32 KiB
32 KiB
import pandas as pd
columns = ['FileId','Paper', 'Idk1', 'Year','Idk2','Idk3', 'LeftContext', 'RightContext']
# dev_data = pd.read_csv('dev-0/in.tsv', sep='\t', names=columns, engine='python', quotechar='"', error_bad_lines=False)
# dev_expected = pd.read_csv('dev-0/expected.tsv', sep='\t', engine='python', quotechar='"', error_bad_lines=False)
dev_data = list()
with open('dev-0/in.tsv', "r") as f:
for line in f.readlines():
dev_data.append(line.split('\t')[-2])
dev_expected = list()
with open('dev-0/expected.tsv', "r") as f:
for line in f.readlines():
dev_expected.append(line.replace('\n',''))
from nltk.tokenize import word_tokenize
def createBigram(data, expected):
listOfBigrams = []
bigramCounts = {}
unigramCounts = {}
for i in range(len(data)):
tokenized = word_tokenize(data[i])
word = tokenized[-1]
listOfBigrams.append((word, expected[i]))
if (word, expected[i]) in bigramCounts:
bigramCounts[(word, expected[i])] += 1
else:
bigramCounts[(word, expected[i])] = 1
if data[i] in unigramCounts:
unigramCounts[word] += 1
else:
unigramCounts[word] = 1
return listOfBigrams, unigramCounts, bigramCounts
def calcBigramProb(listOfBigrams, unigramCounts, bigramCounts):
listOfProb = {}
for bigram in listOfBigrams:
word1 = bigram[0]
word2 = bigram[1]
listOfProb[bigram] = (bigramCounts.get(bigram))/(unigramCounts.get(word1))
return listOfProb
bigrams, uniCounts, biCounts = createBigram(dev_data, dev_expected)
probs = calcBigramProb(bigrams, uniCounts, biCounts)
probs
'day'): 1.0, ('ol', 'powers'): 1.0, ('real', 'Asiatic'): 1.0, ('perfect', 'and'): 1.0, ('stcu-\\\\n', 'i«d'): 1.0, ('The', 'commis-'): 1.0, ('otr', 'just'): 1.0, ('for', 'men.'): 1.0, ('She', 'his'): 1.0, ('in\\\\n', 'thccityol'): 1.0, ('j\\\\n', 'ons'): 1.0, ('tlio', 'Convention'): 1.0, ('9rdick', 'is'): 1.0, ("'s", 'weight'): 1.0, ('Charleston', 'to'): 1.0, ('foaming', 'beasts'): 1.0, ('of\\\\n', 'these'): 1.0, ('pay\\\\nin', 'that'): 1.0, ('from', '$1'): 1.0, ('quack', 'medicines.'): 1.0, ('found', 'neces-'): 1.0, ('west', 'lino'): 1.0, ('to\\\\nsay', 'whether'): 1.0, ('away\\\\nuntil', 'the'): 1.0, ('givo', 'it'): 1.0, ('from', 'the'): 12.0, (',', 'too,'): 1.0, ('paws\\\\nhad', 'been'): 1.0, ('organs', ';'): 1.0, ('capitalists', 'great'): 1.0, (',', 'whllt'): 1.0, ('guarantees', 'the'): 1.0, ('than\\\\ndo', 'so,'): 1.0, ('\\\\n', 'And'): 1.0, ('support\\\\n', '1'): 1.0, ('legislative', 'body'): 1.0, ('\\\\n', 'as'): 4.0, ('fishes.\\\\n', 'We'): 1.0, ('Tho', 'night'): 1.0, ('wages', 'of'): 1.0, ('of', 'returning'): 1.0, ('are', 'for'): 1.0, ('w.s', 'recently'): 1.0, ('te', 'the'): 1.0, ('the', 'finances,'): 1.0, ('that', 'Imrns'): 1.0, ('a', 'trust'): 1.0, ('next', 'year,'): 1.0, ('ready\\\\n', 'to'): 1.0, ('nt', 'a'): 1.0, ('Noth-\\\\n', 'ng,'): 1.0, ('agree', 'on'): 1.0, ('were', 'present.'): 1.0, ('Ills', 'country,'): 1.0, ('crossing\\\\nBoar', 'River;'): 1.0, ('the', 'place'): 3.0, ('This', 'reception'): 1.0, ('de-\\\\n', 'pendent'): 1.0, ('tribunals', 'will'): 1.0, ('a', 'steamer'): 1.0, ('I', 'am'): 3.0, (',', 'at'): 3.0, ('on', 'or'): 1.0, ('preached', 'on'): 1.0, ('of\\\\n', 'things'): 1.0, ('for', 'the'): 13.0, (']', 'e'): 1.0, ('the', 'transit'): 1.0, ('hy\\\\n', 'which'): 1.0, ('opinion', 'that'): 1.0, ('.', 'At'): 3.0, ('’', 'I'): 1.0, ('and\\\\n', 'and'): 1.0, ('atrango', 'positions'): 1.0, ('pn', 'Tues\xad'): 1.0, ('and', 'all'): 4.0, ('is', 'honestly'): 1.0, ('honorable', 'citizens.'): 1.0, ('per', 'cent'): 1.0, ('riveting', 'it,'): 1.0, ('the\\\\nCommissioner', 'of'): 1.0, ('separating', 'from'): 1.0, ('are', 'startled'): 1.0, ('voice', 'for'): 1.0, ('when', 'thete'): 1.0, ('\\\\nformed', 'the'): 1.0, ('remembered', 'that'): 1.0, ('#', 'of'): 1.0, ('very', 'process'): 1.0, ('would', 'gel'): 1.0, ('me', 'with'): 1.0, ('aflllcted', 'with'): 1.0, ('ulti\\\\n', 'mate'): 1.0, ('utmost\\\\nstretch', 'of'): 1.0, ('-rstand', 'much'): 1.0, ('was', 'after'): 1.0, ('Its\\\\npresent', 'strength,'): 1.0, ('the\\\\n', 'peiiod'): 1.0, ('son\\\\nhas', 'been'): 1.0, ('is', 'covered'): 1.0, ('Female\\\\n', 'Seminary;'): 1.0, ('they', 'used'): 1.0, ('out-\\\\n', 'numbered'): 1.0, ('came\\\\nfrom', 'heavy'): 1.0, ('a\\\\n', 'pall'): 1.0, ('adranoe', 'guard.'): 1.0, ('some\xad\\\\n', 'what'): 1.0, ('tho', 'sulo'): 1.0, ('upper', 'navigation'): 1.0, ('whs\\\\n', 'therefore'): 1.0, ('against', 'the'): 2.0, ('expendi-\\\\n', 'tures'): 1.0, ('treason\\\\nwith', 'indignant'): 1.0, ('very', 'strong'): 1.0, ('mil-\\\\n', 'lions'): 1.0, ('rights', 'supported'): 1.0, (',', 'shall'): 2.0, ('Moat\\\\nbeing', 'piloted'): 1.0, ('be-\\\\n', 'ing'): 2.0, ('little', 'barefooted'): 1.0, ('of\\\\n', 'developenient'): 1.0, ('be-\\\\n', 'Cause'): 1.0, ("'Abraham\\\\n", 'llu.li'): 1.0, ('the', 'estate'): 2.0, ('his', 'friends'): 1.0, ('P', "('nderwood.a"): 1.0, ('the\\\\n', 'roof'): 1.0, ('Cwk', 'r-;'): 1.0, ('.', "Johnson's"): 1.0, (';', 'while'): 1.0, ('*', 'of'): 1.0, ('have', 'power'): 1.0, ('in', 'search'): 1.0, ('and\\\\nthe', 'principal'): 1.0, ('HAY.the\\\\nlast', 'named'): 1.0, ('have', 'occasioned;'): 1.0, ('the\\\\nWestern', 'boundary'): 1.0, (',', 'whose'): 1.0, ('be', 'visited'): 1.0, ('\\\\n', 'and'): 13.0, ('party', 'zeal;—and'): 1.0, ('exercise', 'over'): 1.0, ('foremost', 'in'): 1.0, ('three', 'pounds'): 1.0, ('exceed-\\\\n', 'ed'): 1.0, ('could', 'find,'): 1.0, ('-', '.'): 1.0, ('could\\\\n', 'f.'): 1.0, ('our', 'power.'): 1.0, ('intimated', 'that'): 1.0, ('Thomas', 'J.'): 2.0, ('laid', 'me'): 1.0, ('that', 'there'): 3.0, ('that', 'on'): 1.0, ('it', 'to'): 2.0, ('Mc-\\\\n', 'Xamara.'): 1.0, ('and\\\\nthrough', 'the'): 1.0, ('trembled', 'with'): 1.0, ('chin-imps.\\\\nling', 'him,as'): 1.0, ('the', 'agricultural'): 1.0, ('have', 'proceeded'): 1.0, (',', 'P.'): 1.0, ('rlin', 'sale'): 1.0, ('sight', 'of'): 2.0, ('\\\\n', 'rails'): 1.0, ('know\\\\nof', 'no'): 1.0, ('.', 'MCI).Bids.'): 1.0, ('member', 'of'): 1.0, ('\\\\nand', 'they'): 1.0, ("'", 'of'): 1.0, ('the', 'ground;'): 1.0, (',', 'and'): 88.0, ('traverses', 'the'): 1.0, ('could', 'lie'): 1.0, ('sounded', 'by'): 1.0, ('kianr.h', 'of'): 1.0, ('be\\\\n', 'promptly'): 1.0, ('what', 'history'): 1.0, ('high', 'taxation.'): 1.0, ('they', 'will'): 4.0, ('with', 'the'): 13.0, ('ho', '"would'): 1.0, ("'s", 'hole'): 1.0, ('these', 'circumstances.'): 1.0, ('n', 'belief'): 1.0, ('because', 'they'): 1.0, ('.', 'When'): 2.0, (',', 'a'): 12.0, ('as', 'far'): 2.0, ('the', 'means'): 3.0, ('receive', 'as'): 1.0, ('business', 'of'): 1.0, ('them.\\\\nWhy', 'should'): 1.0, ('tangled', 'thickets'): 1.0, (',', "Blannerhasset's"): 1.0, ('happiness', 'of'): 1.0, ('district', 'of'): 1.0, ('\\\\n', 'chosen'): 1.0, ('lias', 'sustained'): 1.0, ('mid', 'large'): 1.0, ('work', 'now."'): 1.0, ('certified', 'by'): 1.0, ('were', 'entitled,'): 1.0, ('submission', 'fb'): 1.0, ('bind¬\\\\n', 'ing'): 1.0, ('or\\\\n', 'in'): 1.0, ('vir\xad\\\\n', 'tue'): 1.0, ('asking', 'that'): 1.0, ('as', 'there'): 2.0, ('immediate', 'approval'): 1.0, ('thcro\\\\nwas', 'not'): 1.0, ('kind', 'of'): 2.0, ('us\\\\n', 'ow'): 1.0, ('thence', 'North'): 1.0, ('bring-\\\\n', 'ing'): 1.0, ('.', '-Cut'): 1.0, ('a', 'supper'): 1.0, ('surroundings.\\\\n', '“You’re'): 1.0, ('the', 'men'): 3.0, ('Is\\\\n', 'formed'): 1.0, ('intrinsic', 'value'): 1.0, ('ordinance.\\\\n', 'Section'): 1.0, ('tojustily', 'Protection,'): 1.0, ('scramble\\\\n', 'for'): 1.0, ('s', 'part,'): 1.0, ('both', 'to'): 1.0, ('with\\\\nthe', 'idea'): 1.0, ('tell', 'of'): 1.0, ('gone', 'by'): 1.0, ('the', 'liberty'): 1.0, ('they', 'lived'): 1.0, ('skating\\\\n', 'rink,'): 1.0, (',', 'se'): 1.0, ('work', 'and'): 2.0, ('last\\\\n', 'sale,'): 1.0, ('modern', 'times'): 1.0, ('Icould', 'see'): 1.0, ('they', 'led'): 1.0, ('all\\\\nalong', 'the'): 1.0, ('of\\\\n', 'all'): 2.0, ('1919', 'certificate'): 1.0, ('from', 'my'): 1.0, ('that', 'the'): 9.0, ('aeenmed', 'that'): 1.0, ('on', 'Wednesday,'): 2.0, ('kept\\\\n', 'up'): 2.0, ('after', 'tea'): 1.0, ('equipping', 'each'): 1.0, ('mode\\\\n', 'of'): 1.0, ('the\\\\n', 'ocean,'): 1.0, ('.', 'Messersmith'): 1.0, ('not\\\\n', 'there,'): 1.0, ('n', 'fam-'): 1.0, ('beg', 'this'): 1.0, ('to', 'attempt'): 1.0, ('and\\\\n', 'the'): 5.0, ('they\\\\n', 'were'): 1.0, ('be', 'more'): 1.0, ('ui.cieisioi.ti\\\\n', 'b\\\\'): 1.0, ('our\\\\n', 'constitutional'): 1.0, ('to', 'die'): 1.0, ('and', 'honest'): 1.0, ('bo', 'too'): 1.0, ('to', 'take'): 2.0, (',', 'Thomas'): 1.0, ('many', 'months'): 1.0, ('150', 'of'): 1.0, ('Billy\\\\n', 'one'): 1.0, ('.', 'His'): 2.0, ('ancP\\\\n', '67-100'): 1.0, ('conduct', 'the'): 1.0, ('the', 'small'): 1.0, ('by', 'ample'): 1.0, ('be', 'well'): 3.0, ('speak', 'of'): 1.0, ('de-\\\\n', 'termined'): 1.0, ('window.\\\\n', 'I'): 1.0, ('not', 'bo'): 1.0, ('train', 'hearing'): 1.0, ('minds\\\\nof', 'men'): 1.0, ('supply', 'this'): 1.0, ('.', 'Also'): 1.0, ('we', 'sought'): 1.0, ('chief', 'houor'): 1.0, ('road', 'was'): 1.0, ('strikes', 'in'): 1.0, ('at', "Hawkins'"): 1.0, ('sure', 'that'): 1.0, ('lelease\\\\n', 'he'): 1.0, ('in\\\\neach', 'year,'): 1.0, ('proclaimed\\\\n', 'by'): 1.0, ('polirira\\\\n', 'Course'): 1.0, ('the', 'advance'): 1.0, ('elaborate', 'frescoing'): 1.0, ('work', 'nnd'): 1.0, ('pension', 'frauds'): 1.0, ('was', 'in'): 1.0, ('.', 'Gen.'): 1.0, ('west\\\\n', 'coast,'): 1.0, ('where', 'Charles'): 1.0, ('the', 'stare'): 1.0, ('for', 'all'): 1.0, ('.', 'But'): 4.0, ('the', 'Committee'): 2.0, ('so', 'as'): 4.0, ('upon\\\\n', 'their'): 1.0, ('from', 'just'): 1.0, ('the', 'valley'): 3.0, ('\\\\n', 'lie'): 1.0, ('You\\\\n', 'must'): 1.0, ('harvest.\\\\n', 'The'): 1.0, (',', 'will,'): 1.0, ('—', 'Burleigh'): 1.0, (',', 'of'): 5.0, ('of', 'fun-'): 1.0, ('are', 'gen-'): 1.0, ('he', 'was'): 4.0, (',', 'another'): 1.0, ('\\\\nand', 'possession'): 1.0, ('to\\\\n', 'gu’de'): 1.0, ('come.\\\\n', 'The'): 1.0, ('\\\\nthat', 'it'): 1.0, ('think\\\\nIt', 'a'): 1.0, ('the', 'receipt'): 1.0, ('those', 'districts,'): 1.0, ('firing\\\\n', 'pan'): 1.0, ('contempt', 'of'): 1.0, ('George\\\\n', 'J.'): 1.0, ('of', '*00'): 1.0, ('the\\\\nhomestead', 'might'): 1.0, ('se\\\\nwho', 'have'): 1.0, ('place', 'the'): 1.0, ('for\\\\n', '1916'): 1.0, (',', 'which'): 9.0, ('that', 'their'): 1.0, ('the', 'gen-'): 2.0, ('would\\\\n', 'do'): 1.0, ('be', 're-'): 1.0, ('unharmed.\\\\n', 'I'): 1.0, ('a\\\\n', 'substitute'): 1.0, ('n\\\\n', 'prodigy'): 1.0, ('switchmen', 'to-'): 1.0, ('rest', 'in'): 1.0, ('when\\\\n', 'heavily'): 1.0, ('that', 'question,'): 1.0, ('capable', 'of'): 1.0, ('to', 'lupn'): 1.0, ('very', 'in"-*\''): 1.0, ('.', 'In'): 4.0, ('phenomenal', 'growth.'): 1.0, ('hut', 'we'): 1.0, ('that', 'he'): 3.0, ('the', 'earliest'): 1.0, ('the', 'gun,'): 1.0, ('I', 'know'): 2.0, ('about', 'the'): 2.0, ('to', 'President'): 1.0, ('The', 'British'): 1.0, ('the', 'colored'): 1.0, ('recent', 'au-'): 1.0, ('new', 'proprietary'): 1.0, ('a', 'village'): 1.0, ('will\\\\n', 'equaliy'): 1.0, ('but', 'also'): 1.0, ('\\\\n', 'No'): 1.0, ('be\\\\nenforced', 'with'): 1.0, ('statement', 'is'): 1.0, ('questioning', 'the'): 1.0, ('ihe\\\\n', 'I'): 1.0, ('he', 'appreciate'): 1.0, ('MortunY', 'Traveller'): 1.0, ('was', 'to'): 1.0, ('once', 'formed'): 1.0, ('traduced', 'her'): 1.0, (',', 'according'): 2.0, (',', 'alwavs'): 1.0, ('6|d', ':'): 1.0, ('\\\\n', 'which'): 4.0, ('were', 'fit'): 1.0, ('references\\\\n', 'to'): 1.0, ('of\\\\n', 'feet'): 1.0, ('brick', 'fioor'): 1.0, ('was', 'not'): 4.0, ('is', 'more'): 1.0, ('consider', 'it'): 2.0, ('The', 'latter'): 1.0, ('in', 'a'): 8.0, ('good\\\\nname', 'and'): 1.0, (',', 'trom'): 1.0, ('several\\\\njoints', 'were'): 1.0, ('the', 'party'): 1.0, ('not', 'know'): 2.0, ('\\\\n', '1913,'): 2.0, ('is', 'possible'): 1.0, ('is', 'seven'): 1.0, ('powerful', 'foree'): 1.0, ('a\\\\ngood', 'jilace,'): 1.0, ('\\\\nit', 'the'): 1.0, ('for\\\\nalUr', 'taking'): 1.0, ('anil', 'did'): 1.0, ('defeat', 'the'): 1.0, ('attempts', 'lo'): 1.0, ('State', 'of'): 1.0, ('a\\\\n', 'quaint'): 1.0, (',', 'doing'): 1.0, ('Frias\\\\nhis', 'Minister'): 1.0, ('moon\\\\nlight', 'nights'): 1.0, ('pav', 't«xthr'): 1.0, ('proposition', 'was'): 1.0, ('Into\\\\n', 'the'): 1.0, ('ask', 'him'): 1.0, ('Houses', 'of'): 1.0, ('be', 'brought'): 1.0, ('engaged', 'in'): 1.0, ('Dos-\\\\n', 'well'): 1.0, ('of', 'depriving'): 1.0, ('from', 'a'): 2.0, ('return', 'to'): 1.0, ('pay-\\\\n', 'ment'): 1.0, ('fact', 'that'): 1.0, ('night\\\\nThe', 'strictest'): 1.0, ('\\\\n', '<'): 1.0, ('*', 'before'): 1.0, ('Australia', 'live'): 1.0, ('a', 'majority,'): 1.0, ('the\\\\n', 'arc'): 1.0, ('the\\\\n', 'result'): 1.0, ('heartily\\\\n', 'accede'): 1.0, ('years', 'ago'): 1.0, ('pa\\\\n', 'yers,'): 1.0, ('\\\\n', 'gave'): 1.0, ('that', 'lien'): 1.0, ('deny', 'that'): 1.0, (',', '1884.'): 1.0, ('in', 'this'): 2.0, ('inform\\\\n', 'Congress'): 1.0, ('stoop', 'to'): 1.0, ('transferred', 'the'): 1.0, ('\\\\n', 'has'): 1.0, ('by', 'the'): 13.0, ('event\\\\n', 'an'): 1.0, ('rn\\\\n', 'than'): 1.0, ('advan-\\\\n', 'tages.'): 1.0, ('at', 'tho'): 1.0, ('yard\\\\n', 'when'): 1.0, ('only\\\\nsuffeicr', 'nolmdy'): 1.0, ('the', 'Indians'): 1.0, ('And', 'unless'): 1.0, ('ordinary', 'American'): 1.0, ('death.\\\\n', '“Jesus'): 1.0, ('to', 'ascend'): 1.0, ('but', 'those'): 1.0, ('death.\\\\n', 'We'): 1.0, ('it', 'he'): 1.0, ('are\\\\n', 'not'): 1.0, ('the', 'coura'): 1.0, ('wastes\\\\nheat', 'most'): 1.0, ('as', 'Vice'): 1.0, ('claimants', 'of'): 1.0, ('returned', 'tt)'): 1.0, ('San', 'Francisco'): 1.0, ('to', 'civil'): 1.0, ('Hanks\\\\n', 'of'): 1.0, ('wife—as\\\\n', 'she'): 1.0, (',', '7'): 1.0, ('tri-\\\\nfle', 'taller'): 1.0, ('him', 'a'): 1.0, (',', 'Miss'): 1.0, ('it', 'has'): 3.0, ('will', 'erect'): 1.0, ('testified', 'that'): 1.0, ('seed', 'potatoes,'): 1.0, ('control', 'over'): 1.0, ('ap\\\\n', 'proved,'): 1.0, ('have', 'added'): 1.0, ('cents', 'for'): 1.0, ('committee\\\\n', 'and'): 1.0, ('of', 'such'): 2.0, ('and', 'that'): 2.0, ('District\\\\nNumber', '7,'): 1.0, ('every\\\\nand', 'he'): 1.0, ('union', 'of'): 1.0, ('the', 'oilier'): 1.0, ('and', 'hopelessly'): 1.0, ('the', 'notes'): 1.0, ('the', 'floor'): 1.0, ('with', 'tons'): 1.0, ('disregard\\\\n', '«»f'): 1.0, ('at\\\\n', 'Per'): 1.0, ('\\\\ncountry', 'will'): 1.0, ('yet\\\\nthe', 'ball'): 1.0, ('.', 'Glick'): 1.0, ('any', 'district'): 1.0, ('is', 'qualified'): 1.0, ('to', 'wait'): 1.0, ('and\\\\n', 'that'): 2.0, ('west', 'by'): 1.0, (',', ';ynl'): 1.0, ('different\\\\n', 'kinds'): 1.0, ('benefit', 'he'): 1.0, ('initiaiiec', 'wiil'): 1.0, ('a', 'noise'): 1.0, (',', 'l/ic~M'): 1.0, ('Bv\\\\n', 'this'): 1.0, ('the', 'respec\xad'): 1.0, ('cash', 'in'): 1.0, ('scarce', 'bear'): 1.0, ('coin\\\\nfinely', 'into'): 1.0, ('now', 'to'): 1.0, ('relief', 'that'): 1.0, ('at\\\\n', 'Aldershot'): 1.0, ('benefit', 'of'): 2.0, ('the', 'nation’s'): 1.0, ('of\\\\n', 'her'): 1.0, ('after', 'the'): 3.0, ('will', 'he'): 1.0, ('That', 'all'): 1.0, ('reach\\\\nLloyd', 'George'): 1.0, ('Judg\\\\n', 'ing'): 1.0, ('of', '"Vic'): 1.0, ('of', 'Pensaco-'): 1.0, (',', 'although'): 1.0, ('by', 'their'): 1.0, ('xan\\\\n', 'raise'): 1.0, (',', 'Jno'): 1.0, ('of\\\\n', 'Congrtss.'): 1.0, ('mind', 'of'): 1.0, (',', 'light'): 1.0, ('strange', 'that'): 1.0, ('sullied', 'its'): 1.0, ('easy', 'and'): 1.0, ('The', 'case,'): 1.0, (',', 'without'): 2.0, ('it', 'would'): 3.0, ('feet\\\\nless', 'altitude'): 1.0, ('fall', 'and'): 1.0, ('castles\\\\n', 'which'): 1.0, ('there', 'is'): 4.0, ('In', 'the'): 6.0, ('his', 'duly'): 2.0, ('I\\\\nhad', 'seen'): 1.0, ('all', 'his'): 1.0, ('who\\\\n', 'is'): 1.0, ('Grand', 'Prize'): 1.0, ('he', 'entcitaiued,'): 1.0, ('sentiments', 'to-'): 1.0, ('court\\\\n', 'and'): 1.0, ('turh', 'uias:niliccul'): 1.0, ('capacities', 'for'): 1.0, ('the', 'hospital.'): 1.0, ('armies\\\\n', 'and'): 1.0, ('the', 'bond,'): 1.0, (')', 'from'): 1.0, ('and', 'competent,'): 1.0, (',', 'or'): 9.0, ('to\\\\n', 'go'): 1.0, ('that\\\\n', 'ordinarily'): 1.0, ('duty.\\\\n', 'Resolved,'): 1.0, ('an', 'infetlor'): 1.0, ('enough', 'of'): 1.0, ('his', 'native'): 1.0, ('four', 'artillery'): 1.0, ('Paul\\\\n', 'half'): 1.0, ('the', 'appearance'): 2.0, ('inha-\\\\nbitants', 'on'): 1.0, ('and', 'resolutions'): 1.0, ('anil', 'exhibits,'): 1.0, ('keeping', 'myself'): 1.0, ('hand', 'of'): 1.0, ('as', 'I'): 1.0, (',', 'never'): 1.0, ('my\\\\n', 'soda'): 1.0, ('pro.\\\\nclaiming', 'that'): 1.0, ('sta-\\\\ntioned', 'in'): 1.0, (',', 'the'): 16.0, ('F.iurth\\\\n', 'avenue'): 1.0, ('remote', 'objects,'): 1.0, ('certain', 'Masons'): 1.0, ('Jefferson', ':'): 1.0, ('to', 'participate'): 2.0, ('the', 'farmer'): 1.0, ('the', 'city'): 5.0, ('Supreme', 'Judge,'): 1.0, ('City', 'authorities'): 1.0, ('.', 'The'): 22.0, ('mar\\\\n', 'vellous'): 1.0, ('distant', 'as'): 1.0, ('with-\\\\nin', 'the'): 1.0, ('Blundle', 'Maple'): 1.0, ('e', ',o'): 1.0, ('much', 'surprised'): 1.0, ('moro\\\\n', 'wanton'): 1.0, ('divided\\\\n', 'among'): 1.0, ('the', 'tame'): 1.0, ('manager', 'qf'): 1.0, ('by\\\\n', 'Mrs.'): 1.0, ('young\\\\n', 'theologians'): 1.0, ('the', 'lib*'): 1.0, ('recent', 'homo'): 1.0, ('said\\\\n', 'administrator'): 1.0, ('It', 'has'): 1.0, (',', 'Concentrated'): 1.0, ('the', 'sugar'): 1.0, ('little', 'bov'): 1.0, ('min', 'W'): 1.0, ('dupes', 'of'): 1.0, ('One', 'of'): 2.0, ('Mr.\\\\n', 'Bo:tj'): 1.0, ('Bunker', 'Hill'): 1.0, ('judgment', 'Bhall'): 1.0, ('In', 'part:'): 1.0, ('to', 'file'): 1.0, ('New', 'Jersey'): 1.0, (',', 'she'): 2.0, ('tasacl', 'out,'): 1.0, ('of', 'alarm'): 1.0, ('it', 'in'): 2.0, ('.', 'W.'): 1.0, ('and', 'computed'): 1.0, ('complaint', 'came'): 1.0, ('and', 'not'): 1.0, ('distrust\\\\n', 'each'): 1.0, ('knew', 'how'): 1.0, ('In', '1898'): 1.0, ('republicanism', 'must'): 1.0, ('posi\xad\\\\n', 'tion'): 1.0, ('break\\\\n', 'troth'): 1.0, ('.\\\\n', 'Diploma'): 1.0, ('did', 'Ia6t.'): 1.0, ('is', 'real,'): 1.0, ('that\\\\n', 'Cato,'): 1.0, ('.', 'in'): 1.0, ('throwing', 'off'): 1.0, ('have', 'been'): 9.0, ('Folding', 'Cae'): 1.0, ('will\\\\nhave', 'a'): 1.0, ('re\\\\n', 'garding'): 1.0, ('but\\\\n', 'trom'): 1.0, ('walked', 'be-'): 1.0, ('swept', 'away'): 1.0, ('until\\\\n', 'fairly'): 1.0, ('awakened', 'by'): 1.0, ('tha\\\\n', 'smallest'): 1.0, ('prop', 'r'): 1.0, ('is', 'kept'): 2.0, ('circumstance.\\\\n', 'Had'): 1.0, ('are\\\\nvariant—some', 'saying'): 1.0, ('when', 'president.'): 1.0, ('j\\\\nmeat', 'oj'): 1.0, ('help', 'ye'): 1.0, ('on\\\\neach', 'one'): 1.0, ('by\\\\n', 'the'): 3.0, ('four', 'thousand'): 2.0, ('quarrH', '-'): 1.0, ('\\\\n', 'muscular,'): 1.0, ('his', 'own'): 3.0, ('Maryland\\\\nRailroad', 'Company,'): 1.0, ('!', 'Innocent'): 1.0, ('eradicating', 'all'): 1.0, (',', 'that'): 14.0, ('damage', 'done,'): 1.0, ('lie', 'knew'): 1.0, ('get', 'seed,'): 1.0, ('the', 'bidder,'): 2.0, ('and', 'the'): 18.0, ('ef-\\\\n', 'fective.'): 1.0, ('the\\\\n', 'extent'): 1.0, ('quite', 'firm.'): 1.0, ('Away\\\\nfrom', 'home'): 1.0, (',', 'have'): 2.0, ('the\\\\n', 'means'): 1.0, ('indifference.\\\\n', 'Tuberculosis'): 1.0, ('home\\\\n', 'with'): 1.0, ('never', 'have'): 1.0, ('to', 'show'): 1.0, ('thence\\\\n', 'south'): 1.0, ('laid', 'in'): 1.0, ('and\\\\nTruekee', 'Kailroad'): 1.0, ('.', 'Brown'): 1.0, ('the', 'death'): 2.0, ('horses', 'Mrs.'): 1.0, ('statistics', 'in'): 1.0, ('on', 'timothy'): 1.0, ('shall', 'be'): 8.0, ('the', 'prejudices'): 1.0, ('stallion\\\\n', '|'): 1.0, ('half', 'of'): 1.0, ('it', 'is'): 9.0, ('do', 'it;'): 1.0, ('declares', 'that'): 1.0, ('themselves', 'f-atriots'): 1.0, ('which', 'you'): 2.0, ('this\\\\n', 'tide'): 1.0, ('en\xad\\\\ntitled', 'to'): 1.0, ('all', 'round.'): 1.0, ('the', 'free.'): 1.0, (',', 'be'): 1.0, ('oi', 'till'): 1.0, ('utterest\\\\n', 'scorn'): 1.0, ('was', 'over'): 1.0, ('the', 'besl'): 1.0, ('third\\\\nof', 'the*'): 1.0, ('admission', 'that'): 1.0, ('been', 'put'): 1.0, ('164', 'perchei'): 1.0, ('no', 'an-'): 1.0, ('twenty', 'lings'): 1.0, ('It', 'is'): 6.0, ('hard', 'to'): 1.0, (',', 'is'): 4.0, ('sides', 'and'): 1.0, ('deprived', 'the'): 1.0, ('elo\xad\\\\n', 'quently'): 1.0, ('s', 'who'): 1.0, ('advantages\\\\nwould', 'not'): 1.0, ('Foushec', 'ft.'): 1.0, ('.', 'Clair’s'): 1.0, ('the\\\\n', 'Young'): 1.0, ('was', 'clear,'): 1.0, ('food\\\\nfrom', 'a'): 1.0, ('not', 'only'): 3.0, ('blood-stained', 'weap'): 1.0, ('property\\\\n', 'has'): 1.0, ('aro', 'perfectly'): 1.0, ('the', 'iumily'): 1.0, (',', 'reed*,'): 1.0, ('just', 'for'): 1.0, ('the', 'D'): 1.0, ('had', 'evidently'): 1.0, ('the', 'measures'): 1.0, ('I\\\\n', 'finally'): 1.0, ('people', 'of'): 2.0, ('the', 'expense'): 1.0, ('felt', 'if'): 1.0, ('jour-\\\\nnalism', 'which'): 1.0, ('as', 'to'): 7.0, ('47', 'deg.'): 1.0, ("'", 'after'): 1.0, ('.', 'He'): 11.0, ('About\\\\n', 'midnight'): 1.0, ('my', 'wife'): 2.0, ('effect', 'npon'): 1.0, ('throughout', 'the"'): 1.0, ('the', 'last'): 4.0, ('of', 'Kennehee'): 1.0, ('.V', 'York.'): 1.0, ('of\\\\n', 'Inue.'): 1.0, ('are', 'awarded'): 1.0, ('bound', 'to'): 1.0, ('the', 'upper'): 1.0, ('species', 'of'): 1.0, ('day', 'ol'): 1.0, ('a', 'fair'): 3.0, ('public', 'trustee'): 1.0, ('has', 'become'): 1.0, ('lading', 'and,'): 1.0, ('Another', 'potent'): 1.0, ('to', 'ihe'): 1.0, (';', 'the'): 3.0, ('a', 'large'): 4.0, ('II.\\\\n', 'one'): 1.0, ('ben-\\\\n', 'efit'): 1.0, ('which\\\\nwaa', 'fastened'): 1.0, ('is', 'laid'): 1.0, ('in', 'Smith'): 1.0, ('the\\\\nbest', 'Mexico'): 1.0, ('each', 'three'): 1.0, ('a', 'moun-'): 1.0, ...}