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),
 ('dvd', 1324),
 ('later', 1324),
 ('war', 1310),
 ('whole', 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),
 ('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),
 ('short', 1009),
 ('fan', 1009),
 ('second', 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),
 ('less', 934),
 ('live', 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),
 ('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),
 ('idea', 731),
 ('yes', 731),
 ('late', 730),
 ('despite', 729),
 ('becomes', 729),
 ('case', 726),
 ('able', 726),
 ('money', 723),
 ('completely', 721),
 ('child', 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),
 ('either', 683),
 ('name', 683),
 ('doing', 677),
 ('turns', 674),
 ('close', 671),
 ('wants', 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),
 ('musical', 625),
 ('known', 625),
 ('chance', 621),
 ('score', 620),
 ('already', 619),
 ('hit', 619),
 ('feeling', 619),
 ('voice', 615),
 ('living', 612),
 ('moment', 612),
 ('low', 610),
 ('supporting', 610),
 ('ago', 609),
 ('themselves', 608),
 ('reality', 605),
 ('hilarious', 605),
 ('jack', 604),
 ('told', 603),
 ('hand', 601),
 ('moving', 600),
 ('quality', 600),
 ('dialogue', 600),
 ('happy', 599),
 ('song', 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),
 ('sound', 578),
 ('type', 578),
 ('view', 573),
 ('enjoyable', 573),
 ('number', 572),
 ('husband', 572),
 ('romantic', 572),
 ('daughter', 572),
 ('documentary', 571),
 ('self', 570),
 ('modern', 569),
 ('robert', 569),
 ('superb', 569),
 ('took', 569),
 ('mean', 566),
 ('shown', 563),
 ('coming', 561),
 ('important', 560),
 ('leave', 559),
 ('king', 559),
 ('change', 558),
 ('wanted', 555),
 ('somewhat', 555),
 ('tells', 554),
 ('run', 552),
 ('country', 552),
 ('career', 552),
 ('events', 552),
 ('season', 550),
 ('heard', 550),
 ('girls', 549),
 ('greatest', 549),
 ('etc', 547),
 ('care', 546),
 ('starts', 545),
 ('english', 542),
 ('killer', 541),
 ('totally', 540),
 ('tale', 540),
 ('guys', 540),
 ('animation', 540),
 ('usual', 539),
 ('miss', 535),
 ('opinion', 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),
 ('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),
 ('sad', 497),
 ('taken', 497),
 ('ways', 496),
 ('richard', 495),
 ('knows', 494),
 ('atmosphere', 493),
 ('similar', 491),
 ('taking', 491),
 ('car', 491),
 ('surprised', 491),
 ('george', 490),
 ('perfectly', 490),
 ('sequence', 489),
 ('eye', 489),
 ('across', 489),
 ('team', 489),
 ('serious', 488),
 ('powerful', 488),
 ('among', 488),
 ('room', 488),
 ('due', 488),
 ('b', 487),
 ('strange', 487),
 ('cannot', 487),
 ('order', 487),
 ('beauty', 486),
 ('famous', 485),
 ('tries', 484),
 ('myself', 484),
 ('herself', 484),
 ('happened', 484),
 ('class', 483),
 ('four', 482),
 ('cool', 481),
 ('release', 479),
 ('theme', 479),
 ('anyway', 479),
 ('opening', 478),
 ('entertainment', 477),
 ('exactly', 475),
 ('slow', 475),
 ('ends', 475),
 ('unique', 475),
 ('o', 474),
 ('level', 474),
 ('easily', 474),
 ('red', 474),
 ('interest', 472),
 ('happen', 471),
 ('crime', 470),
 ('viewing', 468),
 ('memorable', 467),
 ('sets', 467),
 ('stop', 466),
 ('group', 466),
 ('message', 463),
 ('problems', 463),
 ('sister', 463),
 ('dance', 463),
 ('working', 463),
 ('knew', 462),
 ('nature', 461),
 ('mystery', 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),
 ('usually', 452),
 ('tom', 452),
 ('peter', 452),
 ('soundtrack', 452),
 ('local', 450),
 ('certain', 448),
 ('follow', 448),
 ('whether', 447),
 ('possible', 446),
 ('emotional', 445),
 ('above', 444),
 ('killed', 444),
 ('de', 444),
 ('god', 443),
 ('middle', 443),
 ('happens', 442),
 ('needs', 442),
 ('flick', 442),
 ('masterpiece', 441),
 ('major', 440),
 ('period', 440),
 ('named', 439),
 ('haven', 439),
 ('th', 438),
 ('particular', 438),
 ('earth', 437),
 ('feature', 437),
 ('stand', 436),
 ('typical', 435),
 ('words', 435),
 ('elements', 433),
 ('obviously', 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),
 ('japanese', 417),
 ('sweet', 417),
 ('leads', 417),
 ('deal', 416),
 ('poor', 416),
 ('personal', 413),
 ('incredible', 413),
 ('fast', 412),
 ('deep', 410),
 ('became', 410),
 ('hours', 409),
 ('giving', 408),
 ('dream', 408),
 ('nearly', 408),
 ('clearly', 407),
 ('turned', 407),
 ('near', 406),
 ('obvious', 406),
 ('surprise', 405),
 ('cut', 405),
 ('era', 404),
 ('body', 404),
 ('five', 403),
 ('hour', 403),
 ('female', 403),
 ('note', 399),
 ('learn', 398),
 ('truth', 398),
 ('feels', 397),
 ('match', 397),
 ('tony', 397),
 ('except', 397),
 ('clear', 394),
 ('complete', 394),
 ('filmed', 394),
 ('older', 393),
 ('keeps', 393),
 ('eventually', 393),
 ('street', 393),
 ('lots', 393),
 ('buy', 392),
 ('william', 391),
 ('stewart', 391),
 ('joe', 390),
 ('meet', 390),
 ('fall', 390),
 ('talking', 389),
 ('unlike', 389),
 ('rating', 389),
 ('difficult', 389),
 ('shots', 389),
 ('means', 388),
 ('dramatic', 388),
 ('wonder', 386),
 ('situation', 386),
 ('subject', 386),
 ('appears', 386),
 ('present', 386),
 ('comments', 385),
 ('general', 383),
 ('sequences', 383),
 ('lee', 383),
 ('earlier', 382),
 ('points', 382),
 ('gone', 379),
 ('check', 379),
 ('ten', 378),
 ('suspense', 378),
 ('recommended', 378),
 ('business', 377),
 ('third', 377),
 ('beyond', 375),
 ('talk', 375),
 ('leaves', 375),
 ('portrayal', 374),
 ('beautifully', 373),
 ('bill', 372),
 ('single', 372),
 ('plenty', 371),
 ('word', 371),
 ('falls', 370),
 ('whom', 370),
 ('non', 369),
 ('battle', 369),
 ('figure', 369),
 ('scary', 369),
 ('return', 368),
 ('using', 368),
 ('doubt', 367),
 ('add', 367),
 ('hear', 366),
 ('solid', 366),
 ('success', 366),
 ('jokes', 365),
 ('touching', 365),
 ('political', 365),
 ('oh', 365),
 ('awesome', 364),
 ('hell', 364),
 ('boys', 364),
 ('sexual', 362),
 ('dog', 362),
 ('recently', 362),
 ('wouldn', 361),
 ('please', 361),
 ('features', 361),
 ('straight', 361),
 ('lack', 360),
 ('forget', 360),
 ('setting', 360),
 ('married', 359),
 ('mark', 359),
 ('social', 357),
 ('adventure', 356),
 ('interested', 356),
 ('terrific', 355),
 ('actual', 355),
 ('brothers', 355),
 ('sees', 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),
 ('smith', 345),
 ('screenplay', 345),
 ('towards', 344),
 ('hate', 344),
 ('noir', 343),
 ('kelly', 342),
 ('outstanding', 342),
 ('decent', 342),
 ('directors', 341),
 ('journey', 341),
 ('none', 340),
 ('looked', 340),
 ('effective', 340),
 ('cold', 339),
 ('caught', 339),
 ('storyline', 339),
 ('mary', 339),
 ('fi', 339),
 ('sci', 339),
 ('charming', 338),
 ('rich', 338),
 ('manages', 337),
 ('rare', 337),
 ('harry', 337),
 ('popular', 337),
 ('spirit', 336),
 ('open', 335),
 ('appreciate', 335),
 ('moves', 334),
 ('acted', 334),
 ('basically', 334),
 ('pace', 333),
 ('mention', 333),
 ('deserves', 333),
 ('inside', 333),
 ('subtle', 333),
 ('boring', 333),
 ('century', 333),
 ('background', 332),
 ('familiar', 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),
 ('saying', 325),
 ('intelligent', 325),
 ('realize', 324),
 ('scott', 324),
 ('material', 324),
 ('telling', 324),
 ('singing', 323),
 ('dancing', 322),
 ('visual', 321),
 ('imagine', 321),
 ('adult', 321),
 ('office', 320),
 ('kept', 320),
 ('uses', 319),
 ('pure', 318),
 ('stunning', 318),
 ('wait', 318),
 ('seriously', 317),
 ('review', 317),
 ('previous', 317),
 ('copy', 317),
 ('reading', 316),
 ('created', 316),
 ('somehow', 316),
 ('create', 316),
 ('magic', 316),
 ('hot', 316),
 ('frank', 315),
 ('air', 315),
 ('crazy', 315),
 ('attempt', 315),
 ('escape', 315),
 ('stay', 315),
 ('hands', 314),
 ('filled', 313),
 ('surprisingly', 312),
 ('expected', 312),
 ('average', 312),
 ('complex', 311),
 ('quickly', 310),
 ('successful', 310),
 ('studio', 310),
 ('male', 309),
 ('plus', 309),
 ('co', 307),
 ('following', 306),
 ('casting', 306),
 ('images', 306),
 ('minute', 306),
 ('exciting', 306),
 ('follows', 305),
 ('reasons', 305),
 ('e', 305),
 ('german', 305),
 ('themes', 305),
 ('members', 305),
 ('free', 304),
 ('genius', 304),
 ('cute', 304),
 ('touch', 304),
 ('edge', 304),
 ('outside', 303),
 ('reviews', 302),
 ('ok', 302),
 ('younger', 302),
 ('admit', 302),
 ('fighting', 301),
 ('odd', 301),
 ('master', 301),
 ('thanks', 300),
 ('comment', 300),
 ('recent', 300),
 ('break', 300),
 ('apart', 299),
 ('lovely', 298),
 ('begin', 298),
 ('emotions', 298),
 ('italian', 297),
 ('party', 297),
 ('doctor', 297),
 ('sequel', 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),
 ('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),
 ('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),
 ('captivating', 1.3862943611198906),
 ('davies', 1.3862943611198906),
 ('fisher', 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),
 ('holly', 1.2527629684953681),
 ('panic', 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),
 ('carrey', 0.98082925301172619),
 ('guilt', 0.98082925301172619),
 ('glover', 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),
 ('grim', 0.96873720724669754),
 ('lonely', 0.96873720724669754),
 ('sport', 0.96825047080486615),
 ('debut', 0.96508089604358704),
 ('destiny', 0.96343751029985703),
 ('thrillers', 0.96281074750904794),
 ('tears', 0.95977584381389391),
 ('rose', 0.95664202739772253),
 ('ginger', 0.95551144502743635),
 ('feelings', 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),
 ('norman', 0.89994159387262562),
 ('pleased', 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),
 ('subtitles', 0.88730319500090271),
 ('baseball', 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),
 ('modesty', 0.84342938360928321),
 ('craig', 0.84342938360928321),
 ('relate', 0.84326559685926517),
 ('episodes', 0.84223712084137292),
 ('strong', 0.84167135777060931),
 ('smith', 0.83959811108590054),
 ('tear', 0.83704136022001441),
 ('apartment', 0.83333115290549531),
 ('disagree', 0.83290912293510388),
 ('princess', 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),
 ('deals', 0.80535917116687328),
 ('traditional', 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),
 ('eyre', 0.79850769621777162),
 ('develops', 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),
 ('jean', 0.78845736036427028),
 ('environment', 0.78845736036427028),
 ('sentimental', 0.7864791203521645),
 ('captured', 0.78623760362595729),
 ('daring', 0.78592891401091158),
 ('styles', 0.78592891401091158),
 ('frank', 0.78275933924963248),
 ('backgrounds', 0.78275933924963248),
 ('tense', 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),
 ('sunday', 0.75666058628227129),
 ('titanic', 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),
 ('leslie', 0.74533293373051557),
 ('golden', 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),
 ('stylish', 0.69314718055994529),
 ('wave', 0.69314718055994529),
 ('affected', 0.69314718055994529),
 ('cowboy', 0.69314718055994529),
 ('britain', 0.69314718055994529),
 ('patient', 0.69314718055994529),
 ('beatty', 0.69314718055994529),
 ('meets', 0.69314718055994529),
 ('bitter', 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),
 ('striking', 0.66071190480679143),
 ('tricks', 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),
 ('demands', 0.65392646740666405),
 ('marriage', 0.65392646740666405),
 ('father', 0.65172321672194655),
 ('page', 0.65123628494430852),
 ('instant', 0.65058756614114943),
 ('era', 0.6495567444850836),
 ('saga', 0.64934455790155243),
 ('ruthless', 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),
 ('individual', 0.64313675998528386),
 ('pushing', 0.64313675998528386),
 ('meeting', 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),
 ('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),
 ('charismatic', 0.60613580357031549),
 ('peoples', 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),
 ('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),
 ('falk', 0.58525821854876026),
 ('morality', 0.58525821854876026),
 ('growing', 0.58466653756587539),
 ('stood', 0.58314628534561685),
 ('experiences', 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),
 ('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),
 ('variety', 0.56368911332305849),
 ('suspenseful', 0.56368911332305849),
 ('true', 0.56281525180810066),
 ('jr', 0.56220982311246936),
 ('psychological', 0.56108745854687891),
 ('odds', 0.55961578793542266),
 ('grand', 0.55961578793542266),
 ('wealth', 0.55961578793542266),
 ('sent', 0.55961578793542266),
 ('overwhelming', 0.55961578793542266),
 ('performing', 0.55961578793542266),
 ('reminiscent', 0.55961578793542266),
 ('branagh', 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),
 ('bug', 0.54654370636806993),
 ('disc', 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),
 ('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),
 ('dealt', 0.53408248593025787),
 ('share', 0.53408248593025787),
 ('providing', 0.53329847961804933),
 ('explore', 0.53329847961804933),
 ('series', 0.5325809226575603),
 ('fellow', 0.5323318289869543),
 ('olivier', 0.53062825106217038),
 ('roman', 0.53062825106217038),
 ('revolution', 0.53062825106217038),
 ('loves', 0.53062825106217038),
 ('century', 0.53002783074992665),
 ('musical', 0.52966871156747064),
 ('heroic', 0.52925932545482868),
 ('ironically', 0.52806743020049673),
 ('temple', 0.52806743020049673),
 ('approach', 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),
 ('alan', 0.51082562376599072),
 ('countryside', 0.51082562376599072),
 ('fits', 0.51082562376599072),
 ('visit', 0.51082562376599072),
 ('provided', 0.51082562376599072),
 ('aging', 0.51082562376599072),
 ('carter', 0.51082562376599072),
 ('ring', 0.51082562376599072),
 ('begins', 0.51015650363396647),
 ('japan', 0.50900578704900468),
 ('success', 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),
 ('investigation', 0.50262885656181222),
 ('shining', 0.50262885656181222),
 ('cameron', 0.5020919437972361),
 ('duo', 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),
 ('answers', 0.49578774640145024),
 ('league', 0.49578774640145024),
 ('helping', 0.49578774640145024),
 ('stunts', 0.49561620510246196),
 ('traveling', 0.49532143723002542),
 ('thoroughly', 0.49414593456733524),
 ('depicted', 0.49317068852726992),
 ('differences', 0.49247648509779424),
 ('combination', 0.49247648509779424),
 ('honor', 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),
 ('desperation', 0.48550781578170082),
 ('san', 0.48550781578170082),
 ('strongly', 0.48460242866688824),
 ('necessary', 0.48302334245403883),
 ('humanity', 0.48265474679929443),
 ('drama', 0.48221998493060503),
 ('cuba', 0.48183808689273838),
 ('warming', 0.48183808689273838),
 ('intrigue', 0.48183808689273838),
 ('nonetheless', 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),
 ('piano', 0.47260441094579297),
 ('cup', 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),
 ('inevitable', 0.46262352194811296),
 ('remains', 0.46262352194811296),
 ('soviet', 0.4618180446592961),
 ('ryan', 0.46134556650262099),
 ('african', 0.46112595521371813),
 ('smaller', 0.46081520319132935),
 ('techniques', 0.46052488529119184),
 ('information', 0.46034171833399862),
 ('deserved', 0.45999798712841444),
 ('tour', 0.45953232937844013),
 ('spielberg', 0.45953232937844013),
 ('lynch', 0.45953232937844013),
 ('francisco', 0.45953232937844013),
 ('cynical', 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),
 ('segments', 0.44701411102103689),
 ('closely', 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),
 ('web', 0.44183275227903923),
 ('closer', 0.44183275227903923),
 ('fame', 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', 0.43872232986464682),
 ('marry', 0.43861731542506488),
 ('oz', 0.43825493093115531),
 ('controversial', 0.43825493093115531),
 ('learned', 0.43825493093115531),
 ('slowly', 0.43785660389939979),
 ('thrilling', 0.43721380642274466),
 ('bridge', 0.43721380642274466),
 ('comedic', 0.43721380642274466),
 ('wayne', 0.43721380642274466),
 ('married', 0.43658501682196887),
 ('nazi', 0.4361020775700542),
 ('physical', 0.4353180712578455),
 ('murder', 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),
 ('enormous', 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]:





['',
 'magon',
 'reroutes',
 'malden',
 'timidity',
 'quickly',
 'oro',
 'eulogies',
 'viewability',
 'espace',
 'miniver',
 'colwell',
 'reliquary',
 'twentyish',
 'inescapeable',
 'ingnue',
 'foregoing',
 'wirework',
 'tactile',
 'toothy',
 'array',
 'dietrichesque',
 'hiroyuki',
 'pertwees',
 'syberia',
 'typed',
 'sounds',
 'armourae',
 'cleares',
 'foppishly',
 'mobius',
 'thunderdome',
 'critic',
 'mauri',
 'chih',
 'plump',
 'saath',
 'amiable',
 'guv',
 'abetted',
 'stave',
 'osmosis',
 'babelfish',
 'included',
 'differences',
 'caan',
 'jerkingly',
 'swarthy',
 'booboo',
 'sequins',
 'crept',
 'grandiosely',
 'vieila',
 'luved',
 'kayla',
 'angsty',
 'troyes',
 'todd',
 'reah',
 'weapon',
 'megas',
 'collapse',
 'dildo',
 'inconsistencies',
 'popwell',
 'onwhich',
 'samuari',
 'privateer',
 'grungy',
 'photograpy',
 'junctions',
 'unpopularity',
 'conquered',
 'division',
 'loutish',
 'undead',
 'hayman',
 'conroy',
 'loust',
 'moving',
 'precocious',
 'confiscating',
 'usb',
 'triffids',
 'shrimp',
 'xylophonist',
 'aaww',
 'arranging',
 'worth',
 'variety',
 'mavis',
 'waldron',
 'reties',
 'hitler',
 'ober',
 'smashing',
 'mykelti',
 'transpiring',
 'paresh',
 'nightfire',
 'misapprehension',
 'aguilera',
 'adrian',
 'shooked',
 'jocks',
 'artless',
 'pogees',
 'brutes',
 'enright',
 'fellatio',
 'petter',
 'alothugh',
 'ask',
 'flashman',
 'bakshki',
 'highpoints',
 'sedates',
 'inflected',
 'tape',
 'normalcy',
 'napolean',
 'behaviours',
 'schedules',
 'lagomorpha',
 'seeber',
 'skews',
 'overextended',
 'nieves',
 'fallin',
 'cheery',
 'massy',
 'inhibited',
 'metzger',
 'crass',
 'adder',
 'loyal',
 'commas',
 'hullabaloo',
 'resneck',
 'cinnamon',
 'embarking',
 'blackwell',
 'budget',
 'traumatized',
 'mirage',
 'miklos',
 'terse',
 'intensive',
 'mysterio',
 'sprog',
 'laddish',
 'committal',
 'reginal',
 'bootstraps',
 'cardinale',
 'lk',
 'neighbors',
 'fer',
 'accumulation',
 'stickers',
 'purply',
 'reassuringly',
 'unremembered',
 'ambricourt',
 'noirs',
 'wrangler',
 'lbs',
 'protection',
 'maruja',
 'parricide',
 'muss',
 'roadrunners',
 'stock',
 'ulaganaayakan',
 'blocky',
 'metaphysical',
 'cinematographed',
 'aachen',
 'psychological',
 'kirby',
 'telepathically',
 'traviata',
 'newsflash',
 'defrosts',
 'mathematical',
 'stark',
 'expanse',
 'sindhoor',
 'penguin',
 'gems',
 'median',
 'classist',
 'sargent',
 'charachter',
 'samples',
 'mazinger',
 'quarreled',
 'jodorowsky',
 'arigatou',
 'withouts',
 'farfetched',
 'vin',
 'kier',
 'worriedly',
 'stop',
 'equestrian',
 'heeeeaaarrt',
 'soutendijk',
 'tweeness',
 'yilmaz',
 'superceeds',
 'aspiring',
 'yamashiro',
 'malik',
 'soulplane',
 'mechanized',
 'jazzy',
 'flown',
 'raye',
 'divvies',
 'apps',
 'professorial',
 'moles',
 'limps',
 'mockingly',
 'imitate',
 'litel',
 'digestive',
 'ke',
 'timmy',
 'resentful',
 'bugsy',
 'grill',
 'dishonest',
 'utterance',
 'congradulations',
 'conquistadors',
 'innkeeper',
 'mooin',
 'watchers',
 'virtzer',
 'volckman',
 'twentysomething',
 'simmer',
 'laggan',
 'lajos',
 'ilha',
 'flea',
 'yuunagi',
 'lil',
 'monet',
 'beroemd',
 'asbestos',
 'teasers',
 'vipco',
 'sharon',
 'hopeless',
 'reunions',
 'despicably',
 'grimms',
 'flunks',
 'piracy',
 'slr',
 'lovett',
 'reformer',
 'proprietor',
 'cristal',
 'slavery',
 'essenay',
 'cumparsita',
 'feels',
 'barmen',
 'rouve',
 'interspersed',
 'expats',
 'resonant',
 'beneficence',
 'capiche',
 'discarded',
 'mindfck',
 'gingrich',
 'tidwell',
 'myths',
 'cinematography',
 'fiorentino',
 'impacted',
 'differentiates',
 'rancid',
 'fn',
 'yancey',
 'bol',
 'spinola',
 'hav',
 'burrowed',
 'bama',
 'snowman',
 'houses',
 'filmcritic',
 'halt',
 'exhorting',
 'rungs',
 'struggling',
 'indy',
 'toed',
 'bickle',
 'overanxious',
 'married',
 'loew',
 'encino',
 'indulge',
 'flatman',
 'authentically',
 'giallio',
 'incorrectness',
 'finance',
 'jianjun',
 'goldberg',
 'primitiveness',
 'rollerblades',
 'jam',
 'suv',
 'salute',
 'zenda',
 'magnification',
 'jorobado',
 'goff',
 'bogayevicz',
 'bleating',
 'talky',
 'communists',
 'tir',
 'pfcs',
 'subordinates',
 'kidnapper',
 'validates',
 'orchestrated',
 'facts',
 'backcountry',
 'turtledom',
 'jrvi',
 'tuengerthal',
 'stupefaction',
 'adolfo',
 'richter',
 'gregoire',
 'eyeroller',
 'shrewd',
 'tenma',
 'ohmigod',
 'upscale',
 'entwine',
 'wildfire',
 'banquet',
 'nothan',
 'evenings',
 'bare',
 'mortem',
 'bapu',
 'wags',
 'calcium',
 'weighing',
 'wiest',
 'leonard',
 'mischievousness',
 'flinstone',
 'farce',
 'commenters',
 'wales',
 'fintail',
 'mentions',
 'unbiased',
 'japrisot',
 'mendelito',
 'appreciably',
 'produce',
 'underestimation',
 'incinerate',
 'indigineous',
 'meyerling',
 'hypothesized',
 'ingemar',
 'schreiner',
 'qaida',
 'respectable',
 'screwy',
 'johhnie',
 'skateboards',
 'unforgiving',
 'floor',
 'lisbeth',
 'priscilla',
 'maitresse',
 'apparatus',
 'wall',
 'barring',
 'banu',
 'yodel',
 'traffic',
 'rumanian',
 'plumbers',
 'brisson',
 'eulogy',
 'akyroyd',
 'pongo',
 'sweid',
 'semana',
 'annick',
 'competitors',
 'kameena',
 'granville',
 'inventor',
 'chest',
 'backup',
 'homosexuals',
 'hoola',
 'roller',
 'crooning',
 'abstain',
 'ari',
 'rahm',
 'styalised',
 'offender',
 'zap',
 'implausible',
 'allan',
 'brag',
 'biryani',
 'madelyn',
 'amaturish',
 'constraining',
 'outlet',
 'amg',
 'delicates',
 'graduate',
 'lovelorn',
 'roz',
 'triton',
 'groteque',
 'beeping',
 'bathes',
 'normalos',
 'bentsen',
 'hino',
 'pangborn',
 'cosma',
 'lektor',
 'stanley',
 'backgroundother',
 'tall',
 'wagered',
 'profession',
 'consistancy',
 'lurched',
 'dunst',
 'bearing',
 'landmark',
 'montanas',
 'coed',
 'bugler',
 'overindulging',
 'roams',
 'obeys',
 'apparatchik',
 'olen',
 'kohl',
 'xenophobe',
 'authorize',
 'vadar',
 'reprises',
 'tarring',
 'natch',
 'mahiro',
 'convincedness',
 'southerners',
 'patronization',
 'garcea',
 'others',
 'ignacio',
 'silverado',
 'photographs',
 'programme',
 'hightailing',
 'verdant',
 'lai',
 'tenderloin',
 'admixtures',
 'think',
 'debunked',
 'disbarred',
 'betterthan',
 'couer',
 'parapluies',
 'grotty',
 'ramones',
 'kirkland',
 'damningly',
 'overcoat',
 'goodies',
 'counselor',
 'flashbacks',
 'masterbates',
 'exceptions',
 'prate',
 'wipe',
 'eighteen',
 'polymer',
 'luis',
 'hear',
 'gaff',
 'benot',
 'nautilus',
 'traveller',
 'ps',
 'suspenser',
 'slavoj',
 'pj',
 'aspiration',
 'lakeshore',
 'groaning',
 'jafar',
 'nevertheless',
 'derangement',
 'clio',
 'barricaded',
 'hungama',
 'guffawed',
 'lash',
 'shep',
 'dusting',
 'mhmmm',
 'realisation',
 'responsible',
 'gag',
 'signalman',
 'abrasive',
 'dissatisfaction',
 'fodder',
 'kyoko',
 'keepin',
 'wv',
 'accorded',
 'tredge',
 'morely',
 'portaraying',
 'descents',
 'edged',
 'investigates',
 'bouchet',
 'revived',
 'zippers',
 'fancy',
 'graduated',
 'magnificient',
 'dick',
 'homey',
 'duquenne',
 'huddle',
 'integrate',
 'unseasonably',
 'sharing',
 'michele',
 'masking',
 'ammonia',
 'unbenownst',
 'april',
 'emissaries',
 'afest',
 'swigs',
 'reamke',
 'necessitating',
 'spirits',
 'applewhite',
 'bering',
 'linguistically',
 'climbs',
 'diffuses',
 'grauman',
 'missourians',
 'frelling',
 'revels',
 'basque',
 'amusingly',
 'pythonesque',
 'scorscese',
 'contagonists',
 'downloading',
 'welcomes',
 'egyptologistic',
 'squids',
 'britt',
 'homesteading',
 'clay',
 'peugeot',
 'gelo',
 'farrago',
 'fieriness',
 'arthy',
 'alto',
 'conlin',
 'alrite',
 'santas',
 'blooded',
 'mizz',
 'heaps',
 'whatsername',
 'starringrichard',
 'ler',
 'heartwarming',
 'conversation',
 'embellishments',
 'reticent',
 'sandu',
 'scoffs',
 'dusenberry',
 'where',
 'dispatching',
 'gunfights',
 'camped',
 'affinit',
 'brawling',
 'encultured',
 'warships',
 'manley',
 'tolokonnikov',
 'mars',
 'evenhanded',
 'characther',
 'puffing',
 'ragno',
 'iben',
 'kangaroo',
 'whaddayagonndo',
 'watcxh',
 'ohara',
 'sheri',
 'obs',
 'wistfully',
 'ignite',
 'jewels',
 'framingham',
 'customer',
 'uo',
 'patroni',
 'evident',
 'aff',
 'dateless',
 'prepoire',
 'phiiistine',
 'bedding',
 'remarrying',
 'gogool',
 'jacquin',
 'handsomely',
 'byu',
 'trifecta',
 'haggardly',
 'gallagher',
 'inborn',
 'murky',
 'rankings',
 'boobage',
 'juries',
 'toysrus',
 'kinnison',
 'monograph',
 'confuses',
 'umbopa',
 'conformity',
 'splattered',
 'hereditary',
 'inveighing',
 'talos',
 'michalis',
 'perishable',
 'jang',
 'lloyed',
 'usurious',
 'shurikens',
 'contiguous',
 'sunk',
 'blustering',
 'orchestra',
 'titlesyou',
 'presenting',
 'knuckles',
 'puckett',
 'glamed',
 'delongpre',
 'ryder',
 'garrel',
 'mortitz',
 'awards',
 'disses',
 'glimpsing',
 'hyperdrive',
 'crocket',
 'ioc',
 'bigardo',
 'sedition',
 'lusciousness',
 'doc',
 'gah',
 'misconstrued',
 'hindenburg',
 'rapturously',
 'scheie',
 'stradling',
 'secretive',
 'enshrouded',
 'bait',
 'escorted',
 'exhude',
 'inroads',
 'shyer',
 'cohorts',
 'westerberg',
 'wickedness',
 'rookery',
 'amu',
 'leprachaun',
 'storing',
 'ballyhooed',
 'findlay',
 'sparse',
 'funnily',
 'deteriorating',
 'manmade',
 'noteworthy',
 'remembers',
 'vegtigris',
 'scoobidoo',
 'worshiper',
 'navigation',
 'supposedly',
 'janetty',
 'slobbery',
 'kenneth',
 'daivari',
 'martino',
 'huffing',
 'shor',
 'cineastic',
 'haynes',
 'pago',
 'bachman',
 'arsenical',
 'heldar',
 'steadying',
 'tak',
 'regehr',
 'pumps',
 'franchina',
 'omigod',
 'particulars',
 'recollects',
 'unpardonably',
 'prizzi',
 'newsstand',
 'maclaine',
 'unerring',
 'hormone',
 'thingamajigs',
 'pant',
 'bagpipe',
 'budah',
 'sexiest',
 'tybor',
 'cholesterol',
 'silences',
 'archie',
 'marcellous',
 'beautiful',
 'scummy',
 'nought',
 'giancaro',
 'autism',
 'crooke',
 'sics',
 'manheim',
 'konerak',
 'toretton',
 'parmistan',
 'karn',
 'rehearsal',
 'waterworld',
 'mutable',
 'netted',
 'stoltz',
 'indicate',
 'revelations',
 'brawl',
 'likelew',
 'irks',
 'dudikoff',
 'assures',
 'favourably',
 'hoyden',
 'sophisticatedly',
 'catweazle',
 'bankroll',
 'sorted',
 'remaking',
 'preferentiate',
 'comediennes',
 'guerro',
 'concider',
 'questionthat',
 'dexterity',
 'madison',
 'bogs',
 'graffitiing',
 'loyalk',
 'pr',
 'remarquable',
 'wsj',
 'burning',
 'morgana',
 'noah',
 'manhandled',
 'tooting',
 'thingie',
 'tiara',
 'montezuma',
 'foxy',
 'regiments',
 'amamoto',
 'fairies',
 'extraterrestrial',
 'professione',
 'wobbled',
 'transistions',
 'haywagon',
 'daimen',
 'slowness',
 'transceiver',
 'nova',
 'skyraiders',
 'sasural',
 'englishman',
 'activism',
 'roquevert',
 'meanies',
 'potentate',
 'opportunities',
 'evaluation',
 'invinicible',
 'aauugghh',
 'stalled',
 'phantasmagorical',
 'ho',
 'diss',
 'mountian',
 'bankers',
 'dushman',
 'doldrums',
 'fiascos',
 'arriba',
 'officialsall',
 'correl',
 'delores',
 'mulling',
 'gel',
 'syncher',
 'elvia',
 'prinze',
 'entertaingly',
 'proletarions',
 'interrogator',
 'benella',
 'inserted',
 'navigable',
 'quote',
 'timecop',
 'warthog',
 'tubed',
 'maronna',
 'drunk',
 'grandmas',
 'lesser',
 'lostlove',
 'arachnophobia',
 'subpaar',
 'mold',
 'we',
 'brull',
 'laura',
 'fragment',
 'carpet',
 'insatiable',
 'sais',
 'chainsaws',
 'dickenson',
 'conducting',
 'swath',
 'ohmagod',
 'eugenia',
 'jeez',
 'makutsi',
 'mailbox',
 'khmer',
 'foolhardy',
 'ghostly',
 'spurist',
 'darden',
 'iconic',
 'setup',
 'montgomery',
 'shift',
 'hte',
 'locally',
 'belyt',
 'humorous',
 'helsig',
 'wii',
 'bookthe',
 'absolutey',
 'roegs',
 'isolating',
 'accessed',
 'grigsby',
 'nourish',
 'dragoon',
 'realizable',
 'metabolism',
 'dbbe',
 'trusty',
 'msr',
 'reworked',
 'populations',
 'needlessly',
 'shud',
 'dupes',
 'portraited',
 'falseness',
 'paralleled',
 'crypton',
 'ferhan',
 'pelted',
 'mutually',
 'oldies',
 'ruination',
 'fistsof',
 'rrhs',
 'seasonal',
 'premeditated',
 'schmidt',
 'lehar',
 'moroni',
 'supplemented',
 'mumblecore',
 'magick',
 'giulio',
 'riefenstall',
 'hyroglyph',
 'nomenclature',
 'rashly',
 'excercise',
 'thundiiayil',
 'sewage',
 'thatwasjunk',
 'cipher',
 'sortie',
 'macanally',
 'chattered',
 'progressed',
 'jinx',
 'kumar',
 'cardona',
 'videodrome',
 'from',
 'rooted',
 'owned',
 'gunfight',
 'snazzily',
 'klondike',
 'mosaic',
 'devilment',
 'favorable',
 'inflexible',
 'technician',
 'tidal',
 'endorsing',
 'afl',
 'tractor',
 'casings',
 'renaldo',
 'professor',
 'sipping',
 'bonds',
 'goony',
 'trusted',
 'advocates',
 'stinging',
 'quotes',
 'interfering',
 'silencing',
 'arp',
 'apeshyt',
 'tested',
 'ran',
 ...]

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,
 'magon': 1,
 'reroutes': 2,
 'timidity': 4,
 'bashevis': 72656,
 'quickly': 5,
 'punted': 61478,
 'eulogies': 7,
 'computational': 12338,
 'espace': 9,
 'colwell': 11,
 'twentyish': 13,
 'inescapeable': 14,
 'ingnue': 15,
 'wirework': 17,
 'toothy': 19,
 'array': 20,
 'cinenephile': 12340,
 'dietrichesque': 21,
 'hiroyuki': 22,
 'behooves': 57918,
 'pertwees': 23,
 'intrudes': 65006,
 'armourae': 27,
 'cleares': 28,
 'foppishly': 29,
 'mobius': 30,
 'thunderdome': 31,
 'critic': 32,
 'thrifty': 57916,
 'chih': 34,
 'saath': 36,
 'extricates': 49177,
 'amiable': 37,
 'guv': 38,
 'abetted': 39,
 'stave': 40,
 'osmosis': 41,
 'babelfish': 42,
 'caan': 45,
 'differences': 44,
 'jerkingly': 46,
 'swarthy': 47,
 'miniver': 10,
 'troupe': 27046,
 'sequins': 49,
 'reallllllllly': 26018,
 'crept': 50,
 'grandiosely': 51,
 'tampax': 61484,
 'copyrighted': 65760,
 'vieila': 52,
 'luved': 53,
 'kayla': 54,
 'reliquary': 12,
 'troyes': 56,
 'todd': 57,
 'reah': 58,
 'weapon': 59,
 'megas': 60,
 'photograpy': 69,
 'dildo': 62,
 'inconsistencies': 63,
 'privateer': 67,
 'junctions': 70,
 'superbabies': 12348,
 'bustelo': 24600,
 'aristocats': 64903,
 'foregoing': 16,
 'conquered': 72,
 'contessa': 24603,
 'division': 73,
 'conroy': 77,
 'hayman': 76,
 'loust': 78,
 'resignedly': 49185,
 'moving': 79,
 'precocious': 80,
 'confiscating': 81,
 'usb': 82,
 'radiator': 48139,
 'shrimp': 84,
 'yawnaroony': 49187,
 'xylophonist': 85,
 'aaww': 86,
 'arranging': 87,
 'worth': 88,
 'variety': 89,
 'mavis': 90,
 'hitler': 93,
 'ober': 94,
 'mykelti': 96,
 'malice': 12351,
 'paresh': 98,
 'aguilera': 101,
 'adrian': 102,
 'artless': 105,
 'pogees': 106,
 'hardcastle': 12354,
 'kazuhiro': 67248,
 'fellatio': 109,
 'petter': 110,
 'alothugh': 111,
 'resolute': 36913,
 'ask': 112,
 'bakshki': 114,
 'mesmerized': 35301,
 'highpoints': 115,
 'sedates': 116,
 'inflected': 117,
 'tape': 118,
 'normalcy': 119,
 'lagomorpha': 123,
 'behaviours': 121,
 'seeber': 124,
 'overextended': 126,
 'nieves': 127,
 'massy': 130,
 'inhibited': 131,
 'metzger': 132,
 'crass': 133,
 'adder': 134,
 'loyal': 135,
 'hullabaloo': 137,
 'resneck': 138,
 'cinnamon': 139,
 'embarking': 140,
 'blackwell': 141,
 'budget': 142,
 'syberia': 24,
 'miklos': 145,
 'terse': 146,
 'sprog': 149,
 'wrenched': 36918,
 'laddish': 150,
 'committal': 151,
 'army': 19330,
 'reginal': 152,
 'bootstraps': 153,
 'cardinale': 154,
 'lk': 155,
 'neighbors': 156,
 'fer': 157,
 'accumulation': 158,
 'stickers': 159,
 'typed': 25,
 'reassuringly': 161,
 'unremembered': 162,
 'noirs': 164,
 'lbs': 166,
 'protection': 167,
 'parricide': 169,
 'thornhill': 49196,
 'muss': 170,
 'roadrunners': 171,
 'ulaganaayakan': 173,
 'blocky': 174,
 'metaphysical': 175,
 'eliason': 61503,
 'coughs': 63762,
 'paschendale': 49197,
 'aachen': 177,
 'shared': 52739,
 'psychological': 178,
 'muril': 61505,
 'kirby': 179,
 'telepathically': 180,
 'traviata': 181,
 'newsflash': 182,
 'insisting': 12363,
 'defrosts': 183,
 'mathematical': 184,
 'stark': 185,
 'expanse': 186,
 'sindhoor': 187,
 'leads': 67585,
 'median': 190,
 'gems': 189,
 'classist': 191,
 'charachter': 193,
 'samples': 194,
 'quarreled': 196,
 'arigatou': 198,
 'withouts': 199,
 'mauri': 33,
 'taht': 31609,
 'vin': 201,
 'kier': 202,
 'worriedly': 203,
 'stop': 204,
 'equestrian': 205,
 'heeeeaaarrt': 206,
 'ora': 49203,
 'yilmaz': 209,
 'superceeds': 210,
 'aspiring': 211,
 'soulplane': 214,
 'mechanized': 215,
 'limps': 223,
 'flown': 217,
 'raye': 218,
 'divvies': 219,
 'apps': 220,
 'moles': 222,
 'neikov': 12367,
 'expletives': 36932,
 'imitate': 225,
 'adaptor': 66860,
 'litel': 226,
 'digestive': 227,
 'ke': 228,
 'timmy': 229,
 'resentful': 230,
 'grill': 232,
 'utterance': 234,
 'maharajah': 61510,
 'congradulations': 235,
 'innkeeper': 237,
 'mooin': 238,
 'volckman': 241,
 'virtzer': 240,
 'flea': 247,
 'simmer': 243,
 'laggan': 244,
 'lajos': 245,
 'yuunagi': 248,
 'lil': 249,
 'monet': 250,
 'raunchiest': 28201,
 'included': 43,
 'beroemd': 251,
 'hilcox': 12370,
 'asbestos': 252,
 'yell': 49206,
 'teasers': 253,
 'vipco': 254,
 'sharon': 255,
 'hopeless': 256,
 'despicably': 258,
 'flunks': 260,
 'carnaby': 12374,
 'booboo': 48,
 'piracy': 261,
 'overlaid': 49210,
 'slr': 262,
 'playwriting': 18325,
 'lovett': 263,
 'vays': 12379,
 'abductee': 19481,
 'cristal': 266,
 'rosentrasse': 24636,
 'barmen': 271,
 'capiche': 277,
 'rouve': 272,
 'feels': 270,
 'expats': 274,
 'resonant': 275,
 'beneficence': 276,
 'discarded': 278,
 'moneypenny': 12380,
 'gingrich': 280,
 'tidwell': 281,
 'impacted': 285,
 'cinematography': 283,
 'fiorentino': 284,
 'shined': 18096,
 'differentiates': 286,
 'fn': 288,
 'cures': 12381,
 'yancey': 289,
 'bol': 290,
 'programs': 61516,
 'spinola': 291,
 'hav': 292,
 'whaddya': 4814,
 'burrowed': 293,
 'roebuck': 30739,
 'bama': 294,
 'snowman': 295,
 'filmcritic': 297,
 'halt': 298,
 'rungs': 300,
 'struggling': 301,
 'indy': 302,
 'toed': 303,
 'bickle': 304,
 'overanxious': 305,
 'married': 306,
 'loew': 307,
 'encino': 308,
 'giallio': 312,
 'flatman': 310,
 'authentically': 311,
 'incorrectness': 313,
 'finance': 314,
 'jianjun': 315,
 'rollerblades': 318,
 'suv': 320,
 'jorobado': 324,
 'magnification': 323,
 'goff': 325,
 'bogayevicz': 326,
 'bleating': 327,
 'enormously': 28044,
 'angsty': 55,
 'pfcs': 331,
 'communists': 329,
 'subordinates': 332,
 'kidnapper': 333,
 'validates': 334,
 'orchestrated': 335,
 'facts': 336,
 'backcountry': 337,
 'fumiya': 24645,
 'wendingo': 47307,
 'fabinyi': 12394,
 'jrvi': 339,
 'tuengerthal': 340,
 'stupefaction': 341,
 'adolfo': 342,
 'richter': 343,
 'gregoire': 344,
 'eyeroller': 345,
 'shrewd': 346,
 'gagging': 61531,
 'tenma': 347,
 'ohmigod': 348,
 'starships': 69514,
 'awakebarely': 24650,
 'bostwick': 57930,
 'entwine': 350,
 'banquet': 352,
 'collapse': 61,
 'nothan': 353,
 'evenings': 354,
 'bare': 355,
 'mortem': 356,
 'wags': 358,
 'ropey': 49231,
 'calcium': 359,
 'weighing': 360,
 'wiest': 361,
 'leonard': 362,
 'flinstone': 364,
 'raggedys': 67985,
 'farce': 365,
 'commenters': 366,
 'samuari': 66,
 'fintail': 368,
 'mentions': 369,
 'unbiased': 370,
 'japrisot': 371,
 'mendelito': 372,
 'produce': 374,
 'underestimation': 375,
 'fessenden': 36960,
 'indigineous': 377,
 'meyerling': 378,
 'ingemar': 380,
 'schreiner': 381,
 'qaida': 382,
 'recreations': 55936,
 'formulas': 58076,
 'respectable': 383,
 'johhnie': 385,
 'unforgiving': 387,
 'floor': 388,
 'considerations': 12403,
 'lisbeth': 389,
 'priscilla': 390,
 'maitresse': 391,
 'echoy': 36966,
 'apparatus': 392,
 'keillor': 55109,
 'beggins': 49240,
 'wall': 393,
 'banu': 395,
 'nuit': 62416,
 'traffic': 397,
 'comparitive': 36969,
 'plumbers': 399,
 'stotz': 12408,
 'brisson': 400,
 'annick': 406,
 'akyroyd': 402,
 'pongo': 403,
 'repo': 37945,
 'kameena': 408,
 'granville': 409,
 'inventor': 410,
 'backup': 412,
 'homosexuals': 413,
 'devotions': 61541,
 'abstain': 417,
 'styalised': 420,
 'jaret': 24664,
 'swapping': 12412,
 'offender': 421,
 'zap': 422,
 'allan': 424,
 'brag': 425,
 'madelyn': 427,
 'klangs': 53915,
 'amaturish': 428,
 'tibbets': 67986,
 'constraining': 429,
 'outlet': 430,
 'amg': 431,
 'orange': 50008,
 'undead': 75,
 'lovelorn': 434,
 'roz': 435,
 'triton': 436,
 'groteque': 437,
 'bathes': 439,
 'alleging': 71901,
 'valereon': 49244,
 'normalos': 440,
 'gallop': 24668,
 'bentsen': 441,
 'hino': 442,
 'cosma': 444,
 'hickcock': 61548,
 'sensitivity': 23415,
 'lektor': 445,
 'stanley': 446,
 'backgroundother': 447,
 'tall': 448,
 'doc': 700,
 'lurched': 452,
 'consistancy': 451,
 'calahan': 15367,
 'dunst': 453,
 'bearing': 454,
 'landmark': 455,
 'montanas': 456,
 'coed': 457,
 'borges': 12417,
 'bugler': 458,
 'waterboy': 61552,
 'overindulging': 459,
 'nuptials': 24671,
 'roams': 460,
 'pang': 70334,
 'obeys': 461,
 'apparatchik': 462,
 'olen': 463,
 'kohl': 464,
 'perceived': 10673,
 'xenophobe': 465,
 'authorize': 466,
 'vadar': 467,
 'reprises': 468,
 'tarring': 469,
 'natch': 470,
 'convincedness': 472,
 'southerners': 473,
 'patronization': 474,
 'ronet': 37882,
 'forefront': 36980,
 'garcea': 475,
 'foresees': 69410,
 'ignacio': 477,
 'blondel': 19101,
 'silverado': 478,
 'triffids': 83,
 'programme': 480,
 'opposite': 49250,
 'lai': 483,
 'tenderloin': 484,
 'admixtures': 485,
 'disbarred': 488,
 'dependence': 61354,
 'couer': 490,
 'parapluies': 491,
 'riser': 50557,
 'twister': 63897,
 'besting': 24677,
 'grotty': 492,
 'ramones': 493,
 'damningly': 495,
 'withdraws': 68305,
 'overcoat': 496,
 'reburn': 24678,
 'goodies': 497,
 'waldron': 91,
 'counselor': 498,
 'nightclub': 12422,
 'flashbacks': 499,
 'reties': 92,
 'masterbates': 500,
 'exceptions': 501,
 'eighteen': 504,
 'isaac': 36989,
 'catty': 29493,
 'polymer': 505,
 'gaff': 508,
 'hear': 507,
 'substitution': 36991,
 'nautilus': 510,
 'traveller': 511,
 'ps': 512,
 'aspiration': 516,
 'slavoj': 514,
 'lakeshore': 517,
 'johnathon': 54989,
 'clio': 522,
 'jafar': 519,
 'hungama': 524,
 'derangement': 521,
 'barricaded': 523,
 'guffawed': 525,
 'shooked': 103,
 'lash': 526,
 'shep': 527,
 'consignations': 67835,
 'dusting': 528,
 'mhmmm': 529,
 'realisation': 530,
 'responsible': 531,
 'gag': 532,
 'signalman': 533,
 'dissatisfaction': 535,
 'cs': 4784,
 'fodder': 536,
 'keepin': 538,
 'ingersoll': 69673,
 'deft': 49266,
 'accorded': 540,
 'tredge': 541,
 'morely': 542,
 'portaraying': 543,
 'descents': 544,
 'margin': 54705,
 'edged': 545,
 'bannings': 71840,
 'sheepishly': 38657,
 'bouchet': 547,
 'revived': 548,
 'zippers': 549,
 'fancy': 550,
 'magnificient': 552,
 'dick': 553,
 'unseasonably': 558,
 'duquenne': 555,
 'integrate': 557,
 'sharing': 559,
 'michele': 560,
 'masking': 561,
 'ammonia': 562,
 'ores': 12434,
 'unbenownst': 563,
 'brutes': 107,
 'april': 564,
 'kels': 49273,
 'afest': 566,
 'swigs': 567,
 'reamke': 568,
 'bering': 572,
 'frelling': 578,
 'applewhite': 571,
 'grauman': 576,
 'climbs': 574,
 'diffuses': 575,
 'incongruent': 65150,
 'revels': 579,
 'clothes': 12436,
 'annik': 59992,
 'amusingly': 581,
 'scorscese': 583,
 'ehrlich': 49362,
 'contagonists': 584,
 'downloading': 585,
 'welcomes': 586,
 'egyptologistic': 587,
 'friz': 24693,
 'homesteading': 590,
 'akira': 33842,
 'clay': 591,
 'allright': 3757,
 'peugeot': 592,
 'farrago': 594,
 'arthy': 596,
 'fahklempt': 24695,
 'alto': 597,
 'conlin': 598,
 'alrite': 599,
 'tammuz': 12183,
 'santas': 600,
 'hunnicutt': 56703,
 'blooded': 601,
 'heaps': 603,
 'bankrolled': 52468,
 'starringrichard': 605,
 'ler': 606,
 'embellishments': 609,
 'conversation': 608,
 'cokes': 49281,
 'reticent': 610,
 'sandu': 611,
 'dusenberry': 613,
 'where': 614,
 'cantankerous': 24701,
 'dispatching': 615,
 'affinit': 618,
 'camped': 617,
 'manley': 622,
 'tolokonnikov': 623,
 'liveliness': 63879,
 'mars': 624,
 'evenhanded': 625,
 'ragno': 628,
 'puffing': 627,
 'gunshot': 70903,
 'iben': 629,
 'ohara': 633,
 'whaddayagonndo': 631,
 'watcxh': 632,
 'sheri': 634,
 'ignite': 637,
 'dateless': 645,
 'framingham': 639,
 'customer': 640,
 'uo': 641,
 'patroni': 642,
 'evident': 643,
 'aff': 644,
 'gogool': 650,
 'prepoire': 646,
 'schedules': 122,
 'bedding': 648,
 'jacquin': 651,
 'haggardly': 655,
 'byu': 653,
 'inborn': 657,
 'gallagher': 656,
 'murky': 658,
 'monograph': 664,
 'juries': 661,
 'toysrus': 662,
 'forcible': 49293,
 'witchiepoo': 59320,
 'confuses': 665,
 'umbopa': 666,
 'experimentalism': 49289,
 'conformity': 667,
 'brain': 24709,
 'michalis': 672,
 'hereditary': 669,
 'inveighing': 670,
 'talos': 671,
 'jang': 674,
 'lloyed': 675,
 'shurikens': 677,
 'contiguous': 678,
 'sunk': 679,
 'fallin': 128,
 'blustering': 680,
 'orchestra': 681,
 'puckett': 685,
 'cheery': 129,
 'delongpre': 687,
 'jabberwocky': 24714,
 'ryder': 688,
 'garrel': 689,
 'mortitz': 690,
 'awards': 691,
 'disses': 692,
 'bethard': 37016,
 'glimpsing': 693,
 'hyperdrive': 694,
 'crocket': 695,
 'ioc': 696,
 'bigardo': 697,
 'conjure': 62183,
 'commas': 136,
 'sedition': 698,
 'lusciousness': 699,
 'misconstrued': 702,
 'wobble': 61586,
 'hindenburg': 703,
 'rapturously': 704,
 'scheie': 705,
 'stradling': 706,
 'secretive': 707,
 'enshrouded': 708,
 'bait': 709,
 'escorted': 710,
 'exhude': 711,
 'mirage': 144,
 'approaching': 54877,
 'inroads': 712,
 'invincibly': 52470,
 'vala': 37026,
 'shyer': 713,
 'cohorts': 714,
 'westerberg': 715,
 'decided': 14591,
 'wickedness': 716,
 'signing': 49304,
 'rookery': 717,
 'amu': 718,
 'leprachaun': 719,
 'storing': 720,
 'ballyhooed': 721,
 'intensive': 147,
 'findlay': 722,
 'chunks': 37031,
 'sparse': 723,
 'hurracanrana': 61593,
 'funnily': 724,
 'deteriorating': 725,
 'manmade': 726,
 'noteworthy': 727,
 'derisory': 61595,
 'scoobidoo': 730,
 'worshiper': 731,
 'navigation': 732,
 'supposedly': 733,
 'slobbery': 735,
 'kenneth': 736,
 'daivari': 737,
 'martino': 738,
 'huffing': 739,
 'cineastic': 741,
 'haynes': 742,
 'pago': 743,
 'bachman': 744,
 'henna': 29789,
 'arsenical': 745,
 'heldar': 746,
 'batman': 12458,
 'steadying': 747,
 'tak': 748,
 'pumps': 750,
 'franchina': 751,
 'omigod': 752,
 'particulars': 753,
 'recollects': 754,
 'prizzi': 756,
 'juggernaut': 64535,
 'piercing': 52474,
 'newsstand': 757,
 'thingamajigs': 761,
 'unerring': 759,
 'hormone': 760,
 'pant': 762,
 'bagpipe': 763,
 'malamud': 61606,
 'budah': 764,
 'sexiest': 765,
 'silences': 768,
 'archie': 769,
 'marcellous': 770,
 'beautiful': 771,
 'scummy': 772,
 'nought': 773,
 'manica': 37037,
 'autism': 775,
 'crooke': 776,
 'manheim': 778,
 'toretton': 780,
 'konerak': 779,
 'snipped': 24731,
 'karn': 782,
 'entertainingly': 65068,
 'rehearsal': 783,
 'waterworld': 784,
 'mutable': 785,
 'netted': 786,
 'stoltz': 787,
 'indicate': 788,
 'bidding': 37041,
 'revelations': 789,
 'brawl': 790,
 'likelew': 791,
 'irks': 792,
 'dudikoff': 793,
 'assures': 794,
 'chocula': 49313,
 'hoyden': 796,
 'catweazle': 798,
 'mandingo': 61611,
 'bankroll': 799,
 'sorted': 800,
 'remaking': 801,
 'publicist': 37047,
 'tiresomely': 24737,
 'preferentiate': 802,
 'chronopolis': 12466,
 'comediennes': 803,
 'guerro': 804,
 'conceives': 71220,
 'questionthat': 806,
 'greeted': 62977,
 'dexterity': 807,
 'madison': 808,
 'reminisce': 46868,
 'bogs': 809,
 'loyalties': 60551,
 'loyalk': 811,
 'disinformation': 12468,
 'pr': 812,
 'wsj': 814,
 'burning': 815,
 'invalidity': 24740,
 'balcans': 55557,
 'morgana': 816,
 'nacional': 37052,
 'noah': 817,
 'thingie': 820,
 'amamoto': 825,
 'tiara': 821,
 'purply': 160,
 'foxy': 823,
 'regiments': 824,
 'fluids': 73629,
 'ambricourt': 163,
 'fairies': 826,
 'extraterrestrial': 827,
 'transistions': 830,
 'wobbled': 829,
 'haywagon': 831,
 'amulet': 64169,
 'daimen': 832,
 'transceiver': 834,
 'skyraiders': 836,
 'nova': 835,
 'sasural': 837,
 'englishman': 838,
 'activism': 839,
 'roquevert': 840,
 'invinicible': 845,
 'potentate': 842,
 'opportunities': 843,
 'reviewers': 37057,
 'aauugghh': 846,
 'wrangler': 165,
 'stalled': 847,
 'nines': 49324,
 'phantasmagorical': 848,
 'ho': 849,
 'diss': 850,
 'bankers': 852,
 'hectic': 72004,
 'dushman': 853,
 'fiascos': 855,
 'arriba': 856,
 'officialsall': 857,
 'correl': 858,
 'mulling': 860,
 'actra': 70298,
 'gel': 861,
 'elvia': 863,
 'proletarions': 866,
 'entertaingly': 865,
 'interrogator': 867,
 'benella': 868,
 'navigable': 870,
 'quote': 871,
 'timecop': 872,
 'warthog': 873,
 'tubed': 874,
 'por': 12480,
 'pundits': 24746,
 'wilkes': 49331,
 'lily': 61728,
 'quagmires': 65180,
 'maronna': 875,
 'drunk': 876,
 'grandmas': 877,
 'ethnocentrism': 61624,
 'lesser': 878,
 'lostlove': 879,
 'arachnophobia': 880,
 'laura': 885,
 'mold': 882,
 'brull': 884,
 'kevnjeff': 12483,
 'fragment': 886,
 'boiled': 61628,
 'carpet': 887,
 'insatiable': 888,
 'sais': 889,
 'petulant': 24750,
 'chainsaws': 890,
 'dickenson': 891,
 'conducting': 892,
 'baler': 56770,
 'swath': 893,
 'ohmagod': 894,
 'memoir': 61631,
 'mailbox': 898,
 'jeez': 896,
 'foolhardy': 900,
 'khmer': 899,
 'pounced': 49334,
 'ghostly': 901,
 'darden': 903,
 'iconic': 904,
 'focusing': 49336,
 'helsig': 912,
 'montgomery': 906,
 'belyt': 910,
 'hte': 908,
 'locally': 909,
 'humorous': 911,
 'wii': 913,
 'bookthe': 914,
 'roegs': 916,
 'isolating': 917,
 'accessed': 918,
 'grigsby': 919,
 'nourish': 920,
 'wildcat': 45518,
 'realizable': 922,
 'metabolism': 923,
 'granny': 12488,
 'bulk': 37069,
 'dbbe': 924,
 'trusty': 925,
 'msr': 926,
 'portraited': 932,
 'needlessly': 929,
 'dupes': 931,
 'sleepovers': 73471,
 'networks': 55956,
 'falseness': 933,
 'covetous': 65991,
 'crypton': 935,
 'pelted': 937,
 'aout': 24758,
 'unstoppably': 61781,
 'gazing': 37073,
 'mutually': 938,
 'oldies': 939,
 'fistsof': 941,
 'rrhs': 942,
 'seasonal': 943,
 'premeditated': 944,
 'schmidt': 945,
 'lehar': 946,
 'moroni': 947,
 'supplemented': 948,
 'plexiglass': 71666,
 'mumblecore': 949,
 'rachael': 49343,
 'magick': 950,
 'riefenstall': 952,
 'hyroglyph': 953,
 'nomenclature': 954,
 'rashly': 955,
 'welker': 37076,
 'excercise': 956,
 'sewage': 958,
 'nekron': 61645,
 'thatwasjunk': 959,
 'wigstock': 64615,
 'chattered': 963,
 'sortie': 961,
 'macanally': 962,
 'progressed': 964,
 'jinx': 965,
 'kumar': 966,
 'cardona': 967,
 'videodrome': 968,
 'snazzily': 973,
 'rooted': 970,
 'owned': 971,
 'springsteen': 49349,
 'klondike': 974,
 'mosaic': 975,
 'devilment': 976,
 'famously': 37079,
 'ebing': 61650,
 'favorable': 977,
 'endorsing': 981,
 'technician': 979,
 'tidal': 980,
 'afl': 982,
 'goony': 989,
 'renaldo': 985,
 'bonds': 988,
 'sipping': 987,
 'advocates': 991,
 'stinging': 992,
 'quotes': 993,
 'silencing': 995,
 'arp': 996,
 'whimsically': 52730,
 'ballerina': 67609,
 'apeshyt': 997,
 'tested': 998,
 'ran': 999,
 'salesgirl': 66527,
 'refracting': 1004,
 'liebe': 1001,
 'scales': 1002,
 'baccalieri': 1003,
 'bleached': 1005,
 ...}

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 [55]:

    

labels[1]


    

    
Out[55]:





'NEGATIVE'

In [53]:

    

get_target_for_label(labels[1])


    

    
Out[53]:





0