In [1]:

    

def pretty_print_review_and_label(i):
    print(labels[i] + "\t:\t" + reviews[i][:80] + "...")

g = open('reviews.txt','r') # What we know!
reviews = list(map(lambda x:x[:-1],g.readlines()))
g.close()

g = open('labels.txt','r') # What we WANT to know!
labels = list(map(lambda x:x[:-1].upper(),g.readlines()))
g.close()


    

In [2]:

    

len(reviews)


    

    
Out[2]:





25000

In [3]:

    

reviews[0]


    

    
Out[3]:





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

In [4]:

    

labels[0]


    

    
Out[4]:





'POSITIVE'

In [5]:

    

print("labels.txt \t : \t reviews.txt\n")
pretty_print_review_and_label(2137)
pretty_print_review_and_label(12816)
pretty_print_review_and_label(6267)
pretty_print_review_and_label(21934)
pretty_print_review_and_label(5297)
pretty_print_review_and_label(4998)


    

    




labels.txt 	 : 	 reviews.txt

NEGATIVE	:	this movie is terrible but it has some good effects .  ...
POSITIVE	:	adrian pasdar is excellent is this film . he makes a fascinating woman .  ...
NEGATIVE	:	comment this movie is impossible . is terrible  very improbable  bad interpretat...
POSITIVE	:	excellent episode movie ala pulp fiction .  days   suicides . it doesnt get more...
NEGATIVE	:	if you haven  t seen this  it  s terrible . it is pure trash . i saw this about ...
POSITIVE	:	this schiffer guy is a real genius  the movie is of excellent quality and both e...

In [6]:

    

from collections import Counter
import numpy as np


    

In [7]:

    

positive_counts = Counter()
negative_counts = Counter()
total_counts = Counter()


    

In [8]:

    

for i in range(len(reviews)):
    if(labels[i] == 'POSITIVE'):
        for word in reviews[i].split(" "):
            positive_counts[word] += 1
            total_counts[word] += 1
    else:
        for word in reviews[i].split(" "):
            negative_counts[word] += 1
            total_counts[word] += 1


    

In [9]:

    

positive_counts.most_common()


    

    
Out[9]:





[('', 550468),
 ('the', 173324),
 ('.', 159654),
 ('and', 89722),
 ('a', 83688),
 ('of', 76855),
 ('to', 66746),
 ('is', 57245),
 ('in', 50215),
 ('br', 49235),
 ('it', 48025),
 ('i', 40743),
 ('that', 35630),
 ('this', 35080),
 ('s', 33815),
 ('as', 26308),
 ('with', 23247),
 ('for', 22416),
 ('was', 21917),
 ('film', 20937),
 ('but', 20822),
 ('movie', 19074),
 ('his', 17227),
 ('on', 17008),
 ('you', 16681),
 ('he', 16282),
 ('are', 14807),
 ('not', 14272),
 ('t', 13720),
 ('one', 13655),
 ('have', 12587),
 ('be', 12416),
 ('by', 11997),
 ('all', 11942),
 ('who', 11464),
 ('an', 11294),
 ('at', 11234),
 ('from', 10767),
 ('her', 10474),
 ('they', 9895),
 ('has', 9186),
 ('so', 9154),
 ('like', 9038),
 ('about', 8313),
 ('very', 8305),
 ('out', 8134),
 ('there', 8057),
 ('she', 7779),
 ('what', 7737),
 ('or', 7732),
 ('good', 7720),
 ('more', 7521),
 ('when', 7456),
 ('some', 7441),
 ('if', 7285),
 ('just', 7152),
 ('can', 7001),
 ('story', 6780),
 ('time', 6515),
 ('my', 6488),
 ('great', 6419),
 ('well', 6405),
 ('up', 6321),
 ('which', 6267),
 ('their', 6107),
 ('see', 6026),
 ('also', 5550),
 ('we', 5531),
 ('really', 5476),
 ('would', 5400),
 ('will', 5218),
 ('me', 5167),
 ('had', 5148),
 ('only', 5137),
 ('him', 5018),
 ('even', 4964),
 ('most', 4864),
 ('other', 4858),
 ('were', 4782),
 ('first', 4755),
 ('than', 4736),
 ('much', 4685),
 ('its', 4622),
 ('no', 4574),
 ('into', 4544),
 ('people', 4479),
 ('best', 4319),
 ('love', 4301),
 ('get', 4272),
 ('how', 4213),
 ('life', 4199),
 ('been', 4189),
 ('because', 4079),
 ('way', 4036),
 ('do', 3941),
 ('made', 3823),
 ('films', 3813),
 ('them', 3805),
 ('after', 3800),
 ('many', 3766),
 ('two', 3733),
 ('too', 3659),
 ('think', 3655),
 ('movies', 3586),
 ('characters', 3560),
 ('character', 3514),
 ('don', 3468),
 ('man', 3460),
 ('show', 3432),
 ('watch', 3424),
 ('seen', 3414),
 ('then', 3358),
 ('little', 3341),
 ('still', 3340),
 ('make', 3303),
 ('could', 3237),
 ('never', 3226),
 ('being', 3217),
 ('where', 3173),
 ('does', 3069),
 ('over', 3017),
 ('any', 3002),
 ('while', 2899),
 ('know', 2833),
 ('did', 2790),
 ('years', 2758),
 ('here', 2740),
 ('ever', 2734),
 ('end', 2696),
 ('these', 2694),
 ('such', 2590),
 ('real', 2568),
 ('scene', 2567),
 ('back', 2547),
 ('those', 2485),
 ('though', 2475),
 ('off', 2463),
 ('new', 2458),
 ('your', 2453),
 ('go', 2440),
 ('acting', 2437),
 ('plot', 2432),
 ('world', 2429),
 ('scenes', 2427),
 ('say', 2414),
 ('through', 2409),
 ('makes', 2390),
 ('better', 2381),
 ('now', 2368),
 ('work', 2346),
 ('young', 2343),
 ('old', 2311),
 ('ve', 2307),
 ('find', 2272),
 ('both', 2248),
 ('before', 2177),
 ('us', 2162),
 ('again', 2158),
 ('series', 2153),
 ('quite', 2143),
 ('something', 2135),
 ('cast', 2133),
 ('should', 2121),
 ('part', 2098),
 ('always', 2088),
 ('lot', 2087),
 ('another', 2075),
 ('actors', 2047),
 ('director', 2040),
 ('family', 2032),
 ('between', 2016),
 ('own', 2016),
 ('m', 1998),
 ('may', 1997),
 ('same', 1972),
 ('role', 1967),
 ('watching', 1966),
 ('every', 1954),
 ('funny', 1953),
 ('doesn', 1935),
 ('performance', 1928),
 ('few', 1918),
 ('bad', 1907),
 ('look', 1900),
 ('re', 1884),
 ('why', 1855),
 ('things', 1849),
 ('times', 1832),
 ('big', 1815),
 ('however', 1795),
 ('actually', 1790),
 ('action', 1789),
 ('going', 1783),
 ('bit', 1757),
 ('comedy', 1742),
 ('down', 1740),
 ('music', 1738),
 ('must', 1728),
 ('take', 1709),
 ('saw', 1692),
 ('long', 1690),
 ('right', 1688),
 ('fun', 1686),
 ('fact', 1684),
 ('excellent', 1683),
 ('around', 1674),
 ('didn', 1672),
 ('without', 1671),
 ('thing', 1662),
 ('thought', 1639),
 ('got', 1635),
 ('each', 1630),
 ('day', 1614),
 ('feel', 1597),
 ('seems', 1596),
 ('come', 1594),
 ('done', 1586),
 ('beautiful', 1580),
 ('especially', 1572),
 ('played', 1571),
 ('almost', 1566),
 ('want', 1562),
 ('yet', 1556),
 ('give', 1553),
 ('pretty', 1549),
 ('last', 1543),
 ('since', 1519),
 ('different', 1504),
 ('although', 1501),
 ('gets', 1490),
 ('true', 1487),
 ('interesting', 1481),
 ('job', 1470),
 ('enough', 1455),
 ('our', 1454),
 ('shows', 1447),
 ('horror', 1441),
 ('woman', 1439),
 ('tv', 1400),
 ('probably', 1398),
 ('father', 1395),
 ('original', 1393),
 ('girl', 1390),
 ('point', 1379),
 ('plays', 1378),
 ('wonderful', 1372),
 ('far', 1358),
 ('course', 1358),
 ('john', 1350),
 ('rather', 1340),
 ('isn', 1328),
 ('ll', 1326),
 ('later', 1324),
 ('dvd', 1324),
 ('whole', 1310),
 ('war', 1310),
 ('d', 1307),
 ('away', 1306),
 ('found', 1306),
 ('screen', 1305),
 ('nothing', 1300),
 ('year', 1297),
 ('once', 1296),
 ('hard', 1294),
 ('together', 1280),
 ('set', 1277),
 ('am', 1277),
 ('having', 1266),
 ('making', 1265),
 ('place', 1263),
 ('comes', 1260),
 ('might', 1260),
 ('sure', 1253),
 ('american', 1248),
 ('play', 1245),
 ('kind', 1244),
 ('perfect', 1242),
 ('takes', 1242),
 ('performances', 1237),
 ('himself', 1230),
 ('everyone', 1221),
 ('worth', 1221),
 ('anyone', 1214),
 ('actor', 1203),
 ('three', 1201),
 ('wife', 1196),
 ('classic', 1192),
 ('goes', 1186),
 ('ending', 1178),
 ('version', 1168),
 ('star', 1149),
 ('enjoy', 1146),
 ('book', 1142),
 ('nice', 1132),
 ('everything', 1128),
 ('during', 1124),
 ('put', 1118),
 ('seeing', 1111),
 ('least', 1102),
 ('house', 1100),
 ('high', 1095),
 ('watched', 1094),
 ('loved', 1087),
 ('men', 1087),
 ('night', 1082),
 ('anything', 1075),
 ('believe', 1071),
 ('guy', 1071),
 ('top', 1063),
 ('amazing', 1058),
 ('hollywood', 1056),
 ('looking', 1053),
 ('main', 1044),
 ('definitely', 1043),
 ('gives', 1031),
 ('home', 1029),
 ('seem', 1028),
 ('episode', 1023),
 ('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),
 ('picture', 833),
 ('children', 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),
 ('becomes', 729),
 ('despite', 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),
 ('stories', 696),
 ('days', 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),
 ('episodes', 657),
 ('budget', 657),
 ('relationship', 655),
 ('piece', 653),
 ('fantastic', 653),
 ('david', 651),
 ('turn', 648),
 ('murder', 646),
 ('parts', 645),
 ('brother', 644),
 ('absolutely', 643),
 ('head', 643),
 ('experience', 642),
 ('eyes', 641),
 ('sex', 638),
 ('called', 637),
 ('direction', 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),
 ('feeling', 619),
 ('already', 619),
 ('hit', 619),
 ('voice', 615),
 ('moment', 612),
 ('living', 612),
 ('supporting', 610),
 ('low', 610),
 ('ago', 609),
 ('themselves', 608),
 ('hilarious', 605),
 ('reality', 605),
 ('jack', 604),
 ('told', 603),
 ('hand', 601),
 ('dialogue', 600),
 ('moving', 600),
 ('quality', 600),
 ('happy', 599),
 ('song', 599),
 ('matter', 598),
 ('paul', 598),
 ('light', 594),
 ('future', 593),
 ('entire', 592),
 ('finds', 591),
 ('gave', 589),
 ('laugh', 587),
 ('released', 586),
 ('expect', 584),
 ('fight', 581),
 ('particularly', 580),
 ('police', 579),
 ('cinematography', 579),
 ('sound', 578),
 ('whose', 578),
 ('type', 578),
 ('view', 573),
 ('enjoyable', 573),
 ('husband', 572),
 ('number', 572),
 ('romantic', 572),
 ('daughter', 572),
 ('documentary', 571),
 ('self', 570),
 ('took', 569),
 ('robert', 569),
 ('modern', 569),
 ('superb', 569),
 ('mean', 566),
 ('shown', 563),
 ('coming', 561),
 ('important', 560),
 ('leave', 559),
 ('king', 559),
 ('change', 558),
 ('wanted', 555),
 ('somewhat', 555),
 ('tells', 554),
 ('country', 552),
 ('career', 552),
 ('events', 552),
 ('run', 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),
 ('miss', 535),
 ('opinion', 535),
 ('violence', 531),
 ('easy', 531),
 ('songs', 530),
 ('british', 528),
 ('says', 526),
 ('realistic', 525),
 ('writing', 524),
 ('writer', 522),
 ('act', 522),
 ('comic', 521),
 ('thriller', 519),
 ('television', 517),
 ('power', 516),
 ('ones', 515),
 ('kid', 514),
 ('york', 513),
 ('novel', 513),
 ('problem', 512),
 ('alone', 512),
 ('attention', 509),
 ('involved', 508),
 ('kill', 507),
 ('extremely', 507),
 ('seemed', 506),
 ('french', 505),
 ('hero', 505),
 ('rock', 504),
 ('stuff', 501),
 ('wish', 499),
 ('begins', 498),
 ('taken', 497),
 ('sad', 497),
 ('ways', 496),
 ('richard', 495),
 ('knows', 494),
 ('atmosphere', 493),
 ('car', 491),
 ('surprised', 491),
 ('taking', 491),
 ('similar', 491),
 ('perfectly', 490),
 ('george', 490),
 ('team', 489),
 ('sequence', 489),
 ('eye', 489),
 ('across', 489),
 ('room', 488),
 ('serious', 488),
 ('due', 488),
 ('powerful', 488),
 ('among', 488),
 ('strange', 487),
 ('b', 487),
 ('cannot', 487),
 ('order', 487),
 ('beauty', 486),
 ('famous', 485),
 ('happened', 484),
 ('myself', 484),
 ('herself', 484),
 ('tries', 484),
 ('class', 483),
 ('four', 482),
 ('cool', 481),
 ('release', 479),
 ('anyway', 479),
 ('theme', 479),
 ('opening', 478),
 ('entertainment', 477),
 ('unique', 475),
 ('exactly', 475),
 ('slow', 475),
 ('ends', 475),
 ('easily', 474),
 ('red', 474),
 ('o', 474),
 ('level', 474),
 ('interest', 472),
 ('happen', 471),
 ('crime', 470),
 ('viewing', 468),
 ('sets', 467),
 ('memorable', 467),
 ('group', 466),
 ('stop', 466),
 ('dance', 463),
 ('sister', 463),
 ('working', 463),
 ('problems', 463),
 ('message', 463),
 ('knew', 462),
 ('nature', 461),
 ('mystery', 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),
 ('tom', 452),
 ('form', 452),
 ('meets', 452),
 ('peter', 452),
 ('soundtrack', 452),
 ('usually', 452),
 ('local', 450),
 ('follow', 448),
 ('certain', 448),
 ('whether', 447),
 ('possible', 446),
 ('emotional', 445),
 ('de', 444),
 ('above', 444),
 ('killed', 444),
 ('god', 443),
 ('middle', 443),
 ('needs', 442),
 ('flick', 442),
 ('happens', 442),
 ('masterpiece', 441),
 ('period', 440),
 ('major', 440),
 ('haven', 439),
 ('named', 439),
 ('th', 438),
 ('particular', 438),
 ('feature', 437),
 ('earth', 437),
 ('stand', 436),
 ('typical', 435),
 ('words', 435),
 ('elements', 433),
 ('obviously', 433),
 ('romance', 431),
 ('jane', 430),
 ('yourself', 427),
 ('showing', 427),
 ('brings', 426),
 ('fantasy', 426),
 ('america', 423),
 ('guess', 423),
 ('huge', 422),
 ('unfortunately', 422),
 ('indeed', 421),
 ('running', 421),
 ('talent', 420),
 ('stage', 419),
 ('started', 418),
 ('leads', 417),
 ('sweet', 417),
 ('japanese', 417),
 ('poor', 416),
 ('deal', 416),
