 499,
'jonesing': 500,
'savages': 501,
'warship': 502,
'revamp': 503,
'groupe': 504,
'powering': 505,
'tamest': 506,
'massacrenot': 507,
'creativity': 508,
'transmissions': 509,
'ornithologist': 510,
'kenovic': 511,
'terminatrix': 512,
'gander': 513,
'deplore': 514,
'indianapolis': 515,
'pavlov': 516,
'fresnay': 517,
'revealed': 518,
'railways': 519,
'marienbad': 520,
'greystone': 521,
'genndy': 522,
'unfocused': 523,
'pranked': 524,
'huit': 525,
'senegalese': 526,
'everingham': 527,
'lustreless': 528,
'bamboo': 529,
'decoff': 530,
'filmometer': 531,
'notebook': 532,
'yegg': 533,
'dressler': 534,
'manpower': 535,
'sods': 536,
'lulu': 537,
'unlicensed': 538,
'caucasian': 539,
'ghotst': 540,
'pavelic': 541,
'photowise': 542,
'ironside': 543,
'lifshitz': 544,
'sith': 545,
'reccomended': 546,
'interleave': 547,
'uncomprehensible': 548,
'hirsh': 549,
'stables': 550,
'enthrall': 551,
'capitulate': 552,
'submit': 553,
'flirtations': 554,
'kiva': 555,
'sara': 556,
'wah': 557,
'phycho': 558,
'carvalho': 559,
'affirm': 560,
'birthmother': 561,
'defensa': 562,
'forton': 563,
'dardis': 564,
'stereos': 565,
'wnk': 566,
'zzzzzzzzzzzz': 567,
'superwonderscope': 568,
'kurta': 569,
'soulless': 570,
'klebb': 571,
'dictatorial': 572,
'dizzying': 573,
'batouch': 574,
'sportswriter': 575,
'arrrghhhhhhs': 576,
'dcors': 577,
'loureno': 578,
'busybody': 579,
'oppikoppi': 580,
'exhooker': 581,
'pronounced': 582,
'conaughey': 583,
'icarus': 584,
'regained': 585,
'manjayegi': 586,
'broadened': 587,
'nashville': 588,
'capitalise': 589,
'narcissus': 590,
'surprisingly': 591,
'decry': 592,
'sturgeon': 593,
'madolyn': 594,
'admittance': 595,
'neweyes': 596,
'spectecular': 597,
'kaabee': 598,
'napping': 599,
'psychiatrist': 600,
'miscegenation': 601,
'diff': 602,
'prescott': 603,
'hypocritical': 604,
'lwr': 605,
'eeks': 606,
'lennier': 607,
'merman': 608,
'incapacitated': 609,
'strip': 610,
'practice': 611,
'untergang': 612,
'falwell': 613,
'adi': 614,
'ahahahahahaaaaa': 615,
'teen': 616,
'heroes': 617,
'reviled': 618,
'outrageous': 619,
'squatter': 620,
'manoj': 621,
'orlander': 622,
'sadahiv': 623,
'aleck': 624,
'honkytonks': 625,
'pulchritudinous': 626,
'harbored': 627,
'banquo': 628,
'dupes': 629,
'wedgie': 630,
'catholiques': 631,
'pedicab': 632,
'compensate': 633,
'popcorncoke': 634,
'sociopathy': 635,
'torme': 636,
'raged': 637,
'barely': 638,
'ib': 639,
'bethany': 640,
'foolishly': 641,
'deducts': 642,
'hennenlotter': 643,
'thence': 644,
'afterwhile': 645,
'negotiated': 646,
'readable': 647,
'hangar': 648,
'nationalists': 649,
'forces': 650,
'orville': 651,
'untangle': 652,
'curves': 653,
'skeptically': 654,
'snakebite': 655,
'logand': 656,
'constructor': 657,
'intensional': 658,
'superfun': 659,
'regime': 660,
'demagogue': 661,
'hafte': 662,
'argeninean': 663,
'strolls': 664,
'languages': 665,
'inbred': 666,
'adjusted': 667,
'bilge': 668,
'karmas': 669,
'chonopolisians': 670,
'piglet': 671,
'sebastiaans': 672,
'preiti': 673,
'bailout': 674,
'kazuhiro': 675,
'jaden': 676,
'revision': 677,
'shave': 678,
'hears': 679,
'dreamquest': 680,
'portaraying': 681,
'mannequin': 682,
'rayed': 683,
'incidentally': 684,
'dodds': 685,
'truax': 686,
'farmani': 687,
'headlining': 688,
'holman': 689,
'landholdings': 690,
'tomboy': 691,
'redemptions': 692,
'krusty': 693,
'girotti': 694,
'decoder': 695,
'amateuristic': 696,
'cellmates': 697,
'prostitutes': 698,
'pupart': 699,
'stubbed': 700,
'fairly': 701,
'sceptical': 702,
'suzannes': 703,
'eisley': 704,
'discontentment': 705,
'bergen': 706,
'overpopulation': 707,
'exeggcute': 708,
'wippleman': 709,
'keiko': 710,
'youngs': 711,
'jeanie': 712,
'duncan': 713,
'coixet': 714,
'misfit': 715,
'kurtz': 716,
'jimi': 717,
'frequents': 718,
'sharpen': 719,
'confide': 720,
'programmes': 721,
'watcheable': 722,
'barem': 723,
'lippmann': 724,
'socio': 725,
'burbling': 726,
'brulier': 727,
'glitchy': 728,
'newberry': 729,
'awareness': 730,
'craze': 731,
'rebuild': 732,
'destroy': 733,
'diet': 734,
'krug': 735,
'len': 736,
'dde': 737,
'umpf': 738,
'rotary': 739,
'sardine': 740,
'desaturate': 741,
'evanescence': 742,
'suggestion': 743,
'bohemian': 744,
'rehman': 745,
'osiric': 746,
'desperateness': 747,
'jerri': 748,
'apolitical': 749,
'understatedly': 750,
'sturla': 751,
'appendage': 752,
'coexisted': 753,
'ostracization': 754,
'meld': 755,
'mayan': 756,
'pillars': 757,
'syncopated': 758,
'makes': 759,
'eccentricity': 760,
'bestbut': 761,
'presidente': 762,
'apparantly': 763,
'hatching': 764,
'babson': 765,
'ossification': 766,
'tolerant': 767,
'dumbo': 768,
'nationalities': 769,
'vocalist': 770,
'arduously': 771,
'inexpensive': 772,
'backtrack': 773,
'ahahahahahhahahahahahahahahahhahahahahahahah': 774,
'estes': 775,
'expressiveness': 776,
'sunroof': 777,
'biographers': 778,
'lisps': 779,
'whiskey': 780,
'romaro': 781,
'expressively': 782,
'kevnjeff': 783,
'schizophrenia': 784,
'swapping': 785,
'marque': 786,
'southron': 787,
'myth': 788,
'smothered': 789,
'unrealness': 790,
'hoosiers': 791,
'mortis': 792,
'roadrunner': 793,
'cereals': 794,
'follywood': 795,
'shake': 796,
'iraqis': 797,
'outrageousness': 798,
'ply': 799,
'righto': 800,
'eduction': 801,
'mitch': 802,
'condescended': 803,
'sleek': 804,
'janelle': 805,
'flutters': 806,
'tk': 807,
'colette': 808,
'profuse': 809,
'grumbled': 810,
'ont': 811,
'tempts': 812,
'foothold': 813,
'ratcatcher': 814,
'brutish': 815,
'nipper': 816,
'sydney': 817,
'simulation': 818,
'bonnevie': 819,
'sedition': 820,
'gulliver': 821,
'filmhistory': 822,
'harnesses': 823,
'impressionists': 824,
'handshakes': 825,
'plopped': 826,
'ornaments': 827,
'lorri': 828,
'peepers': 829,
'balinese': 830,
'heaving': 831,
'tiglon': 832,
'frogballs': 833,
'meyerowitz': 834,
'leverage': 835,
'jacqui': 836,
'tractor': 837,
'selective': 838,
'sphincter': 839,
'warred': 840,
'pinfold': 841,
'rollan': 842,
'survey': 843,
'financially': 844,
'tipoff': 845,
'investment': 846,
'shredding': 847,
'wright': 848,
'edie': 849,
'paesan': 850,
'couric': 851,
'eurosleaze': 852,
'dahlia': 853,
'weathered': 854,
'yasumi': 855,
'feud': 856,
'brusquely': 857,
'castlevania': 858,
'metamoprhis': 859,
'soured': 860,
'naefe': 861,
'recalled': 862,
'weensy': 863,
'nighty': 864,
'patted': 865,
'menopuasal': 866,
'childs': 867,
'toucan': 868,
'remembers': 869,
'springit': 870,
'elfort': 871,
'mailed': 872,
'spud': 873,
'knockouts': 874,
'coherent': 875,
'ivan': 876,
'sitter': 877,
'poseidon': 878,
'influx': 879,
'escargot': 880,
'wealth': 881,
'goosier': 882,
'dereliction': 883,
'wada': 884,
'shys': 885,
'lawlessness': 886,
'waldeman': 887,
'blessedly': 888,
'couplings': 889,
'public': 890,
'ahhhhhh': 891,
'severin': 892,
'shopkeeper': 893,
'notches': 894,
'metaphorical': 895,
'peliky': 896,
'weihenmeyer': 897,
'poolguy': 898,
'ogi': 899,
'number': 900,
'reccomend': 901,
'herek': 902,
'pomerantz': 903,
'supersize': 904,
'cup': 905,
'stat': 906,
'fluid': 907,
'zasu': 908,
'antartic': 909,
'dass': 910,
'cobern': 911,
'transformers': 912,
'anglos': 913,
'bellamy': 914,
'teletype': 915,
'lessen': 916,
'fatherland': 917,
'appeased': 918,
'clambake': 919,
'yetians': 920,
'dweeb': 921,
'funicello': 922,
'cele': 923,
'km': 924,
'embroidering': 925,
'grayce': 926,
'tait': 927,
'neatly': 928,
'itinerant': 929,
'lack': 930,
'sheeks': 931,
'plainsman': 932,
'metamorphis': 933,
'zapar': 934,
'quoters': 935,
'romps': 936,
'mckee': 937,
'ingalls': 938,
'stubly': 939,
'tur': 940,
'eritated': 941,
'goodluck': 942,
'fanfilm': 943,
'matel': 944,
'barabar': 945,
'oy': 946,
'dini': 947,
'innsbruck': 948,
'charton': 949,
'clowes': 950,
'sportsmen': 951,
'predict': 952,
'kusakari': 953,
'lunceford': 954,
'kish': 955,
'fonterbras': 956,
'fruitfully': 957,
'behold': 958,
'splaining': 959,
'ordell': 960,
'definatey': 961,
'lve': 962,
'shapeshifter': 963,
'hairless': 964,
'inroads': 965,
'diabolic': 966,
'sloooow': 967,
'striesand': 968,
'aag': 969,
'siouxie': 970,
'unbelievable': 971,
'standards': 972,
'slugging': 973,
'barn': 974,
'repressive': 975,
'sportsmanship': 976,
'circulating': 977,
'duilio': 978,
'ravensbrck': 979,
'allowed': 980,
'jir': 981,
'tampax': 982,
'wabbits': 983,
'hindrance': 984,
'macau': 985,
'artificially': 986,
'innuendo': 987,
'boardwalk': 988,
'counterweight': 989,
'trainyard': 990,
'alos': 991,
'alejo': 992,
'anglicised': 993,
'unglued': 994,
'surmounting': 995,
'fruits': 996,
'climates': 997,
'blackmailing': 998,
'kittredge': 999,
...}
In [20]:
def update_input_layer(review):
global layer_0
# clear out previous state, reset the layer to be all 0s
layer_0 *= 0
for word in review.split(" "):
layer_0[0][word2index[word]] += 1
update_input_layer(reviews[0])
In [21]:
layer_0
Out[21]:
array([[ 18., 0., 0., ..., 0., 0., 0.]])
In [22]:
def get_target_for_label(label):
if(label == 'POSITIVE'):
return 1
else:
return 0
In [23]:
labels[0]
Out[23]:
'POSITIVE'
In [24]:
get_target_for_label(labels[0])
Out[24]:
1
In [25]:
labels[1]
Out[25]:
'NEGATIVE'
In [26]:
get_target_for_label(labels[1])
Out[26]:
0
In [27]:
import time, sys
In [2]:
class SentimentNetwork:
def __init__(self, reviews, labels, hidden_nodes=10, learning_rate=0.1):
np.random.seed(1)
self.pre_process_data(reviews, labels)
self.init_network(len(self.review_vocab), hidden_nodes, 1, learning_rate)
def pre_process_data(self, reviews, labels):
review_vocab = []
for review in reviews:
for word in review.split(' '):
review_vocab.append(word)
self.review_vocab = review_vocab
label_vocab = []
for label in labels:
label_vocab.append(label)
self.label_vocab = label_vocab
self.review_vocab_size = len(review_vocab)
self.label_vocab_size = len(label_vocab)
self.word2index = {}
for i, word in enumerate(vocab):
self.word2index[word] = i
self.label2index = {}
for i, label in enumerate(vocab):
self.label2index[label] = i
def init_network(self, input_nodes, hidden_nodes, output_nodes, learning_rate):
self.input_nodes = input_nodes
self.hidden_nodes = hidden_nodes
self.output_nodes = output_nodes
self.weights_input_to_hidden = np.zeros((self.input_nodes, self.hidden_nodes))
self.weights_hidden_to_output = np.random.normal(0.0, self.output_nodes**-0.5,
(self.hidden_nodes, self.output_nodes))
self.learning_rate = learning_rate
self.layer_0 = np.zeros((1,input_nodes))
def update_input_layer(self,review):
# clear out previous state, reset the layer to be all 0s
self.layer_0 *= 0
for word in review.split(" "):
if(word in self.word2index.keys()):
self.layer_0[0][self.word2index[word]] += 1
def get_target_for_label(self,label):
if(label == 'POSITIVE'):
return 1
else:
return 0
def sigmoid(self,x):
return 1 / (1 + np.exp(-x))
def sigmoid_output_2_derivative(self,output):
return output * (1 - output)
def train(self, training_reviews, training_labels):
assert(len(training_reviews) == len(training_labels))
correct_so_far = 0
start = time.time()
for i in range(len(training_reviews)):
review = training_reviews[i]
label = training_labels[i]
### Foward pass ###
# Input layer
self.update_input_layer(review)
# Hidden layer
layer_1 = self.layer_0.dot(self.weights_input_to_hidden)
# Output layer
layer_2 = self.sigmoid(layer_1.dot(self.weights_hidden_to_output))
### Backward pass ###
# Output error
layer_2_error = self.get_target_for_label(label) - layer_2
layer_2_delta = layer_2_error * self.sigmoid_output_2_derivative(layer_2)
# Hidden error
layer_1_error = layer_2_delta.dot(self.weights_hidden_to_output.T)
layer_1_delta = layer_1_error # hidden layer gradients - no nonlinearity so it's the same as the error (?)
### Update weights ###
self.weights_hidden_to_output += self.learning_rate * layer_1.T.dot(layer_2_delta)
self.weights_input_to_hidden += self.learning_rate * self.layer_0.T.dot(layer_1_delta)
if(np.abs(layer_2_error) < 0.5):
correct_so_far += 1
reviews_per_second = i / float(time.time() - start)
sys.stdout.write("\rProgress:" + str(100 * i/float(len(training_reviews)))[:4] \
+ "% Speed(reviews/sec):" + str(reviews_per_second)[0:5] \
+ " #Correct:" + str(correct_so_far) + " #Trained:" + str(i+1) \
+ " Training Accuracy:" + str(correct_so_far * 100 / float(i+1))[:4] + "%")
if(i % 2500 == 0):
print("")
def test(self, testing_reviews, testing_labels):
correct = 0
start = time.time()
for i in range(len(testing_reviews)):
pred = self.run(testing_reviews[i])
if pred == testing_labels[i]:
correct += 1
reviews_per_second = i / float(time.time() - start)
sys.stdout.write("\rProgress:" + str(100 * i/float(len(testing_reviews)))[:4] \
+ "% Speed(reviews/sec):" + str(reviews_per_second)[0:5] \
+ "% #Correct:" + str(correct) + " #Tested:" + str(i+1) \
+ " Testing Accuracy:" + str(correct * 100 / float(i+1))[:4] + "%")
def run(self, review):
# Input layer
self.update_input_layer(review.lower())
# Hidden layer
layer_1 = self.layer_0.dot(self.weights_input_to_hidden)
# Output layer
layer_2 = self.sigmoid(layer_1.dot(self.weights_hidden_to_output))
if(layer_2[0] > 0.5):
return "POSITIVE"
else:
return "NEGATIVE"
In [3]:
mlp = SentimentNetwork(reviews[:-1000],labels[:-1000], learning_rate=0.1)
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-3-db0c07a56840> in <module>()
----> 1 mlp = SentimentNetwork(reviews[:-1000],labels[:-1000], learning_rate=0.1)
<ipython-input-2-e556f707eeca> in __init__(self, reviews, labels, hidden_nodes, learning_rate)
2 def __init__(self, reviews, labels, hidden_nodes=10, learning_rate=0.1):
3
----> 4 np.random.seed(1)
5
6 self.pre_process_data(reviews, labels)
NameError: name 'np' is not defined
In [30]:
mlp.test(reviews[-1000:],labels[-1000:])
Progress:99.9% Speed(reviews/sec):33.96% #Correct:500 #Tested:1000 Testing Accuracy:50.0%
In [ ]:
mlp.train(reviews[:-1000],labels[:-1000])
Progress:0.0% Speed(reviews/sec):0.0 #Correct:0 #Trained:1 Training Accuracy:0.0%
In [ ]:
Content source: danresende/deep-learning
Similar notebooks: