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 [5]:

    

labels[0]


    

    
Out[5]:





'POSITIVE'

In [6]:

    

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 [7]:

    

from collections import Counter
import numpy as np


    

In [8]:

    

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


    

In [9]:

    

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 [10]:

    

positive_counts.most_common()


    

    
Out[10]:





[('', 550468),
 ('the', 173324),
 ('.', 159654),
 ('and', 89722),
 ('a', 83688),
 ('of', 76855),
 ('to', 66746),
 ('is', 57245),
 ('in', 50215),
 ('br', 49235),
 ('it', 48025),
 ('i', 40743),
 ('that', 35630),
 ('this', 35080),
 ('s', 33815),
 ('as', 26308),
 ('with', 23247),
 ('for', 22416),
 ('was', 21917),
 ('film', 20937),
 ('but', 20822),
 ('movie', 19074),
 ('his', 17227),
 ('on', 17008),
 ('you', 16681),
 ('he', 16282),
 ('are', 14807),
 ('not', 14272),
 ('t', 13720),
 ('one', 13655),
 ('have', 12587),
 ('be', 12416),
 ('by', 11997),
 ('all', 11942),
 ('who', 11464),
 ('an', 11294),
 ('at', 11234),
 ('from', 10767),
 ('her', 10474),
 ('they', 9895),
 ('has', 9186),
 ('so', 9154),
 ('like', 9038),
 ('about', 8313),
 ('very', 8305),
 ('out', 8134),
 ('there', 8057),
 ('she', 7779),
 ('what', 7737),
 ('or', 7732),
 ('good', 7720),
 ('more', 7521),
 ('when', 7456),
 ('some', 7441),
 ('if', 7285),
 ('just', 7152),
 ('can', 7001),
 ('story', 6780),
 ('time', 6515),
 ('my', 6488),
 ('great', 6419),
 ('well', 6405),
 ('up', 6321),
 ('which', 6267),
 ('their', 6107),
 ('see', 6026),
 ('also', 5550),
 ('we', 5531),
 ('really', 5476),
 ('would', 5400),
 ('will', 5218),
 ('me', 5167),
 ('had', 5148),
 ('only', 5137),
 ('him', 5018),
 ('even', 4964),
 ('most', 4864),
 ('other', 4858),
 ('were', 4782),
 ('first', 4755),
 ('than', 4736),
 ('much', 4685),
 ('its', 4622),
 ('no', 4574),
 ('into', 4544),
 ('people', 4479),
 ('best', 4319),
 ('love', 4301),
 ('get', 4272),
 ('how', 4213),
 ('life', 4199),
 ('been', 4189),
 ('because', 4079),
 ('way', 4036),
 ('do', 3941),
 ('made', 3823),
 ('films', 3813),
 ('them', 3805),
 ('after', 3800),
 ('many', 3766),
 ('two', 3733),
 ('too', 3659),
 ('think', 3655),
 ('movies', 3586),
 ('characters', 3560),
 ('character', 3514),
 ('don', 3468),
 ('man', 3460),
 ('show', 3432),
 ('watch', 3424),
 ('seen', 3414),
 ('then', 3358),
 ('little', 3341),
 ('still', 3340),
 ('make', 3303),
 ('could', 3237),
 ('never', 3226),
 ('being', 3217),
 ('where', 3173),
 ('does', 3069),
 ('over', 3017),
 ('any', 3002),
 ('while', 2899),
 ('know', 2833),
 ('did', 2790),
 ('years', 2758),
 ('here', 2740),
 ('ever', 2734),
 ('end', 2696),
 ('these', 2694),
 ('such', 2590),
 ('real', 2568),
 ('scene', 2567),
 ('back', 2547),
 ('those', 2485),
 ('though', 2475),
 ('off', 2463),
 ('new', 2458),
 ('your', 2453),
 ('go', 2440),
 ('acting', 2437),
 ('plot', 2432),
 ('world', 2429),
 ('scenes', 2427),
 ('say', 2414),
 ('through', 2409),
 ('makes', 2390),
 ('better', 2381),
 ('now', 2368),
 ('work', 2346),
 ('young', 2343),
 ('old', 2311),
 ('ve', 2307),
 ('find', 2272),
 ('both', 2248),
 ('before', 2177),
 ('us', 2162),
 ('again', 2158),
 ('series', 2153),
 ('quite', 2143),
 ('something', 2135),
 ('cast', 2133),
 ('should', 2121),
 ('part', 2098),
 ('always', 2088),
 ('lot', 2087),
 ('another', 2075),
 ('actors', 2047),
 ('director', 2040),
 ('family', 2032),
 ('between', 2016),
 ('own', 2016),
 ('m', 1998),
 ('may', 1997),
 ('same', 1972),
 ('role', 1967),
 ('watching', 1966),
 ('every', 1954),
 ('funny', 1953),
 ('doesn', 1935),
 ('performance', 1928),
 ('few', 1918),
 ('bad', 1907),
 ('look', 1900),
 ('re', 1884),
 ('why', 1855),
 ('things', 1849),
 ('times', 1832),
 ('big', 1815),
 ('however', 1795),
 ('actually', 1790),
 ('action', 1789),
 ('going', 1783),
 ('bit', 1757),
 ('comedy', 1742),
 ('down', 1740),
 ('music', 1738),
 ('must', 1728),
 ('take', 1709),
 ('saw', 1692),
 ('long', 1690),
 ('right', 1688),
 ('fun', 1686),
 ('fact', 1684),
 ('excellent', 1683),
 ('around', 1674),
 ('didn', 1672),
 ('without', 1671),
 ('thing', 1662),
 ('thought', 1639),
 ('got', 1635),
 ('each', 1630),
 ('day', 1614),
 ('feel', 1597),
 ('seems', 1596),
 ('come', 1594),
 ('done', 1586),
 ('beautiful', 1580),
 ('especially', 1572),
 ('played', 1571),
 ('almost', 1566),
 ('want', 1562),
 ('yet', 1556),
 ('give', 1553),
 ('pretty', 1549),
 ('last', 1543),
 ('since', 1519),
 ('different', 1504),
 ('although', 1501),
 ('gets', 1490),
 ('true', 1487),
 ('interesting', 1481),
 ('job', 1470),
 ('enough', 1455),
 ('our', 1454),
 ('shows', 1447),
 ('horror', 1441),
 ('woman', 1439),
 ('tv', 1400),
 ('probably', 1398),
 ('father', 1395),
 ('original', 1393),
 ('girl', 1390),
 ('point', 1379),
 ('plays', 1378),
 ('wonderful', 1372),
 ('far', 1358),
 ('course', 1358),
 ('john', 1350),
 ('rather', 1340),
 ('isn', 1328),
 ('ll', 1326),
 ('later', 1324),
 ('dvd', 1324),
 ('whole', 1310),
 ('war', 1310),
 ('d', 1307),
 ('found', 1306),
 ('away', 1306),
 ('screen', 1305),
 ('nothing', 1300),
 ('year', 1297),
 ('once', 1296),
 ('hard', 1294),
 ('together', 1280),
 ('set', 1277),
 ('am', 1277),
 ('having', 1266),
 ('making', 1265),
 ('place', 1263),
 ('might', 1260),
 ('comes', 1260),
 ('sure', 1253),
 ('american', 1248),
 ('play', 1245),
 ('kind', 1244),
 ('perfect', 1242),
 ('takes', 1242),
 ('performances', 1237),
 ('himself', 1230),
 ('worth', 1221),
 ('everyone', 1221),
 ('anyone', 1214),
 ('actor', 1203),
 ('three', 1201),
 ('wife', 1196),
 ('classic', 1192),
 ('goes', 1186),
 ('ending', 1178),
 ('version', 1168),
 ('star', 1149),
 ('enjoy', 1146),
 ('book', 1142),
 ('nice', 1132),
 ('everything', 1128),
 ('during', 1124),
 ('put', 1118),
 ('seeing', 1111),
 ('least', 1102),
 ('house', 1100),
 ('high', 1095),
 ('watched', 1094),
 ('loved', 1087),
 ('men', 1087),
 ('night', 1082),
 ('anything', 1075),
 ('believe', 1071),
 ('guy', 1071),
 ('top', 1063),
 ('amazing', 1058),
 ('hollywood', 1056),
 ('looking', 1053),
 ('main', 1044),
 ('definitely', 1043),
 ('gives', 1031),
 ('home', 1029),
 ('seem', 1028),
 ('episode', 1023),
 ('audience', 1020),
 ('sense', 1020),
 ('truly', 1017),
 ('special', 1011),
 ('second', 1009),
 ('short', 1009),
 ('fan', 1009),
 ('mind', 1005),
 ('human', 1001),
 ('recommend', 999),
 ('full', 996),
 ('black', 995),
 ('help', 991),
 ('along', 989),
 ('trying', 987),
 ('small', 986),
 ('death', 985),
 ('friends', 981),
 ('remember', 974),
 ('often', 970),
 ('said', 966),
 ('favorite', 962),
 ('heart', 959),
 ('early', 957),
 ('left', 956),
 ('until', 955),
 ('script', 954),
 ('let', 954),
 ('maybe', 937),
 ('today', 936),
 ('live', 934),
 ('less', 934),
 ('moments', 933),
 ('others', 929),
 ('brilliant', 926),
 ('shot', 925),
 ('liked', 923),
 ('become', 916),
 ('won', 915),
 ('used', 910),
 ('style', 907),
 ('mother', 895),
 ('lives', 894),
 ('came', 893),
 ('stars', 890),
 ('cinema', 889),
 ('looks', 885),
 ('perhaps', 884),
 ('read', 882),
 ('enjoyed', 879),
 ('boy', 875),
 ('drama', 873),
 ('highly', 871),
 ('given', 870),
 ('playing', 867),
 ('use', 864),
 ('next', 859),
 ('women', 858),
 ('fine', 857),
 ('effects', 856),
 ('kids', 854),
 ('entertaining', 853),
 ('need', 852),
 ('line', 850),
 ('works', 848),
 ('someone', 847),
 ('mr', 836),
 ('simply', 835),
 ('picture', 833),
 ('children', 833),
 ('face', 831),
 ('keep', 831),
 ('friend', 831),
 ('dark', 830),
 ('overall', 828),
 ('certainly', 828),
 ('minutes', 827),
 ('wasn', 824),
 ('history', 822),
 ('finally', 820),
 ('couple', 816),
 ('against', 815),
 ('son', 809),
 ('understand', 808),
 ('lost', 807),
 ('michael', 805),
 ('else', 801),
 ('throughout', 798),
 ('fans', 797),
 ('city', 792),
 ('reason', 789),
 ('written', 787),
 ('production', 787),
 ('several', 784),
 ('school', 783),
 ('based', 781),
 ('rest', 781),
 ('try', 780),
 ('dead', 776),
 ('hope', 775),
 ('strong', 768),
 ('white', 765),
 ('tell', 759),
 ('itself', 758),
 ('half', 753),
 ('person', 749),
 ('sometimes', 746),
 ('past', 744),
 ('start', 744),
 ('genre', 743),
 ('beginning', 739),
 ('final', 739),
 ('town', 738),
 ('art', 734),
 ('humor', 732),
 ('game', 732),
 ('yes', 731),
 ('idea', 731),
 ('late', 730),
 ('becomes', 729),
 ('despite', 729),
 ('able', 726),
 ('case', 726),
 ('money', 723),
 ('child', 721),
 ('completely', 721),
 ('side', 719),
 ('camera', 716),
 ('getting', 714),
 ('instead', 712),
 ('soon', 702),
 ('under', 700),
 ('viewer', 699),
 ('age', 697),
 ('days', 696),
 ('stories', 696),
 ('felt', 694),
 ('simple', 694),
 ('roles', 693),
 ('video', 688),
 ('name', 683),
 ('either', 683),
 ('doing', 677),
 ('turns', 674),
 ('wants', 671),
 ('close', 671),
 ('title', 669),
 ('wrong', 668),
 ('went', 666),
 ('james', 665),
 ('evil', 659),
 ('budget', 657),
 ('episodes', 657),
 ('relationship', 655),
 ('fantastic', 653),
 ('piece', 653),
 ('david', 651),
 ('turn', 648),
 ('murder', 646),
 ('parts', 645),
 ('brother', 644),
 ('absolutely', 643),
 ('head', 643),
 ('experience', 642),
 ('eyes', 641),
 ('sex', 638),
 ('direction', 637),
 ('called', 637),
 ('directed', 636),
 ('lines', 634),
 ('behind', 633),
 ('sort', 632),
 ('actress', 631),
 ('lead', 630),
 ('oscar', 628),
 ('including', 627),
 ('example', 627),
 ('known', 625),
 ('musical', 625),
 ('chance', 621),
 ('score', 620),
 ('already', 619),
 ('feeling', 619),
 ('hit', 619),
 ('voice', 615),
 ('moment', 612),
 ('living', 612),
 ('low', 610),
 ('supporting', 610),
 ('ago', 609),
 ('themselves', 608),
 ('reality', 605),
 ('hilarious', 605),
 ('jack', 604),
 ('told', 603),
 ('hand', 601),
 ('quality', 600),
 ('moving', 600),
 ('dialogue', 600),
 ('song', 599),
 ('happy', 599),
 ('matter', 598),
 ('paul', 598),
 ('light', 594),
 ('future', 593),
 ('entire', 592),
 ('finds', 591),
 ('gave', 589),
 ('laugh', 587),
 ('released', 586),
 ('expect', 584),
 ('fight', 581),
 ('particularly', 580),
 ('cinematography', 579),
 ('police', 579),
 ('whose', 578),
 ('type', 578),
 ('sound', 578),
 ('view', 573),
 ('enjoyable', 573),
 ('number', 572),
 ('romantic', 572),
 ('husband', 572),
 ('daughter', 572),
 ('documentary', 571),
 ('self', 570),
 ('superb', 569),
 ('modern', 569),
 ('took', 569),
 ('robert', 569),
 ('mean', 566),
 ('shown', 563),
 ('coming', 561),
 ('important', 560),
 ('king', 559),
 ('leave', 559),
 ('change', 558),
 ('somewhat', 555),
 ('wanted', 555),
 ('tells', 554),
 ('events', 552),
 ('run', 552),
 ('career', 552),
 ('country', 552),
 ('heard', 550),
 ('season', 550),
 ('greatest', 549),
 ('girls', 549),
 ('etc', 547),
 ('care', 546),
 ('starts', 545),
 ('english', 542),
 ('killer', 541),
 ('tale', 540),
 ('guys', 540),
 ('totally', 540),
 ('animation', 540),
 ('usual', 539),
 ('miss', 535),
 ('opinion', 535),
 ('easy', 531),
 ('violence', 531),
 ('songs', 530),
 ('british', 528),
 ('says', 526),
 ('realistic', 525),
 ('writing', 524),
 ('writer', 522),
 ('act', 522),
 ('comic', 521),
 ('thriller', 519),
 ('television', 517),
 ('power', 516),
 ('ones', 515),
 ('kid', 514),
 ('york', 513),
 ('novel', 513),
 ('alone', 512),
 ('problem', 512),
 ('attention', 509),
 ('involved', 508),
 ('kill', 507),
 ('extremely', 507),
 ('seemed', 506),
 ('hero', 505),
 ('french', 505),
 ('rock', 504),
 ('stuff', 501),
 ('wish', 499),
 ('begins', 498),
 ('taken', 497),
 ('sad', 497),
 ('ways', 496),
 ('richard', 495),
 ('knows', 494),
 ('atmosphere', 493),
 ('similar', 491),
 ('surprised', 491),
 ('taking', 491),
 ('car', 491),
 ('george', 490),
 ('perfectly', 490),
 ('across', 489),
 ('team', 489),
 ('eye', 489),
 ('sequence', 489),
 ('room', 488),
 ('due', 488),
 ('among', 488),
 ('serious', 488),
 ('powerful', 488),
 ('strange', 487),
 ('order', 487),
 ('cannot', 487),
 ('b', 487),
 ('beauty', 486),
 ('famous', 485),
 ('happened', 484),
 ('tries', 484),
 ('herself', 484),
 ('myself', 484),
 ('class', 483),
 ('four', 482),
 ('cool', 481),
 ('release', 479),
 ('anyway', 479),
 ('theme', 479),
 ('opening', 478),
 ('entertainment', 477),
 ('slow', 475),
 ('ends', 475),
 ('unique', 475),
 ('exactly', 475),
 ('easily', 474),
 ('level', 474),
 ('o', 474),
 ('red', 474),
 ('interest', 472),
 ('happen', 471),
 ('crime', 470),
 ('viewing', 468),
 ('sets', 467),
 ('memorable', 467),
 ('stop', 466),
 ('group', 466),
 ('problems', 463),
 ('dance', 463),
 ('working', 463),
 ('sister', 463),
 ('message', 463),
 ('knew', 462),
 ('mystery', 461),
 ('nature', 461),
 ('bring', 460),
 ('believable', 459),
 ('thinking', 459),
 ('brought', 459),
 ('mostly', 458),
 ('disney', 457),
 ('couldn', 457),
 ('society', 456),
 ('lady', 455),
 ('within', 455),
 ('blood', 454),
 ('parents', 453),
 ('upon', 453),
 ('viewers', 453),
 ('meets', 452),
 ('form', 452),
 ('peter', 452),
 ('tom', 452),
 ('usually', 452),
 ('soundtrack', 452),
 ('local', 450),
 ('certain', 448),
 ('follow', 448),
 ('whether', 447),
 ('possible', 446),
 ('emotional', 445),
 ('killed', 444),
 ('above', 444),
 ('de', 444),
 ('god', 443),
 ('middle', 443),
 ('needs', 442),
 ('happens', 442),
 ('flick', 442),
 ('masterpiece', 441),
 ('period', 440),
 ('major', 440),
 ('named', 439),
 ('haven', 439),
 ('particular', 438),
 ('th', 438),
 ('earth', 437),
 ('feature', 437),
 ('stand', 436),
 ('words', 435),
 ('typical', 435),
 ('elements', 433),
 ('obviously', 433),
 ('romance', 431),
 ('jane', 430),
 ('yourself', 427),
 ('showing', 427),
 ('brings', 426),
 ('fantasy', 426),
 ('guess', 423),
 ('america', 423),
 ('unfortunately', 422),
 ('huge', 422),
 ('indeed', 421),
 ('running', 421),
 ('talent', 420),
 ('stage', 419),
 ('started', 418),
 ('leads', 417),
 ('sweet', 417),
 ('japanese', 417),
 ('poor', 416),
 ('deal', 416),
 ('incredible', 413),
 ('personal', 413),
 ('fast', 412),
 ('became', 410),
 ('deep', 410),
 ('hours', 409),
 ('giving', 408),
 ('nearly', 408),
 ('dream', 408),
 ('clearly', 407),
 ('turned', 407),
 ('obvious', 406),
 ('near', 406),
 ('cut', 405),
 ('surprise', 405),
 ('era', 404),
 ('body', 404),
 ('hour', 403),
 ('female', 403),
 ('five', 403),
 ('note', 399),
 ('learn', 398),
 ('truth', 398),
 ('except', 397),
 ('feels', 397),
 ('match', 397),
 ('tony', 397),
 ('filmed', 394),
 ('clear', 394),
 ('complete', 394),
 ('street', 393),
 ('eventually', 393),
 ('keeps', 393),
 ('older', 393),
 ('lots', 393),
 ('buy', 392),
 ('william', 391),
 ('stewart', 391),
 ('fall', 390),
 ('joe', 390),
 ('meet', 390),
 ('unlike', 389),
 ('talking', 389),
 ('shots', 389),
 ('rating', 389),
 ('difficult', 389),
 ('dramatic', 388),
 ('means', 388),
 ('situation', 386),
 ('wonder', 386),
 ('present', 386),
 ('appears', 386),
 ('subject', 386),
 ('comments', 385),
 ('general', 383),
 ('sequences', 383),
 ('lee', 383),
 ('points', 382),
 ('earlier', 382),
 ('gone', 379),
 ('check', 379),
 ('suspense', 378),
 ('recommended', 378),
 ('ten', 378),
 ('third', 377),
 ('business', 377),
 ('talk', 375),
 ('leaves', 375),
 ('beyond', 375),
 ('portrayal', 374),
 ('beautifully', 373),
 ('single', 372),
 ('bill', 372),
 ('plenty', 371),
 ('word', 371),
 ('whom', 370),
 ('falls', 370),
 ('scary', 369),
 ('non', 369),
 ('figure', 369),
 ('battle', 369),
 ('using', 368),
 ('return', 368),
 ('doubt', 367),
 ('add', 367),
 ('hear', 366),
 ('solid', 366),
 ('success', 366),
 ('jokes', 365),
 ('oh', 365),
 ('touching', 365),
 ('political', 365),
 ('hell', 364),
 ('awesome', 364),
 ('boys', 364),
 ('sexual', 362),
 ('recently', 362),
 ('dog', 362),
 ('please', 361),
 ('wouldn', 361),
 ('straight', 361),
 ('features', 361),
 ('forget', 360),
 ('setting', 360),
 ('lack', 360),
 ('married', 359),
 ('mark', 359),
 ('social', 357),
 ('interested', 356),
 ('adventure', 356),
 ('actual', 355),
 ('terrific', 355),
 ('sees', 355),
 ('brothers', 355),
 ('move', 354),
 ('call', 354),
 ('various', 353),
 ('theater', 353),
 ('dr', 353),
 ('animated', 352),
 ('western', 351),
 ('baby', 350),
 ('space', 350),
 ('leading', 348),
 ('disappointed', 348),
 ('portrayed', 346),
 ('aren', 346),
 ('screenplay', 345),
 ('smith', 345),
 ('towards', 344),
 ('hate', 344),
 ('noir', 343),
 ('outstanding', 342),
 ('decent', 342),
 ('kelly', 342),
 ('directors', 341),
 ('journey', 341),
 ('none', 340),
 ('looked', 340),
 ('effective', 340),
 ('storyline', 339),
 ('caught', 339),
 ('sci', 339),
 ('fi', 339),
 ('cold', 339),
 ('mary', 339),
 ('rich', 338),
 ('charming', 338),
 ('popular', 337),
 ('rare', 337),
 ('manages', 337),
 ('harry', 337),
 ('spirit', 336),
 ('appreciate', 335),
 ('open', 335),
 ('moves', 334),
 ('basically', 334),
 ('acted', 334),
 ('inside', 333),
 ('boring', 333),
 ('century', 333),
 ('mention', 333),
 ('deserves', 333),
 ('subtle', 333),
 ('pace', 333),
 ('familiar', 332),
 ('background', 332),
 ('ben', 331),
 ('creepy', 330),
 ('supposed', 330),
 ('secret', 329),
 ('die', 328),
 ('jim', 328),
 ('question', 327),
 ('effect', 327),
 ('natural', 327),
 ('impressive', 326),
 ('rate', 326),
 ('language', 326),
 ('saying', 325),
 ('intelligent', 325),
 ('telling', 324),
 ('realize', 324),
 ('material', 324),
 ('scott', 324),
 ('singing', 323),
 ('dancing', 322),
 ('visual', 321),
 ('adult', 321),
 ('imagine', 321),
 ('kept', 320),
 ('office', 320),
 ('uses', 319),
 ('pure', 318),
 ('wait', 318),
 ('stunning', 318),
 ('review', 317),
 ('previous', 317),
 ('copy', 317),
 ('seriously', 317),
 ('reading', 316),
 ('create', 316),
 ('hot', 316),
 ('created', 316),
 ('magic', 316),
 ('somehow', 316),
 ('stay', 315),
 ('attempt', 315),
 ('escape', 315),
 ('crazy', 315),
 ('air', 315),
 ('frank', 315),
 ('hands', 314),
 ('filled', 313),
 ('expected', 312),
 ('average', 312),
 ('surprisingly', 312),
 ('complex', 311),
 ('quickly', 310),
 ('successful', 310),
 ('studio', 310),
 ('plus', 309),
 ('male', 309),
 ('co', 307),
 ('images', 306),
 ('casting', 306),
 ('following', 306),
 ('minute', 306),
 ('exciting', 306),
 ('members', 305),
 ('follows', 305),
 ('themes', 305),
 ('german', 305),
 ('reasons', 305),
 ('e', 305),
 ('touch', 304),
 ('edge', 304),
 ('free', 304),
 ('cute', 304),
 ('genius', 304),
 ('outside', 303),
 ('reviews', 302),
 ('admit', 302),
 ('ok', 302),
 ('younger', 302),
 ('fighting', 301),
 ('odd', 301),
 ('master', 301),
 ('recent', 300),
 ('thanks', 300),
 ('break', 300),
 ('comment', 300),
 ('apart', 299),
 ('emotions', 298),
 ('lovely', 298),
 ('begin', 298),
 ('doctor', 297),
 ('party', 297),
 ('italian', 297),
 ('la', 296),
 ('missed', 296),
 ...]

In [11]:

    

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 [12]:

    

# words most frequently seen in a review with a "POSITIVE" label
pos_neg_ratios.most_common()


    

    
Out[12]:





[('edie', 4.6913478822291435),
 ('paulie', 4.0775374439057197),
 ('felix', 3.1527360223636558),
 ('polanski', 2.8233610476132043),
 ('matthau', 2.8067217286092401),
 ('victoria', 2.6810215287142909),
 ('mildred', 2.6026896854443837),
 ('gandhi', 2.5389738710582761),
 ('flawless', 2.451005098112319),
 ('superbly', 2.2600254785752498),
 ('perfection', 2.1594842493533721),
 ('astaire', 2.1400661634962708),
 ('captures', 2.0386195471595809),
 ('voight', 2.0301704926730531),
 ('wonderfully', 2.0218960560332353),
 ('powell', 1.9783454248084671),
 ('brosnan', 1.9547990964725592),
 ('lily', 1.9203768470501485),
 ('bakshi', 1.9029851043382795),
 ('lincoln', 1.9014583864844796),
 ('refreshing', 1.8551812956655511),
 ('breathtaking', 1.8481124057791867),
 ('bourne', 1.8478489358790986),
 ('lemmon', 1.8458266904983307),
 ('delightful', 1.8002701588959635),
 ('flynn', 1.7996646487351682),
 ('andrews', 1.7764919970972666),
 ('homer', 1.7692866133759964),
 ('beautifully', 1.7626953362841438),
 ('soccer', 1.7578579175523736),
 ('elvira', 1.7397031072720019),
 ('underrated', 1.7197859696029656),
 ('gripping', 1.7165360479904674),
 ('superb', 1.7091514458966952),
 ('delight', 1.6714733033535532),
 ('welles', 1.6677068205580761),
 ('sadness', 1.663505133704376),
 ('sinatra', 1.6389967146756448),
 ('touching', 1.637217476541176),
 ('timeless', 1.62924053973028),
 ('macy', 1.6211339521972916),
 ('unforgettable', 1.6177367152487956),
 ('favorites', 1.6158688027643908),
 ('stewart', 1.6119987332957739),
 ('sullivan', 1.6094379124341003),
 ('extraordinary', 1.6094379124341003),
 ('hartley', 1.6094379124341003),
 ('brilliantly', 1.5950491749820008),
 ('friendship', 1.5677652160335325),
 ('wonderful', 1.5645425925262093),
 ('palma', 1.5553706911638245),
 ('magnificent', 1.54663701119507),
 ('finest', 1.5462590108125689),
 ('jackie', 1.5439233053234738),
 ('ritter', 1.5404450409471491),
 ('tremendous', 1.5184661342283736),
 ('freedom', 1.5091151908062312),
 ('fantastic', 1.5048433868558566),
 ('terrific', 1.5026699370083942),
 ('noir', 1.493925025312256),
 ('sidney', 1.493925025312256),
 ('outstanding', 1.4910053152089213),
 ('pleasantly', 1.4894785973551214),
 ('mann', 1.4894785973551214),
 ('nancy', 1.488077055429833),
 ('marie', 1.4825711915553104),
 ('marvelous', 1.4739999415389962),
 ('excellent', 1.4647538505723599),
 ('ruth', 1.4596256342054401),
 ('stanwyck', 1.4412101187160054),
 ('widmark', 1.4350845252893227),
 ('splendid', 1.4271163556401458),
 ('chan', 1.423108334242607),
 ('exceptional', 1.4201959127955721),
 ('tender', 1.410986973710262),
 ('gentle', 1.4078005663408544),
 ('poignant', 1.4022947024663317),
 ('gem', 1.3932148039644643),
 ('amazing', 1.3919815802404802),
 ('chilling', 1.3862943611198906),
 ('fisher', 1.3862943611198906),
 ('davies', 1.3862943611198906),
 ('captivating', 1.3862943611198906),
 ('darker', 1.3652409519220583),
 ('april', 1.3499267169490159),
 ('kelly', 1.3461743673304654),
 ('blake', 1.3418425985490567),
 ('overlooked', 1.329135947279942),
 ('ralph', 1.32818673031261),
 ('bette', 1.3156767939059373),
 ('hoffman', 1.3150668518315229),
 ('cole', 1.3121863889661687),
 ('shines', 1.3049487216659381),
 ('powerful', 1.2999662776313934),
 ('notch', 1.2950456896547455),
 ('remarkable', 1.2883688239495823),
 ('pitt', 1.286210902562908),
 ('winters', 1.2833463918674481),
 ('vivid', 1.2762934659055623),
 ('gritty', 1.2757524867200667),
 ('giallo', 1.2745029551317739),
 ('portrait', 1.2704625455947689),
 ('innocence', 1.2694300209805796),
 ('psychiatrist', 1.2685113254635072),
 ('favorite', 1.2668956297860055),
 ('ensemble', 1.2656663733312759),
 ('stunning', 1.2622417124499117),
 ('burns', 1.259880436264232),
 ('garbo', 1.258954938743289),
 ('barbara', 1.2580400255962119),
 ('philip', 1.2527629684953681),
 ('panic', 1.2527629684953681),
 ('holly', 1.2527629684953681),
 ('carol', 1.2481440226390734),
 ('perfect', 1.246742480713785),
 ('appreciated', 1.2462482874741743),
 ('favourite', 1.2411123512753928),
 ('journey', 1.2367626271489269),
 ('rural', 1.235471471385307),
 ('bond', 1.2321436812926323),
 ('builds', 1.2305398317106577),
 ('brilliant', 1.2287554137664785),
 ('brooklyn', 1.2286654169163074),
 ('von', 1.225175011976539),
 ('recommended', 1.2163953243244932),
 ('unfolds', 1.2163953243244932),
 ('daniel', 1.20215296760895),
 ('perfectly', 1.1971931173405572),
 ('crafted', 1.1962507582320256),
 ('prince', 1.1939224684724346),
 ('troubled', 1.192138346678933),
 ('consequences', 1.1865810616140668),
 ('haunting', 1.1814999484738773),
 ('cinderella', 1.180052620608284),
 ('alexander', 1.1759989522835299),
 ('emotions', 1.1753049094563641),
 ('boxing', 1.1735135968412274),
 ('subtle', 1.1734135017508081),
 ('curtis', 1.1649873576129823),
 ('rare', 1.1566438362402944),
 ('loved', 1.1563661500586044),
 ('daughters', 1.1526795099383853),
 ('courage', 1.1438688802562305),
 ('dentist', 1.1426722784621401),
 ('highly', 1.1420208631618658),
 ('nominated', 1.1409146683587992),
 ('tony', 1.1397491942285991),
 ('draws', 1.1325138403437911),
 ('everyday', 1.1306150197542835),
 ('contrast', 1.1284652518177909),
 ('cried', 1.1213405397456659),
 ('fabulous', 1.1210851445201684),
 ('ned', 1.120591195386885),
 ('fay', 1.120591195386885),
 ('emma', 1.1184149159642893),
 ('sensitive', 1.113318436057805),
 ('smooth', 1.1089750757036563),
 ('dramas', 1.1080910326226534),
 ('today', 1.1050431789984001),
 ('helps', 1.1023091505494358),
 ('inspiring', 1.0986122886681098),
 ('jimmy', 1.0937696641923216),
 ('awesome', 1.0931328229034842),
 ('unique', 1.0881409888008142),
 ('tragic', 1.0871835928444868),
 ('intense', 1.0870514662670339),
 ('stellar', 1.0857088838322018),
 ('rival', 1.0822184788924332),
 ('provides', 1.0797081340289569),
 ('depression', 1.0782034170369026),
 ('shy', 1.0775588794702773),
 ('carrie', 1.076139432816051),
 ('blend', 1.0753554265038423),
 ('hank', 1.0736109864626924),
 ('diana', 1.0726368022648489),
 ('adorable', 1.0726368022648489),
 ('unexpected', 1.0722255334949147),
 ('achievement', 1.0668635903535293),
 ('bettie', 1.0663514264498881),
 ('happiness', 1.0632729222228008),
 ('glorious', 1.0608719606852626),
 ('davis', 1.0541605260972757),
 ('terrifying', 1.0525211814678428),
 ('beauty', 1.050410186850232),
 ('ideal', 1.0479685558493548),
 ('fears', 1.0467872208035236),
 ('hong', 1.0438040521731147),
 ('seasons', 1.0433496099930604),
 ('fascinating', 1.0414538748281612),
 ('carries', 1.0345904299031787),
 ('satisfying', 1.0321225473992768),
 ('definite', 1.0319209141694374),
 ('touched', 1.0296194171811581),
 ('greatest', 1.0248947127715422),
 ('creates', 1.0241097613701886),
 ('aunt', 1.023388867430522),
 ('walter', 1.022328983918479),
 ('spectacular', 1.0198314108149955),
 ('portrayal', 1.0189810189761024),
 ('ann', 1.0127808528183286),
 ('enterprise', 1.0116009116784799),
 ('musicals', 1.0096648026516135),
 ('deeply', 1.0094845087721023),
 ('incredible', 1.0061677561461084),
 ('mature', 1.0060195018402847),
 ('triumph', 0.99682959435816731),
 ('margaret', 0.99682959435816731),
 ('navy', 0.99493385919326827),
 ('harry', 0.99176919305006062),
 ('lucas', 0.990398704027877),
 ('sweet', 0.98966110487955483),
 ('joey', 0.98794672078059009),
 ('oscar', 0.98721905111049713),
 ('balance', 0.98649499054740353),
 ('warm', 0.98485340331145166),
 ('ages', 0.98449898190068863),
 ('guilt', 0.98082925301172619),
 ('glover', 0.98082925301172619),
 ('carrey', 0.98082925301172619),
 ('learns', 0.97881108885548895),
 ('unusual', 0.97788374278196932),
 ('sons', 0.97777581552483595),
 ('complex', 0.97761897738147796),
 ('essence', 0.97753435711487369),
 ('brazil', 0.9769153536905899),
 ('widow', 0.97650959186720987),
 ('solid', 0.97537964824416146),
 ('beautiful', 0.97326301262841053),
 ('holmes', 0.97246100334120955),
 ('awe', 0.97186058302896583),
 ('vhs', 0.97116734209998934),
 ('eerie', 0.97116734209998934),
 ('lonely', 0.96873720724669754),
 ('grim', 0.96873720724669754),
 ('sport', 0.96825047080486615),
 ('debut', 0.96508089604358704),
 ('destiny', 0.96343751029985703),
 ('thrillers', 0.96281074750904794),
 ('tears', 0.95977584381389391),
 ('rose', 0.95664202739772253),
 ('feelings', 0.95551144502743635),
 ('ginger', 0.95551144502743635),
 ('winning', 0.95471810900804055),
 ('stanley', 0.95387344302319799),
 ('cox', 0.95343027882361187),
 ('paris', 0.95278479030472663),
 ('heart', 0.95238806924516806),
 ('hooked', 0.95155887071161305),
 ('comfortable', 0.94803943018873538),
 ('mgm', 0.94446160884085151),
 ('masterpiece', 0.94155039863339296),
 ('themes', 0.94118828349588235),
 ('danny', 0.93967118051821874),
 ('anime', 0.93378388932167222),
 ('perry', 0.93328830824272613),
 ('joy', 0.93301752567946861),
 ('lovable', 0.93081883243706487),
 ('mysteries', 0.92953595862417571),
 ('hal', 0.92953595862417571),
 ('louis', 0.92871325187271225),
 ('charming', 0.92520609553210742),
 ('urban', 0.92367083917177761),
 ('allows', 0.92183091224977043),
 ('impact', 0.91815814604895041),
 ('italy', 0.91629073187415511),
 ('gradually', 0.91629073187415511),
 ('lifestyle', 0.91629073187415511),
 ('spy', 0.91289514287301687),
 ('treat', 0.91193342650519937),
 ('subsequent', 0.91056005716517008),
 ('kennedy', 0.90981821736853763),
 ('loving', 0.90967549275543591),
 ('surprising', 0.90937028902958128),
 ('quiet', 0.90648673177753425),
 ('winter', 0.90624039602065365),
 ('reveals', 0.90490540964902977),
 ('raw', 0.90445627422715225),
 ('funniest', 0.90078654533818991),
 ('pleased', 0.89994159387262562),
 ('norman', 0.89994159387262562),
 ('thief', 0.89874642222324552),
 ('season', 0.89827222637147675),
 ('secrets', 0.89794159320595857),
 ('colorful', 0.89705936994626756),
 ('highest', 0.8967461358011849),
 ('compelling', 0.89462923509297576),
 ('danes', 0.89248008318043659),
 ('castle', 0.88967708335606499),
 ('kudos', 0.88889175768604067),
 ('great', 0.88810470901464589),
 ('baseball', 0.88730319500090271),
 ('subtitles', 0.88730319500090271),
 ('bleak', 0.88730319500090271),
 ('winner', 0.88643776872447388),
 ('tragedy', 0.88563699078315261),
 ('todd', 0.88551907320740142),
 ('nicely', 0.87924946019380601),
 ('arthur', 0.87546873735389985),
 ('essential', 0.87373111745535925),
 ('gorgeous', 0.8731725250935497),
 ('fonda', 0.87294029100054127),
 ('eastwood', 0.87139541196626402),
 ('focuses', 0.87082835779739776),
 ('enjoyed', 0.87070195951624607),
 ('natural', 0.86997924506912838),
 ('intensity', 0.86835126958503595),
 ('witty', 0.86824103423244681),
 ('rob', 0.8642954367557748),
 ('worlds', 0.86377269759070874),
 ('health', 0.86113891179907498),
 ('magical', 0.85953791528170564),
 ('deeper', 0.85802182375017932),
 ('lucy', 0.85618680780444956),
 ('moving', 0.85566611005772031),
 ('lovely', 0.85290640004681306),
 ('purple', 0.8513711857748395),
 ('memorable', 0.84801189112086062),
 ('sings', 0.84729786038720367),
 ('craig', 0.84342938360928321),
 ('modesty', 0.84342938360928321),
 ('relate', 0.84326559685926517),
 ('episodes', 0.84223712084137292),
 ('strong', 0.84167135777060931),
 ('smith', 0.83959811108590054),
 ('tear', 0.83704136022001441),
 ('apartment', 0.83333115290549531),
 ('princess', 0.83290912293510388),
 ('disagree', 0.83290912293510388),
 ('kung', 0.83173334384609199),
 ('adventure', 0.83150561393278388),
 ('columbo', 0.82667857318446791),
 ('jake', 0.82667857318446791),
 ('adds', 0.82485652591452319),
 ('hart', 0.82472353834866463),
 ('strength', 0.82417544296634937),
 ('realizes', 0.82360006895738058),
 ('dave', 0.8232003088081431),
 ('childhood', 0.82208086393583857),
 ('forbidden', 0.81989888619908913),
 ('tight', 0.81883539572344199),
 ('surreal', 0.8178506590609026),
 ('manager', 0.81770990320170756),
 ('dancer', 0.81574950265227764),
 ('studios', 0.81093021621632877),
 ('con', 0.81093021621632877),
 ('miike', 0.80821651034473263),
 ('realistic', 0.80807714723392232),
 ('explicit', 0.80792269515237358),
 ('kurt', 0.8060875917405409),
 ('traditional', 0.80535917116687328),
 ('deals', 0.80535917116687328),
 ('holds', 0.80493858654806194),
 ('carl', 0.80437281567016972),
 ('touches', 0.80396154690023547),
 ('gene', 0.80314807577427383),
 ('albert', 0.8027669055771679),
 ('abc', 0.80234647252493729),
 ('cry', 0.80011930011211307),
 ('sides', 0.7995275841185171),
 ('develops', 0.79850769621777162),
 ('eyre', 0.79850769621777162),
 ('dances', 0.79694397424158891),
 ('oscars', 0.79633141679517616),
 ('legendary', 0.79600456599965308),
 ('hearted', 0.79492987486988764),
 ('importance', 0.79492987486988764),
 ('portraying', 0.79356592830699269),
 ('impressed', 0.79258107754813223),
 ('waters', 0.79112758892014912),
 ('empire', 0.79078565012386137),
 ('edge', 0.789774016249017),
 ('jean', 0.78845736036427028),
 ('environment', 0.78845736036427028),
 ('sentimental', 0.7864791203521645),
 ('captured', 0.78623760362595729),
 ('styles', 0.78592891401091158),
 ('daring', 0.78592891401091158),
 ('frank', 0.78275933924963248),
 ('tense', 0.78275933924963248),
 ('backgrounds', 0.78275933924963248),
 ('matches', 0.78275933924963248),
 ('gothic', 0.78209466657644144),
 ('sharp', 0.7814397877056235),
 ('achieved', 0.78015855754957497),
 ('court', 0.77947526404844247),
 ('steals', 0.7789140023173704),
 ('rules', 0.77844476107184035),
 ('colors', 0.77684619943659217),
 ('reunion', 0.77318988823348167),
 ('covers', 0.77139937745969345),
 ('tale', 0.77010822169607374),
 ('rain', 0.7683706017975328),
 ('denzel', 0.76804848873306297),
 ('stays', 0.76787072675588186),
 ('blob', 0.76725515271366718),
 ('maria', 0.76214005204689672),
 ('conventional', 0.76214005204689672),
 ('fresh', 0.76158434211317383),
 ('midnight', 0.76096977689870637),
 ('landscape', 0.75852993982279704),
 ('animated', 0.75768570169751648),
 ('titanic', 0.75666058628227129),
 ('sunday', 0.75666058628227129),
 ('spring', 0.7537718023763802),
 ('cagney', 0.7537718023763802),
 ('enjoyable', 0.75246375771636476),
 ('immensely', 0.75198768058287868),
 ('sir', 0.7507762933965817),
 ('nevertheless', 0.75067102469813185),
 ('driven', 0.74994477895307854),
 ('performances', 0.74883252516063137),
 ('memories', 0.74721440183022114),
 ('nowadays', 0.74721440183022114),
 ('simple', 0.74641420974143258),
 ('golden', 0.74533293373051557),
 ('leslie', 0.74533293373051557),
 ('lovers', 0.74497224842453125),
 ('relationship', 0.74484232345601786),
 ('supporting', 0.74357803418683721),
 ('che', 0.74262723782331497),
 ('packed', 0.7410032017375805),
 ('trek', 0.74021469141793106),
 ('provoking', 0.73840377214806618),
 ('strikes', 0.73759894313077912),
 ('depiction', 0.73682224406260699),
 ('emotional', 0.73678211645681524),
 ('secretary', 0.7366322924996842),
 ('influenced', 0.73511137965897755),
 ('florida', 0.73511137965897755),
 ('germany', 0.73288750920945944),
 ('brings', 0.73142936713096229),
 ('lewis', 0.73129894652432159),
 ('elderly', 0.73088750854279239),
 ('owner', 0.72743625403857748),
 ('streets', 0.72666987259858895),
 ('henry', 0.72642196944481741),
 ('portrays', 0.72593700338293632),
 ('bears', 0.7252354951114458),
 ('china', 0.72489587887452556),
 ('anger', 0.72439972406404984),
 ('society', 0.72433010799663333),
 ('available', 0.72415741730250549),
 ('best', 0.72347034060446314),
 ('bugs', 0.72270598280148979),
 ('magic', 0.71878961117328299),
 ('delivers', 0.71846498854423513),
 ('verhoeven', 0.71846498854423513),
 ('jim', 0.71783979315031676),
 ('donald', 0.71667767797013937),
 ('endearing', 0.71465338578090898),
 ('relationships', 0.71393795022901896),
 ('greatly', 0.71256526641704687),
 ('charlie', 0.71024161391924534),
 ('brad', 0.71024161391924534),
 ('simon', 0.70967648251115578),
 ('effectively', 0.70914752190638641),
 ('march', 0.70774597998109789),
 ('atmosphere', 0.70744773070214162),
 ('influence', 0.70733181555190172),
 ('genius', 0.706392407309966),
 ('emotionally', 0.70556970055850243),
 ('ken', 0.70526854109229009),
 ('identity', 0.70484322032313651),
 ('sophisticated', 0.70470800296102132),
 ('dan', 0.70457587638356811),
 ('andrew', 0.70329955202396321),
 ('india', 0.70144598337464037),
 ('roy', 0.69970458110610434),
 ('surprisingly', 0.6995780708902356),
 ('sky', 0.69780919366575667),
 ('romantic', 0.69664981111114743),
 ('match', 0.69566924999265523),
 ('meets', 0.69314718055994529),
 ('cowboy', 0.69314718055994529),
 ('wave', 0.69314718055994529),
 ('bitter', 0.69314718055994529),
 ('patient', 0.69314718055994529),
 ('stylish', 0.69314718055994529),
 ('britain', 0.69314718055994529),
 ('affected', 0.69314718055994529),
 ('beatty', 0.69314718055994529),
 ('love', 0.69198533541937324),
 ('paul', 0.68980827929443067),
 ('andy', 0.68846333124751902),
 ('performance', 0.68797386327972465),
 ('patrick', 0.68645819240914863),
 ('unlike', 0.68546468438792907),
 ('brooks', 0.68433655087779044),
 ('refuses', 0.68348526964820844),
 ('award', 0.6824518914431974),
 ('complaint', 0.6824518914431974),
 ('ride', 0.68229716453587952),
 ('dawson', 0.68171848473632257),
 ('luke', 0.68158635815886937),
 ('wells', 0.68087708796813096),
 ('france', 0.6804081547825156),
 ('sports', 0.68007509899259255),
 ('handsome', 0.68007509899259255),
 ('directs', 0.67875844310784572),
 ('rebel', 0.67875844310784572),
 ('greater', 0.67605274720064523),
 ('dreams', 0.67599410133369586),
 ('effective', 0.67565402311242806),
 ('interpretation', 0.67479804189174875),
 ('works', 0.67445504754779284),
 ('brando', 0.67445504754779284),
 ('noble', 0.6737290947028437),
 ('paced', 0.67314651385327573),
 ('le', 0.67067432470788668),
 ('master', 0.67015766233524654),
 ('h', 0.6696166831497512),
 ('rings', 0.66904962898088483),
 ('easy', 0.66895995494594152),
 ('city', 0.66820823221269321),
 ('sunshine', 0.66782937257565544),
 ('succeeds', 0.66647893347778397),
 ('relations', 0.664159643686693),
 ('england', 0.66387679825983203),
 ('glimpse', 0.66329421741026418),
 ('aired', 0.66268797307523675),
 ('sees', 0.66263163663399482),
 ('both', 0.66248336767382998),
 ('definitely', 0.66199789483898808),
 ('imaginative', 0.66139848224536502),
 ('appreciate', 0.66083893732728749),
 ('tricks', 0.66071190480679143),
 ('striking', 0.66071190480679143),
 ('carefully', 0.65999497324304479),
 ('complicated', 0.65981076029235353),
 ('perspective', 0.65962448852130173),
 ('trilogy', 0.65877953705573755),
 ('future', 0.65834665141052828),
 ('lion', 0.65742909795786608),
 ('douglas', 0.65540685257709819),
 ('victor', 0.65540685257709819),
 ('inspired', 0.65459851044271034),
 ('marriage', 0.65392646740666405),
 ('demands', 0.65392646740666405),
 ('father', 0.65172321672194655),
 ('page', 0.65123628494430852),
 ('instant', 0.65058756614114943),
 ('era', 0.6495567444850836),
 ('ruthless', 0.64934455790155243),
 ('saga', 0.64934455790155243),
 ('joan', 0.64891392558311978),
 ('joseph', 0.64841128671855386),
 ('workers', 0.64829661439459352),
 ('fantasy', 0.64726757480925168),
 ('distant', 0.64551913157069074),
 ('accomplished', 0.64551913157069074),
 ('manhattan', 0.64435701639051324),
 ('personal', 0.64355023942057321),
 ('meeting', 0.64313675998528386),
 ('individual', 0.64313675998528386),
 ('pushing', 0.64313675998528386),
 ('pleasant', 0.64250344774119039),
 ('brave', 0.64185388617239469),
 ('william', 0.64083139119578469),
 ('hudson', 0.64077919504262937),
 ('friendly', 0.63949446706762514),
 ('eccentric', 0.63907995928966954),
 ('awards', 0.63875310849414646),
 ('jack', 0.63838309514997038),
 ('seeking', 0.63808740337691783),
 ('divorce', 0.63757732940513456),
 ('colonel', 0.63757732940513456),
 ('jane', 0.63443957973316734),
 ('keeping', 0.63414883979798953),
 ('gives', 0.63383568159497883),
 ('ted', 0.63342794585832296),
 ('animation', 0.63208692379869902),
 ('progress', 0.6317782341836532),
 ('larger', 0.63127177684185776),
 ('concert', 0.63127177684185776),
 ('nation', 0.6296337748376194),
 ('albeit', 0.62739580299716491),
 ('adapted', 0.62613647027698516),
 ('discovers', 0.62542900650499444),
 ('classic', 0.62504956428050518),
 ('segment', 0.62335141862440335),
 ('morgan', 0.62303761437291871),
 ('mouse', 0.62294292188669675),
 ('impressive', 0.62211140744319349),
 ('artist', 0.62168821657780038),
 ('ultimate', 0.62168821657780038),
 ('griffith', 0.62117368093485603),
 ('drew', 0.62082651898031915),
 ('emily', 0.62082651898031915),
 ('moved', 0.6197197120051281),
 ('families', 0.61903920840622351),
 ('profound', 0.61903920840622351),
 ('innocent', 0.61851219917136446),
 ('versions', 0.61730910416844087),
 ('eddie', 0.61691981517206107),
 ('criticism', 0.61651395453902935),
 ('nature', 0.61594514653194088),
 ('recognized', 0.61518563909023349),
 ('sexuality', 0.61467556511845012),
 ('contract', 0.61400986000122149),
 ('brian', 0.61344043794920278),
 ('remembered', 0.6131044728864089),
 ('determined', 0.6123858239154869),
 ('offers', 0.61207935747116349),
 ('pleasure', 0.61195702582993206),
 ('washington', 0.61180154110599294),
 ('images', 0.61159731359583758),
 ('games', 0.61067095873570676),
 ('academy', 0.60872983874736208),
 ('fashioned', 0.60798937221963845),
 ('melodrama', 0.60749173598145145),
 ('rough', 0.60613580357031549),
 ('charismatic', 0.60613580357031549),
 ('peoples', 0.60613580357031549),
 ('dealing', 0.60517840761398811),
 ('fine', 0.60496962268013299),
 ('tap', 0.60391604683200273),
 ('trio', 0.60157998703445481),
 ('russell', 0.60120968523425966),
 ('figures', 0.60077386042893011),
 ('ward', 0.60005675749393339),
 ('shine', 0.59911823091166894),
 ('brady', 0.59911823091166894),
 ('job', 0.59845562125168661),
 ('satisfied', 0.59652034487087369),
 ('river', 0.59637962862495086),
 ('brown', 0.595773016534769),
 ('believable', 0.59566072133302495),
 ('always', 0.59470710774669278),
 ('bound', 0.59470710774669278),
 ('hall', 0.5933967777928858),
 ('cook', 0.5916777203950857),
 ('claire', 0.59136448625000293),
 ('broadway', 0.59033768669372433),
 ('anna', 0.58778666490211906),
 ('peace', 0.58628403501758408),
 ('visually', 0.58539431926349916),
 ('morality', 0.58525821854876026),
 ('falk', 0.58525821854876026),
 ('growing', 0.58466653756587539),
 ('experiences', 0.58314628534561685),
 ('stood', 0.58314628534561685),
 ('touch', 0.58122926435596001),
 ('lives', 0.5810976767513224),
 ('kubrick', 0.58066919713325493),
 ('timing', 0.58047401805583243),
 ('expressions', 0.57981849525294216),
 ('struggles', 0.57981849525294216),
 ('authentic', 0.57848427223980559),
 ('helen', 0.57763429343810091),
 ('pre', 0.57700753064729182),
 ('quirky', 0.5753641449035618),
 ('young', 0.57531672344534313),
 ('inner', 0.57454143815209846),
 ('mexico', 0.57443087372056334),
 ('clint', 0.57380042292737909),
 ('sisters', 0.57286101468544337),
 ('realism', 0.57226528899949558),
 ('french', 0.5720692490067093),
 ('personalities', 0.5720692490067093),
 ('surprises', 0.57113222999698177),
 ('adventures', 0.57113222999698177),
 ('overcome', 0.5697681593994407),
 ('timothy', 0.56953322459276867),
 ('tales', 0.56909453188996639),
 ('war', 0.56843317302781682),
 ('civil', 0.5679840376059393),
 ('countries', 0.56737779327091187),
 ('streep', 0.56710645966458029),
 ('tradition', 0.56685345523565323),
 ('oliver', 0.56673325570428668),
 ('australia', 0.56580775818334383),
 ('understanding', 0.56531380905006046),
 ('players', 0.56509525370004821),
 ('knowing', 0.56489284503626647),
 ('rogers', 0.56421349718405212),
 ('suspenseful', 0.56368911332305849),
 ('variety', 0.56368911332305849),
 ('true', 0.56281525180810066),
 ('jr', 0.56220982311246936),
 ('psychological', 0.56108745854687891),
 ('sent', 0.55961578793542266),
 ('grand', 0.55961578793542266),
 ('branagh', 0.55961578793542266),
 ('reminiscent', 0.55961578793542266),
 ('performing', 0.55961578793542266),
 ('wealth', 0.55961578793542266),
 ('overwhelming', 0.55961578793542266),
 ('odds', 0.55961578793542266),
 ('brothers', 0.55891181043362848),
 ('howard', 0.55811089675600245),
 ('david', 0.55693122256475369),
 ('generation', 0.55628799784274796),
 ('grow', 0.55612538299565417),
 ('survival', 0.55594605904646033),
 ('mainstream', 0.55574731115750231),
 ('dick', 0.55431073570572953),
 ('charm', 0.55288175575407861),
 ('kirk', 0.55278982286502287),
 ('twists', 0.55244729845681018),
 ('gangster', 0.55206858230003986),
 ('jeff', 0.55179306225421365),
 ('family', 0.55116244510065526),
 ('tend', 0.55053307336110335),
 ('thanks', 0.55049088015842218),
 ('world', 0.54744234723432639),
 ('sutherland', 0.54743536937855164),
 ('life', 0.54695514434959924),
 ('disc', 0.54654370636806993),
 ('bug', 0.54654370636806993),
 ('tribute', 0.5455111817538808),
 ('europe', 0.54522705048332309),
 ('sacrifice', 0.54430155296238014),
 ('color', 0.54405127139431109),
 ('superior', 0.54333490233128523),
 ('york', 0.54318235866536513),
 ('pulls', 0.54266622962164945),
 ('jackson', 0.54232429082536171),
 ('hearts', 0.54232429082536171),
 ('enjoy', 0.54124285135906114),
 ('redemption', 0.54056759296472823),
 ('madness', 0.540384426007535),
 ('stands', 0.5389965007326869),
 ('trial', 0.5389965007326869),
 ('greek', 0.5389965007326869),
 ('hamilton', 0.5389965007326869),
 ('each', 0.5388212312554177),
 ('faithful', 0.53773307668591508),
 ('received', 0.5372768098531604),
 ('documentaries', 0.53714293208336406),
 ('jealous', 0.53714293208336406),
 ('different', 0.53709860682460819),
 ('describes', 0.53680111016925136),
 ('shorts', 0.53596159703753288),
 ('brilliance', 0.53551823635636209),
 ('mountains', 0.53492317534505118),
 ('share', 0.53408248593025787),
 ('dealt', 0.53408248593025787),
 ('providing', 0.53329847961804933),
 ('explore', 0.53329847961804933),
 ('series', 0.5325809226575603),
 ('fellow', 0.5323318289869543),
 ('loves', 0.53062825106217038),
 ('revolution', 0.53062825106217038),
 ('olivier', 0.53062825106217038),
 ('roman', 0.53062825106217038),
 ('century', 0.53002783074992665),
 ('musical', 0.52966871156747064),
 ('heroic', 0.52925932545482868),
 ('approach', 0.52806743020049673),
 ('ironically', 0.52806743020049673),
 ('temple', 0.52806743020049673),
 ('moves', 0.5279372642387119),
 ('gift', 0.52702030968597136),
 ('julie', 0.52609309589677911),
 ('tells', 0.52415107836314001),
 ('radio', 0.52394671172868779),
 ('uncle', 0.52354439617376536),
 ('union', 0.52324814376454787),
 ('deep', 0.52309571635780505),
 ('reminds', 0.52157841554225237),
 ('famous', 0.52118841080153722),
 ('jazz', 0.52053443789295151),
 ('dennis', 0.51987545928590861),
 ('epic', 0.51919387343650736),
 ('adult', 0.519167695083386),
 ('shows', 0.51915322220375304),
 ('performed', 0.5191244265806858),
 ('demons', 0.5191244265806858),
 ('discovered', 0.51879379341516751),
 ('eric', 0.51879379341516751),
 ('youth', 0.5185626062681431),
 ('human', 0.51851411224987087),
 ('tarzan', 0.51813827061227724),
 ('ourselves', 0.51794309153485463),
 ('wwii', 0.51758240622887042),
 ('passion', 0.5162164724008671),
 ('desire', 0.51607497965213445),
 ('pays', 0.51581316527702981),
 ('dirty', 0.51557622652458857),
 ('fox', 0.51557622652458857),
 ('sympathetic', 0.51546600332249293),
 ('symbolism', 0.51546600332249293),
 ('attitude', 0.51530993621331933),
 ('appearances', 0.51466440007315639),
 ('jeremy', 0.51466440007315639),
 ('fun', 0.51439068993048687),
 ('south', 0.51420972175023116),
 ('arrives', 0.51409894911095988),
 ('present', 0.51341965894303732),
 ('com', 0.51326167856387173),
 ('smile', 0.51265880484765169),
 ('alan', 0.51082562376599072),
 ('ring', 0.51082562376599072),
 ('visit', 0.51082562376599072),
 ('fits', 0.51082562376599072),
 ('provided', 0.51082562376599072),
 ('carter', 0.51082562376599072),
 ('aging', 0.51082562376599072),
 ('countryside', 0.51082562376599072),
 ('begins', 0.51015650363396647),
 ('success', 0.50900578704900468),
 ('japan', 0.50900578704900468),
 ('accurate', 0.50895471583017893),
 ('proud', 0.50800474742434931),
 ('daily', 0.5075946031845443),
 ('karloff', 0.50724780241810674),
 ('atmospheric', 0.50724780241810674),
 ('recently', 0.50714914903668207),
 ('fu', 0.50704490092608467),
 ('horrors', 0.50656122497953315),
 ('finding', 0.50637127341661037),
 ('lust', 0.5059356384717989),
 ('hitchcock', 0.50574947073413001),
 ('among', 0.50334004951332734),
 ('viewing', 0.50302139827440906),
 ('investigation', 0.50262885656181222),
 ('shining', 0.50262885656181222),
 ('duo', 0.5020919437972361),
 ('cameron', 0.5020919437972361),
 ('finds', 0.50128303100539795),
 ('contemporary', 0.50077528791248915),
 ('genuine', 0.50046283673044401),
 ('frightening', 0.49995595152908684),
 ('plays', 0.49975983848890226),
 ('age', 0.49941323171424595),
 ('position', 0.49899116611898781),
 ('continues', 0.49863035067217237),
 ('roles', 0.49839716550752178),
 ('james', 0.49837216269470402),
 ('individuals', 0.49824684155913052),
 ('brought', 0.49783842823917956),
 ('hilarious', 0.49714551986191058),
 ('brutal', 0.49681488669639234),
 ('appropriate', 0.49643688631389105),
 ('dance', 0.49581998314812048),
 ('league', 0.49578774640145024),
 ('helping', 0.49578774640145024),
 ('answers', 0.49578774640145024),
 ('stunts', 0.49561620510246196),
 ('traveling', 0.49532143723002542),
 ('thoroughly', 0.49414593456733524),
 ('depicted', 0.49317068852726992),
 ('combination', 0.49247648509779424),
 ('honor', 0.49247648509779424),
 ('differences', 0.49247648509779424),
 ('fully', 0.49213349075383811),
 ('tracy', 0.49159426183810306),
 ('battles', 0.49140753790888908),
 ('possibility', 0.49112055268665822),
 ('romance', 0.4901589869574316),
 ('initially', 0.49002249613622745),
 ('happy', 0.4898997500608791),
 ('crime', 0.48977221456815834),
 ('singing', 0.4893852925281213),
 ('especially', 0.48901267837860624),
 ('shakespeare', 0.48754793889664511),
 ('hugh', 0.48729512635579658),
 ('detail', 0.48609484250827351),
 ('julia', 0.48550781578170082),
 ('san', 0.48550781578170082),
 ('guide', 0.48550781578170082),
 ('desperation', 0.48550781578170082),
 ('companion', 0.48550781578170082),
 ('strongly', 0.48460242866688824),
 ('necessary', 0.48302334245403883),
 ('humanity', 0.48265474679929443),
 ('drama', 0.48221998493060503),
 ('nonetheless', 0.48183808689273838),
 ('intrigue', 0.48183808689273838),
 ('warming', 0.48183808689273838),
 ('cuba', 0.48183808689273838),
 ('planned', 0.47957308026188628),
 ('pictures', 0.47929937011921681),
 ('broadcast', 0.47849024312305422),
 ('nine', 0.47803580094299974),
 ('settings', 0.47743860773325364),
 ('history', 0.47732966933780852),
 ('ordinary', 0.47725880012690741),
 ('trade', 0.47692407209030935),
 ('official', 0.47608267532211779),
 ('primary', 0.47608267532211779),
 ('episode', 0.47529620261150429),
 ('role', 0.47520268270188676),
 ('spirit', 0.47477690799839323),
 ('grey', 0.47409361449726067),
 ('ways', 0.47323464982718205),
 ('cup', 0.47260441094579297),
 ('piano', 0.47260441094579297),
 ('familiar', 0.47241617565111949),
 ('sinister', 0.47198579044972683),
 ('reveal', 0.47171449364936496),
 ('max', 0.47150852042515579),
 ('dated', 0.47121648567094482),
 ('losing', 0.47000362924573563),
 ('discovery', 0.47000362924573563),
 ('vicious', 0.47000362924573563),
 ('genuinely', 0.46871413841586385),
 ('hatred', 0.46734051182625186),
 ('mistaken', 0.46702300110759781),
 ('dream', 0.46608972992459924),
 ('challenge', 0.46608972992459924),
 ('crisis', 0.46575733836428446),
 ('photographed', 0.46488852857896512),
 ('critics', 0.46430560813109778),
 ('bird', 0.46430560813109778),
 ('machines', 0.46430560813109778),
 ('born', 0.46411383518967209),
 ('detective', 0.4636633473511525),
 ('higher', 0.46328467899699055),
 ('remains', 0.46262352194811296),
 ('inevitable', 0.46262352194811296),
 ('soviet', 0.4618180446592961),
 ('ryan', 0.46134556650262099),
 ('african', 0.46112595521371813),
 ('smaller', 0.46081520319132935),
 ('techniques', 0.46052488529119184),
 ('information', 0.46034171833399862),
 ('deserved', 0.45999798712841444),
 ('lynch', 0.45953232937844013),
 ('spielberg', 0.45953232937844013),
 ('cynical', 0.45953232937844013),
 ('tour', 0.45953232937844013),
 ('francisco', 0.45953232937844013),
 ('struggle', 0.45911782160048453),
 ('language', 0.45902121257712653),
 ('visual', 0.45823514408822852),
 ('warner', 0.45724137763188427),
 ('social', 0.45720078250735313),
 ('reality', 0.45719346885019546),
 ('hidden', 0.45675840249571492),
 ('breaking', 0.45601738727099561),
 ('sometimes', 0.45563021171182794),
 ('modern', 0.45500247579345005),
 ('surfing', 0.45425527227759638),
 ('popular', 0.45410691533051023),
 ('surprised', 0.4534409399850382),
 ('follows', 0.45245361754408348),
 ('keeps', 0.45234869400701483),
 ('john', 0.4520909494482197),
 ('mixed', 0.45198512374305722),
 ('defeat', 0.45198512374305722),
 ('justice', 0.45142724367280018),
 ('treasure', 0.45083371313801535),
 ('presents', 0.44973793178615257),
 ('years', 0.44919197032104968),
 ('chief', 0.44895022004790319),
 ('shadows', 0.44802472252696035),
 ('closely', 0.44701411102103689),
 ('segments', 0.44701411102103689),
 ('lose', 0.44658335503763702),
 ('caine', 0.44628710262841953),
 ('caught', 0.44610275383999071),
 ('hamlet', 0.44558510189758965),
 ('chinese', 0.44507424620321018),
 ('welcome', 0.44438052435783792),
 ('birth', 0.44368632092836219),
 ('represents', 0.44320543609101143),
 ('puts', 0.44279106572085081),
 ('visuals', 0.44183275227903923),
 ('fame', 0.44183275227903923),
 ('closer', 0.44183275227903923),
 ('web', 0.44183275227903923),
 ('criminal', 0.4412745608048752),
 ('minor', 0.4409224199448939),
 ('jon', 0.44086703515908027),
 ('liked', 0.44074991514020723),
 ('restaurant', 0.44031183943833246),
 ('de', 0.43983275161237217),
 ('flaws', 0.43983275161237217),
 ('searching', 0.4393666597838457),
 ('rap', 0.43891304217570443),
 ('light', 0.43884433018199892),
 ('elizabeth', 0.43872232986464682),
 ('marry', 0.43861731542506488),
 ('learned', 0.43825493093115531),
 ('controversial', 0.43825493093115531),
 ('oz', 0.43825493093115531),
 ('slowly', 0.43785660389939979),
 ('comedic', 0.43721380642274466),
 ('wayne', 0.43721380642274466),
 ('thrilling', 0.43721380642274466),
 ('bridge', 0.43721380642274466),
 ('married', 0.43658501682196887),
 ('nazi', 0.4361020775700542),
 ('murder', 0.4353180712578455),
 ('physical', 0.4353180712578455),
 ('johnny', 0.43483971678806865),
 ('michelle', 0.43445264498141672),
 ('wallace', 0.43403848055222038),
 ('comedies', 0.43395706390247063),
 ('silent', 0.43395706390247063),
 ('played', 0.43387244114515305),
 ('international', 0.43363598507486073),
 ('vision', 0.43286408229627887),
 ('intelligent', 0.43196704885367099),
 ('shop', 0.43078291609245434),
 ('also', 0.43036720209769169),
 ('levels', 0.4302451371066513),
 ('miss', 0.43006426712153217),
 ('movement', 0.4295626596872249),
 ...]

In [13]:

    

# words most frequently seen in a review with a "NEGATIVE" label
list(reversed(pos_neg_ratios.most_common()))[0:30]


    

    
Out[13]:





[('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 [14]:

    

from IPython.display import Image

review = "This was a horrible, terrible movie."

Image(filename='sentiment_network.png')


    

    
Out[14]:

In [15]:

    

review = "The movie was excellent"

Image(filename='sentiment_network_pos.png')


    

    
Out[15]:

In [16]:

    

vocab = set(total_counts.keys())
vocab_size = len(vocab)
print(vocab_size)


    

    




74074

In [17]:

    

list(vocab)


    

    
Out[17]:





['',
 'munchies',
 'replaced',
 'scuffles',
 'contributed',
 'liberation',
 'jaffar',
 'pumkinhead',
 'milhalovitch',
 'newsday',
 'phalke',
 'honeys',
 'magruder',
 'doping',
 'raghubir',
 'castulo',
 'transcend',
 'bulletins',
 'bumblers',
 'anodyne',
 'breakthroughs',
 'recommendations',
 'suposed',
 'sabotages',
 'disjunct',
 'trekkers',
 'giving',
 'capitalists',
 'linguistics',
 'jannings',
 'landa',
 'looooooooong',
 'approximations',
 'flashier',
 'entitlements',
 'miyaan',
 'covering',
 'frameworks',
 'abkani',
 'psyches',
 'loquacious',
 'seeded',
 'toledo',
 'jasbir',
 'karun',
 'contemporaneity',
 'igenious',
 'gropes',
 'verikoan',
 'cooed',
 'flailing',
 'rookery',
 'sobering',
 'avonlea',
 'manasota',
 'volunteers',
 'watcheable',
 'ejaculating',
 'weaselly',
 'cups',
 'borg',
 'freighted',
 'thornbury',
 'haliburton',
 'joycelyn',
 'byambition',
 'photograpy',
 'iqubal',
 'bacri',
 'thaw',
 'counterpoints',
 'camcorder',
 'typecast',
 'auxiliary',
 'ian',
 'marca',
 'bille',
 'neolithic',
 'ruptured',
 'timpani',
 'fab',
 'dane',
 'hoosiers',
 'doddering',
 'sarda',
 'devolving',
 'commander',
 'gregory',
 'awkward',
 'virtue',
 'jolson',
 'carbide',
 'shuddery',
 'pastries',
 'midsts',
 'donell',
 'cashes',
 'stadvec',
 'besties',
 'vilified',
 'infrared',
 'gronsky',
 'scornful',
 'wil',
 'premee',
 'libbed',
 'unrelatable',
 'lump',
 'lenses',
 'candlelit',
 'basterds',
 'icecap',
 'knitting',
 'caution',
 'atrocity',
 'patekar',
 'mollecular',
 'clausen',
 'inauguration',
 'dwarfed',
 'vampirefilm',
 'preclude',
 'outstripped',
 'dumpty',
 'rightness',
 'roeg',
 'fleshes',
 'heezy',
 'beack',
 'lockheed',
 'tenny',
 'nasal',
 'hickham',
 'pere',
 'spilled',
 'masterfully',
 'borowczyk',
 'ackerman',
 'rescore',
 'screams',
 'ler',
 'luger',
 'plough',
 'argonauts',
 'balsamic',
 'belive',
 'ridiculousness',
 'caselli',
 'surly',
 'bloodrayne',
 'minutiae',
 'unionism',
 'dietrichesque',
 'rapprochement',
 'warn',
 'oblast',
 'pinched',
 'sleepers',
 'yeller',
 'repulsion',
 'retentive',
 'thunk',
 'mehta',
 'blank',
 'rear',
 'venezia',
 'bowls',
 'rea',
 'sissies',
 'hornomania',
 'harper',
 'unbearded',
 'lassie',
 'viciente',
 'reassuringly',
 'theses',
 'involvement',
 'voorhees',
 'mummy',
 'uden',
 'springerland',
 'lbeck',
 'parasarolophus',
 'plaggy',
 'wether',
 'vangard',
 'marseille',
 'swabby',
 'cha',
 'morisette',
 'hoodwinks',
 'dreadcentral',
 'capaldi',
 'tenets',
 'enthusiastic',
 'communicating',
 'preggo',
 'wiliams',
 'convened',
 'quien',
 'exoskeleton',
 'microwave',
 'kalamazoo',
 'giulia',
 'qt',
 'hubschmid',
 'reenberg',
 'margins',
 'voyeurism',
 'provisions',
 'relate',
 'torsos',
 'expansionist',
 'grandee',
 'thalassa',
 'groundless',
 'anglicized',
 'spasms',
 'untucked',
 'resting',
 'pentecostal',
 'averages',
 'distinguishes',
 'resurfacing',
 'heusen',
 'fitter',
 'consecutively',
 'line',
 'resemble',
 'modular',
 'vulvas',
 'roadrunners',
 'rollercoaster',
 'superdome',
 'eod',
 'audiencemembers',
 'chickens',
 'hendersons',
 'leeli',
 'gazzo',
 'mclaughlin',
 'ralf',
 'telecommunicational',
 'secretes',
 'towel',
 'connely',
 'sargeant',
 'gestured',
 'quisessential',
 'silvestar',
 'secede',
 'amanda',
 'villard',
 'rajah',
 'embarassing',
 'golightly',
 'judge',
 'implementation',
 'takeoff',
 'edulcorated',
 'aleck',
 'flacks',
 'verily',
 'kroona',
 'mindfck',
 'uganda',
 'inward',
 'mutir',
 'p',
 'obsessives',
 'masters',
 'booked',
 'oland',
 'depravities',
 'letterboxed',
 'adaptaion',
 'apporiate',
 'godby',
 'mckoy',
 'clockwatchers',
 'carasso',
 'duncan',
 'comatose',
 'compass',
 'vonda',
 'unmanned',
 'incongruities',
 'hoffer',
 'embraceable',
 'hype',
 'vandenberg',
 'aaker',
 'metamorphoses',
 'karishma',
 'liposuction',
 'yoji',
 'sempre',
 'mystified',
 'sandoval',
 'sadler',
 'fireexplosionsgreat',
 'dratic',
 'arrrghhhhhhs',
 'sociopathic',
 'archived',
 'blackie',
 'paraso',
 'wetters',
 'amlie',
 'arbitrariness',
 'pint',
 'enunciated',
 'messily',
 'strawberries',
 'triumf',
 'lifeguard',
 'physical',
 'surrah',
 'paedophiliac',
 'archambault',
 'paragraphs',
 'showdowns',
 'carraway',
 'propeganda',
 'lameness',
 'attractions',
 'resignation',
 'ilva',
 'abruptness',
 'vancouver',
 'outgrown',
 'canadian',
 'contradicted',
 'bushel',
 'exceptions',
 'hanka',
 'ounce',
 'crab',
 'toyoko',
 'directional',
 'mnica',
 'chethe',
 'playstation',
 'figueroa',
 'sorted',
 'tolland',
 'shortcut',
 'distastefully',
 'karloff',
 'greedo',
 'date',
 'admiralty',
 'misquotes',
 'debauched',
 'extravagant',
 'miriam',
 'nuts',
 'vir',
 'malarky',
 'gabe',
 'sarlacc',
 'itself',
 'knickers',
 'gueule',
 'publishers',
 'oozin',
 'ardelean',
 'damiano',
 'wb',
 'treading',
 'bjork',
 'imm',
 'rarer',
 'seventeenth',
 'preconception',
 'boundless',
 'matthaw',
 'fanfan',
 'beacon',
 'wills',
 'ishaak',
 'commotion',
 'complying',
 'nicodemus',
 'resided',
 'heston',
 'waxman',
 'honcho',
 'cooperated',
 'dandified',
 'scripted',
 'dread',
 'receding',
 'congratulatory',
 'ineptness',
 'cocoran',
 'hemmed',
 'loyalists',
 'scavenger',
 'unbind',
 'waters',
 'moviewise',
 'ankylosaurus',
 'pseudonyms',
 'acrimony',
 'subordinate',
 'teenagers',
 'solondz',
 'tormentor',
 'rawhide',
 'shagger',
 'concentric',
 'tamed',
 'herzegowina',
 'slippery',
 'gruenberg',
 'suresh',
 'stoumen',
 'michol',
 'sensualists',
 'seamlessly',
 'kabuki',
 'katy',
 'dassin',
 'muy',
 'tytus',
 'redid',
 'superstitions',
 'nekojiru',
 'tutu',
 'stepper',
 'cloned',
 'interfering',
 'bins',
 'contactable',
 'channeled',
 'cooling',
 'secombe',
 'redistribute',
 'ishwar',
 'missable',
 'sacredness',
 'dirs',
 'beefheart',
 'offsuit',
 'munsters',
 'entanglement',
 'assessment',
 'symbiotic',
 'eighteen',
 'ominous',
 'dorsal',
 'sho',
 'astros',
 'braces',
 'moimeme',
 'bigfoot',
 'luthor',
 'unability',
 'pressberger',
 'textually',
 'gpm',
 'mohnish',
 'doh',
 'folds',
 'levinspiel',
 'esque',
 'chen',
 'grady',
 'astrid',
 'scepticism',
 'corp',
 'cautionary',
 'futon',
 'sinese',
 'schlesinger',
 'strasberg',
 'verbosity',
 'canoing',
 'bayonne',
 'protanganists',
 'dressing',
 'inclined',
 'toad',
 'unearp',
 'involvements',
 'unglamourous',
 'shnieder',
 'scrip',
 'baritone',
 'borat',
 'pimpernel',
 'wastebasket',
 'sortee',
 'conceptualized',
 'kikuno',
 'sedate',
 'naish',
 'sackhoff',
 'sculpture',
 'luthien',
 'harangue',
 'tentpoles',
 'nightsky',
 'ads',
 'walpurgis',
 'dorkish',
 'knifed',
 'inherits',
 'betti',
 'screwball',
 'fffrreeaakkyy',
 'eager',
 'imdb',
 'hatosy',
 'druid',
 'hatstand',
 'scoping',
 'gaye',
 'muff',
 'chiselled',
 'plonk',
 'behemoths',
 'fainted',
 'quantitative',
 'quadrophenia',
 'dunham',
 'zinnemann',
 'hynde',
 'bookworm',
 'illusion',
 'corben',
 'johannsen',
 'horseplay',
 'hellriders',
 'hitter',
 'mcdougall',
 'falk',
 'mechanisms',
 'hardcover',
 'doest',
 'soothe',
 'drouin',
 'ctv',
 'rehabbed',
 'kronfeld',
 'invention',
 'reclusive',
 'showbiz',
 'bertolucci',
 'plaster',
 'orgasms',
 'batali',
 'kruk',
 'extremite',
 'settlefor',
 'juicier',
 'attended',
 'barbed',
 'waterworks',
 'preparation',
 'condo',
 'voicing',
 'desiging',
 'effectual',
 'bumble',
 'rejectable',
 'faith',
 'kinkade',
 'celario',
 'flimsily',
 'juliette',
 'sprawling',
 'swanston',
 'piscipo',
 'rougher',
 'snuggly',
 'mcnally',
 'reassembled',
 'gunshots',
 'unescapably',
 'changings',
 'chromatic',
 'uncoordinated',
 'inexperienced',
 'stylist',
 'earthy',
 'winchester',
 'lifting',
 'shte',
 'ivin',
 'petunia',
 'casual',
 'debbie',
 'symbolically',
 'mindful',
 'bosox',
 'investing',
 'pai',
 'hastens',
 'pontificating',
 'creepinessthe',
 'indignities',
 'inventions',
 'beltway',
 'metoo',
 'ouroboros',
 'slade',
 'bakhtyari',
 'goku',
 'pettit',
 'loosen',
 'hrolfgar',
 'conny',
 'mockumentaries',
 'decoding',
 'deyniacs',
 'slickest',
 'karsis',
 'energised',
 'descovered',
 'baptised',
 'mambazo',
 'deb',
 'memorably',
 'rehearsed',
 'hedron',
 'gun',
 'disparity',
 'bear',
 'scarefest',
 'dryer',
 'hospitalization',
 'responded',
 'boudoir',
 'shawlee',
 'laurence',
 'meningitis',
 'midwestern',
 'moviesuntil',
 'glasgow',
 'learns',
 'terrifically',
 'antagonists',
 'gleefulness',
 'aire',
 'ejection',
 'nolo',
 'dilemma',
 'souza',
 'downside',
 'hobart',
 'tongued',
 'op',
 'considerable',
 'juvenile',
 'pantangeli',
 'whirling',
 'lacked',
 'lisbon',
 'hatchway',
 'boskovich',
 'guinneth',
 'astricky',
 'kukuanaland',
 'thudding',
 'cinma',
 'jerilderie',
 'crediting',
 'hideko',
 'booooooooo',
 'lavin',
 'stiltedness',
 'numbness',
 'macer',
 'timidity',
 'heartbreaks',
 'litvak',
 'defects',
 'shallower',
 'abbasi',
 'namers',
 'bypassing',
 'rewind',
 'mgr',
 'clarksberg',
 'participants',
 'dibler',
 'glb',
 'reaaaally',
 'later',
 'squished',
 'ahista',
 'additional',
 'mined',
 'aborting',
 'uninitiated',
 'shahan',
 'reloading',
 'kurita',
 'billingsley',
 'kuwait',
 'imperioli',
 'tilmac',
 'dishonorable',
 'antibodies',
 'despondency',
 'kotero',
 'appointment',
 'bystander',
 'complications',
 'mohammad',
 'shagged',
 'blackfoot',
 'poutily',
 'requested',
 'holland',
 'religion',
 'michio',
 'isabelwho',
 'capas',
 'nash',
 'hanks',
 'snaggle',
 'hawkes',
 'frightening',
 'diabolism',
 'bicker',
 'brigitte',
 'decipher',
 'hells',
 'decisionsin',
 'tobikage',
 'sluggish',
 'assertiveness',
 'fargo',
 'pretences',
 'visionary',
 'poignant',
 'affectionnates',
 'lewton',
 'lampooned',
 'ukraine',
 'webber',
 'headly',
 'zukovic',
 'jymn',
 'deemed',
 'originalbut',
 'tempo',
 'avoid',
 'cravings',
 'eurail',
 'neff',
 'beeblebrox',
 'wichita',
 'elephantsfar',
 'morricones',
 'squelched',
 'ogres',
 'allover',
 'jurrasic',
 'reside',
 'endangered',
 'shiko',
 'caf',
 'glancingly',
 'desperately',
 'villages',
 'herngren',
 'mead',
 'keys',
 'hermitage',
 'cadavers',
 'retaining',
 'uhhhh',
 'peww',
 'asthma',
 'coxsucker',
 'cannibals',
 'filmcritics',
 'malay',
 'tarentino',
 'propagated',
 'phyton',
 'vacationing',
 'shor',
 'dormael',
 'essay',
 'overdone',
 'fairuza',
 'ltas',
 'rivero',
 'elas',
 'saldana',
 'howes',
 'possibly',
 'zatichi',
 'tellers',
 'goddesses',
 'gudrun',
 'mention',
 'dehumanize',
 'knoller',
 'shanghainese',
 'rediscovery',
 'dearies',
 'saturates',
 'patriarchy',
 'hearby',
 'misshappenings',
 'willie',
 'soothing',
 'omelet',
 'sunning',
 'troops',
 'grabbed',
 'tohma',
 'pompadour',
 'paparazzi',
 'ali',
 'combos',
 'refinery',
 'formation',
 'crabs',
 'registration',
 'cpo',
 'chimera',
 'aisles',
 'uniformly',
 'rosalione',
 'payoffs',
 'astride',
 'rabid',
 'firsts',
 'beckon',
 'bucke',
 'pavle',
 'ddlj',
 'hara',
 'orifices',
 'certificates',
 'raking',
 'intensely',
 'obs',
 'timm',
 'dunkin',
 'goaul',
 'eck',
 'backers',
 'alphabet',
 'magicfest',
 'loudness',
 'andrea',
 'morland',
 'rhoda',
 'kora',
 'parading',
 'folowing',
 'delight',
 'eeriness',
 'aeneid',
 'pollutions',
 'straddled',
 'vaseekaramaana',
 'restrooms',
 'cowgirl',
 'shrinkwrap',
 'plantage',
 'childless',
 'iqs',
 'strange',
 'pumbaa',
 'hisself',
 'shoo',
 'heartrenching',
 'enlarges',
 'insurance',
 'janine',
 'jox',
 'augustus',
 'etzel',
 'waldsterben',
 'donated',
 'infatuated',
 'exploitatively',
 'busting',
 'calamine',
 'tesmacher',
 'unfit',
 'alones',
 'spinetingling',
 'preliterate',
 'lujn',
 'redd',
 'patricia',
 'eurohorror',
 'bucolic',
 'smokes',
 'inflaming',
 'referee',
 'sequenes',
 'luise',
 'droids',
 'paisley',
 'perseverence',
 'boreanaz',
 'maoist',
 'hoke',
 'awwww',
 'mattia',
 'perpetuate',
 'bossman',
 'match',
 'nikhilji',
 'maples',
 'barjatya',
 'legitimacy',
 'clumped',
 'mortally',
 'robotic',
 'herculean',
 'haley',
 'abercrombie',
 'ansonia',
 'althea',
 'pressure',
 'canceling',
 'publicdomain',
 'decked',
 'tughlaq',
 'hawke',
 'golddigger',
 'macbeth',
 'withering',
 'nayland',
 'constantly',
 'drapery',
 'fckd',
 'underlining',
 'insure',
 'harmony',
 'int',
 'bipolarity',
 'roeh',
 'batwoman',
 'hotd',
 'seus',
 'nonfictional',
 'windmills',
 'floradora',
 'squandering',
 'zenda',
 'fowarded',
 'futures',
 'mardi',
 'jell',
 'remembrance',
 'amos',
 'wendell',
 'yannis',
 'globes',
 'chevalia',
 'knight',
 'tajmahal',
 'oceanic',
 'easygoing',
 'daze',
 'yakmallah',
 'nosedived',
 'ochoa',
 'derated',
 'thief',
 'rennes',
 'retells',
 'sotd',
 'mcdonell',
 'monger',
 'thicker',
 'peasants',
 'speakman',
 'torpedos',
 'miamis',
 'bilal',
 'enachanted',
 'brava',
 'marano',
 'oscars',
 'silicon',
 'pudgy',
 'cucacha',
 'institutionalization',
 'stinson',
 'brice',
 'karamazov',
 'tsutomu',
 'willingness',
 'lasted',
 'denigrati',
 'dearable',
 ...]

In [18]:

    

import numpy as np

layer_0 = np.zeros((1,vocab_size))
layer_0


    

    
Out[18]:





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

In [19]:

    

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


    

    
Out[19]:

In [20]:

    

word2index = {}

for i,word in enumerate(vocab):
    word2index[word] = i
word2index


    

    
Out[20]:





{'': 0,
 'munchies': 1,
 'replaced': 2,
 'scuffles': 3,
 'contributed': 4,
 'liberation': 5,
 'jaffar': 6,
 'pumkinhead': 7,
 'milhalovitch': 8,
 'newsday': 9,
 'phalke': 10,
 'honeys': 11,
 'magruder': 12,
 'doping': 13,
 'raghubir': 14,
 'castulo': 15,
 'transcend': 16,
 'bulletins': 17,
 'bumblers': 18,
 'anodyne': 19,
 'breakthroughs': 20,
 'recommendations': 21,
 'suposed': 22,
 'sabotages': 23,
 'disjunct': 24,
 'trekkers': 25,
 'giving': 26,
 'capitalists': 27,
 'linguistics': 28,
 'jannings': 29,
 'landa': 30,
 'looooooooong': 31,
 'approximations': 32,
 'flashier': 33,
 'entitlements': 34,
 'miyaan': 35,
 'covering': 36,
 'frameworks': 37,
 'abkani': 38,
 'psyches': 39,
 'loquacious': 40,
 'seeded': 41,
 'toledo': 42,
 'jasbir': 43,
 'karun': 44,
 'contemporaneity': 45,
 'igenious': 46,
 'gropes': 47,
 'verikoan': 48,
 'cooed': 49,
 'flailing': 50,
 'rookery': 51,
 'sobering': 52,
 'avonlea': 53,
 'manasota': 54,
 'volunteers': 55,
 'watcheable': 56,
 'ejaculating': 57,
 'weaselly': 58,
 'cups': 59,
 'borg': 60,
 'freighted': 61,
 'thornbury': 62,
 'haliburton': 63,
 'joycelyn': 64,
 'byambition': 65,
 'photograpy': 66,
 'iqubal': 67,
 'bacri': 68,
 'thaw': 69,
 'counterpoints': 70,
 'camcorder': 71,
 'typecast': 72,
 'auxiliary': 73,
 'ian': 74,
 'marca': 75,
 'bille': 76,
 'neolithic': 77,
 'ruptured': 78,
 'timpani': 79,
 'fab': 80,
 'dane': 81,
 'hoosiers': 82,
 'doddering': 83,
 'sarda': 84,
 'devolving': 85,
 'commander': 86,
 'gregory': 87,
 'awkward': 88,
 'virtue': 89,
 'jolson': 90,
 'carbide': 91,
 'shuddery': 92,
 'pastries': 93,
 'midsts': 94,
 'donell': 95,
 'cashes': 96,
 'stadvec': 97,
 'besties': 98,
 'vilified': 99,
 'infrared': 100,
 'gronsky': 101,
 'scornful': 102,
 'wil': 103,
 'premee': 104,
 'libbed': 105,
 'unrelatable': 106,
 'lump': 107,
 'lenses': 108,
 'candlelit': 109,
 'basterds': 110,
 'icecap': 111,
 'knitting': 112,
 'caution': 113,
 'atrocity': 114,
 'patekar': 115,
 'mollecular': 116,
 'clausen': 117,
 'inauguration': 118,
 'dwarfed': 119,
 'vampirefilm': 120,
 'preclude': 121,
 'outstripped': 122,
 'dumpty': 123,
 'rightness': 124,
 'roeg': 125,
 'fleshes': 126,
 'heezy': 127,
 'beack': 128,
 'lockheed': 129,
 'tenny': 130,
 'nasal': 131,
 'hickham': 132,
 'pere': 133,
 'spilled': 134,
 'masterfully': 135,
 'borowczyk': 136,
 'ackerman': 137,
 'rescore': 138,
 'screams': 139,
 'ler': 140,
 'luger': 141,
 'plough': 142,
 'argonauts': 143,
 'balsamic': 144,
 'belive': 145,
 'ridiculousness': 146,
 'caselli': 147,
 'surly': 148,
 'bloodrayne': 149,
 'minutiae': 150,
 'unionism': 151,
 'dietrichesque': 152,
 'rapprochement': 153,
 'warn': 154,
 'oblast': 155,
 'pinched': 156,
 'sleepers': 157,
 'yeller': 158,
 'repulsion': 159,
 'retentive': 160,
 'thunk': 161,
 'mehta': 162,
 'blank': 163,
 'rear': 164,
 'venezia': 165,
 'bowls': 166,
 'rea': 167,
 'sissies': 168,
 'hornomania': 169,
 'harper': 170,
 'unbearded': 171,
 'lassie': 172,
 'viciente': 173,
 'reassuringly': 174,
 'theses': 175,
 'involvement': 176,
 'voorhees': 177,
 'mummy': 178,
 'uden': 179,
 'springerland': 180,
 'lbeck': 181,
 'parasarolophus': 182,
 'plaggy': 183,
 'wether': 184,
 'vangard': 185,
 'marseille': 186,
 'swabby': 187,
 'cha': 188,
 'morisette': 189,
 'hoodwinks': 190,
 'dreadcentral': 191,
 'capaldi': 192,
 'tenets': 193,
 'enthusiastic': 194,
 'communicating': 195,
 'preggo': 196,
 'wiliams': 197,
 'convened': 198,
 'quien': 199,
 'exoskeleton': 200,
 'microwave': 201,
 'kalamazoo': 202,
 'giulia': 203,
 'qt': 204,
 'hubschmid': 205,
 'reenberg': 206,
 'margins': 207,
 'voyeurism': 208,
 'provisions': 209,
 'relate': 210,
 'torsos': 211,
 'expansionist': 212,
 'grandee': 213,
 'thalassa': 214,
 'groundless': 215,
 'anglicized': 216,
 'spasms': 217,
 'untucked': 218,
 'resting': 219,
 'pentecostal': 220,
 'averages': 221,
 'distinguishes': 222,
 'resurfacing': 223,
 'heusen': 224,
 'fitter': 225,
 'consecutively': 226,
 'line': 227,
 'resemble': 228,
 'modular': 229,
 'vulvas': 230,
 'roadrunners': 231,
 'rollercoaster': 232,
 'superdome': 233,
 'eod': 234,
 'audiencemembers': 235,
 'chickens': 236,
 'hendersons': 237,
 'leeli': 238,
 'gazzo': 239,
 'mclaughlin': 240,
 'ralf': 241,
 'telecommunicational': 242,
 'secretes': 243,
 'towel': 244,
 'connely': 245,
 'sargeant': 246,
 'gestured': 247,
 'quisessential': 248,
 'silvestar': 249,
 'secede': 250,
 'amanda': 251,
 'villard': 252,
 'rajah': 253,
 'embarassing': 254,
 'golightly': 255,
 'judge': 256,
 'implementation': 257,
 'takeoff': 258,
 'edulcorated': 259,
 'aleck': 260,
 'flacks': 261,
 'verily': 262,
 'kroona': 263,
 'mindfck': 264,
 'uganda': 265,
 'inward': 266,
 'mutir': 267,
 'p': 268,
 'obsessives': 269,
 'masters': 270,
 'booked': 271,
 'oland': 272,
 'depravities': 273,
 'letterboxed': 274,
 'adaptaion': 275,
 'apporiate': 276,
 'godby': 277,
 'mckoy': 278,
 'clockwatchers': 279,
 'carasso': 280,
 'duncan': 281,
 'comatose': 282,
 'compass': 283,
 'vonda': 284,
 'unmanned': 285,
 'incongruities': 286,
 'hoffer': 287,
 'embraceable': 288,
 'hype': 289,
 'vandenberg': 290,
 'aaker': 291,
 'metamorphoses': 292,
 'karishma': 293,
 'liposuction': 294,
 'yoji': 295,
 'sempre': 296,
 'mystified': 297,
 'sandoval': 298,
 'sadler': 299,
 'fireexplosionsgreat': 300,
 'dratic': 301,
 'arrrghhhhhhs': 302,
 'sociopathic': 303,
 'archived': 304,
 'blackie': 305,
 'paraso': 306,
 'wetters': 307,
 'amlie': 308,
 'arbitrariness': 309,
 'pint': 310,
 'enunciated': 311,
 'messily': 312,
 'strawberries': 313,
 'triumf': 314,
 'lifeguard': 315,
 'physical': 316,
 'surrah': 317,
 'paedophiliac': 318,
 'archambault': 319,
 'paragraphs': 320,
 'showdowns': 321,
 'carraway': 322,
 'propeganda': 323,
 'lameness': 324,
 'attractions': 325,
 'resignation': 326,
 'ilva': 327,
 'abruptness': 328,
 'vancouver': 329,
 'outgrown': 330,
 'canadian': 331,
 'contradicted': 332,
 'bushel': 333,
 'exceptions': 334,
 'hanka': 335,
 'ounce': 336,
 'crab': 337,
 'toyoko': 338,
 'directional': 339,
 'mnica': 340,
 'chethe': 341,
 'playstation': 342,
 'figueroa': 343,
 'sorted': 344,
 'tolland': 345,
 'shortcut': 346,
 'distastefully': 347,
 'karloff': 348,
 'greedo': 349,
 'date': 350,
 'admiralty': 351,
 'misquotes': 352,
 'debauched': 353,
 'extravagant': 354,
 'miriam': 355,
 'nuts': 356,
 'vir': 357,
 'malarky': 358,
 'gabe': 359,
 'sarlacc': 360,
 'itself': 361,
 'knickers': 362,
 'gueule': 363,
 'publishers': 364,
 'oozin': 365,
 'ardelean': 366,
 'damiano': 367,
 'wb': 368,
 'treading': 369,
 'bjork': 370,
 'imm': 371,
 'rarer': 372,
 'seventeenth': 373,
 'preconception': 374,
 'boundless': 375,
 'matthaw': 376,
 'fanfan': 377,
 'beacon': 378,
 'wills': 379,
 'ishaak': 380,
 'commotion': 381,
 'complying': 382,
 'nicodemus': 383,
 'resided': 384,
 'heston': 385,
 'waxman': 386,
 'honcho': 387,
 'cooperated': 388,
 'dandified': 389,
 'scripted': 390,
 'dread': 391,
 'receding': 392,
 'congratulatory': 393,
 'ineptness': 394,
 'cocoran': 395,
 'hemmed': 396,
 'loyalists': 397,
 'scavenger': 398,
 'unbind': 399,
 'waters': 400,
 'moviewise': 401,
 'ankylosaurus': 402,
 'pseudonyms': 403,
 'acrimony': 404,
 'subordinate': 405,
 'teenagers': 406,
 'solondz': 407,
 'tormentor': 408,
 'rawhide': 409,
 'shagger': 410,
 'concentric': 411,
 'tamed': 412,
 'herzegowina': 413,
 'slippery': 414,
 'gruenberg': 415,
 'suresh': 416,
 'stoumen': 417,
 'michol': 418,
 'sensualists': 419,
 'seamlessly': 420,
 'kabuki': 421,
 'katy': 422,
 'dassin': 423,
 'muy': 424,
 'tytus': 425,
 'redid': 426,
 'superstitions': 427,
 'nekojiru': 428,
 'tutu': 429,
 'stepper': 430,
 'cloned': 431,
 'interfering': 432,
 'bins': 433,
 'contactable': 434,
 'channeled': 435,
 'cooling': 436,
 'secombe': 437,
 'redistribute': 438,
 'ishwar': 439,
 'missable': 440,
 'sacredness': 441,
 'dirs': 442,
 'beefheart': 443,
 'offsuit': 444,
 'munsters': 445,
 'entanglement': 446,
 'assessment': 447,
 'symbiotic': 448,
 'eighteen': 449,
 'ominous': 450,
 'dorsal': 451,
 'sho': 452,
 'astros': 453,
 'braces': 454,
 'moimeme': 455,
 'bigfoot': 456,
 'luthor': 457,
 'unability': 458,
 'pressberger': 459,
 'textually': 460,
 'gpm': 461,
 'mohnish': 462,
 'doh': 463,
 'folds': 464,
 'levinspiel': 465,
 'esque': 466,
 'chen': 467,
 'grady': 468,
 'astrid': 469,
 'scepticism': 470,
 'corp': 471,
 'cautionary': 472,
 'futon': 473,
 'sinese': 474,
 'schlesinger': 475,
 'strasberg': 476,
 'verbosity': 477,
 'canoing': 478,
 'bayonne': 479,
 'protanganists': 480,
 'dressing': 481,
 'inclined': 482,
 'toad': 483,
 'unearp': 484,
 'involvements': 485,
 'unglamourous': 486,
 'shnieder': 487,
 'scrip': 488,
 'baritone': 489,
 'borat': 490,
 'pimpernel': 491,
 'wastebasket': 492,
 'sortee': 493,
 'conceptualized': 494,
 'kikuno': 495,
 'sedate': 496,
 'naish': 497,
 'sackhoff': 498,
 'sculpture': 499,
 'luthien': 500,
 'harangue': 501,
 'tentpoles': 502,
 'nightsky': 503,
 'ads': 504,
 'walpurgis': 505,
 'dorkish': 506,
 'knifed': 507,
 'inherits': 508,
 'betti': 509,
 'screwball': 510,
 'fffrreeaakkyy': 511,
 'eager': 512,
 'imdb': 513,
 'hatosy': 514,
 'druid': 515,
 'hatstand': 516,
 'scoping': 517,
 'gaye': 518,
 'muff': 519,
 'chiselled': 520,
 'plonk': 521,
 'behemoths': 522,
 'fainted': 523,
 'quantitative': 524,
 'quadrophenia': 525,
 'dunham': 526,
 'zinnemann': 527,
 'hynde': 528,
 'bookworm': 529,
 'illusion': 530,
 'corben': 531,
 'johannsen': 532,
 'horseplay': 533,
 'hellriders': 534,
 'hitter': 535,
 'mcdougall': 536,
 'falk': 537,
 'mechanisms': 538,
 'hardcover': 539,
 'doest': 540,
 'soothe': 541,
 'drouin': 542,
 'ctv': 543,
 'rehabbed': 544,
 'kronfeld': 545,
 'invention': 546,
 'reclusive': 547,
 'showbiz': 548,
 'bertolucci': 549,
 'plaster': 550,
 'orgasms': 551,
 'batali': 552,
 'kruk': 553,
 'extremite': 554,
 'settlefor': 555,
 'juicier': 556,
 'attended': 557,
 'barbed': 558,
 'waterworks': 559,
 'preparation': 560,
 'condo': 561,
 'voicing': 562,
 'desiging': 563,
 'effectual': 564,
 'bumble': 565,
 'rejectable': 566,
 'faith': 567,
 'kinkade': 568,
 'celario': 569,
 'flimsily': 570,
 'juliette': 571,
 'sprawling': 572,
 'swanston': 573,
 'piscipo': 574,
 'rougher': 575,
 'snuggly': 576,
 'mcnally': 577,
 'reassembled': 578,
 'gunshots': 579,
 'unescapably': 580,
 'changings': 581,
 'chromatic': 582,
 'uncoordinated': 583,
 'inexperienced': 584,
 'stylist': 585,
 'earthy': 586,
 'winchester': 587,
 'lifting': 588,
 'shte': 589,
 'ivin': 590,
 'petunia': 591,
 'casual': 592,
 'debbie': 593,
 'symbolically': 594,
 'mindful': 595,
 'bosox': 596,
 'investing': 597,
 'pai': 598,
 'hastens': 599,
 'pontificating': 600,
 'creepinessthe': 601,
 'indignities': 602,
 'inventions': 603,
 'beltway': 604,
 'metoo': 605,
 'ouroboros': 606,
 'slade': 607,
 'bakhtyari': 608,
 'goku': 609,
 'pettit': 610,
 'loosen': 611,
 'hrolfgar': 612,
 'conny': 613,
 'mockumentaries': 614,
 'decoding': 615,
 'deyniacs': 616,
 'slickest': 617,
 'karsis': 618,
 'energised': 619,
 'descovered': 620,
 'baptised': 621,
 'mambazo': 622,
 'deb': 623,
 'memorably': 624,
 'rehearsed': 625,
 'hedron': 626,
 'gun': 627,
 'disparity': 628,
 'bear': 629,
 'scarefest': 630,
 'dryer': 631,
 'hospitalization': 632,
 'responded': 633,
 'boudoir': 634,
 'shawlee': 635,
 'laurence': 636,
 'meningitis': 637,
 'midwestern': 638,
 'moviesuntil': 639,
 'glasgow': 640,
 'learns': 641,
 'terrifically': 642,
 'antagonists': 643,
 'gleefulness': 644,
 'aire': 645,
 'ejection': 646,
 'nolo': 647,
 'dilemma': 648,
 'souza': 649,
 'downside': 650,
 'hobart': 651,
 'tongued': 652,
 'op': 653,
 'considerable': 654,
 'juvenile': 655,
 'pantangeli': 656,
 'whirling': 657,
 'lacked': 658,
 'lisbon': 659,
 'hatchway': 660,
 'boskovich': 661,
 'guinneth': 662,
 'astricky': 663,
 'kukuanaland': 664,
 'thudding': 665,
 'cinma': 666,
 'jerilderie': 667,
 'crediting': 668,
 'hideko': 669,
 'booooooooo': 670,
 'lavin': 671,
 'stiltedness': 672,
 'numbness': 673,
 'macer': 674,
 'timidity': 675,
 'heartbreaks': 676,
 'litvak': 677,
 'defects': 678,
 'shallower': 679,
 'abbasi': 680,
 'namers': 681,
 'bypassing': 682,
 'rewind': 683,
 'mgr': 684,
 'clarksberg': 685,
 'participants': 686,
 'dibler': 687,
 'glb': 688,
 'reaaaally': 689,
 'later': 690,
 'squished': 691,
 'ahista': 692,
 'additional': 693,
 'mined': 694,
 'aborting': 695,
 'uninitiated': 696,
 'shahan': 697,
 'reloading': 698,
 'kurita': 699,
 'billingsley': 700,
 'kuwait': 701,
 'imperioli': 702,
 'tilmac': 703,
 'dishonorable': 704,
 'antibodies': 705,
 'despondency': 706,
 'kotero': 707,
 'appointment': 708,
 'bystander': 709,
 'complications': 710,
 'mohammad': 711,
 'shagged': 712,
 'blackfoot': 713,
 'poutily': 714,
 'requested': 715,
 'holland': 716,
 'religion': 717,
 'michio': 718,
 'isabelwho': 719,
 'capas': 720,
 'nash': 721,
 'hanks': 722,
 'snaggle': 723,
 'hawkes': 724,
 'frightening': 725,
 'diabolism': 726,
 'bicker': 727,
 'brigitte': 728,
 'decipher': 729,
 'hells': 730,
 'decisionsin': 731,
 'tobikage': 732,
 'sluggish': 733,
 'assertiveness': 734,
 'fargo': 735,
 'pretences': 736,
 'visionary': 737,
 'poignant': 738,
 'affectionnates': 739,
 'lewton': 740,
 'lampooned': 741,
 'ukraine': 742,
 'webber': 743,
 'headly': 744,
 'zukovic': 745,
 'jymn': 746,
 'deemed': 747,
 'originalbut': 748,
 'tempo': 749,
 'avoid': 750,
 'cravings': 751,
 'eurail': 752,
 'neff': 753,
 'beeblebrox': 754,
 'wichita': 755,
 'elephantsfar': 756,
 'morricones': 757,
 'squelched': 758,
 'ogres': 759,
 'allover': 760,
 'jurrasic': 761,
 'reside': 762,
 'endangered': 763,
 'shiko': 764,
 'caf': 765,
 'glancingly': 766,
 'desperately': 767,
 'villages': 768,
 'herngren': 769,
 'mead': 770,
 'keys': 771,
 'hermitage': 772,
 'cadavers': 773,
 'retaining': 774,
 'uhhhh': 775,
 'peww': 776,
 'asthma': 777,
 'coxsucker': 778,
 'cannibals': 779,
 'filmcritics': 780,
 'malay': 781,
 'tarentino': 782,
 'propagated': 783,
 'phyton': 784,
 'vacationing': 785,
 'shor': 786,
 'dormael': 787,
 'essay': 788,
 'overdone': 789,
 'fairuza': 790,
 'ltas': 791,
 'rivero': 792,
 'elas': 793,
 'saldana': 794,
 'howes': 795,
 'possibly': 796,
 'zatichi': 797,
 'tellers': 798,
 'goddesses': 799,
 'gudrun': 800,
 'mention': 801,
 'dehumanize': 802,
 'knoller': 803,
 'shanghainese': 804,
 'rediscovery': 805,
 'dearies': 806,
 'saturates': 807,
 'patriarchy': 808,
 'hearby': 809,
 'misshappenings': 810,
 'willie': 811,
 'soothing': 812,
 'omelet': 813,
 'sunning': 814,
 'troops': 815,
 'grabbed': 816,
 'tohma': 817,
 'pompadour': 818,
 'paparazzi': 819,
 'ali': 820,
 'combos': 821,
 'refinery': 822,
 'formation': 823,
 'crabs': 824,
 'registration': 825,
 'cpo': 826,
 'chimera': 827,
 'aisles': 828,
 'uniformly': 829,
 'rosalione': 830,
 'payoffs': 831,
 'astride': 832,
 'rabid': 833,
 'firsts': 834,
 'beckon': 835,
 'bucke': 836,
 'pavle': 837,
 'ddlj': 838,
 'hara': 839,
 'orifices': 840,
 'certificates': 841,
 'raking': 842,
 'intensely': 843,
 'obs': 844,
 'timm': 845,
 'dunkin': 846,
 'goaul': 847,
 'eck': 848,
 'backers': 849,
 'alphabet': 850,
 'magicfest': 851,
 'loudness': 852,
 'andrea': 853,
 'morland': 854,
 'rhoda': 855,
 'kora': 856,
 'parading': 857,
 'folowing': 858,
 'delight': 859,
 'eeriness': 860,
 'aeneid': 861,
 'pollutions': 862,
 'straddled': 863,
 'vaseekaramaana': 864,
 'restrooms': 865,
 'cowgirl': 866,
 'shrinkwrap': 867,
 'plantage': 868,
 'childless': 869,
 'iqs': 870,
 'strange': 871,
 'pumbaa': 872,
 'hisself': 873,
 'shoo': 874,
 'heartrenching': 875,
 'enlarges': 876,
 'insurance': 877,
 'janine': 878,
 'jox': 879,
 'augustus': 880,
 'etzel': 881,
 'waldsterben': 882,
 'donated': 883,
 'infatuated': 884,
 'exploitatively': 885,
 'busting': 886,
 'calamine': 887,
 'tesmacher': 888,
 'unfit': 889,
 'alones': 890,
 'spinetingling': 891,
 'preliterate': 892,
 'lujn': 893,
 'redd': 894,
 'patricia': 895,
 'eurohorror': 896,
 'bucolic': 897,
 'smokes': 898,
 'inflaming': 899,
 'referee': 900,
 'sequenes': 901,
 'luise': 902,
 'droids': 903,
 'paisley': 904,
 'perseverence': 905,
 'boreanaz': 906,
 'maoist': 907,
 'hoke': 908,
 'awwww': 909,
 'mattia': 910,
 'perpetuate': 911,
 'bossman': 912,
 'match': 913,
 'nikhilji': 914,
 'maples': 915,
 'barjatya': 916,
 'legitimacy': 917,
 'clumped': 918,
 'mortally': 919,
 'robotic': 920,
 'herculean': 921,
 'haley': 922,
 'abercrombie': 923,
 'ansonia': 924,
 'althea': 925,
 'pressure': 926,
 'canceling': 927,
 'publicdomain': 928,
 'decked': 929,
 'tughlaq': 930,
 'hawke': 931,
 'golddigger': 932,
 'macbeth': 933,
 'withering': 934,
 'nayland': 935,
 'constantly': 936,
 'drapery': 937,
 'fckd': 938,
 'underlining': 939,
 'insure': 940,
 'harmony': 941,
 'int': 942,
 'bipolarity': 943,
 'roeh': 944,
 'batwoman': 945,
 'hotd': 946,
 'seus': 947,
 'nonfictional': 948,
 'windmills': 949,
 'floradora': 950,
 'squandering': 951,
 'zenda': 952,
 'fowarded': 953,
 'futures': 954,
 'mardi': 955,
 'jell': 956,
 'remembrance': 957,
 'amos': 958,
 'wendell': 959,
 'yannis': 960,
 'globes': 961,
 'chevalia': 962,
 'knight': 963,
 'tajmahal': 964,
 'oceanic': 965,
 'easygoing': 966,
 'daze': 967,
 'yakmallah': 968,
 'nosedived': 969,
 'ochoa': 970,
 'derated': 971,
 'thief': 972,
 'rennes': 973,
 'retells': 974,
 'sotd': 975,
 'mcdonell': 976,
 'monger': 977,
 'thicker': 978,
 'peasants': 979,
 'speakman': 980,
 'torpedos': 981,
 'miamis': 982,
 'bilal': 983,
 'enachanted': 984,
 'brava': 985,
 'marano': 986,
 'oscars': 987,
 'silicon': 988,
 'pudgy': 989,
 'cucacha': 990,
 'institutionalization': 991,
 'stinson': 992,
 'brice': 993,
 'karamazov': 994,
 'tsutomu': 995,
 'willingness': 996,
 'lasted': 997,
 'denigrati': 998,
 'dearable': 999,
 ...}

In [21]:

    

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 [22]:

    

layer_0


    

    
Out[22]:





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

In [23]:

    

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


    

In [24]:

    

labels[0]


    

    
Out[24]:





'POSITIVE'

In [25]:

    

get_target_for_label(labels[0])


    

    
Out[25]:





1

In [26]:

    

labels[1]


    

    
Out[26]:





'NEGATIVE'

In [27]:

    

get_target_for_label(labels[1])


    

    
Out[27]:





0

In [28]:

    

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 [29]:

    

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


    

In [30]:

    

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


    

    




Progress:99.9% Speed(reviews/sec):540.6% #Correct:500 #Tested:1000 Testing Accuracy:50.0%

In [31]:

    

# 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):109.4 #Correct:1250 #Trained:2501 Training Accuracy:49.9%
Progress:20.8% Speed(reviews/sec):109.4 #Correct:2500 #Trained:5001 Training Accuracy:49.9%
Progress:31.2% Speed(reviews/sec):109.5 #Correct:3750 #Trained:7501 Training Accuracy:49.9%
Progress:41.6% Speed(reviews/sec):109.8 #Correct:5000 #Trained:10001 Training Accuracy:49.9%
Progress:52.0% Speed(reviews/sec):110.0 #Correct:6250 #Trained:12501 Training Accuracy:49.9%
Progress:62.5% Speed(reviews/sec):107.6 #Correct:7500 #Trained:15001 Training Accuracy:49.9%
Progress:72.9% Speed(reviews/sec):107.8 #Correct:8750 #Trained:17501 Training Accuracy:49.9%
Progress:83.3% Speed(reviews/sec):107.6 #Correct:10000 #Trained:20001 Training Accuracy:49.9%
Progress:93.7% Speed(reviews/sec):106.2 #Correct:11250 #Trained:22501 Training Accuracy:49.9%
Progress:99.9% Speed(reviews/sec):105.4 #Correct:11999 #Trained:24000 Training Accuracy:49.9%

In [32]:

    

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


    

In [33]:

    

# 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):120.7 #Correct:1247 #Trained:2501 Training Accuracy:49.8%
Progress:20.8% Speed(reviews/sec):126.1 #Correct:2497 #Trained:5001 Training Accuracy:49.9%
Progress:31.2% Speed(reviews/sec):126.6 #Correct:3747 #Trained:7501 Training Accuracy:49.9%
Progress:41.6% Speed(reviews/sec):128.1 #Correct:4997 #Trained:10001 Training Accuracy:49.9%
Progress:52.0% Speed(reviews/sec):129.0 #Correct:6247 #Trained:12501 Training Accuracy:49.9%
Progress:62.5% Speed(reviews/sec):129.8 #Correct:7490 #Trained:15001 Training Accuracy:49.9%
Progress:72.9% Speed(reviews/sec):129.4 #Correct:8739 #Trained:17501 Training Accuracy:49.9%
Progress:83.3% Speed(reviews/sec):128.8 #Correct:10069 #Trained:20001 Training Accuracy:50.3%
Progress:83.9% Speed(reviews/sec):128.7 #Correct:10141 #Trained:20155 Training Accuracy:50.3%





    




/home/alex/anaconda3/envs/dlnd/lib/python3.6/site-packages/ipykernel/__main__.py:75: RuntimeWarning: overflow encountered in exp






    




Progress:93.7% Speed(reviews/sec):128.6 #Correct:11383 #Trained:22501 Training Accuracy:50.5%
Progress:99.9% Speed(reviews/sec):129.0 #Correct:12163 #Trained:24000 Training Accuracy:50.6%

In [34]:

    

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


    

In [35]:

    

# 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):84.34 #Correct:1265 #Trained:2501 Training Accuracy:50.5%
Progress:20.8% Speed(reviews/sec):81.59 #Correct:2664 #Trained:5001 Training Accuracy:53.2%
Progress:31.2% Speed(reviews/sec):82.44 #Correct:4114 #Trained:7501 Training Accuracy:54.8%
Progress:41.6% Speed(reviews/sec):82.85 #Correct:5668 #Trained:10001 Training Accuracy:56.6%
Progress:52.0% Speed(reviews/sec):83.13 #Correct:7230 #Trained:12501 Training Accuracy:57.8%
Progress:62.5% Speed(reviews/sec):82.82 #Correct:8787 #Trained:15001 Training Accuracy:58.5%
Progress:72.9% Speed(reviews/sec):82.30 #Correct:10403 #Trained:17501 Training Accuracy:59.4%
Progress:83.3% Speed(reviews/sec):81.26 #Correct:12128 #Trained:20001 Training Accuracy:60.6%
Progress:93.7% Speed(reviews/sec):80.25 #Correct:13808 #Trained:22501 Training Accuracy:61.3%
Progress:99.9% Speed(reviews/sec):80.22 #Correct:14852 #Trained:24000 Training Accuracy:61.8%