 ('incredible', 413),
 ('personal', 413),
 ('fast', 412),
 ('became', 410),
 ('deep', 410),
 ('hours', 409),
 ('dream', 408),
 ('giving', 408),
 ('nearly', 408),
 ('clearly', 407),
 ('turned', 407),
 ('obvious', 406),
 ('near', 406),
 ('cut', 405),
 ('surprise', 405),
 ('era', 404),
 ('body', 404),
 ('hour', 403),
 ('five', 403),
 ('female', 403),
 ('note', 399),
 ('learn', 398),
 ('truth', 398),
 ('feels', 397),
 ('except', 397),
 ('match', 397),
 ('tony', 397),
 ('clear', 394),
 ('complete', 394),
 ('filmed', 394),
 ('eventually', 393),
 ('older', 393),
 ('street', 393),
 ('lots', 393),
 ('keeps', 393),
 ('buy', 392),
 ('william', 391),
 ('stewart', 391),
 ('meet', 390),
 ('joe', 390),
 ('fall', 390),
 ('difficult', 389),
 ('talking', 389),
 ('rating', 389),
 ('shots', 389),
 ('unlike', 389),
 ('dramatic', 388),
 ('means', 388),
 ('subject', 386),
 ('appears', 386),
 ('situation', 386),
 ('present', 386),
 ('wonder', 386),
 ('comments', 385),
 ('lee', 383),
 ('general', 383),
 ('sequences', 383),
 ('points', 382),
 ('earlier', 382),
 ('gone', 379),
 ('check', 379),
 ('ten', 378),
 ('suspense', 378),
 ('recommended', 378),
 ('third', 377),
 ('business', 377),
 ('beyond', 375),
 ('talk', 375),
 ('leaves', 375),
 ('portrayal', 374),
 ('beautifully', 373),
 ('single', 372),
 ('bill', 372),
 ('word', 371),
 ('plenty', 371),
 ('whom', 370),
 ('falls', 370),
 ('battle', 369),
 ('scary', 369),
 ('figure', 369),
 ('non', 369),
 ('return', 368),
 ('using', 368),
 ('add', 367),
 ('doubt', 367),
 ('success', 366),
 ('hear', 366),
 ('solid', 366),
 ('touching', 365),
 ('political', 365),
 ('oh', 365),
 ('jokes', 365),
 ('hell', 364),
 ('boys', 364),
 ('awesome', 364),
 ('sexual', 362),
 ('dog', 362),
 ('recently', 362),
 ('features', 361),
 ('wouldn', 361),
 ('straight', 361),
 ('please', 361),
 ('lack', 360),
 ('setting', 360),
 ('forget', 360),
 ('married', 359),
 ('mark', 359),
 ('social', 357),
 ('interested', 356),
 ('adventure', 356),
 ('brothers', 355),
 ('actual', 355),
 ('sees', 355),
 ('terrific', 355),
 ('call', 354),
 ('move', 354),
 ('dr', 353),
 ('theater', 353),
 ('various', 353),
 ('animated', 352),
 ('western', 351),
 ('space', 350),
 ('baby', 350),
 ('leading', 348),
 ('disappointed', 348),
 ('portrayed', 346),
 ('aren', 346),
 ('smith', 345),
 ('screenplay', 345),
 ('hate', 344),
 ('towards', 344),
 ('noir', 343),
 ('outstanding', 342),
 ('kelly', 342),
 ('decent', 342),
 ('directors', 341),
 ('journey', 341),
 ('effective', 340),
 ('looked', 340),
 ('none', 340),
 ('sci', 339),
 ('fi', 339),
 ('caught', 339),
 ('mary', 339),
 ('cold', 339),
 ('storyline', 339),
 ('charming', 338),
 ('rich', 338),
 ('harry', 337),
 ('manages', 337),
 ('popular', 337),
 ('rare', 337),
 ('spirit', 336),
 ('appreciate', 335),
 ('open', 335),
 ('moves', 334),
 ('basically', 334),
 ('acted', 334),
 ('pace', 333),
 ('deserves', 333),
 ('mention', 333),
 ('inside', 333),
 ('century', 333),
 ('boring', 333),
 ('subtle', 333),
 ('familiar', 332),
 ('background', 332),
 ('ben', 331),
 ('creepy', 330),
 ('supposed', 330),
 ('secret', 329),
 ('jim', 328),
 ('die', 328),
 ('natural', 327),
 ('effect', 327),
 ('question', 327),
 ('language', 326),
 ('rate', 326),
 ('impressive', 326),
 ('intelligent', 325),
 ('saying', 325),
 ('telling', 324),
 ('material', 324),
 ('realize', 324),
 ('scott', 324),
 ('singing', 323),
 ('dancing', 322),
 ('adult', 321),
 ('imagine', 321),
 ('visual', 321),
 ('kept', 320),
 ('office', 320),
 ('uses', 319),
 ('stunning', 318),
 ('pure', 318),
 ('wait', 318),
 ('previous', 317),
 ('review', 317),
 ('copy', 317),
 ('seriously', 317),
 ('hot', 316),
 ('reading', 316),
 ('create', 316),
 ('magic', 316),
 ('somehow', 316),
 ('created', 316),
 ('air', 315),
 ('crazy', 315),
 ('escape', 315),
 ('attempt', 315),
 ('frank', 315),
 ('stay', 315),
 ('hands', 314),
 ('filled', 313),
 ('surprisingly', 312),
 ('expected', 312),
 ('average', 312),
 ('complex', 311),
 ('successful', 310),
 ('studio', 310),
 ('quickly', 310),
 ('male', 309),
 ('plus', 309),
 ('co', 307),
 ('casting', 306),
 ('minute', 306),
 ('following', 306),
 ('exciting', 306),
 ('images', 306),
 ('members', 305),
 ('e', 305),
 ('follows', 305),
 ('reasons', 305),
 ('themes', 305),
 ('german', 305),
 ('cute', 304),
 ('free', 304),
 ('genius', 304),
 ('edge', 304),
 ('touch', 304),
 ('outside', 303),
 ('younger', 302),
 ('admit', 302),
 ('reviews', 302),
 ('ok', 302),
 ('fighting', 301),
 ('master', 301),
 ('odd', 301),
 ('thanks', 300),
 ('break', 300),
 ('comment', 300),
 ('recent', 300),
 ('apart', 299),
 ('begin', 298),
 ('emotions', 298),
 ('lovely', 298),
 ('doctor', 297),
 ('party', 297),
 ('italian', 297),
 ('la', 296),
 ('sequel', 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),
 ('extraordinary', 1.6094379124341003),
 ('sullivan', 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),
 ('fisher', 1.3862943611198906),
 ('captivating', 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),
 ('philip', 1.2527629684953681),
 ('holly', 1.2527629684953681),
 ('carol', 1.2481440226390734),
 ('perfect', 1.246742480713785),
 ('appreciated', 1.2462482874741743),
 ('favourite', 1.2411123512753928),
 ('journey', 1.2367626271489269),
 ('rural', 1.235471471385307),
 ('bond', 1.2321436812926323),
 ('builds', 1.2305398317106577),
 ('brilliant', 1.2287554137664785),
 ('brooklyn', 1.2286654169163074),
 ('von', 1.225175011976539),
 ('recommended', 1.2163953243244932),
 ('unfolds', 1.2163953243244932),
 ('daniel', 1.20215296760895),
 ('perfectly', 1.1971931173405572),
 ('crafted', 1.1962507582320256),
 ('prince', 1.1939224684724346),
 ('troubled', 1.192138346678933),
 ('consequences', 1.1865810616140668),
 ('haunting', 1.1814999484738773),
 ('cinderella', 1.180052620608284),
 ('alexander', 1.1759989522835299),
 ('emotions', 1.1753049094563641),
 ('boxing', 1.1735135968412274),
 ('subtle', 1.1734135017508081),
 ('curtis', 1.1649873576129823),
 ('rare', 1.1566438362402944),
 ('loved', 1.1563661500586044),
 ('daughters', 1.1526795099383853),
 ('courage', 1.1438688802562305),
 ('dentist', 1.1426722784621401),
 ('highly', 1.1420208631618658),
 ('nominated', 1.1409146683587992),
 ('tony', 1.1397491942285991),
 ('draws', 1.1325138403437911),
 ('everyday', 1.1306150197542835),
 ('contrast', 1.1284652518177909),
 ('cried', 1.1213405397456659),
 ('fabulous', 1.1210851445201684),
 ('ned', 1.120591195386885),
 ('fay', 1.120591195386885),
 ('emma', 1.1184149159642893),
 ('sensitive', 1.113318436057805),
 ('smooth', 1.1089750757036563),
 ('dramas', 1.1080910326226534),
 ('today', 1.1050431789984001),
 ('helps', 1.1023091505494358),
 ('inspiring', 1.0986122886681098),
 ('jimmy', 1.0937696641923216),
 ('awesome', 1.0931328229034842),
 ('unique', 1.0881409888008142),
 ('tragic', 1.0871835928444868),
 ('intense', 1.0870514662670339),
 ('stellar', 1.0857088838322018),
 ('rival', 1.0822184788924332),
 ('provides', 1.0797081340289569),
 ('depression', 1.0782034170369026),
 ('shy', 1.0775588794702773),
 ('carrie', 1.076139432816051),
 ('blend', 1.0753554265038423),
 ('hank', 1.0736109864626924),
 ('diana', 1.0726368022648489),
 ('adorable', 1.0726368022648489),
 ('unexpected', 1.0722255334949147),
 ('achievement', 1.0668635903535293),
 ('bettie', 1.0663514264498881),
 ('happiness', 1.0632729222228008),
 ('glorious', 1.0608719606852626),
 ('davis', 1.0541605260972757),
 ('terrifying', 1.0525211814678428),
 ('beauty', 1.050410186850232),
 ('ideal', 1.0479685558493548),
 ('fears', 1.0467872208035236),
 ('hong', 1.0438040521731147),
 ('seasons', 1.0433496099930604),
 ('fascinating', 1.0414538748281612),
 ('carries', 1.0345904299031787),
 ('satisfying', 1.0321225473992768),
 ('definite', 1.0319209141694374),
 ('touched', 1.0296194171811581),
 ('greatest', 1.0248947127715422),
 ('creates', 1.0241097613701886),
 ('aunt', 1.023388867430522),
 ('walter', 1.022328983918479),
 ('spectacular', 1.0198314108149955),
 ('portrayal', 1.0189810189761024),
 ('ann', 1.0127808528183286),
 ('enterprise', 1.0116009116784799),
 ('musicals', 1.0096648026516135),
 ('deeply', 1.0094845087721023),
 ('incredible', 1.0061677561461084),
 ('mature', 1.0060195018402847),
 ('triumph', 0.99682959435816731),
 ('margaret', 0.99682959435816731),
 ('navy', 0.99493385919326827),
 ('harry', 0.99176919305006062),
 ('lucas', 0.990398704027877),
 ('sweet', 0.98966110487955483),
 ('joey', 0.98794672078059009),
 ('oscar', 0.98721905111049713),
 ('balance', 0.98649499054740353),
 ('warm', 0.98485340331145166),
 ('ages', 0.98449898190068863),
 ('carrey', 0.98082925301172619),
 ('glover', 0.98082925301172619),
 ('guilt', 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),
 ('eerie', 0.97116734209998934),
 ('vhs', 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),
 ('mysteries', 0.92953595862417571),
 ('hal', 0.92953595862417571),
 ('louis', 0.92871325187271225),
 ('charming', 0.92520609553210742),
 ('urban', 0.92367083917177761),
 ('allows', 0.92183091224977043),
 ('impact', 0.91815814604895041),
 ('lifestyle', 0.91629073187415511),
 ('italy', 0.91629073187415511),
 ('gradually', 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),
 ('baseball', 0.88730319500090271),
 ('bleak', 0.88730319500090271),
 ('subtitles', 0.88730319500090271),
 ('winner', 0.88643776872447388),
 ('tragedy', 0.88563699078315261),
 ('todd', 0.88551907320740142),
 ('nicely', 0.87924946019380601),
 ('arthur', 0.87546873735389985),
 ('essential', 0.87373111745535925),
 ('gorgeous', 0.8731725250935497),
 ('fonda', 0.87294029100054127),
 ('eastwood', 0.87139541196626402),
 ('focuses', 0.87082835779739776),
 ('enjoyed', 0.87070195951624607),
 ('natural', 0.86997924506912838),
 ('intensity', 0.86835126958503595),
 ('witty', 0.86824103423244681),
 ('rob', 0.8642954367557748),
 ('worlds', 0.86377269759070874),
 ('health', 0.86113891179907498),
 ('magical', 0.85953791528170564),
 ('deeper', 0.85802182375017932),
 ('lucy', 0.85618680780444956),
 ('moving', 0.85566611005772031),
 ('lovely', 0.85290640004681306),
 ('purple', 0.8513711857748395),
 ('memorable', 0.84801189112086062),
 ('sings', 0.84729786038720367),
 ('craig', 0.84342938360928321),
 ('modesty', 0.84342938360928321),
 ('relate', 0.84326559685926517),
 ('episodes', 0.84223712084137292),
 ('strong', 0.84167135777060931),
 ('smith', 0.83959811108590054),
 ('tear', 0.83704136022001441),
 ('apartment', 0.83333115290549531),
 ('princess', 0.83290912293510388),
 ('disagree', 0.83290912293510388),
 ('kung', 0.83173334384609199),
 ('adventure', 0.83150561393278388),
 ('columbo', 0.82667857318446791),
 ('jake', 0.82667857318446791),
 ('adds', 0.82485652591452319),
 ('hart', 0.82472353834866463),
 ('strength', 0.82417544296634937),
 ('realizes', 0.82360006895738058),
 ('dave', 0.8232003088081431),
 ('childhood', 0.82208086393583857),
 ('forbidden', 0.81989888619908913),
 ('tight', 0.81883539572344199),
 ('surreal', 0.8178506590609026),
 ('manager', 0.81770990320170756),
 ('dancer', 0.81574950265227764),
 ('studios', 0.81093021621632877),
 ('con', 0.81093021621632877),
 ('miike', 0.80821651034473263),
 ('realistic', 0.80807714723392232),
 ('explicit', 0.80792269515237358),
 ('kurt', 0.8060875917405409),
 ('traditional', 0.80535917116687328),
 ('deals', 0.80535917116687328),
 ('holds', 0.80493858654806194),
 ('carl', 0.80437281567016972),
 ('touches', 0.80396154690023547),
 ('gene', 0.80314807577427383),
 ('albert', 0.8027669055771679),
 ('abc', 0.80234647252493729),
 ('cry', 0.80011930011211307),
 ('sides', 0.7995275841185171),
 ('develops', 0.79850769621777162),
 ('eyre', 0.79850769621777162),
 ('dances', 0.79694397424158891),
 ('oscars', 0.79633141679517616),
 ('legendary', 0.79600456599965308),
 ('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),
 ('daring', 0.78592891401091158),
 ('styles', 0.78592891401091158),
 ('tense', 0.78275933924963248),
 ('frank', 0.78275933924963248),
 ('backgrounds', 0.78275933924963248),
 ('matches', 0.78275933924963248),
 ('gothic', 0.78209466657644144),
 ('sharp', 0.7814397877056235),
 ('achieved', 0.78015855754957497),
 ('court', 0.77947526404844247),
 ('steals', 0.7789140023173704),
 ('rules', 0.77844476107184035),
 ('colors', 0.77684619943659217),
 ('reunion', 0.77318988823348167),
 ('covers', 0.77139937745969345),
 ('tale', 0.77010822169607374),
 ('rain', 0.7683706017975328),
 ('denzel', 0.76804848873306297),
 ('stays', 0.76787072675588186),
 ('blob', 0.76725515271366718),
 ('maria', 0.76214005204689672),
 ('conventional', 0.76214005204689672),
 ('fresh', 0.76158434211317383),
 ('midnight', 0.76096977689870637),
 ('landscape', 0.75852993982279704),
 ('animated', 0.75768570169751648),
 ('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),
 ('nowadays', 0.74721440183022114),
 ('memories', 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),
 ('florida', 0.73511137965897755),
 ('influenced', 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),
 ('brad', 0.71024161391924534),
 ('charlie', 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),
 ('bitter', 0.69314718055994529),
 ('beatty', 0.69314718055994529),
 ('britain', 0.69314718055994529),
 ('affected', 0.69314718055994529),
 ('cowboy', 0.69314718055994529),
 ('meets', 0.69314718055994529),
 ('wave', 0.69314718055994529),
 ('patient', 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),
 ('directs', 0.67875844310784572),
 ('rebel', 0.67875844310784572),
 ('greater', 0.67605274720064523),
 ('dreams', 0.67599410133369586),
 ('effective', 0.67565402311242806),
 ('interpretation', 0.67479804189174875),
 ('brando', 0.67445504754779284),
 ('works', 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),
 ('ruthless', 0.64934455790155243),
 ('saga', 0.64934455790155243),
 ('joan', 0.64891392558311978),
 ('joseph', 0.64841128671855386),
 ('workers', 0.64829661439459352),
 ('fantasy', 0.64726757480925168),
 ('distant', 0.64551913157069074),
 ('accomplished', 0.64551913157069074),
 ('manhattan', 0.64435701639051324),
 ('personal', 0.64355023942057321),
 ('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),
 ('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),
 ('ultimate', 0.62168821657780038),
 ('artist', 0.62168821657780038),
 ('griffith', 0.62117368093485603),
 ('drew', 0.62082651898031915),
 ('emily', 0.62082651898031915),
 ('moved', 0.6197197120051281),
 ('families', 0.61903920840622351),
 ('profound', 0.61903920840622351),
 ('innocent', 0.61851219917136446),
 ('versions', 0.61730910416844087),
 ('eddie', 0.61691981517206107),
 ('criticism', 0.61651395453902935),
 ('nature', 0.61594514653194088),
 ('recognized', 0.61518563909023349),
 ('sexuality', 0.61467556511845012),
 ('contract', 0.61400986000122149),
 ('brian', 0.61344043794920278),
 ('remembered', 0.6131044728864089),
 ('determined', 0.6123858239154869),
 ('offers', 0.61207935747116349),
 ('pleasure', 0.61195702582993206),
 ('washington', 0.61180154110599294),
 ('images', 0.61159731359583758),
 ('games', 0.61067095873570676),
 ('academy', 0.60872983874736208),
 ('fashioned', 0.60798937221963845),
 ('melodrama', 0.60749173598145145),
 ('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),
 ('brady', 0.59911823091166894),
 ('shine', 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),
 ('french', 0.5720692490067093),
 ('personalities', 0.5720692490067093),
 ('surprises', 0.57113222999698177),
 ('adventures', 0.57113222999698177),
 ('overcome', 0.5697681593994407),
 ('timothy', 0.56953322459276867),
 ('tales', 0.56909453188996639),
 ('war', 0.56843317302781682),
 ('civil', 0.5679840376059393),
 ('countries', 0.56737779327091187),
 ('streep', 0.56710645966458029),
 ('tradition', 0.56685345523565323),
 ('oliver', 0.56673325570428668),
 ('australia', 0.56580775818334383),
 ('understanding', 0.56531380905006046),
 ('players', 0.56509525370004821),
 ('knowing', 0.56489284503626647),
 ('rogers', 0.56421349718405212),
 ('suspenseful', 0.56368911332305849),
 ('variety', 0.56368911332305849),
 ('true', 0.56281525180810066),
 ('jr', 0.56220982311246936),
 ('psychological', 0.56108745854687891),
 ('branagh', 0.55961578793542266),
 ('grand', 0.55961578793542266),
 ('wealth', 0.55961578793542266),
 ('sent', 0.55961578793542266),
 ('odds', 0.55961578793542266),
 ('reminiscent', 0.55961578793542266),
 ('overwhelming', 0.55961578793542266),
 ('performing', 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),
 ('greek', 0.5389965007326869),
 ('stands', 0.5389965007326869),
 ('trial', 0.5389965007326869),
 ('hamilton', 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),
 ('revolution', 0.53062825106217038),
 ('loves', 0.53062825106217038),
 ('roman', 0.53062825106217038),
 ('olivier', 0.53062825106217038),
 ('century', 0.53002783074992665),
 ('musical', 0.52966871156747064),
 ('heroic', 0.52925932545482868),
 ('approach', 0.52806743020049673),
 ('temple', 0.52806743020049673),
 ('ironically', 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),
 ('demons', 0.5191244265806858),
 ('performed', 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),
 ('jeremy', 0.51466440007315639),
 ('appearances', 0.51466440007315639),
 ('fun', 0.51439068993048687),
 ('south', 0.51420972175023116),
 ('arrives', 0.51409894911095988),
 ('present', 0.51341965894303732),
 ('com', 0.51326167856387173),
 ('smile', 0.51265880484765169),
 ('countryside', 0.51082562376599072),
 ('alan', 0.51082562376599072),
 ('visit', 0.51082562376599072),
 ('provided', 0.51082562376599072),
 ('fits', 0.51082562376599072),
 ('carter', 0.51082562376599072),
 ('aging', 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),
 ('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),
 ('helping', 0.49578774640145024),
 ('league', 0.49578774640145024),
 ('answers', 0.49578774640145024),
 ('stunts', 0.49561620510246196),
 ('traveling', 0.49532143723002542),
 ('thoroughly', 0.49414593456733524),
 ('depicted', 0.49317068852726992),
 ('differences', 0.49247648509779424),
 ('honor', 0.49247648509779424),
 ('combination', 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),
 ('desperation', 0.48550781578170082),
 ('guide', 0.48550781578170082),
 ('san', 0.48550781578170082),
 ('companion', 0.48550781578170082),
 ('julia', 0.48550781578170082),
 ('strongly', 0.48460242866688824),
 ('necessary', 0.48302334245403883),
 ('humanity', 0.48265474679929443),
 ('drama', 0.48221998493060503),
 ('intrigue', 0.48183808689273838),
 ('warming', 0.48183808689273838),
 ('cuba', 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),
 ('cup', 0.47260441094579297),
 ('piano', 0.47260441094579297),
 ('familiar', 0.47241617565111949),
 ('sinister', 0.47198579044972683),
 ('reveal', 0.47171449364936496),
 ('max', 0.47150852042515579),
 ('dated', 0.47121648567094482),
 ('discovery', 0.47000362924573563),
 ('losing', 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),
 ('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),
 ('lynch', 0.45953232937844013),
 ('tour', 0.45953232937844013),
 ('spielberg', 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),
 ('fame', 0.44183275227903923),
 ('closer', 0.44183275227903923),
 ('web', 0.44183275227903923),
 ('criminal', 0.4412745608048752),
 ('minor', 0.4409224199448939),
 ('jon', 0.44086703515908027),
 ('liked', 0.44074991514020723),
 ('restaurant', 0.44031183943833246),
 ('de', 0.43983275161237217),
 ('flaws', 0.43983275161237217),
 ('searching', 0.4393666597838457),
 ('rap', 0.43891304217570443),
 ('light', 0.43884433018199892),
 ('elizabeth', 0.43872232986464682),
 ('marry', 0.43861731542506488),
 ('controversial', 0.43825493093115531),
 ('learned', 0.43825493093115531),
 ('oz', 0.43825493093115531),
 ('slowly', 0.43785660389939979),
 ('thrilling', 0.43721380642274466),
 ('bridge', 0.43721380642274466),
 ('wayne', 0.43721380642274466),
 ('comedic', 0.43721380642274466),
 ('married', 0.43658501682196887),
 ('nazi', 0.4361020775700542),
 ('physical', 0.4353180712578455),
 ('murder', 0.4353180712578455),
 ('johnny', 0.43483971678806865),
 ('michelle', 0.43445264498141672),
 ('wallace', 0.43403848055222038),
 ('comedies', 0.43395706390247063),
 ('silent', 0.43395706390247063),
 ('played', 0.43387244114515305),
 ('international', 0.43363598507486073),
 ('vision', 0.43286408229627887),
 ('intelligent', 0.43196704885367099),
 ('shop', 0.43078291609245434),
 ('also', 0.43036720209769169),
 ('levels', 0.4302451371066513),
 ('miss', 0.43006426712153217),
 ('revolutionary', 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]:





['',
 'reinforcing',
 'stylistically',
 'undermined',
 'regretting',
 'bootlegged',
 'esk',
 'destructing',
 'poignant',
 'uth',
 'juggles',
 'gladiator',
 'rooting',
 'bakersfield',
 'dramatizations',
 'symbiont',
 'unredeemably',
 'medioacre',
 'referees',
 'outrageous',
 'deosnt',
 'blurred',
 'hofeus',
 'desmond',
 'azaria',
 'strangeness',
 'simpley',
 'proclaim',
 'cristina',
 'brown',
 'counter',
 'tutors',
 'goldstien',
 'hairdoed',
 'pickford',
 'hampton',
 'sorcia',
 'originates',
 'violin',
 'saphead',
 'wanton',
 'hollandish',
 'cardinal',
 'shaaadaaaap',
 'fleshy',
 'cripplingly',
 'maturation',
 'dalmers',
 'taken',
 'documentary',
 'noses',
 'guadalajara',
 'vanquished',
 'trampy',
 'absentmindedly',
 'ansons',
 'willpower',
 'worringly',
 'roslyn',
 'unprecedented',
 'asphyxiated',
 'lala',
 'overplays',
 'tendentiousness',
 'laborers',
 'pharisees',
 'occult',
 'disastor',
 'kraft',
 'unglamourous',
 'conceptionless',
 'uppity',
 'singaporean',
 'granted',
 'darkwolf',
 'justifiably',
 'preoccupied',
 'bambi',
 'coincidence',
 'tapeworm',
 'minot',
 'spree',
 'neverland',
 'sedona',
 'fumbling',
 'sustainable',
 'gilberte',
 'bremen',
 'barfuss',
 'moolah',
 'schultz',
 'wasters',
 'suresh',
 'brambell',
 'corson',
 'decaunes',
 'jrr',
 'tcp',
 'mesmerize',
 'supersize',
 'moebius',
 'maybe',
 'ghibi',
 'trustworthiness',
 'hak',
 'soba',
 'clampets',
 'markell',
 'core',
 'blanks',
 'astaire',
 'witters',
 'randoph',
 'turtles',
 'sprawls',
 'underaged',
 'majored',
 'henie',
 'luvahire',
 'piotr',
 'audi',
 'seals',
 'extemporaneous',
 'ralphy',
 'indeed',
 'awara',
 'jeopardizing',
 'rapid',
 'escalation',
 'ohad',
 'favo',
 'laughingly',
 'peacocks',
 'swagger',
 'exhausted',
 'reverse',
 'channing',
 'skims',
 'manny',
 'hoffbrauhaus',
 'chearator',
 'extent',
 'providing',
 'section',
 'merly',
 'obtains',
 'infiltrates',
 'dorthy',
 'agusti',
 'straws',
 'hj',
 'turks',
 'graduating',
 'cleanliness',
 'stripteases',
 'haltingly',
 'diggers',
 'beringer',
 'hagarty',
 'deere',
 'biochemical',
 'boatload',
 'blank',
 'machina',
 'helgeland',
 'panzer',
 'punishing',
 'shimada',
 'decide',
 'pennie',
 'fretted',
 'verdoux',
 'reprint',
 'ricchi',
 'inane',
 'barrels',
 'sisley',
 'sandwiched',
 'garth',
 'usn',
 'doss',
 'deeeeeep',
 'leeway',
 'anvil',
 'gutteridge',
 'correlli',
 'trussed',
 'mincemeat',
 'lad',
 'daisenso',
 'vaudevillians',
 'beln',
 'renderings',
 'menon',
 'bulls',
 'manchester',
 'timberflake',
 'cc',
 'wellesley',
 'westlake',
 'viewings',
 'abkani',
 'takeover',
 'seachd',
 'maadri',
 'henry',
 'ca',
 'niel',
 'bosoms',
 'someones',
 'breathtaking',
 'seduce',
 'unbound',
 'costar',
 'japp',
 'drilled',
 'altough',
 'unshakable',
 'rawks',
 'fianc',
 'roundup',
 'parasarolophus',
 'glittering',
 'felecia',
 'unending',
 'lumiere',
 'gratefull',
 'volleyball',
 'awwwwww',
 'whined',
 'frivilous',
 'summoning',
 'headlight',
 'vila',
 'huntress',
 'championship',
 'tae',
 'saura',
 'ashraf',
 'yoke',
 'booted',
 'sherriff',
 'provinces',
 'impression',
 'weatherworn',
 'headmaster',
 'leonov',
 'summit',
 'insemination',
 'doggerel',
 'journeyed',
 'banked',
 'jacket',
 'chothes',
 'baiting',
 'latest',
 'unlikely',
 'basing',
 'guiccioli',
 'bats',
 'cesare',
 'herselfthat',
 'nads',
 'kneejerk',
 'strider',
 'behrman',
 'mannered',
 'awakening',
 'runners',
 'regarded',
 'incoherently',
 'instrumentalists',
 'jeanette',
 'reconciling',
 'filmstrip',
 'latts',
 'bloss',
 'glowed',
 'grimy',
 'mm',
 'mackenna',
 'timed',
 'kj',
 'gravelings',
 'tryfon',
 'hatton',
 'username',
 'adamos',
 'selina',
 'zang',
 'solidarity',
 'interesting',
 'needle',
 'chillers',
 'seldes',
 'plumping',
 'rapidshare',
 'yelli',
 'embellishments',
 'wholike',
 'caballe',
 'stupider',
 'gianni',
 'costard',
 'stressing',
 'feldman',
 'xenomorphs',
 'iu',
 'janet',
 'callous',
 'frustrates',
 'stroking',
 'ballet',
 'garcin',
 'frustrating',
 'recieve',
 'seasons',
 'color',
 'kojak',
 'lick',
 'azn',
 'meanies',
 'kongs',
 'consecutive',
 'fickle',
 'unappreciative',
 'jill',
 'joyride',
 'everybodies',
 'srbljanovic',
 'ganay',
 'functioning',
 'prism',
 'obligingly',
 'fabinder',
 'amrican',
 'construe',
 'amemiya',
 'evokes',
 'rubin',
 'colic',
 'schrab',
 'yoo',
 'blomkamp',
 'cycs',
 'tidwell',
 'fountains',
 'wearing',
 'errr',
 'boastful',
 'atrociousthe',
 'knowable',
 'montazuma',
 'philosophizing',
 'bergenon',
 'missionaries',
 'boomerangs',
 'fakk',
 'challiya',
 'crucified',
 'crystin',
 'upward',
 'bids',
 'charms',
 'implant',
 'sensationialism',
 'counterman',
 'bisexual',
 'bios',
 'mroavich',
 'dossiers',
 'officials',
 'phile',
 'towner',
 'plug',
 'tormented',
 'wilful',
 'ripner',
 'fanned',
 'dazzle',
 'acceptable',
 'maps',
 'teaming',
 'upsides',
 'sanam',
 'hideout',
 'hesteria',
 'moviestar',
 'cheetos',
 'gerschwin',
 'muzzle',
 'guerilla',
 'quests',
 'woronow',
 'poolboys',
 'dowager',
 'renounces',
 'wowwwwww',
 'bargain',
 'blackest',
 'mowed',
 'timing',
 'figureheads',
 'rtd',
 'allan',
 'undercard',
 'wathced',
 'disturbed',
 'regurgitating',
 'guessing',
 'librarianship',
 'skedaddled',
 'hottub',
 'mails',
 'cran',
 'davalos',
 'bulimics',
 'simmer',
 'dispatching',
 'dolores',
 'preventable',
 'loudmouthed',
 'stumpfinger',
 'prescience',
 'rve',
 'cartwright',
 'tractored',
 'wildenbrck',
 'stv',
 'destitute',
 'disseminating',
 'magnified',
 'tuckwiller',
 'wearying',
 'sensitiveness',
 'seto',
 'pumkinhead',
 'logophobic',
 'littleoff',
 'idiocracy',
 'telemovie',
 'verizon',
 'drip',
 'sporadically',
 'extravagantly',
 'negatives',
 'gesturing',
 'griped',
 'canals',
 'acquisition',
 'harpo',
 'directs',
 'wanky',
 'undervalued',
 'advices',
 'codgers',
 'orchestration',
 'zhuzh',
 'bins',
 'elicits',
 'soy',
 'timetable',
 'thrall',
 'chronological',
 'sidetracking',
 'misquotes',
 'believable',
 'rascal',
 'advances',
 'panjabi',
 'anjali',
 'jodorowsky',
 'kaffeine',
 'whether',
 'tutorial',
 'symptom',
 'campy',
 'yar',
 'metro',
 'triads',
 'pealed',
 'squadron',
 'enthralls',
 'nuimage',
 'lacking',
 'cinematic',
 'toppling',
 'jetty',
 'crayons',
 'housewife',
 'coorain',
 'unbeknowst',
 'lumberjack',
 'forcefulness',
 'dress',
 'delayed',
 'anthonyu',
 'stargaard',
 'albinoni',
 'installments',
 'hoffa',
 'coming',
 'nl',
 'db',
 'sarasohn',
 'sheng',
 'gestapo',
 'memorized',
 'splatterish',
 'tankentai',
 'crushes',
 'irresistibly',
 'dramasare',
 'falsely',
 'felled',
 'stuntmen',
 'mortgages',
 'begotten',
 'bleachers',
 'walters',
 'unpleasant',
 'figuration',
 'sanctity',
 'transitory',
 'athens',
 'rediculous',
 'bloodless',
 'brood',
 'ahahhahahaha',
 'burakov',
 'alliance',
 'haryanavi',
 'bedding',
 'hunch',
 'yoghurt',
 'ang',
 'homoerotica',
 'derives',
 'bronson',
 'jhtml',
 'transferred',
 'unboxed',
 'incisively',
 'shadyac',
 'frees',
 'sweid',
 'bh',
 'aventura',
 'receipt',
 'stefaniuk',
 'sickens',
 'uprosing',
 'downers',
 'meu',
 'finer',
 'sugarcoating',
 'craggy',
 'anatole',
 'reginald',
 'panda',
 'napunsaktha',
 'devlin',
 'dot',
 'speculation',
 'encroached',
 'anthropophagous',
 'double',
 'extremis',
 'sip',
 'springs',
 'tempi',
 'bhamra',
 'winkelman',
 'ofhe',
 'scabby',
 'xo',
 'dvder',
 'cheri',
 'seam',
 'hendrix',
 'scripturally',
 'feline',
 'piaf',
 'encounting',
 'afilm',
 'meagre',
 'overprotective',
 'katrina',
 'kercheval',
 'libe',
 'scouts',
 'narrations',
 'incompleteness',
 'maughan',
 'nauseous',
 'leers',
 'fante',
 'greenscreens',
 'unkown',
 'gamely',
 'ethnicity',
 'add',
 'unkwown',
 'suman',
 'braslia',
 'buddies',
 'outsides',
 'spotlights',
 'robbery',
 'fox',
 'sacrilegious',
 'juggling',
 'improvisation',
 'potch',
 'expiration',
 'turnup',
 'unfamiliarity',
 'auteur',
 'angasm',
 'eesh',
 'comedy',
 'happy',
 'flatly',
 'hideshi',
 'shakiness',
 'benny',
 'idaho',
 'putu',
 'ordell',
 'cackling',
 'holt',
 'soutendijk',
 'till',
 'councilors',
 'homeboy',
 'hell',
 'pubes',
 'easton',
 'delerium',
 'narasimha',
 'kittredge',
 'fandango',
 'cratchit',
 'smelt',
 'collums',
 'collide',
 'features',
 'gazooks',
 'unredeemable',
 'reckon',
 'proteins',
 'hiccuping',
 'avoidable',
 'cordial',
 'vapours',
 'mayans',
 'phantom',
 'flimsier',
 'oligarchy',
 'jowett',
 'arahan',
 'risibly',
 'babesti',
 'mos',
 'disapprove',
 'module',
 'ragneks',
 'swamplands',
 'succes',
 'lawyerly',
 'strombel',
 'accordance',
 'asst',
 'left',
 'suppressant',
 'platinum',
 'paperino',
 'stalkers',
 'ladie',
 'begging',
 'flake',
 'enshrine',
 'gadabout',
 'dmytyk',
 'borg',
 'yester',
 'feeling',
 'besides',
 'farrar',
 'lasseter',
 'gory',
 'boss',
 'hamfisted',
 'traceys',
 'semantics',
 'terrify',
 'loughlin',
 'duty',
 'tip',
 'imitator',
 'indulgence',
 'selectively',
 'ignors',
 'tam',
 'reevaluate',
 'lipped',
 'sailing',
 'studios',
 'braley',
 'repetitevness',
 'frontieres',
 'satisfactory',
 'titillated',
 'gourd',
 'blum',
 'krummernes',
 'yuko',
 'ghouls',
 'hannay',
 'outfield',
 'insanity',
 'jaden',
 'awarding',
 'dudes',
 'copiously',
 'byu',
 'def',
 'morbius',
 'purchassed',
 'kirron',
 'redemptions',
 'kamisori',
 'ebing',
 'unglamorous',
 'counselor',
 'rokkuchan',
 'meantime',
 'sews',
 'freaksa',
 'tarkovsky',
 'jovic',
 'contenders',
 'threads',
 'enos',
 'propound',
 'raunchiness',
 'broadly',
 'mimics',
 'changin',
 'moorish',
 'bluntly',
 'alesia',
 'handbasket',
 'executive',
 'vernacular',
 'wes',
 'memo',
 'wippleman',
 'stephinie',
 'internalizes',
 'prodigal',
 'eve',
 'inveresk',
 'jost',
 'killshot',
 'sweatshops',
 'immobile',
 'chocco',
 'woodbury',
 'dirtiest',
 'leguizano',
 'winced',
 'posteriors',
 'adult',
 'angelos',
 'robin',
 'rootbeer',
 'daneldoradoyahoo',
 'rhonda',
 'lings',
 'puce',
 'defilers',
 'imitated',
 'softie',
 'predictably',
 'comes',
 'videographer',
 'bannacheck',
 'siesta',
 'splatter',
 'drawers',
 'medevil',
 'cassella',
 'temporarily',
 'paiyan',
 'inferiority',
 'jalapeno',
 'sanitation',
 'russborrough',
 'androse',
 'pecan',
 'goldblum',
 'dominance',
 'manojlovic',
 'communism',
 'neutrality',
 'diaper',
 'abskani',
 'revamped',
 'ribsi',
 'chynna',
 'edmunds',
 'murry',
 'gutwrenching',
 'obvious',
 'cornyness',
 'outlived',
 'escorts',
 'lorri',
 'nurses',
 'delenn',
 'feasts',
 'debutante',
 'musseum',
 'ayda',
 'unpalatable',
 'iraquis',
 'deoxys',
 'dishonored',
 'unlisted',
 'sidenotes',
 'gah',
 'katzenberg',
 'gruenberg',
 'wingtip',
 'muerte',
 'fantasticaly',
 'agrarian',
 'conklin',
 'conversion',
 'longstreet',
 'drawled',
 'fracas',
 'goldman',
 'sauntering',
 'mutinous',
 'zelenka',
 'nofth',
 'tease',
 'stormy',
 'petrn',
 'morgus',
 'dullards',
 'utilities',
 'tanya',
 'mano',
 'eartha',
 'elainor',
 'throw',
 'discernable',
 'haye',
 'communinity',
 'underpin',
 'toy',
 'supporter',
 'contrasted',
 'carapace',
 'bwahahha',
 'monologues',
 'poisons',
 'simira',
 'ific',
 'worldand',
 'deterrance',
 'patronised',
 'shopper',
 'constipated',
 'doth',
 'digested',
 'prival',
 'whooping',
 'still',
 'unofficial',
 'modernisation',
 'woodman',
 'twitty',
 'cynics',
 'anagram',
 'gahannah',
 'gonsalves',
 'stupifyingly',
 'earwax',
 'ranger',
 'gaily',
 'connect',
 'homey',
 'terrifiying',
 'sisyphean',
 'baltz',
 'pulaski',
 'tyranasaurus',
 'buttered',
 'wadd',
 'unquiet',
 'fcc',
 'wcw',
 'coverings',
 'tuxedo',
 'aaaaah',
 'trashbin',
 'sinny',
 'startling',
 'highbrows',
 'craigs',
 'survived',
 'degenerate',
 'tyrants',
 'tennessee',
 'patrolling',
 'ambassador',
 'treasurer',
 'sorrento',
 'pacula',
 'grandmas',
 'coughthe',
 'sufferes',
 'deemed',
 'budah',
 'flavourless',
 'engines',
 'gracelessness',
 'dracko',
 'repetitive',
 'bourn',
 'bigscreen',
 'wrede',
 'persistence',
 'different',
 'powerlessly',
 'expenses',
 'barem',
 'kaho',
 'inexcusable',
 'mahin',
 'greytack',
 'tempered',
 'viccaro',
 'hour',
 'mufti',
 'saxony',
 'opioion',
 'kazakhstan',
 'sensitivity',
 'sweeet',
 'spongebob',
 'complacence',
 'patresi',
 'rainbow',
 'distorted',
 'classless',
 'primatologists',
 'popcorncoke',
 'sherawali',
 'correctable',
 'furniture',
 'sprezzatura',
 'tuner',
 'raghupati',
 'kerri',
 'companyman',
 'splash',
 'chronologically',
 'taraporevala',
 'dekho',
 'oppurunity',
 'godwin',
 'worldliness',
 'moralizing',
 'flattery',
 'meticulously',
 'acumen',
 'bharai',
 'cordless',
 'shirow',
 'flak',
 'cking',
 'dazzy',
 'overthrowing',
 'drama',
 'jumpiness',
 'hayworth',
 'summery',
 'collateral',
 'honostly',
 'bailsman',
 'ota',
 'whetted',
 'cte',
 'braids',
 'joan',
 ...]

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,
 'reinforcing': 1,
 'regretting': 4,
 'undermined': 3,
 'uth': 9,
 'sixties': 36932,
 'esk': 6,
 'destructing': 7,
 'poignant': 8,
 'juggles': 10,
 'damne': 31400,
 'gladiator': 11,
 'rooting': 12,
 'bakersfield': 13,
 'dramatizations': 14,
 'medioacre': 17,
 'stylistically': 2,
 'incredibly': 59714,
 'outrageous': 19,
 'bootlegged': 5,
 'deosnt': 20,
 'blurred': 21,
 'rds': 24671,
 'hofeus': 22,
 'desmond': 23,
 'azaria': 24,
 'strangeness': 25,
 'cristina': 28,
 'proclaim': 27,
 'brown': 29,
 'counter': 30,
 'tutors': 31,
 'goldstien': 32,
 'hairdoed': 33,
 'mattolini': 49238,
 'hampton': 35,
 'sorcia': 36,
 'originates': 37,
 'violin': 38,
 'saphead': 39,
 'hollandish': 41,
 'cardinal': 42,
 'shaaadaaaap': 43,
 'fleshy': 44,
 'cripplingly': 45,
 'maturation': 46,
 'taken': 48,
 'noses': 50,
 'illustrious': 58462,
 'guadalajara': 51,
 'van': 12253,
 'vanquished': 52,
 'trampy': 53,
 'absentmindedly': 54,
 'ansons': 55,
 'willpower': 56,
 'worringly': 57,
 'castlebeck': 57327,
 'stripper': 49243,
 'roslyn': 58,
 'groovay': 68596,
 'unprecedented': 59,
 'lala': 61,
 'unredeemably': 16,
 'overplays': 62,
 'tendentiousness': 63,
 'laborers': 64,
 'occult': 66,
 'unglamourous': 69,
 'kraft': 68,
 'conceptionless': 70,
 'uppity': 71,
 'singaporean': 72,
 'granted': 73,
 'macclaine': 49247,
 'preoccupied': 76,
 'bambi': 77,
 'tapeworm': 79,
 'minot': 80,
 'spree': 81,
 'sedona': 83,
 'fumbling': 84,
 'gilberte': 86,
 'bremen': 87,
 'barfuss': 88,
 'moolah': 89,
 'schultz': 90,
 'wasters': 91,
 'suresh': 92,
 'brambell': 93,
 'corson': 94,
 'decaunes': 95,
 'violette': 49250,
 'supersize': 99,
 'mesmerize': 98,
 'trustworthiness': 103,
 'maybe': 101,
 'ghibi': 102,
 'caprica': 49252,
 'hak': 104,
 'soba': 105,
 'clampets': 106,
 'markell': 107,
 'astaire': 110,
 'witters': 111,
 'randoph': 112,
 'underaged': 115,
 'sprawls': 114,
 'possessingand': 5971,
 'henie': 117,
 'luvahire': 118,
 'piotr': 119,
 'audi': 120,
 'extemporaneous': 122,
 'indeed': 124,
 'boulders': 30335,
 'awara': 125,
 'jeopardizing': 126,
 'rapid': 127,
 'escalation': 128,
 'ohad': 129,
 'favo': 130,
 'laughingly': 131,
 'peacocks': 132,
 'swagger': 133,
 'nancy': 36951,
 'ganster': 57075,
 'exhausted': 134,
 'reverse': 135,
 'skims': 137,
 'manny': 138,
 'hoffbrauhaus': 139,
 'stroked': 66554,
 'letheren': 12268,
 'chearator': 140,
 'extent': 141,
 'providing': 142,
 'section': 143,
 'infiltrates': 146,
 'labourer': 70626,
 'agusti': 148,
 'straws': 149,
 'hj': 150,
 'turks': 151,
 'graduating': 152,
 'cleanliness': 153,
 'stripteases': 154,
 'diggers': 156,
 'beringer': 157,
 'deere': 159,
 'biochemical': 160,
 'blank': 162,
 'toothbrush': 48718,
 'helgeland': 164,
 'panzer': 165,
 'punishing': 166,
 'shimada': 167,
 'decide': 168,
 'pennie': 169,
 'fretted': 170,
 'verdoux': 171,
 'reprint': 172,
 'ricchi': 173,
 'simpley': 26,
 'usn': 179,
 'garth': 178,
 'sisley': 176,
 'marlow': 70842,
 'anvil': 183,
 'doss': 180,
 'leeway': 182,
 'gutteridge': 184,
 'correlli': 185,
 'trussed': 186,
 'underhanded': 12274,
 'trema': 5308,
 'giamatti': 58979,
 'governmental': 18389,
 'mincemeat': 187,
 'mice': 56118,
 'lad': 188,
 'daisenso': 189,
 'vaudevillians': 190,
 'beln': 191,
 'renderings': 192,
 'menon': 193,
 'bulls': 194,
 'manchester': 195,
 'timberflake': 196,
 'cc': 197,
 'wellesley': 198,
 'viewings': 200,
 'ci': 61792,
 'abkani': 201,
 'takeover': 202,
 'maadri': 204,
 'henry': 205,
 'composure': 24694,
 'niel': 207,
 'bosoms': 208,
 'someones': 209,
 'breathtaking': 210,
 'seduce': 211,
 'unbound': 212,
 'costar': 213,
 'altough': 216,
 'rates': 36967,
 'unshakable': 217,
 'bodybuilders': 61797,
 'rawks': 218,
 'fianc': 219,
 'roundup': 220,
 'acin': 24698,
 'glittering': 222,
 'lumiere': 225,
 'gratefull': 226,
 'volleyball': 227,
 'awwwwww': 228,
 'pickford': 34,
 'flacks': 61803,
 'whined': 229,
 'summoning': 231,
 'headlight': 232,
 'pucelle': 69371,
 'huntress': 234,
 'championship': 235,
 'saura': 237,
 'qayamat': 24700,
 'ashraf': 238,
 'yoke': 239,
 'booted': 240,
 'ipecac': 36970,
 'on': 29435,
 'provinces': 242,
 'impression': 243,
 'wanton': 40,
 'weatherworn': 244,
 'headmaster': 245,
 'leonov': 246,
 'summit': 247,
 'insemination': 248,
 'doggerel': 249,
 'journeyed': 250,
 'banked': 251,
 'jacket': 252,
 'wali': 35347,
 'baiting': 254,
 'basing': 257,
 'unlikely': 256,
 'employees': 36972,
 'guiccioli': 258,
 'cesare': 260,
 'herselfthat': 261,
 'kneejerk': 263,
 'sport': 24707,
 'strider': 264,
 'behrman': 265,
 'mannered': 266,
 'awakening': 267,
 'rossetti': 24708,
 'runners': 268,
 'instrumentalists': 271,
 'incoherently': 270,
 'jeanette': 272,
 'shakesphere': 24710,
 'filmstrip': 274,
 'bloss': 276,
 'glowed': 277,
 'mackenna': 280,
 'mm': 279,
 'timed': 281,
 'boost': 61811,
 'kj': 282,
 'rungs': 12291,
 'gravelings': 283,
 'tryfon': 284,
 'ansen': 24774,
 'username': 286,
 'zang': 289,
 'solidarity': 290,
 'needle': 292,
 'renewals': 33035,
 'seldes': 294,
 'plumping': 295,
 'rapidshare': 296,
 'dalmers': 47,
 'yelli': 297,
 'preppies': 4459,
 'anenokoji': 12296,
 'embellishments': 298,
 'wholike': 299,
 'caballe': 300,
 'stupider': 301,
 'stressing': 304,
 'costard': 303,
 'feldman': 305,
 'leaderships': 22497,
 'impelled': 73674,
 'iu': 307,
 'janet': 308,
 'stroking': 311,
 'ballet': 312,
 'documentary': 49,
 'frustrating': 314,
 'recieve': 315,
 'seasons': 316,
 'helping': 36985,
 'color': 317,
 'kojak': 318,
 'lick': 319,
 'unappreciative': 325,
 'meanies': 321,
 'kongs': 322,
 'consecutive': 323,
 'fickle': 324,
 'joyride': 327,
 'srbljanovic': 329,
 'ganay': 330,
 'functioning': 331,
 'fabinder': 334,
 'construe': 336,
 'amemiya': 337,
 'evokes': 338,
 'idiosyncratically': 36987,
 'samedi': 30981,
 'colic': 340,
 'yoo': 342,
 'digisoft': 55832,
 'mantra': 73878,
 'blomkamp': 343,
 'cycs': 344,
 'tidwell': 345,
 'fountains': 346,
 'wearing': 347,
 'boastful': 349,
 'atrociousthe': 350,
 'knowable': 351,
 'philosophizing': 353,
 'bergenon': 354,
 'missionaries': 355,
 'fakk': 357,
 'magtena': 36990,
 'predestination': 12305,
 'challiya': 358,
 'crucified': 359,
 'crystin': 360,
 'sensationialism': 365,
 'bids': 362,
 'counterman': 366,
 'implant': 364,
 'dossiers': 370,
 'bios': 368,
 'mroavich': 369,
 'despict': 16409,
 'officials': 371,
 'phile': 372,
 'towner': 373,
 'tormented': 375,
 'wilful': 376,
 'ripner': 377,
 'dazzle': 379,
 'steamy': 56423,
 'acceptable': 380,
 'maps': 381,
 'diy': 64250,
 'teaming': 382,
 'upsides': 383,
 'sanam': 384,
 'hesteria': 386,
 'moviestar': 387,
 'cheetos': 388,
 'gerschwin': 389,
 'muzzle': 390,
 'guerilla': 391,
 'woronow': 393,
 'poolboys': 394,
 'clarence': 68048,
 'dowager': 395,
 'renounces': 396,
 'sanctifies': 51783,
 'wowwwwww': 397,
 'bargain': 398,
 'blackest': 399,
 'mowed': 400,
 'timing': 401,
 'undercard': 405,
 'allan': 404,
 'wathced': 406,
 'disturbed': 407,
 'regurgitating': 408,
 'guessing': 409,
 'librarianship': 410,
 'skedaddled': 411,
 'hottub': 412,
 'cran': 414,
 'bulimics': 416,
 'simmer': 417,
 'dispatching': 418,
 'dolores': 419,
 'spurned': 73837,
 'stumpfinger': 422,
 'misses': 24734,
 'fidel': 36663,
 'prescience': 423,
 'rve': 424,
 'bulldozed': 24735,
 'disseminating': 430,
 'tractored': 426,
 'wildenbrck': 427,
 'stv': 428,
 'tuckwiller': 432,
 'imagines': 31335,
 'unafraid': 73923,
 'wearying': 433,
 'sensitiveness': 434,
 'seto': 435,
 'pumkinhead': 436,
 'scrooge': 56390,
 'logophobic': 437,
 'littleoff': 438,
 'verizon': 441,
 'telemovie': 440,
 'disastor': 67,
 'sporadically': 443,
 'extravagantly': 444,
 'griped': 447,
 'canals': 448,
 'acquisition': 449,
 'harpo': 450,
 'directs': 451,
 'wanky': 452,
 'undervalued': 453,
 'codgers': 455,
 'orchestration': 456,
 'employ': 61838,
 'zhuzh': 457,
 'yeh': 49317,
 'soy': 460,
 'thrall': 462,
 'sidetracking': 464,
 'misquotes': 465,
 'rascal': 467,
 'favorable': 37007,
 'advances': 468,
 'anjali': 470,
 'jodorowsky': 471,
 'kaffeine': 472,
 'whether': 473,
 'aids': 49322,
 'darkwolf': 74,
 'sorter': 61395,
 'stockpile': 49320,
 'tutorial': 474,
 'puppo': 24744,
 'symptom': 475,
 'yar': 477,
 'justifiably': 75,
 'pealed': 480,
 'triads': 479,
 'enthralls': 482,
 'affixed': 71598,
 'withers': 12318,
 'nuimage': 483,
 'lacking': 484,
 'cinematic': 485,
 'toppling': 486,
 'krull': 3781,
 'jetty': 487,
 'coorain': 490,
 'housewife': 489,
 'coincidence': 78,
 'unbeknowst': 491,
 'garofolo': 61844,
 'forcefulness': 493,
 'albinoni': 498,
 'delayed': 495,
 'anthonyu': 496,
 'stargaard': 497,
 'installments': 499,
 'neverland': 82,
 'coming': 501,
 'sarasohn': 504,
 'sheng': 505,
 'gestapo': 506,
 'memorized': 507,
 'splatterish': 508,
 'falsely': 513,
 'yen': 56209,
 'irresistibly': 511,
 'dramasare': 512,
 'felled': 514,
 'yumiko': 37014,
 'stuntmen': 515,
 'mortgages': 516,
 'begotten': 517,
 'bleachers': 518,
 'unpleasant': 520,
 'sanctity': 522,
 'transitory': 523,
 'rediculous': 525,
 'bloodless': 526,
 'brood': 527,
 'ahahhahahaha': 528,
 'burakov': 529,
 'sustainable': 85,
 'yoghurt': 534,
 'stagger': 49332,
 'ang': 535,
 'homoerotica': 536,
 'derives': 537,
 'bronson': 538,
 'jhtml': 539,
 'transferred': 540,
 'unboxed': 541,
 'yankee': 61853,
 'incisively': 542,
 'shadyac': 543,
 'frees': 544,
 'sweid': 545,
 'bothered': 69844,
 'bh': 546,
 'aventura': 547,
 'receipt': 548,
 'stefaniuk': 549,
 'sickens': 550,
 'uprosing': 551,
 'downers': 552,
 'meu': 553,
 'finer': 554,
 'craggy': 556,
 'anatole': 557,
 'reginald': 558,
 'panda': 559,
 'napunsaktha': 560,
 'devlin': 561,
 'dot': 562,
 'encroached': 564,
 'extremis': 567,
 'double': 566,
 'issue': 31832,
 'transcend': 33664,
 'tempi': 570,
 'bhamra': 571,
 'winkelman': 572,
 'scabby': 574,
 'xo': 575,
 'dvder': 576,
 'shola': 61859,
 'cheri': 577,
 'piaf': 582,
 'hendrix': 579,
 'scripturally': 580,
 'egoyan': 43615,
 'overprotective': 586,
 'katrina': 587,
 'meagre': 585,
 'judds': 19225,
 'kercheval': 588,
 'fante': 596,
 'narrations': 591,
 'incompleteness': 592,
 'unkown': 598,
 'leers': 595,
 'questionably': 49281,
 'gamely': 599,
 'ethnicity': 600,
 'add': 601,
 'unkwown': 602,
 'suman': 603,
 'outsides': 606,
 'spotlights': 607,
 'robbery': 608,
 'jrr': 96,
 'fox': 609,
 'juggling': 611,
 'unfamiliarity': 616,
 'turnup': 615,
 'expiration': 614,
 'auteur': 617,
 'angasm': 618,
 'eesh': 619,
 'blackadder': 48981,
 'nop': 49347,
 'sub': 68990,
 'flatly': 622,
 'happy': 621,
 'benny': 625,
 'shakiness': 624,
 'idaho': 626,
 'ordell': 628,
 'cackling': 629,
 'soutendijk': 631,
 'tcp': 97,
 'till': 632,
 'freeloader': 61864,
 'councilors': 633,
 'easton': 637,
 'hell': 635,
 'pubes': 636,
 'insistent': 24765,
 'trace': 12347,
 'delerium': 638,
 'idiom': 37031,
 'cratchit': 642,
 'kittredge': 640,
 'moebius': 100,
 'smelt': 643,
 'collums': 644,
 'collide': 645,
 'tobias': 37034,
 'features': 646,
 'gazooks': 647,
 'unredeemable': 648,
 'reckon': 649,
 'proteins': 650,
 'purdom': 49355,
 'avoidable': 652,
 'vapours': 654,
 'rejuvenated': 24768,
 'oligarchy': 658,
 'phantom': 656,
 'flimsier': 657,
 'doers': 49357,
 'risibly': 661,
 'arahan': 660,
 'babesti': 662,
 'disapprove': 664,
 'ragneks': 666,
 'swamplands': 667,
 'succes': 668,
 'lawyerly': 669,
 'accordance': 671,
 'paperino': 676,
 'asst': 672,
 'left': 673,
 'suppressant': 674,
 'platinum': 675,
 'subjective': 49361,
 'stalkers': 677,
 'ladie': 678,
 'begging': 679,
 'chil': 48732,
 'flake': 680,
 'enshrine': 681,
 'gadabout': 682,
 'dmytyk': 683,
 'borg': 684,
 'yester': 685,
 'feeling': 686,
 'mireille': 49364,
 'besides': 687,
 'farrar': 688,
 'means': 59400,
 'lasseter': 689,
 'gory': 690,
 'medusa': 38127,
 'boss': 691,
 'traceys': 693,
 'semantics': 694,
 'terrify': 695,
 'loughlin': 696,
 'imitator': 699,
 'tip': 698,
 'indulgence': 700,
 'malkovich': 5849,
 'residing': 30890,
 'ignors': 702,
 'tam': 703,
 'reevaluate': 704,
 'simplistic': 38498,
 'lipped': 705,
 'sailing': 706,
 'studios': 707,
 'braley': 708,
 'suborned': 24776,
 'stalking': 12361,
 'repetitevness': 709,
 'frontieres': 710,
 'titillated': 712,
 'gourd': 713,
 'blum': 714,
 'krummernes': 715,
 'duplicity': 12362,
 'yuko': 716,
 'ghouls': 717,
 'hannay': 718,
 'outfield': 719,
 'opened': 12804,
 'insanity': 720,
 'awarding': 722,
 'seals': 121,
 'byu': 725,
 'def': 726,
 'morbius': 727,
 'kirron': 729,
 'phonograph': 73234,
 'establishment': 49374,
 'redemptions': 730,
 'kamisori': 731,
 'unglamorous': 733,
 'counselor': 734,
 'rokkuchan': 735,
 'banalities': 63713,
 'meantime': 736,
 'freaksa': 738,
 'enrages': 64868,
 'tarkovsky': 739,
 'humanizing': 44301,
 'contenders': 741,
 'threads': 742,
 'enos': 743,
 'propound': 744,
 'raunchiness': 745,
 'broadly': 746,
 'mimics': 747,
 'changin': 748,
 'moorish': 749,
 'handbasket': 752,
 'executive': 753,
 'firefighters': 24789,
 'wes': 755,
 'memo': 756,
 'wippleman': 757,
 'internalizes': 759,
 'hazy': 12372,
 'eve': 761,
 'sweatshops': 765,
 'immobile': 766,
 'chocco': 767,
 'dirtiest': 769,
 'leguizano': 770,
 'winced': 771,
 'rootbeer': 776,
 'robin': 775,
 'flattop': 61886,
 'daneldoradoyahoo': 777,
 'rhonda': 778,
 'isnt': 37062,
 'lings': 779,
 'puce': 780,
 'defilers': 781,
 'imitated': 782,
 'softie': 783,
 'predictably': 784,
 'comes': 785,
 'thielemans': 24799,
 'videographer': 786,
 'bannacheck': 787,
 'funt': 49384,
 'siesta': 788,
 'spinoff': 38755,
 'splatter': 789,
 'drawers': 790,
 'conlin': 49386,
 'cassella': 792,
 'degli': 72694,
 'temporarily': 793,
 'paiyan': 794,
 'inferiority': 795,
 'jalapeno': 796,
 'sanitation': 797,
 'striped': 39082,
 'russborrough': 798,
 'pecan': 800,
 'magnolia': 28246,
 'goldblum': 801,
 'dominance': 802,
 'neutrality': 805,
 'communism': 804,
 'diaper': 806,
 'abskani': 807,
 'ribsi': 809,
 'chynna': 810,
 'murry': 812,
 'amic': 61896,
 'gutwrenching': 813,
 'obvious': 814,
 'cornyness': 815,
 'outlived': 816,
 'regulatory': 61894,
 'escorts': 817,
 'lorri': 818,
 'nurses': 819,
 'delenn': 820,
 'feasts': 821,
 'ayda': 824,
 'mismatches': 37072,
 'unpalatable': 825,
 'iraquis': 826,
 'biding': 57629,
 'deoxys': 827,
 'dishonored': 828,
 'unlisted': 829,
 'gah': 831,
 'wingtip': 834,
 'katzenberg': 832,
 'gruenberg': 833,
 'muerte': 835,
 'fantasticaly': 836,
 'agrarian': 837,
 'conklin': 838,
 'conversion': 839,
 'zelenka': 846,
 'nofth': 847,
 'snag': 37076,
 'goldman': 843,
 'sauntering': 844,
 'mutinous': 845,
 'telehobbie': 49391,
 'morgus': 851,
 'stormy': 849,
 'petrn': 850,
 'dullards': 852,
 'utilities': 853,
 'ulcerating': 70416,
 'tanya': 854,
 'mano': 855,
 'eartha': 856,
 'communinity': 861,
 'discernable': 859,
 'masterpiecebefore': 24811,
 'underpin': 862,
 'toy': 863,
 'poisons': 869,
 'carapace': 866,
 'bwahahha': 867,
 'monologues': 868,
 'simira': 870,
 'worldand': 872,
 'merly': 144,
 'deterrance': 873,
 'ladyfriend': 58767,
 'shopper': 875,
 'constipated': 876,
 'kamikaze': 49395,
 'digested': 878,
 'confucian': 61907,
 'boisterous': 25472,
 'obtains': 145,
 'whooping': 880,
 'still': 881,
 'modernisation': 883,
 'anagram': 887,
 'twitty': 885,
 'gahannah': 888,
 'gonsalves': 889,
 'stupifyingly': 890,
 'earwax': 891,
 'ranger': 892,
 'gaily': 893,
 'connect': 894,
 'dunston': 57929,
 'sisyphean': 897,
 'wellesian': 24818,
 'baltz': 898,
 'lightfoot': 49404,
 'pulaski': 899,
 'tyranasaurus': 900,
 'unquiet': 903,
 'wadd': 902,
 'fcc': 904,
 'aaaaah': 908,
 'coverings': 906,
 'tuxedo': 907,
 'trashbin': 909,
 'highbrows': 912,
 'tyrants': 916,
 'craigs': 913,
 'survived': 914,
 'degenerate': 915,
 'tennessee': 917,
 'patrolling': 918,
 'ugliness': 68924,
 'steep': 73312,
 'ambassador': 919,
 'sorrento': 921,
 'pacula': 922,
 'grandmas': 923,
 'supervillian': 53219,
 'coughthe': 924,
 'versios': 57631,
 'deemed': 926,
 'bespectacled': 53377,
 'flavourless': 928,
 'engines': 929,
 'propagate': 37090,
 'gracelessness': 930,
 'dracko': 931,
 'repetitive': 932,
 'bourn': 933,
 'bigscreen': 934,
 'wrede': 935,
 'persistence': 936,
 'different': 937,
 'powerlessly': 938,
 'expenses': 939,
 'kaho': 941,
 'mahin': 943,
 'hagarty': 158,
 'greytack': 944,
 'viccaro': 946,
 'saxony': 949,
 'kazakhstan': 951,
 'opioion': 950,
 'sweeet': 953,
 'boatload': 161,
 'patresi': 956,
 'shepherdess': 39691,
 'frwl': 22595,
 'immensity': 37094,
 'kavalier': 61917,
 'machina': 163,
 'distorted': 958,
 'correctable': 963,
 'walter': 49416,
 'popcorncoke': 961,
 'sherawali': 962,
 'furniture': 964,
 'sprezzatura': 965,
 'tuner': 966,
 'raghupati': 967,
 'kerri': 968,
 'companyman': 969,
 'splash': 970,
 'chronologically': 971,
 'taraporevala': 972,
 'dekho': 973,
 'oppurunity': 974,
 'worldliness': 976,
 'moralizing': 977,
 'flattery': 978,
 'cordless': 982,
 'shirow': 983,
 'flak': 984,
 'cking': 985,
 'dazzy': 986,
 'drama': 988,
 'webster': 57709,
 'hayworth': 990,
 'summery': 991,
 'collateral': 992,
 'kornbluth': 12395,
 'honostly': 993,
 'bailsman': 994,
 'ota': 995,
 'whetted': 996,
 'cte': 997,
 'joan': 999,
 'idiosyncratic': 1000,
 'abominations': 1001,
 'frownland': 1002,
 'dorday': 1003,
 'hacks': 1004,
 'antipathy': 1005,
 'crisi': 1006,
 'taxation': 1008,
 'everyman': 1009,
 'bimalda': 73033,
 'clunkers': 1010,
 'mustachioed': 1011,
 'merhi': 1012,
 'unsubtle': 1013,
 'karmas': 1016,
 'emilio': 1015,
 'derrick': 49422,
 'upriver': 1019,
 'pauls': 1018,
 'easily': 1020,
 'tarrantino': 1022,
 'prote': 1023,
 'superstation': 1026,
 'multitask': 1027,
 'consumptive': 49427,
 'sandwiched': 177,
 'camaraderie': 1029,
 'creditors': 1030,
 'reveille': 1033,
 'barrels': 175,
 'istead': 1034,
 'nyt': 1035,
 'steadies': 24842,
 'unsweaty': 1038,
 'backsliding': 1039,
 'rothschild': 1040,
 'sects': 61930,
 'strangers': 1042,
 'gret': 1043,
 'profoundness': 1044,
 'babyhood': 1047,
 'portion': 51647,
 'mudbank': 1048,
 'younglings': 1049,
 'waisting': 1051,
 'tricking': 66075,
 'wetters': 49430,
 'deeeeeep': 181,
 'hailed': 1052,
 'pantangeli': 1053,
 'circuitous': 1054,
 'stalinist': 1055,
 ...}

In [20]:

    

def update_input_layer(review):
    
    global layer_0
    
    # clear out previous state, reset the layer to be all 0s
    layer_0 *= 0
    for word in review.split(" "):
        layer_0[0][word2index[word]] += 1

update_input_layer(reviews[0])


    

In [21]:

    

layer_0


    

    
Out[21]:





array([[ 18.,   0.,   0., ...,   0.,   0.,   0.]])

In [22]:

    

def get_target_for_label(label):
    if(label == 'POSITIVE'):
        return 1
    else:
        return 0


    

In [23]:

    

labels[0]


    

    
Out[23]:





'POSITIVE'

In [24]:

    

get_target_for_label(labels[0])


    

    
Out[24]:





1

In [25]:

    

labels[1]


    

    
Out[25]:





'NEGATIVE'

In [26]:

    

get_target_for_label(labels[1])


    

    
Out[26]:





0

In [27]:

    

import time
import sys
import numpy as np

# Let's tweak our network from before to model these phenomena
class SentimentNetwork:
    def __init__(self, reviews,labels,hidden_nodes = 10, learning_rate = 0.1):
       
        # set our random number generator 
        np.random.seed(1)
    
        self.pre_process_data(reviews, labels)
        
        self.init_network(len(self.review_vocab),hidden_nodes, 1, learning_rate)
        
        
    def pre_process_data(self, reviews, labels):
        
        review_vocab = set()
        for review in reviews:
            for word in review.split(" "):
                review_vocab.add(word)
        self.review_vocab = list(review_vocab)
        
        label_vocab = set()
        for label in labels:
            label_vocab.add(label)
        
        self.label_vocab = list(label_vocab)
        
        self.review_vocab_size = len(self.review_vocab)
        self.label_vocab_size = len(self.label_vocab)
        
        self.word2index = {}
        for i, word in enumerate(self.review_vocab):
            self.word2index[word] = i
        
        self.label2index = {}
        for i, label in enumerate(self.label_vocab):
            self.label2index[label] = i
         
        
    def init_network(self, input_nodes, hidden_nodes, output_nodes, learning_rate):
        # Set number of nodes in input, hidden and output layers.
        self.input_nodes = input_nodes
        self.hidden_nodes = hidden_nodes
        self.output_nodes = output_nodes

        # Initialize weights
        self.weights_0_1 = np.zeros((self.input_nodes,self.hidden_nodes))
    
        self.weights_1_2 = np.random.normal(0.0, self.output_nodes**-0.5, 
                                                (self.hidden_nodes, self.output_nodes))
        
        self.learning_rate = learning_rate
        
        self.layer_0 = np.zeros((1,input_nodes))
    
        
    def update_input_layer(self,review):

        # clear out previous state, reset the layer to be all 0s
        self.layer_0 *= 0
        for word in review.split(" "):
            if(word in self.word2index.keys()):
                self.layer_0[0][self.word2index[word]] += 1
                
    def get_target_for_label(self,label):
        if(label == 'POSITIVE'):
            return 1
        else:
            return 0
        
    def sigmoid(self,x):
        return 1 / (1 + np.exp(-x))
    
    
    def sigmoid_output_2_derivative(self,output):
        return output * (1 - output)
    
    def train(self, training_reviews, training_labels):
        
        assert(len(training_reviews) == len(training_labels))
        
        correct_so_far = 0
        
        start = time.time()
        
        for i in range(len(training_reviews)):
            
            review = training_reviews[i]
            label = training_labels[i]
            
            #### Implement the forward pass here ####
            ### Forward pass ###

            # Input Layer
            self.update_input_layer(review)

            # Hidden layer
            layer_1 = self.layer_0.dot(self.weights_0_1)

            # Output layer
            layer_2 = self.sigmoid(layer_1.dot(self.weights_1_2))

            #### Implement the backward pass here ####
            ### Backward pass ###

            # TODO: Output error
            layer_2_error = layer_2 - self.get_target_for_label(label) # Output layer error is the difference between desired target and actual output.
            layer_2_delta = layer_2_error * self.sigmoid_output_2_derivative(layer_2)

            # TODO: Backpropagated error
            layer_1_error = layer_2_delta.dot(self.weights_1_2.T) # errors propagated to the hidden layer
            layer_1_delta = layer_1_error # hidden layer gradients - no nonlinearity so it's the same as the error

            # TODO: Update the weights
            self.weights_1_2 -= layer_1.T.dot(layer_2_delta) * self.learning_rate # update hidden-to-output weights with gradient descent step
            self.weights_0_1 -= self.layer_0.T.dot(layer_1_delta) * self.learning_rate # update input-to-hidden weights with gradient descent step

            if(np.abs(layer_2_error) < 0.5):
                correct_so_far += 1
            
            reviews_per_second = i / float(time.time() - start)
            
            sys.stdout.write("\rProgress:" + str(100 * i/float(len(training_reviews)))[:4] + "% Speed(reviews/sec):" + str(reviews_per_second)[0:5] + " #Correct:" + str(correct_so_far) + " #Trained:" + str(i+1) + " Training Accuracy:" + str(correct_so_far * 100 / float(i+1))[:4] + "%")
            if(i % 2500 == 0):
                print("")
    
    def test(self, testing_reviews, testing_labels):
        
        correct = 0
        
        start = time.time()
        
        for i in range(len(testing_reviews)):
            pred = self.run(testing_reviews[i])
            if(pred == testing_labels[i]):
                correct += 1
            
            reviews_per_second = i / float(time.time() - start)
            
            sys.stdout.write("\rProgress:" + str(100 * i/float(len(testing_reviews)))[:4] \
                             + "% Speed(reviews/sec):" + str(reviews_per_second)[0:5] \
                            + "% #Correct:" + str(correct) + " #Tested:" + str(i+1) + " Testing Accuracy:" + str(correct * 100 / float(i+1))[:4] + "%")
    
    def run(self, review):
        
        # Input Layer
        self.update_input_layer(review.lower())

        # Hidden layer
        layer_1 = self.layer_0.dot(self.weights_0_1)

        # Output layer
        layer_2 = self.sigmoid(layer_1.dot(self.weights_1_2))
        
        if(layer_2[0] > 0.5):
            return "POSITIVE"
        else:
            return "NEGATIVE"


    

In [28]:

    

mlp = SentimentNetwork(reviews[:-1000],labels[:-1000], learning_rate=0.1)


    

In [29]:

    

# evaluate our model before training (just to show how horrible it is)
mlp.test(reviews[-1000:],labels[-1000:])


    

    




Progress:99.9% Speed(reviews/sec):1255.% #Correct:500 #Tested:1000 Testing Accuracy:50.0%

In [30]:

    

# train the network
mlp.train(reviews[:-1000],labels[:-1000])


    

    




Progress:0.0% Speed(reviews/sec):0.0 #Correct:0 #Trained:1 Training Accuracy:0.0%
Progress:10.4% Speed(reviews/sec):158.3 #Correct:1250 #Trained:2501 Training Accuracy:49.9%
Progress:20.8% Speed(reviews/sec):159.9 #Correct:2500 #Trained:5001 Training Accuracy:49.9%
Progress:31.2% Speed(reviews/sec):160.6 #Correct:3750 #Trained:7501 Training Accuracy:49.9%
Progress:41.6% Speed(reviews/sec):160.2 #Correct:5000 #Trained:10001 Training Accuracy:49.9%
Progress:52.0% Speed(reviews/sec):163.2 #Correct:6250 #Trained:12501 Training Accuracy:49.9%
Progress:62.5% Speed(reviews/sec):164.1 #Correct:7500 #Trained:15001 Training Accuracy:49.9%
Progress:72.9% Speed(reviews/sec):165.4 #Correct:8750 #Trained:17501 Training Accuracy:49.9%
Progress:83.3% Speed(reviews/sec):166.0 #Correct:10000 #Trained:20001 Training Accuracy:49.9%
Progress:93.7% Speed(reviews/sec):166.2 #Correct:11250 #Trained:22501 Training Accuracy:49.9%
Progress:99.9% Speed(reviews/sec):165.5 #Correct:11999 #Trained:24000 Training Accuracy:49.9%

In [31]:

    

mlp = SentimentNetwork(reviews[:-1000],labels[:-1000], learning_rate=0.01)


    

In [32]:

    

# train the network
mlp.train(reviews[:-1000],labels[:-1000])


    

    




Progress:0.0% Speed(reviews/sec):0.0 #Correct:0 #Trained:1 Training Accuracy:0.0%
Progress:10.4% Speed(reviews/sec):254.6 #Correct:1247 #Trained:2501 Training Accuracy:49.8%
Progress:20.8% Speed(reviews/sec):262.2 #Correct:2497 #Trained:5001 Training Accuracy:49.9%
Progress:31.2% Speed(reviews/sec):266.1 #Correct:3747 #Trained:7501 Training Accuracy:49.9%
Progress:41.6% Speed(reviews/sec):265.8 #Correct:4997 #Trained:10001 Training Accuracy:49.9%
Progress:52.0% Speed(reviews/sec):265.7 #Correct:6247 #Trained:12501 Training Accuracy:49.9%
Progress:62.5% Speed(reviews/sec):264.8 #Correct:7493 #Trained:15001 Training Accuracy:49.9%
Progress:72.9% Speed(reviews/sec):261.6 #Correct:8743 #Trained:17501 Training Accuracy:49.9%
Progress:83.3% Speed(reviews/sec):260.9 #Correct:9993 #Trained:20001 Training Accuracy:49.9%
Progress:93.7% Speed(reviews/sec):260.2 #Correct:11243 #Trained:22501 Training Accuracy:49.9%
Progress:99.9% Speed(reviews/sec):259.3 #Correct:11992 #Trained:24000 Training Accuracy:49.9%

In [33]:

    

mlp = SentimentNetwork(reviews[:-1000],labels[:-1000], learning_rate=0.001)


    

In [34]:

    

# train the network
mlp.train(reviews[:-1000],labels[:-1000])


    

    




Progress:0.0% Speed(reviews/sec):0.0 #Correct:0 #Trained:1 Training Accuracy:0.0%
Progress:10.4% Speed(reviews/sec):195.6 #Correct:1266 #Trained:2501 Training Accuracy:50.6%
Progress:20.8% Speed(reviews/sec):221.8 #Correct:2648 #Trained:5001 Training Accuracy:52.9%
Progress:31.2% Speed(reviews/sec):233.5 #Correct:4039 #Trained:7501 Training Accuracy:53.8%
Progress:41.6% Speed(reviews/sec):240.2 #Correct:5553 #Trained:10001 Training Accuracy:55.5%
Progress:52.0% Speed(reviews/sec):242.7 #Correct:7119 #Trained:12501 Training Accuracy:56.9%
Progress:62.5% Speed(reviews/sec):244.8 #Correct:8746 #Trained:15001 Training Accuracy:58.3%
Progress:72.9% Speed(reviews/sec):245.7 #Correct:10349 #Trained:17501 Training Accuracy:59.1%
Progress:83.3% Speed(reviews/sec):248.1 #Correct:12039 #Trained:20001 Training Accuracy:60.1%
Progress:93.7% Speed(reviews/sec):248.8 #Correct:13688 #Trained:22501 Training Accuracy:60.8%
Progress:99.9% Speed(reviews/sec):250.0 #Correct:14701 #Trained:24000 Training Accuracy:61.2%

In [35]:

    

from IPython.display import Image
Image(filename='sentiment_network.png')


    

    
Out[35]:

In [36]:

    

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 [37]:

    

layer_0


    

    
Out[37]:





array([[ 18.,   0.,   0., ...,   0.,   0.,   0.]])

In [38]:

    

review_counter = Counter()


    

In [39]:

    

for word in reviews[0].split(" "):
    review_counter[word] += 1


    

In [40]:

    

review_counter.most_common()


    

    
Out[40]:





[('.', 27),
 ('', 18),
 ('the', 9),
 ('to', 6),
 ('i', 5),
 ('high', 5),
 ('of', 4),
 ('teachers', 4),
 ('bromwell', 4),
 ('that', 4),
 ('a', 4),
 ('is', 4),
 ('my', 2),
 ('their', 2),
 ('me', 2),
 ('in', 2),
 ('it', 2),
 ('school', 2),
 ('students', 2),
 ('at', 2),
 ('student', 2),
 ('as', 2),
 ('ran', 1),
 ('cartoon', 1),
 ('time', 1),
 ('adults', 1),
 ('many', 1),
 ('burn', 1),
 ('through', 1),
 ('recalled', 1),
 ('here', 1),
 ('closer', 1),
 ('right', 1),
 ('think', 1),
 ('tried', 1),
 ('believe', 1),
 ('and', 1),
 ('saw', 1),
 ('than', 1),
 ('immediately', 1),
 ('sack', 1),
 ('inspector', 1),
 ('s', 1),
 ('financially', 1),
 ('pomp', 1),
 ('who', 1),
 ('fetched', 1),
 ('isn', 1),
 ('profession', 1),
 ('programs', 1),
 ('down', 1),
 ('welcome', 1),
 ('expect', 1),
 ('t', 1),
 ('satire', 1),
 ('scramble', 1),
 ('pathetic', 1),
 ('other', 1),
 ('much', 1),
 ('repeatedly', 1),
 ('some', 1),
 ('episode', 1),
 ('remind', 1),
 ('lead', 1),
 ('reality', 1),
 ('survive', 1),
 ('years', 1),
 ('such', 1),
 ('all', 1),
 ('pity', 1),
 ('age', 1),
 ('schools', 1),
 ('same', 1),
 ('far', 1),
 ('which', 1),
 ('pettiness', 1),
 ('m', 1),
 ('teaching', 1),
 ('life', 1),
 ('knew', 1),
 ('insightful', 1),
 ('when', 1),
 ('see', 1),
 ('about', 1),
 ('can', 1),
 ('situation', 1),
 ('classic', 1),
 ('whole', 1),
 ('one', 1),
 ('your', 1),
 ('comedy', 1),
 ('what', 1),
 ('line', 1)]

In [ ]: