by Andrew Trask
In [15]:
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 [16]:
len(reviews)
Out[16]:
25000
In [14]:
reviews[0]
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-14-b83a86b02354> in <module>()
----> 1 reviews[0]
NameError: name 'reviews' is not defined
In [6]:
labels[0]
Out[6]:
'POSITIVE'
In [7]:
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 [9]:
from collections import Counter
import numpy as np
In [10]:
positive_counts = Counter()
negative_counts = Counter()
total_counts = Counter()
In [11]:
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 [12]:
positive_counts.most_common()
Out[12]:
[('', 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),
('war', 1310),
('whole', 1310),
('d', 1307),
('away', 1306),
('found', 1306),
('screen', 1305),
('nothing', 1300),
('year', 1297),
('once', 1296),
('hard', 1294),
('together', 1280),
('am', 1277),
('set', 1277),
('having', 1266),
('making', 1265),
('place', 1263),
('comes', 1260),
('might', 1260),
('sure', 1253),
('american', 1248),
('play', 1245),
('kind', 1244),
('takes', 1242),
('perfect', 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),
('men', 1087),
('loved', 1087),
('night', 1082),
('anything', 1075),
('guy', 1071),
('believe', 1071),
('top', 1063),
('amazing', 1058),
('hollywood', 1056),
('looking', 1053),
('main', 1044),
('definitely', 1043),
('gives', 1031),
('home', 1029),
('seem', 1028),
('episode', 1023),
('sense', 1020),
('audience', 1020),
('truly', 1017),
('special', 1011),
('fan', 1009),
('second', 1009),
('short', 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),
('let', 954),
('script', 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),
('children', 833),
('picture', 833),
('face', 831),
('friend', 831),
('keep', 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),
('rest', 781),
('based', 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),
('final', 739),
('beginning', 739),
('town', 738),
('art', 734),
('game', 732),
('humor', 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),
('piece', 653),
('fantastic', 653),
('david', 651),
('turn', 648),
('murder', 646),
('parts', 645),
('brother', 644),
('head', 643),
('absolutely', 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),
('example', 627),
('including', 627),
('known', 625),
('musical', 625),
('chance', 621),
('score', 620),
('feeling', 619),
('already', 619),
('hit', 619),
('voice', 615),
('moment', 612),
('living', 612),
('low', 610),
('supporting', 610),
('ago', 609),
('themselves', 608),
('hilarious', 605),
('reality', 605),
('jack', 604),
('told', 603),
('hand', 601),
('moving', 600),
('dialogue', 600),
('quality', 600),
('song', 599),
('happy', 599),
('paul', 598),
('matter', 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),
('enjoyable', 573),
('view', 573),
('husband', 572),
('romantic', 572),
('number', 572),
('daughter', 572),
('documentary', 571),
('self', 570),
('modern', 569),
('robert', 569),
('took', 569),
('superb', 569),
('mean', 566),
('shown', 563),
('coming', 561),
('important', 560),
('king', 559),
('leave', 559),
('change', 558),
('wanted', 555),
('somewhat', 555),
('tells', 554),
('run', 552),
('events', 552),
('country', 552),
('career', 552),
('heard', 550),
('season', 550),
('girls', 549),
('greatest', 549),
('etc', 547),
('care', 546),
('starts', 545),
('english', 542),
('killer', 541),
('animation', 540),
('guys', 540),
('totally', 540),
('tale', 540),
('usual', 539),
('opinion', 535),
('miss', 535),
('violence', 531),
('easy', 531),
('songs', 530),
('british', 528),
('says', 526),
('realistic', 525),
('writing', 524),
('act', 522),
('writer', 522),
('comic', 521),
('thriller', 519),
('television', 517),
('power', 516),
('ones', 515),
('kid', 514),
('novel', 513),
('york', 513),
('problem', 512),
('alone', 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),
('surprised', 491),
('similar', 491),
('taking', 491),
('car', 491),
('george', 490),
('perfectly', 490),
('across', 489),
('sequence', 489),
('eye', 489),
('team', 489),
('serious', 488),
('powerful', 488),
('room', 488),
('due', 488),
('among', 488),
('order', 487),
('b', 487),
('cannot', 487),
('strange', 487),
('beauty', 486),
('famous', 485),
('tries', 484),
('myself', 484),
('happened', 484),
('herself', 484),
('class', 483),
('four', 482),
('cool', 481),
('release', 479),
('anyway', 479),
('theme', 479),
('opening', 478),
('entertainment', 477),
('unique', 475),
('ends', 475),
('slow', 475),
('exactly', 475),
('red', 474),
('o', 474),
('level', 474),
('easily', 474),
('interest', 472),
('happen', 471),
('crime', 470),
('viewing', 468),
('memorable', 467),
('sets', 467),
('group', 466),
('stop', 466),
('dance', 463),
('message', 463),
('sister', 463),
('working', 463),
('problems', 463),
('knew', 462),
('mystery', 461),
('nature', 461),
('bring', 460),
('believable', 459),
('thinking', 459),
('brought', 459),
('mostly', 458),
('couldn', 457),
('disney', 457),
('society', 456),
('within', 455),
('lady', 455),
('blood', 454),
('upon', 453),
('viewers', 453),
('parents', 453),
('meets', 452),
('form', 452),
('soundtrack', 452),
('usually', 452),
('tom', 452),
('peter', 452),
('local', 450),
('certain', 448),
('follow', 448),
('whether', 447),
('possible', 446),
('emotional', 445),
('killed', 444),
('de', 444),
('above', 444),
('middle', 443),
('god', 443),
('happens', 442),
('flick', 442),
('needs', 442),
('masterpiece', 441),
('major', 440),
('period', 440),
('haven', 439),
('named', 439),
('th', 438),
('particular', 438),
('earth', 437),
('feature', 437),
('stand', 436),
('words', 435),
('typical', 435),
('obviously', 433),
('elements', 433),
('romance', 431),
('jane', 430),
('yourself', 427),
('showing', 427),
('fantasy', 426),
('brings', 426),
('america', 423),
('guess', 423),
('huge', 422),
('unfortunately', 422),
('indeed', 421),
('running', 421),
('talent', 420),
('stage', 419),
('started', 418),
('sweet', 417),
('leads', 417),
('japanese', 417),
('poor', 416),
('deal', 416),
('personal', 413),
('incredible', 413),
('fast', 412),
('became', 410),
('deep', 410),
('hours', 409),
('nearly', 408),
('dream', 408),
('giving', 408),
('turned', 407),
('clearly', 407),
('near', 406),
('obvious', 406),
('cut', 405),
('surprise', 405),
('body', 404),
('era', 404),
('female', 403),
('hour', 403),
('five', 403),
('note', 399),
('learn', 398),
('truth', 398),
('match', 397),
('feels', 397),
('except', 397),
('tony', 397),
('filmed', 394),
('complete', 394),
('clear', 394),
('older', 393),
('street', 393),
('lots', 393),
('eventually', 393),
('keeps', 393),
('buy', 392),
('stewart', 391),
('william', 391),
('joe', 390),
('meet', 390),
('fall', 390),
('shots', 389),
('talking', 389),
('difficult', 389),
('unlike', 389),
('rating', 389),
('means', 388),
('dramatic', 388),
('appears', 386),
('subject', 386),
('wonder', 386),
('present', 386),
('situation', 386),
('comments', 385),
('sequences', 383),
('general', 383),
('lee', 383),
('earlier', 382),
('points', 382),
('check', 379),
('gone', 379),
('ten', 378),
('suspense', 378),
('recommended', 378),
('business', 377),
('third', 377),
('talk', 375),
('leaves', 375),
('beyond', 375),
('portrayal', 374),
('beautifully', 373),
('single', 372),
('bill', 372),
('word', 371),
('plenty', 371),
('falls', 370),
('whom', 370),
('figure', 369),
('battle', 369),
('scary', 369),
('non', 369),
('return', 368),
('using', 368),
('doubt', 367),
('add', 367),
('hear', 366),
('solid', 366),
('success', 366),
('touching', 365),
('political', 365),
('oh', 365),
('jokes', 365),
('awesome', 364),
('hell', 364),
('boys', 364),
('dog', 362),
('recently', 362),
('sexual', 362),
('please', 361),
('wouldn', 361),
('features', 361),
('straight', 361),
('lack', 360),
('forget', 360),
('setting', 360),
('mark', 359),
('married', 359),
('social', 357),
('adventure', 356),
('interested', 356),
('brothers', 355),
('sees', 355),
('actual', 355),
('terrific', 355),
('move', 354),
('call', 354),
('various', 353),
('dr', 353),
('theater', 353),
('animated', 352),
('western', 351),
('space', 350),
('baby', 350),
('leading', 348),
('disappointed', 348),
('portrayed', 346),
('aren', 346),
('screenplay', 345),
('smith', 345),
('hate', 344),
('towards', 344),
('noir', 343),
('outstanding', 342),
('decent', 342),
('kelly', 342),
('directors', 341),
('journey', 341),
('none', 340),
('effective', 340),
('looked', 340),
('caught', 339),
('cold', 339),
('storyline', 339),
('fi', 339),
('sci', 339),
('mary', 339),
('rich', 338),
('charming', 338),
('harry', 337),
('popular', 337),
('manages', 337),
('rare', 337),
('spirit', 336),
('open', 335),
('appreciate', 335),
('basically', 334),
('moves', 334),
('acted', 334),
('deserves', 333),
('subtle', 333),
('mention', 333),
('inside', 333),
('pace', 333),
('century', 333),
('boring', 333),
('familiar', 332),
('background', 332),
('ben', 331),
('creepy', 330),
('supposed', 330),
('secret', 329),
('jim', 328),
('die', 328),
('question', 327),
('effect', 327),
('natural', 327),
('rate', 326),
('language', 326),
('impressive', 326),
('intelligent', 325),
('saying', 325),
('material', 324),
('realize', 324),
('telling', 324),
('scott', 324),
('singing', 323),
('dancing', 322),
('adult', 321),
('imagine', 321),
('visual', 321),
('kept', 320),
('office', 320),
('uses', 319),
('pure', 318),
('wait', 318),
('stunning', 318),
('copy', 317),
('review', 317),
('previous', 317),
('seriously', 317),
('somehow', 316),
('created', 316),
('magic', 316),
('create', 316),
('hot', 316),
('reading', 316),
('crazy', 315),
('air', 315),
('frank', 315),
('stay', 315),
('escape', 315),
('attempt', 315),
('hands', 314),
('filled', 313),
('surprisingly', 312),
('expected', 312),
('average', 312),
('complex', 311),
('studio', 310),
('successful', 310),
('quickly', 310),
('male', 309),
('plus', 309),
('co', 307),
('minute', 306),
('images', 306),
('casting', 306),
('exciting', 306),
('following', 306),
('members', 305),
('german', 305),
('e', 305),
('reasons', 305),
('follows', 305),
('themes', 305),
('touch', 304),
('genius', 304),
('free', 304),
('edge', 304),
('cute', 304),
('outside', 303),
('ok', 302),
('admit', 302),
('younger', 302),
('reviews', 302),
('odd', 301),
('fighting', 301),
('master', 301),
('break', 300),
('thanks', 300),
('recent', 300),
('comment', 300),
('apart', 299),
('lovely', 298),
('begin', 298),
('emotions', 298),
('doctor', 297),
('italian', 297),
('party', 297),
('la', 296),
('missed', 296),
...]
In [20]:
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 [21]:
# words most frequently seen in a review with a "POSITIVE" label
pos_neg_ratios.most_common()
Out[21]:
[('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),
('hartley', 1.6094379124341003),
('sullivan', 1.6094379124341003),
('extraordinary', 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),
('mann', 1.4894785973551214),
('pleasantly', 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),
('captivating', 1.3862943611198906),
('fisher', 1.3862943611198906),
('davies', 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),
('panic', 1.2527629684953681),
('holly', 1.2527629684953681),
('philip', 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),
('unfolds', 1.2163953243244932),
('recommended', 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),
('glover', 0.98082925301172619),
('guilt', 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),
('hal', 0.92953595862417571),
('mysteries', 0.92953595862417571),
('louis', 0.92871325187271225),
('charming', 0.92520609553210742),
('urban', 0.92367083917177761),
('allows', 0.92183091224977043),
('impact', 0.91815814604895041),
('gradually', 0.91629073187415511),
('lifestyle', 0.91629073187415511),
('italy', 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),
('con', 0.81093021621632877),
('studios', 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),
('importance', 0.79492987486988764),
('hearted', 0.79492987486988764),
('portraying', 0.79356592830699269),
('impressed', 0.79258107754813223),
('waters', 0.79112758892014912),
('empire', 0.79078565012386137),
('edge', 0.789774016249017),
('environment', 0.78845736036427028),
('jean', 0.78845736036427028),
('sentimental', 0.7864791203521645),
('captured', 0.78623760362595729),
('styles', 0.78592891401091158),
('daring', 0.78592891401091158),
('backgrounds', 0.78275933924963248),
('frank', 0.78275933924963248),
('matches', 0.78275933924963248),
('tense', 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),
('conventional', 0.76214005204689672),
('maria', 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),
('verhoeven', 0.71846498854423513),
('delivers', 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),
('britain', 0.69314718055994529),
('beatty', 0.69314718055994529),
('affected', 0.69314718055994529),
('cowboy', 0.69314718055994529),
('wave', 0.69314718055994529),
('stylish', 0.69314718055994529),
('bitter', 0.69314718055994529),
('patient', 0.69314718055994529),
('meets', 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),
('handsome', 0.68007509899259255),
('sports', 0.68007509899259255),
('rebel', 0.67875844310784572),
('directs', 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),
('victor', 0.65540685257709819),
('douglas', 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),
('accomplished', 0.64551913157069074),
('distant', 0.64551913157069074),
('manhattan', 0.64435701639051324),
('personal', 0.64355023942057321),
('pushing', 0.64313675998528386),
('meeting', 0.64313675998528386),
('individual', 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),
('colonel', 0.63757732940513456),
('divorce', 0.63757732940513456),
('jane', 0.63443957973316734),
('keeping', 0.63414883979798953),
('gives', 0.63383568159497883),
('ted', 0.63342794585832296),
('animation', 0.63208692379869902),
('progress', 0.6317782341836532),
('concert', 0.63127177684185776),
('larger', 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),
('emily', 0.62082651898031915),
('drew', 0.62082651898031915),
('moved', 0.6197197120051281),
('profound', 0.61903920840622351),
('families', 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),
('peoples', 0.60613580357031549),
('charismatic', 0.60613580357031549),
('rough', 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),
('bound', 0.59470710774669278),
('always', 0.59470710774669278),
('hall', 0.5933967777928858),
('cook', 0.5916777203950857),
('claire', 0.59136448625000293),
('broadway', 0.59033768669372433),
('anna', 0.58778666490211906),
('peace', 0.58628403501758408),
('visually', 0.58539431926349916),
('falk', 0.58525821854876026),
('morality', 0.58525821854876026),
('growing', 0.58466653756587539),
('experiences', 0.58314628534561685),
('stood', 0.58314628534561685),
('touch', 0.58122926435596001),
('lives', 0.5810976767513224),
('kubrick', 0.58066919713325493),
('timing', 0.58047401805583243),
('struggles', 0.57981849525294216),
('expressions', 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),
('personalities', 0.5720692490067093),
('french', 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),
('branagh', 0.55961578793542266),
('wealth', 0.55961578793542266),
('performing', 0.55961578793542266),
('odds', 0.55961578793542266),
('sent', 0.55961578793542266),
('reminiscent', 0.55961578793542266),
('grand', 0.55961578793542266),
('overwhelming', 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),
('hearts', 0.54232429082536171),
('jackson', 0.54232429082536171),
('enjoy', 0.54124285135906114),
('redemption', 0.54056759296472823),
('madness', 0.540384426007535),
('hamilton', 0.5389965007326869),
('stands', 0.5389965007326869),
('trial', 0.5389965007326869),
('greek', 0.5389965007326869),
('each', 0.5388212312554177),
('faithful', 0.53773307668591508),
('received', 0.5372768098531604),
('jealous', 0.53714293208336406),
('documentaries', 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),
('olivier', 0.53062825106217038),
('revolution', 0.53062825106217038),
('roman', 0.53062825106217038),
('century', 0.53002783074992665),
('musical', 0.52966871156747064),
('heroic', 0.52925932545482868),
('ironically', 0.52806743020049673),
('approach', 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),
('eric', 0.51879379341516751),
('discovered', 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),
('fox', 0.51557622652458857),
('dirty', 0.51557622652458857),
('symbolism', 0.51546600332249293),
('sympathetic', 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),
('fits', 0.51082562376599072),
('provided', 0.51082562376599072),
('carter', 0.51082562376599072),
('ring', 0.51082562376599072),
('aging', 0.51082562376599072),
('countryside', 0.51082562376599072),
('alan', 0.51082562376599072),
('visit', 0.51082562376599072),
('begins', 0.51015650363396647),
('success', 0.50900578704900468),
('japan', 0.50900578704900468),
('accurate', 0.50895471583017893),
('proud', 0.50800474742434931),
('daily', 0.5075946031845443),
('atmospheric', 0.50724780241810674),
('karloff', 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),
('shining', 0.50262885656181222),
('investigation', 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),
('honor', 0.49247648509779424),
('combination', 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),
('guide', 0.48550781578170082),
('companion', 0.48550781578170082),
('julia', 0.48550781578170082),
('san', 0.48550781578170082),
('desperation', 0.48550781578170082),
('strongly', 0.48460242866688824),
('necessary', 0.48302334245403883),
('humanity', 0.48265474679929443),
('drama', 0.48221998493060503),
('warming', 0.48183808689273838),
('intrigue', 0.48183808689273838),
('nonetheless', 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),
('primary', 0.47608267532211779),
('official', 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),
('discovery', 0.47000362924573563),
('vicious', 0.47000362924573563),
('losing', 0.47000362924573563),
('genuinely', 0.46871413841586385),
('hatred', 0.46734051182625186),
('mistaken', 0.46702300110759781),
('dream', 0.46608972992459924),
('challenge', 0.46608972992459924),
('crisis', 0.46575733836428446),
('photographed', 0.46488852857896512),
('machines', 0.46430560813109778),
('critics', 0.46430560813109778),
('bird', 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),
('cynical', 0.45953232937844013),
('lynch', 0.45953232937844013),
('francisco', 0.45953232937844013),
('tour', 0.45953232937844013),
('spielberg', 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),
('defeat', 0.45198512374305722),
('mixed', 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),
('fame', 0.44183275227903923),
('closer', 0.44183275227903923),
('visuals', 0.44183275227903923),
('web', 0.44183275227903923),
('criminal', 0.4412745608048752),
('minor', 0.4409224199448939),
('jon', 0.44086703515908027),
('liked', 0.44074991514020723),
('restaurant', 0.44031183943833246),
('flaws', 0.43983275161237217),
('de', 0.43983275161237217),
('searching', 0.4393666597838457),
('rap', 0.43891304217570443),
('light', 0.43884433018199892),
('elizabeth', 0.43872232986464677),
('marry', 0.43861731542506488),
('oz', 0.43825493093115531),
('controversial', 0.43825493093115531),
('learned', 0.43825493093115531),
('slowly', 0.43785660389939979),
('bridge', 0.43721380642274466),
('thrilling', 0.43721380642274466),
('wayne', 0.43721380642274466),
('comedic', 0.43721380642274466),
('married', 0.43658501682196887),
('nazi', 0.4361020775700542),
('murder', 0.4353180712578455),
('physical', 0.4353180712578455),
('johnny', 0.43483971678806865),
('michelle', 0.43445264498141672),
('wallace', 0.43403848055222038),
('silent', 0.43395706390247063),
('comedies', 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),
('ocean', 0.4295626596872249),
...]
In [22]:
# words most frequently seen in a review with a "NEGATIVE" label
list(reversed(pos_neg_ratios.most_common()))[0:30]
Out[22]:
[('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 [26]:
from IPython.display import Image
review = "This was a horrible, terrible movie."
Image(filename='sentiment_network.png')
Out[26]:
In [27]:
review = "The movie was excellent"
Image(filename='sentiment_network_pos.png')
Out[27]:
In [74]:
vocab = set(total_counts.keys())
vocab_size = len(vocab)
print(vocab_size)
74074
In [75]:
list(vocab)
Out[75]:
['',
'inhabitants',
'goku',
'stunts',
'catepillar',
'kristensen',
'senegal',
'goddess',
'distroy',
'unexplainably',
'concoctions',
'petite',
'scribe',
'stevson',
'sctv',
'soundscape',
'rana',
'metamorphose',
'immortalizer',
'henstridge',
'planning',
'akiva',
'plod',
'eko',
'orderly',
'zeleznice',
'verbose',
'amplify',
'resonation',
'critize',
'jefferies',
'mountainbillies',
'steinbichler',
'vowel',
'rafe',
'bonbons',
'tulipe',
'clot',
'distended',
'his',
'impatiently',
'unfortuntly',
'lung',
'scapegoats',
'muzzle',
'pscychosexual',
'outbid',
'obit',
'sideshows',
'jugde',
'particolare',
'kevloun',
'masterful',
'quartier',
'unravelling',
'necessarily',
'antiques',
'strutts',
'tilts',
'disconcert',
'dossiers',
'sorriest',
'blart',
'iberia',
'situations',
'frmann',
'daniell',
'rays',
'pried',
'khoobsurat',
'leavitt',
'caiano',
'sagan',
'attractiveness',
'kitaparaporn',
'hamilton',
'massages',
'reasonably',
'horgan',
'chemist',
'audrey',
'jana',
'dutch',
'override',
'spasms',
'resumed',
'stinson',
'widows',
'stonewall',
'palatial',
'neuman',
'abandon',
'anglophile',
'marathon',
'chevette',
'unscary',
'eponymously',
'spoilerific',
'fleashens',
'brigand',
'politeness',
'clued',
'dermatonecrotic',
'grady',
'mulligan',
'ol',
'bertolucci',
'incubation',
'oldboy',
'snden',
'plaintiffs',
'fk',
'deply',
'franchot',
'cyhper',
'glorifying',
'mazovia',
'elizabeth',
'palestine',
'robby',
'wongo',
'moshing',
'eeeee',
'doltish',
'bree',
'postponed',
'gunslinger',
'debacles',
'kamm',
'herman',
'rapture',
'rolando',
'tetsuothe',
'premises',
'bruck',
'loosely',
'boylen',
'proportions',
'grecianized',
'wodehousian',
'encapsuling',
'partly',
'posative',
'calms',
'stadling',
'austrailia',
'shortland',
'wheeling',
'darkie',
'mckellar',
'cushy',
'ooookkkk',
'milky',
'unfolded',
'degrades',
'authenticating',
'rotheroe',
'beart',
'neath',
'grispin',
'intoxicants',
'nnette',
'slinging',
'tsukamoto',
'stows',
'suddenness',
'waqt',
'degrading',
'camazotz',
'blarney',
'shakher',
'delinquency',
'tomreynolds',
'insecticide',
'charlton',
'hare',
'wayland',
'nakada',
'urbane',
'sadomasochistic',
'larnia',
'hyping',
'yr',
'hebert',
'accentuating',
'deathrow',
'galligan',
'unmediated',
'treble',
'alphabet',
'soad',
'donen',
'lord',
'recess',
'handsome',
'center',
'vignettes',
'rescuers',
'pairings',
'uselful',
'sanders',
'nots',
'hatsumomo',
'appleby',
'tampax',
'sprinkling',
'defacing',
'lofty',
'opaque',
'tlc',
'romagna',
'tablespoons',
'bernhard',
'verger',
'acumen',
'percentages',
'wendingo',
'resonating',
'vntoarea',
'redundancies',
'red',
'pitied',
'belying',
'gleefulness',
'bibbidi',
'heiligt',
'gitane',
'journalist',
'focusing',
'plethora',
'citizen',
'coster',
'clunkers',
'deplorable',
'forgive',
'proplems',
'magwood',
'bankers',
'aqua',
'donated',
'disbelieving',
'acomplication',
'immediately',
'contrasted',
'reidelsheimer',
'fox',
'springs',
'toolbox',
'contacting',
'ace',
'washrooms',
'raving',
'dynamism',
'mae',
'sky',
'disharmony',
'untutored',
'icarus',
'taint',
'kargil',
'captain',
'paucity',
'fits',
'tumbles',
'amer',
'bueller',
'redubbed',
'cleansed',
'kollos',
'shara',
'humma',
'felichy',
'outa',
'piglets',
'gombell',
'supermen',
'superlow',
'enhance',
'goode',
'shalt',
'kubanskie',
'zenith',
'ananda',
'ocd',
'matlin',
'nosed',
'presumptuous',
'rerun',
'toyko',
'mazar',
'sundry',
'bilb',
'fugly',
'orchestrating',
'prosaically',
'maricarmen',
'moveis',
'conelly',
'estrange',
'lusciously',
'seasonings',
'sums',
'delirious',
'quincey',
'flesh',
'tootsie',
'ai',
'tenma',
'appropriations',
'chainsaw',
'ides',
'surrogacy',
'pungent',
'gallon',
'damaso',
'caribou',
'perico',
'supplying',
'ro',
'yuy',
'valium',
'debuted',
'robbin',
'mounts',
'interpolated',
'aetv',
'plummer',
'competence',
'toadies',
'dubiel',
'clavichord',
'asunder',
'sublety',
'airfix',
'stoltzfus',
'ruth',
'fluorescent',
'improves',
'rebenga',
'russells',
'deliberation',
'zsa',
'dardino',
'macs',
'servile',
'jlb',
'apallonia',
'crossbows',
'locus',
'mislead',
'corey',
'blundered',
'jeopardizes',
'disorganized',
'discuss',
'longish',
'tieing',
'ledger',
'speechifying',
'amitabhz',
'bbc',
'chimayo',
'pranked',
'superman',
'aggravated',
'rifleman',
'yvone',
'radiant',
'galico',
'debris',
'waking',
'btw',
'havnt',
'francen',
'chattered',
'scathed',
'pic',
'ceremonies',
'watergate',
'betsy',
'majorca',
'meercat',
'noirs',
'grunts',
'drecky',
'tribulations',
'avery',
'talladega',
'eights',
'dumbing',
'alloimono',
'scrutinising',
'geta',
'beltrami',
'pvc',
'horse',
'tiburon',
'huitime',
'ripple',
'loitering',
'forensics',
'nearly',
'elizabethan',
'ellington',
'uzi',
'sicily',
'camion',
'motivated',
'rung',
'gao',
'licitates',
'protocol',
'smirker',
'torin',
'newlywed',
'rich',
'dismay',
'skyler',
'moonwalks',
'haranguing',
'sunburst',
'grifter',
'undersold',
'chearator',
'marino',
'scala',
'conditioner',
'ulysses',
'lamarre',
'figueroa',
'flane',
'allllllll',
'slide',
'lateness',
'selbst',
'gandhis',
'dramatizing',
'catchphrase',
'doable',
'stadiums',
'alexanderplatz',
'pandemonium',
'misrepresents',
'earth',
'mounties',
'seeker',
'cheat',
'outbreaks',
'snowstorm',
'baur',
'schedules',
'bathetic',
'incorrect',
'johnathon',
'rosanne',
'mundanely',
'cauldrons',
'forrest',
'poky',
'legislation',
'womanness',
'spender',
'crazy',
'rational',
'terrell',
'zero',
'coincides',
'thoughout',
'mathew',
'narnia',
'naseeruddin',
'bucks',
'affronts',
'topple',
'degree',
'preyed',
'passionately',
'defeats',
'torchwood',
'sources',
'botticelli',
'compactor',
'kosturica',
'waiving',
'gunnar',
'stiffler',
'fwd',
'kawajiri',
'eleanor',
'sistahs',
'soulhunter',
'belies',
'wrathful',
'americans',
'ferdinandvongalitzien',
'kendra',
'weirdy',
'unforgivably',
'chepart',
'tatta',
'departmentthe',
'dig',
'blatty',
'marionettes',
'atop',
'chim',
'saurian',
'woes',
'cloudscape',
'resignedly',
'unrooted',
'keuck',
'hitlerian',
'stylings',
'crewed',
'bedeviled',
'unfurnished',
'reedus',
'circumstances',
'grasped',
'smurfettes',
'fn',
'dishwashers',
'roadie',
'ruthlessness',
'refrains',
'lampooning',
'semblance',
'richart',
'legions',
'gwenneth',
'enmity',
'assess',
'manufacturer',
'bullosa',
'outrun',
'hogan',
'chekov',
'blithe',
'code',
'drillings',
'revolvers',
'aredavid',
'robespierre',
'achcha',
'boyfriendhe',
'wallow',
'toga',
'graphed',
'tonking',
'going',
'bosnians',
'willy',
'rohauer',
'fim',
'forbidding',
'yew',
'rationalised',
'shimomo',
'opposition',
'landis',
'minded',
'despicableness',
'easting',
'arghhhhh',
'ebb',
'trialat',
'protected',
'negras',
'rick',
'muti',
'tracker',
'shawl',
'differentiates',
'sweetheart',
'deepened',
'manmohan',
'trevethyn',
'brain',
'incomprehensibly',
'piercing',
'pasadena',
'shtick',
'ute',
'viggo',
'supersedes',
'ack',
'cites',
'taurus',
'relevent',
'minidress',
'philosopher',
'bel',
'mahattan',
'moden',
'compiling',
'advertising',
'rogues',
'unimaginative',
'subpaar',
'ademir',
'darkly',
'saturate',
'fledgling',
'breaths',
'padre',
'aszombi',
'pachabel',
'incalculable',
'ozone',
'sped',
'mpho',
'rawail',
'forbid',
'synth',
'guttersnipe',
'reputedly',
'holiness',
'unessential',
'hampden',
'asylum',
'bolye',
'strangers',
'rantzen',
'farrellys',
'vigourous',
'cantinflas',
'enshrined',
'boris',
'expetations',
'replaying',
'prestige',
'bukater',
'overpaid',
'exhude',
'backsides',
'topless',
'sufferings',
'nitwits',
'cordova',
'incensed',
'danira',
'unrelenting',
'disabling',
'ferdy',
'gerard',
'drewitt',
'mero',
'monsters',
'precautions',
'lamping',
'relinquish',
'demy',
'drink',
'chamberlin',
'unjustifiably',
'cove',
'floodwaters',
'searing',
'isral',
'ling',
'grossness',
'pickier',
'pax',
'wierd',
'tereasa',
'smog',
'girotti',
'spat',
'sera',
'noxious',
'misbehaving',
'scouts',
'refreshments',
'autobiographic',
'shi',
'toyomichi',
'bits',
'psychotics',
'barzell',
'colt',
'shivering',
'pugilist',
'gladiator',
'dryer',
'reissues',
'scrivener',
'predicable',
'objection',
'marmalade',
'seems',
'spellbind',
'trifecta',
'innovator',
'shriekfest',
'inthused',
'contestants',
'goody',
'samotri',
'serviced',
'nozires',
'ins',
'mutilating',
'dupes',
'launius',
'widescreen',
'joo',
'discretionary',
'enlivens',
'bushes',
'chills',
'header',
'activist',
'gethsemane',
'phoenixs',
'wreathed',
'sacrine',
'electrifyingly',
'basely',
'ghidora',
'binder',
'dogfights',
'sugar',
'doddsville',
'porkys',
'scattershot',
'refunded',
'rudely',
'insteadit',
'zatichi',
'eurotrash',
'radioraptus',
'hurls',
'boogeman',
'weighs',
'danniele',
'converging',
'hypothermia',
'glorfindel',
'birthdays',
'attentive',
'mallepa',
'spacewalk',
'manoy',
'bombshells',
'farts',
'lyoko',
'southron',
'destruction',
'flemming',
'manhole',
'elainor',
'bowersock',
'lowly',
'wfst',
'limousines',
'skolimowski',
'saban',
'koen',
'malaysia',
'uwi',
'cyd',
'apeing',
'bonecrushing',
'dini',
'merest',
'janina',
'chemotrodes',
'trials',
'authorize',
'whilhelm',
'asthmatic',
'broads',
'missteps',
'embittered',
'chandeliers',
'seeming',
'miscalculate',
'recommeded',
'schoolwork',
'coy',
'mcconaughey',
'philosophically',
'waver',
'fanny',
'mestressat',
'unwatchably',
'saggy',
'topness',
'dwellings',
'breakup',
'hasselhoff',
'superstars',
'replay',
'aggravates',
'balances',
'urging',
'snidely',
'aleksandar',
'hildy',
'kazuhiro',
'slayer',
'tangy',
'brussels',
'horne',
'masayuki',
'molden',
'unravel',
'goodtime',
'interrogates',
'bismillahhirrahmannirrahim',
'rowboat',
'dumann',
'datedness',
'astrotheology',
'dekhiye',
'valga',
'kata',
'wipes',
'hostilities',
'sentimentalising',
'documentary',
'salesman',
'virtue',
'unreasonably',
'haver',
'cei',
'unglamorised',
'balky',
'complementary',
'paychecks',
'mnica',
'wada',
'ily',
'prc',
'ennobling',
'functionality',
'dissociated',
'elk',
'throbbing',
'tempe',
'linoleum',
'photogrsphed',
'bottacin',
'hipper',
'titillating',
'barging',
'untie',
'sacchetti',
'gnat',
'roedel',
'cohabitation',
'performs',
'sales',
'migrs',
'teachs',
'nanavati',
'fresco',
'davison',
'obstinate',
'burglar',
'masue',
'dickory',
'grills',
'appelagate',
'linkage',
'enables',
'loesser',
'patties',
'prudent',
'mallorquins',
'nativetex',
'suprise',
'drippy',
'quill',
'speeded',
'farscape',
'saddening',
'centuries',
'mos',
'improvisationally',
'neccessarily',
'transmitter',
'tankers',
'latte',
'mechanisation',
'faracy',
'synthetically',
'thoughtless',
'rake',
'ropes',
'desirable',
'whitewashed',
'donal',
'crabby',
'lifeless',
'perfidy',
'teresa',
'bulldog',
'cockamamie',
'rasberries',
'notethe',
'captivity',
'chiseling',
'smaller',
'clampets',
'alerts',
'tough',
'wellingtonian',
'aaaahhhhhhh',
'dither',
'incertitude',
'florentine',
'imperioli',
'licking',
'disparagement',
'artfully',
'feds',
'fumiya',
'tearfully',
'lanchester',
'undertaken',
'longlost',
'netted',
'carrell',
'uncompelling',
'reliefs',
'leona',
'autorenfilm',
'unfriendly',
'typewriter',
'shifted',
'bertrand',
'blesses',
'tricking',
'fireflies',
'zanes',
'unknowingly',
'unnerve',
'caning',
'flat',
'recluse',
'dcreasy',
'chipmunk',
'dipper',
'musee',
'cousin',
'shys',
'berserkers',
'eve',
'conflagration',
'irks',
'restricts',
'parsing',
'positronic',
'copout',
'khala',
'swiftness',
'higginson',
'imprint',
'walter',
'sundance',
'whispering',
'thematically',
'underimpressed',
'uno',
'expressly',
'russkies',
'discos',
'shaping',
'verson',
'prototype',
'chapman',
'trafficker',
'semetary',
'unrealistically',
'lifewell',
'rivas',
'consequent',
'katsu',
'titantic',
'jalees',
'ranee',
'shipbuilding',
'gambles',
'dispenses',
'disfigurement',
'bright',
'cristian',
'puertorricans',
'constituent',
'capta',
'jewel',
'erect',
'farah',
'despondently',
'avoide',
'inconnu',
'headquarters',
'sanguisga',
...]
In [46]:
import numpy as np
layer_0 = np.zeros((1,vocab_size))
layer_0
Out[46]:
array([[ 0., 0., 0., ..., 0., 0., 0.]])
In [47]:
from IPython.display import Image
Image(filename='sentiment_network.png')
Out[47]:
In [48]:
word2index = {}
for i,word in enumerate(vocab):
word2index[word] = i
word2index
Out[48]:
{'': 0,
'inhabitants': 1,
'goku': 2,
'stunts': 3,
'catepillar': 4,
'kristensen': 5,
'goddess': 7,
'offing': 49797,
'distroy': 8,
'unexplainably': 9,
'concoctions': 10,
'petite': 11,
'paramilitary': 24759,
'scribe': 12,
'stevson': 13,
'senegal': 6,
'sctv': 14,
'soundscape': 15,
'rana': 16,
'immortalizer': 18,
'rene': 67354,
'eko': 23,
'planning': 20,
'akiva': 21,
'plod': 22,
'orderly': 24,
'zeleznice': 25,
'critize': 29,
'baguettes': 25649,
'jefferies': 30,
'uncertainties': 61695,
'mountainbillies': 31,
'steinbichler': 32,
'vowel': 33,
'rafe': 34,
'donig': 68719,
'tulipe': 36,
'clot': 37,
'hack': 12526,
'distended': 38,
'cornered': 37116,
'impatiently': 40,
'batrice': 12525,
'unfortuntly': 41,
'lung': 42,
'scapegoats': 43,
'pscychosexual': 45,
'outbid': 46,
'obit': 47,
'sideshows': 48,
'jugde': 49,
'kevloun': 51,
'quartier': 53,
'harp': 61948,
'unravelling': 54,
'antiques': 56,
'strutts': 57,
'tilts': 58,
'disconcert': 59,
'dossiers': 60,
'sorriest': 61,
'craftsman': 49412,
'blart': 62,
'dependence': 37120,
'sated': 61698,
'iberia': 63,
'sagan': 72,
'frmann': 65,
'daniell': 66,
'rays': 67,
'pried': 68,
'khoobsurat': 69,
'leavitt': 70,
'caiano': 71,
'attractiveness': 73,
'kitaparaporn': 74,
'hamilton': 75,
'massages': 76,
'horgan': 78,
'chemist': 79,
'audrey': 80,
'yeow': 55655,
'jana': 81,
'dutch': 82,
'pinchot': 24773,
'override': 83,
'dwervick': 63223,
'spasms': 84,
'resumed': 85,
'tamale': 66259,
'calibanian': 49636,
'stinson': 86,
'widows': 87,
'stonewall': 88,
'palatial': 89,
'neuman': 90,
'abandon': 91,
'lemmings': 65314,
'anglophile': 92,
'ertha': 61706,
'chevette': 94,
'unscary': 95,
'spoilerific': 97,
'neworleans': 67639,
'metamorphose': 17,
'brigand': 99,
'cheating': 41603,
'clued': 101,
'dermatonecrotic': 102,
'grady': 103,
'mulligan': 104,
'ol': 105,
'incubation': 107,
'plaintiffs': 110,
'snden': 109,
'fk': 111,
'deply': 112,
'franchot': 113,
'henstridge': 19,
'cyhper': 114,
'verbose': 26,
'mazovia': 116,
'elizabeth': 117,
'palestine': 118,
'robby': 119,
'wongo': 120,
'moshing': 121,
'mstified': 12543,
'eeeee': 122,
'doltish': 123,
'bree': 124,
'postponed': 125,
'debacles': 127,
'amplify': 27,
'kamm': 128,
'phantom': 18893,
'boylen': 136,
'rolando': 131,
'premises': 133,
'bruck': 134,
'loosely': 135,
'wodehousian': 139,
'onishi': 70389,
'encapsuling': 140,
'partly': 141,
'stadling': 144,
'calms': 143,
'darkie': 148,
'wheeling': 147,
'ursla': 15875,
'subsidized': 49420,
'mckellar': 149,
'ooookkkk': 151,
'milky': 152,
'unfolded': 153,
'degrades': 154,
'authenticating': 155,
'writeup': 12548,
'rotheroe': 156,
'beart': 157,
'intoxicants': 160,
'grispin': 159,
'cannes': 61718,
'antithetical': 70398,
'nnette': 161,
'tsukamoto': 163,
'antwones': 44205,
'stows': 164,
'suddenness': 165,
'vol': 61720,
'waqt': 166,
'camazotz': 168,
'paps': 55042,
'shakher': 170,
'terminate': 63868,
'kotex': 56419,
'delinquency': 171,
'bromwell': 25214,
'insecticide': 173,
'charlton': 174,
'nakada': 177,
'titted': 24791,
'urbane': 178,
'depicted': 54491,
'sadomasochistic': 179,
'hyping': 181,
'yr': 182,
'hebert': 183,
'waxwork': 12990,
'deathrow': 185,
'nourishes': 24792,
'unmediated': 187,
'tamper': 37143,
'soad': 190,
'alphabet': 189,
'donen': 191,
'lord': 192,
'recess': 193,
'watchably': 61023,
'handsome': 194,
'vignettes': 196,
'pairings': 198,
'uselful': 199,
'sanders': 200,
'outbursts': 72891,
'nots': 201,
'hatsumomo': 202,
'actioned': 18292,
'krimi': 24797,
'appleby': 203,
'tampax': 204,
'sprinkling': 205,
'defacing': 206,
'lofty': 207,
'verger': 213,
'tablespoons': 211,
'bernhard': 212,
'goosebump': 64565,
'acumen': 214,
'percentages': 215,
'wendingo': 216,
'resonating': 217,
'vntoarea': 218,
'redundancies': 219,
'strictly': 57081,
'pitied': 221,
'belying': 222,
'michelangelo': 53153,
'gleefulness': 223,
'environmentalist': 24803,
'gitane': 226,
'corrected': 66547,
'journalist': 227,
'focusing': 228,
'plethora': 229,
'his': 39,
'citizen': 230,
'south': 55579,
'clunkers': 232,
'pendulous': 55991,
'mounds': 24805,
'deplorable': 233,
'forgive': 234,
'proplems': 235,
'bankers': 237,
'aqua': 238,
'donated': 239,
'disbelieving': 240,
'acomplication': 241,
'contrasted': 243,
'muzzle': 44,
'amphibians': 72141,
'springs': 246,
'reformatted': 49443,
'toolbox': 247,
'contacting': 248,
'washrooms': 250,
'raving': 251,
'dynamism': 252,
'mae': 253,
'disharmony': 255,
'molls': 72979,
'dewaere': 12569,
'untutored': 256,
'icarus': 257,
'taint': 258,
'kargil': 259,
'captain': 260,
'paucity': 261,
'fits': 262,
'tumbles': 263,
'amer': 264,
'bueller': 265,
'cleansed': 267,
'shara': 269,
'humma': 270,
'outa': 272,
'piglets': 273,
'gombell': 274,
'supermen': 275,
'superlow': 276,
'kubanskie': 280,
'goode': 278,
'disorganised': 45570,
'zenith': 281,
'ananda': 282,
'matlin': 284,
'particolare': 50,
'presumptuous': 286,
'rerun': 287,
'toyko': 288,
'bilb': 291,
'sundry': 290,
'fugly': 292,
'orchestrating': 293,
'prosaically': 294,
'moveis': 296,
'conelly': 297,
'estrange': 298,
'elfriede': 49455,
'masterful': 52,
'seasonings': 300,
'quincey': 303,
'frowning': 49456,
'painkillers': 53444,
'high': 25515,
'flesh': 304,
'tootsie': 305,
'ai': 306,
'tenma': 307,
'duguay': 71257,
'appropriations': 308,
'ides': 310,
'rui': 61734,
'surrogacy': 311,
'pungent': 312,
'damaso': 314,
'authoritarian': 61736,
'caribou': 315,
'ro': 318,
'supplying': 317,
'yuy': 319,
'debuted': 321,
'mounts': 323,
'interpolated': 324,
'aetv': 325,
'plummer': 326,
'asunder': 331,
'airfix': 333,
'dubiel': 329,
'clavichord': 330,
'crafty': 50465,
'sublety': 332,
'stoltzfus': 334,
'ruth': 335,
'fluorescent': 336,
'improves': 337,
'russells': 339,
'tick': 43838,
'zsa': 341,
'macs': 343,
'jlb': 345,
'locus': 348,
'mislead': 349,
'merly': 49461,
'corey': 350,
'blundered': 351,
'humourless': 3568,
'disorganized': 353,
'discuss': 354,
'sharifi': 45391,
'tieing': 356,
'kats': 34784,
'bbc': 360,
'pranked': 362,
'superman': 363,
'holroyd': 9223,
'aggravated': 364,
'rifleman': 365,
'yvone': 366,
'vaugier': 24820,
'radiant': 367,
'galico': 368,
'debris': 369,
'btw': 371,
'denote': 24822,
'havnt': 372,
'francen': 373,
'chattered': 374,
'scathed': 375,
'pic': 376,
'ceremonies': 377,
'everyplace': 65309,
'betsy': 379,
'finster': 37176,
'meercat': 381,
'noirs': 382,
'grunts': 383,
'tribulations': 385,
'apparatus': 47673,
'martnez': 25825,
'telethons': 24825,
'talladega': 387,
'alloimono': 390,
'situations': 64,
'scrutinising': 391,
'geta': 392,
'beltrami': 393,
'pvc': 394,
'horse': 395,
'tiburon': 396,
'huitime': 397,
'ripple': 398,
'exceed': 61748,
'loitering': 399,
'forensics': 400,
'nearly': 401,
'ellington': 403,
'uzi': 404,
'rung': 408,
'pillaged': 24829,
'gao': 409,
'licitates': 410,
'protocol': 411,
'smirker': 412,
'torin': 413,
'vizier': 31853,
'newlywed': 414,
'dismay': 416,
'moonwalks': 418,
'skyler': 417,
'invested': 18455,
'grifter': 421,
'undersold': 422,
'chearator': 423,
'marino': 424,
'scala': 425,
'conditioner': 426,
'lamarre': 428,
'figueroa': 429,
'mcinnerny': 61753,
'allllllll': 431,
'slide': 432,
'lateness': 433,
'selbst': 434,
'dramatizing': 436,
'doable': 438,
'hollywoodize': 27207,
'alexanderplatz': 440,
'wholesome': 45745,
'pandemonium': 441,
'earth': 443,
'mounties': 444,
'seeker': 445,
'cheat': 446,
'outbreaks': 447,
'savagely': 61759,
'snowstorm': 448,
'baur': 449,
'schedules': 450,
'bathetic': 451,
'johnathon': 453,
'origonal': 57843,
'rosanne': 454,
'cauldrons': 456,
'forrest': 457,
'poky': 458,
'aristos': 54856,
'womanness': 460,
'spender': 461,
'pagliai': 37108,
'rational': 463,
'terrell': 464,
'affronts': 472,
'concise': 49476,
'mathew': 468,
'narnia': 469,
'naseeruddin': 470,
'bucks': 471,
'proceeds': 69809,
'topple': 473,
'degree': 474,
'passionately': 476,
'defeats': 477,
'gras': 49477,
'sources': 479,
'pflug': 49976,
'botticelli': 480,
'fwd': 486,
'waiving': 483,
'gunnar': 484,
'stiffler': 485,
'unwise': 49480,
'kawajiri': 487,
'sistahs': 489,
'swallowed': 30511,
'soulhunter': 490,
'belies': 491,
'wrathful': 492,
'badmouth': 16696,
'floradora': 61766,
'unforgivably': 497,
'weirdy': 496,
'violation': 63309,
'chepart': 498,
'departmentthe': 500,
'posehn': 49483,
'peyote': 37188,
'psychiatrically': 24846,
'marionettes': 503,
'blatty': 502,
'atop': 504,
'debases': 25135,
'henze': 24845,
'unrooted': 510,
'cloudscape': 508,
'resignedly': 509,
'begin': 49917,
'hitlerian': 512,
'reedus': 517,
'crewed': 514,
'bedeviled': 515,
'unfurnished': 516,
'herrmann': 12602,
'circumstances': 518,
'grasped': 519,
'fn': 521,
'beefed': 22200,
'scwatch': 64018,
'dishwashers': 522,
'roadie': 523,
'ruthlessness': 524,
'migrant': 12605,
'refrains': 525,
'preponderance': 44377,
'lampooning': 526,
'richart': 528,
'gwenneth': 530,
'enmity': 531,
'vortex': 61772,
'assess': 532,
'manufacturer': 533,
'bullosa': 534,
'citizenship': 61774,
'chekov': 537,
'hogan': 536,
'blithe': 538,
'aredavid': 542,
'drillings': 540,
'revolvers': 541,
'boyfriendhe': 545,
'achcha': 544,
'wallow': 546,
'toga': 547,
'bosnians': 551,
'going': 550,
'willy': 552,
'fim': 554,
'forbidding': 555,
'delete': 56779,
'rationalised': 557,
'shimomo': 558,
'opposition': 559,
'landis': 560,
'minded': 561,
'arghhhhh': 564,
'trialat': 566,
'protected': 567,
'negras': 568,
'tracker': 571,
'muti': 570,
'dinky': 49489,
'shawl': 572,
'differentiates': 573,
'dipaolo': 61779,
'sweetheart': 574,
'manmohan': 576,
'enamored': 66265,
'trevethyn': 577,
'brain': 578,
'incomprehensibly': 579,
'pasadena': 581,
'bruton': 59142,
'shtick': 582,
'ute': 583,
'viggo': 584,
'relevent': 589,
'cites': 587,
'greenaways': 61781,
'minidress': 590,
'philosopher': 591,
'mahattan': 593,
'moden': 594,
'compiling': 595,
'unimaginative': 598,
'rogues': 597,
'subpaar': 599,
'darkly': 601,
'saturate': 602,
'fledgling': 603,
'breaths': 604,
'sceam': 37206,
'empathized': 58870,
'aszombi': 606,
'incalculable': 608,
'formations': 28596,
'hampden': 619,
'rawail': 612,
'forbid': 613,
'holiness': 617,
'unessential': 618,
'reputedly': 616,
'wage': 63181,
'kewpie': 24860,
'asylum': 620,
'bolye': 621,
'celticism': 63189,
'strangers': 622,
'rantzen': 623,
'farrellys': 624,
'marathon': 93,
'cantinflas': 626,
'disproportionately': 12617,
'bared': 67212,
'enshrined': 627,
'expetations': 629,
'replaying': 630,
'topless': 636,
'bukater': 632,
'overpaid': 633,
'exhude': 634,
'nitwits': 638,
'tsst': 51554,
'sufferings': 637,
'ci': 24693,
'eponymously': 96,
'ferdy': 644,
'danira': 641,
'unrelenting': 642,
'disabling': 643,
'gerard': 645,
'drewitt': 646,
'lamping': 650,
'demy': 652,
'wicklow': 37214,
'relinquish': 651,
'feminized': 64196,
'drink': 653,
'chamberlin': 654,
'floodwaters': 657,
'searing': 658,
'isral': 659,
'ling': 660,
'grossness': 661,
'sassier': 24865,
'pickier': 662,
'pax': 663,
'fleashens': 98,
'wierd': 664,
'tereasa': 665,
'smog': 666,
'girotti': 667,
'zooey': 64814,
'spat': 668,
'sera': 669,
'misbehaving': 671,
'scouts': 672,
'refreshments': 673,
'itll': 39668,
'toyomichi': 676,
'politeness': 100,
'bits': 677,
'psychotics': 678,
'optimistic': 61796,
'barzell': 679,
'colt': 680,
'anita': 49501,
'shivering': 681,
'utah': 59297,
'scrivener': 686,
'predicable': 687,
'dryer': 684,
'reissues': 685,
'sexier': 26115,
'spellbind': 691,
'marmalade': 689,
'seems': 690,
'wyke': 37223,
'innovator': 693,
'inthused': 695,
'scatman': 6309,
'contestants': 696,
'bertolucci': 106,
'serviced': 699,
'nozires': 700,
'ins': 701,
'mutilating': 702,
'dupes': 703,
'launius': 704,
'widescreen': 705,
'joo': 706,
'discretionary': 707,
'enlivens': 708,
'manos': 55596,
'bushes': 709,
'header': 711,
'activist': 712,
'gethsemane': 713,
'phoenixs': 714,
'wreathed': 715,
'oldboy': 108,
'electrifyingly': 717,
'inseparability': 24874,
'ghidora': 719,
'binder': 720,
'tibet': 51530,
'doddsville': 723,
'sugar': 722,
'porkys': 724,
'hopefully': 37226,
'scattershot': 725,
'refunded': 726,
'rudely': 727,
'enacts': 67435,
'insteadit': 728,
'nightwatch': 61803,
'eurotrash': 730,
'radioraptus': 731,
'unreservedly': 73710,
'vall': 49508,
'boogeman': 733,
'flunked': 24880,
'weighs': 734,
'glorfindel': 738,
'hypothermia': 737,
'misled': 64919,
'toiletries': 71501,
'birthdays': 739,
'attentive': 740,
'mallepa': 741,
'manoy': 743,
'bombshells': 744,
'glorifying': 115,
'southron': 747,
'destruction': 748,
'manhole': 750,
'elainor': 751,
'bounder': 13003,
'bowersock': 752,
'lowly': 753,
'wfst': 754,
'limousines': 755,
'skolimowski': 756,
'saban': 757,
'malaysia': 759,
'cyd': 761,
'bonecrushing': 763,
'merest': 765,
'janina': 766,
'chemotrodes': 767,
'trials': 768,
'whilhelm': 770,
'asthmatic': 771,
'missteps': 773,
'melyvn': 24885,
'embittered': 774,
'profit': 37234,
'seeming': 776,
'miscalculate': 777,
'recommeded': 778,
'mankin': 37235,
'schoolwork': 779,
'coy': 780,
'mcconaughey': 781,
'waver': 783,
'unwatchably': 786,
'saggy': 787,
'breakup': 790,
'pufnstuf': 37237,
'superstars': 792,
'replay': 793,
'aggravates': 794,
'urging': 796,
'snidely': 797,
'aleksandar': 798,
'hildy': 799,
'kazuhiro': 800,
'slayer': 801,
'tangy': 802,
'horne': 804,
'masayuki': 805,
'molden': 806,
'unravel': 807,
'goodtime': 808,
'rowboat': 811,
'dekhiye': 815,
'datedness': 813,
'astrotheology': 814,
'suriani': 59610,
'hostilities': 819,
'wipes': 818,
'sentimentalising': 820,
'documentary': 821,
'virtue': 823,
'unreasonably': 824,
'cei': 826,
'hobbled': 37240,
'unglamorised': 827,
'balky': 828,
'complementary': 829,
'paychecks': 830,
'tughlaq': 45551,
'functionality': 836,
'ily': 833,
'prc': 834,
'ennobling': 835,
'dissociated': 837,
'elk': 838,
'throbbing': 839,
'tempe': 840,
'linoleum': 841,
'bottacin': 843,
'hipper': 844,
'barging': 846,
'untie': 847,
'sacchetti': 848,
'gnat': 849,
'roedel': 850,
'performs': 852,
'nanavati': 856,
'migrs': 854,
'teachs': 855,
'gunslinger': 126,
'fresco': 857,
'davison': 858,
'jet': 59446,
'burglar': 860,
'jerker': 69267,
'masue': 861,
'dickory': 862,
'muggy': 46634,
'grills': 863,
'figment': 28693,
'monogamistic': 49527,
'appelagate': 864,
'linkage': 865,
'loesser': 867,
'patties': 868,
'prudent': 869,
'mallorquins': 870,
'nativetex': 871,
'suprise': 872,
'quill': 874,
'angsty': 71451,
'speeded': 875,
'farscape': 876,
'herman': 129,
'saddening': 877,
'centuries': 878,
'mos': 879,
'neccessarily': 881,
'tankers': 883,
'latte': 884,
'faracy': 886,
'stilts': 24897,
'synthetically': 887,
'thoughtless': 888,
'authoring': 62813,
'rake': 889,
'ropes': 890,
'whitewashed': 892,
'donal': 893,
'arching': 4910,
'cockamamie': 899,
'lifeless': 895,
'perfidy': 896,
'teresa': 897,
'bulldog': 898,
'vingh': 73726,
'evacuees': 65858,
'rasberries': 900,
'chiseling': 903,
'clampets': 905,
'grecianized': 138,
'smaller': 904,
'kluznick': 62184,
'alerts': 906,
'aaaahhhhhhh': 909,
'wellingtonian': 908,
'dither': 910,
'incertitude': 911,
'florentine': 912,
'imperioli': 913,
'licking': 914,
'disparagement': 915,
'artfully': 916,
'feds': 917,
'fumiya': 918,
'jbl': 52774,
'tearfully': 919,
'welfare': 24905,
'idyllically': 49534,
'isha': 43702,
'lanchester': 920,
'undertaken': 921,
'longlost': 922,
'netted': 923,
'carrell': 924,
'uncompelling': 925,
'stems': 37258,
'reliefs': 926,
'leona': 927,
'autorenfilm': 928,
'unfriendly': 929,
'typewriter': 930,
'shifted': 931,
'bertrand': 932,
'blesses': 933,
'leukemia': 12666,
'posative': 142,
'tricking': 934,
'zanes': 936,
'dashboard': 12667,
'unknowingly': 937,
'flatmates': 51897,
'unnerve': 938,
'caning': 939,
'shortland': 146,
'recluse': 941,
'dcreasy': 942,
'scratchiness': 24911,
'pms': 30930,
'chipmunk': 943,
'tkachenko': 49537,
'dipper': 944,
'europeans': 61601,
'berserkers': 948,
'shys': 947,
'monte': 68505,
'eve': 949,
'luxury': 61828,
'conflagration': 950,
'water': 46389,
'irks': 951,
'positronic': 954,
'cushy': 150,
'swiftness': 957,
'underimpressed': 964,
'imprint': 959,
'sundance': 961,
'aida': 31951,
'thematically': 963,
'uno': 965,
'expressly': 966,
'russkies': 967,
'discos': 968,
'shaping': 969,
'verson': 970,
'blushed': 61831,
'prototype': 971,
'lifewell': 976,
'trafficker': 973,
'crucifixions': 62188,
'unrealistically': 975,
'rivas': 977,
'consequent': 978,
'katsu': 979,
'titantic': 980,
'jalees': 981,
'ranee': 982,
'gambles': 984,
'dispenses': 985,
'disfigurement': 986,
'bright': 987,
'cristian': 988,
'subculture': 37268,
'capta': 991,
'jewel': 992,
'erect': 993,
'avoide': 996,
'inconnu': 997,
'headquarters': 998,
'babbling': 1000,
'pac': 1001,
'performace': 1003,
'dorrit': 1004,
'runners': 1005,
'sentimentality': 1006,
'marred': 1007,
'commemorative': 1008,
'helpers': 1012,
'chiles': 1011,
'snowy': 1013,
'cheddar': 1014,
'neath': 158,
'outshine': 1016,
'nadu': 1019,
'wellbeing': 1020,
'envisioned': 43779,
'fanaticism': 1021,
'morrisette': 12687,
'sesame': 1024,
'gran': 1023,
'marlina': 1025,
'artificiality': 1030,
'coinsidence': 1027,
'founders': 1028,
'dismissably': 1029,
'dracht': 66299,
'scavengers': 1031,
'neese': 12685,
'pangborn': 1034,
'elmore': 1039,
'bristol': 71162,
'lillies': 1035,
'parkers': 1036,
'skipped': 1038,
'clipboard': 1042,
'jucier': 1041,
'haifa': 1043,
...}
In [49]:
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 [33]:
layer_0
Out[33]:
array([[ 18., 0., 0., ..., 0., 0., 0.]])
In [51]:
def get_target_for_label(label):
if(label == 'POSITIVE'):
return 1
else:
return 0
In [54]:
labels[0]
Out[54]:
'POSITIVE'
In [52]:
get_target_for_label(labels[0])
Out[52]:
1
In [55]:
labels[1]
Out[55]:
'NEGATIVE'
In [53]:
get_target_for_label(labels[1])
Out[53]:
0
In [21]:
%matplotlib inline
%config InlineBackend.figure_format = 'retina'
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from collections import Counter
In [74]:
class NeuralNetwork(object):
def __init__(self, input_nodes, hidden_nodes, output_nodes, learning_rate):
self.pre_process_data(input_nodes)
# Set number of nodes in input, hidden and output layers.
self.input_nodes = len(self.layer_0)
self.hidden_nodes = hidden_nodes
self.output_nodes = output_nodes
# Initialize weights
self.weights_input_to_hidden = np.random.normal(0.0, self.hidden_nodes**-0.5,
(self.hidden_nodes, self.input_nodes))
self.weights_hidden_to_output = np.random.normal(0.0, self.output_nodes**-0.5,
(self.output_nodes, self.hidden_nodes))
self.lr = learning_rate
#### TODO: Set self.activation_function to your implemented sigmoid function ####
#
# Note: in Python, you can define a function with a lambda expression,
# as shown below.
#self.activation_function = lambda x : 1 / (1 + np.exp(-x)) # Replace 0 with your sigmoid calculation.
### If the lambda code above is not something you're familiar with,
# You can uncomment out the following three lines and put your
# implementation there instead.
#
#def sigmoid(x):
# return 0 # Replace 0 with your sigmoid calculation here
#self.activation_function = sigmoid
def train(self, inputs_list, targets_list):
self.update_input_layer(inputs_list)
# Convert inputs list to 2d array
inputs = np.array(self.layer_0, ndmin=2)
targets = np.array(self.get_target_for_label(targets_list), ndmin=2)
#### Implement the forward pass here ####
### Forward pass ###
# TODO: Hidden layer - Replace these values with your calculations.
hidden_inputs = np.dot(self.weights_input_to_hidden,inputs) # signals into hidden layer
hidden_outputs = hidden_inputs # signals from hidden layer
# TODO: Output layer - Replace these values with your calculations.
final_inputs = np.dot(self.weights_hidden_to_output,hidden_outputs) # signals into final output layer
final_outputs = final_inputs # signals from final output layer
#### Implement the backward pass here ####
### Backward pass ###
# TODO: Output error - Replace this value with your calculations.
output_errors = targets - final_outputs # Output layer error is the difference between desired target and actual output.
print(output_errors)
# TODO: Backpropagated error - Replace these values with your calculations.
hidden_errors = np.dot(output_errors.T,self.weights_hidden_to_output)
hidden_grad = 1 # hidden layer gradients
hidden_error_term = hidden_grad * hidden_errors
# TODO: Update the weights - Replace these values with your calculations.
self.weights_hidden_to_output += self.lr * output_errors * hidden_outputs # update hidden-to-output weights with gradient descent step
self.weights_input_to_hidden += self.lr * hidden_error_term * inputs.T # update input-to-hidden weights with gradient descent step
def run(self, inputs_list):
# Run a forward pass through the network
inputs = np.array(inputs_list, ndmin=2).T
#### Implement the forward pass here ####
# TODO: Hidden layer - replace these values with the appropriate calculations.
hidden_inputs = np.dot(self.weights_input_to_hidden, inputs) # signals into hidden layer
hidden_outputs = hidden_inputs # signals from hidden layer
# TODO: Output layer - Replace these values with the appropriate calculations.
final_inputs = np.dot(self.weights_hidden_to_output,hidden_outputs) # signals into final output layer
final_outputs = final_inputs # signals from final output layer
return final_outputs
def pre_process_data(self, reviews):
total_counts=Counter()
for i in range(len(reviews)):
for word in reviews[i].split(" "):
total_counts[word] += 1
self.vocab = set(total_counts.keys())
vocab_size = len(self.vocab)
self.word2index = {}
for i,word in enumerate(self.vocab):
self.word2index[word] = i
self.layer_0 = np.zeros((1,vocab_size))
list(self.layer_0)
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(" "):
self.layer_0[0][self.word2index[word]] += 1
def get_target_for_label(self, label):
if(label == 'POSITIVE'):
return 1
else:
return 0
In [75]:
def MSE(y, Y):
return np.mean((y-Y)**2)
In [77]:
import sys
### Set the hyperparameters here ###
epochs = 1500
learning_rate = 0.01
hidden_nodes = 8
output_nodes = 1
#N_i = len(reviews)
network = NeuralNetwork(reviews, hidden_nodes, output_nodes, learning_rate)
losses = {'train':[], 'validation':[]}
for e in range(epochs):
# Go through a random batch of 128 records from the training data set
#batch = np.random.choice(train_features.index, size=128)
for record, target in zip(reviews,
labels):
print(target)
network.train(record, target)
# Printing out the training progress
#train_loss = MSE(network.run(train_features), train_targets['cnt'].values)
#val_loss = MSE(network.run(val_features), val_targets['cnt'].values)
sys.stdout.write("\rProgress: " + str(100 * e/float(epochs))[:4] \
+ "% ... Training loss: " + str(train_loss)[:5] \
+ " ... Validation loss: " + str(val_loss)[:5])
losses['train'].append(train_loss)
losses['validation'].append(val_loss)
POSITIVE
[[-4.49312825 1. 1. ..., 1. 1. 1. ]]
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-77-04469c7fb0dc> in <module>()
18 labels):
19 print(target)
---> 20 network.train(record, target)
21
22 # Printing out the training progress
<ipython-input-74-9de33343c1a8> in train(self, inputs_list, targets_list)
62
63 # TODO: Update the weights - Replace these values with your calculations.
---> 64 self.weights_hidden_to_output += self.lr * output_errors * hidden_outputs # update hidden-to-output weights with gradient descent step
65 self.weights_input_to_hidden += self.lr * hidden_error_term * inputs.T # update input-to-hidden weights with gradient descent step
66
ValueError: operands could not be broadcast together with shapes (1,8) (8,74074) (1,8)
In [ ]:
plt.plot(losses['train'], label='Training loss')
plt.plot(losses['validation'], label='Validation loss')
plt.legend()
plt.ylim(ymax=1)
In [ ]:
print(network.run())
Content source: julianogalgaro/udacity
Similar notebooks: