def getMeTheNGramModel(tokens, n):
mydict = {}
position = 0
for x in tokens[0:-(n-1)]:
ngram = " ".join( tokens[ position : position + n ] )
mydict[ngram] = mydict.get(ngram, 0) + 1
#print( ngram )
position += 1
relativizeFP(mydict)
return mydict
#!/usr/bin/env python3
# -*- coding: UTF-8 -*-
from math import log
#import corpus
from corpus import getTextFromFile, makeFrequencyProfile, tokenize, relativizeFP
mydict = makeFrequencyProfile( tokenize( getTextFromFile("pg873.txt") ) )
relativizeFP(mydict)
#for key in mydict:
# print(key, mydict[key], sep="\t")
mysportsdict = makeFrequencyProfile( tokenize( getTextFromFile("sports.txt") ) )
relativizeFP(mysportsdict)
unktokens = tokenize("""
The young King was eating pomegranates and talking about his soul and other emotional issues.
""")
probpomeg = 0.0
probsports = 0.0
for token in unktokens:
probpomeg += log(mydict.get(token, 0.00000000000001))
probsports += log(mysportsdict.get(token, 0.00000000000001))
if probpomeg > probsports:
print("This text is probably House of Pomeg.")
else:
youngF = unigrams["young"]
FishermanF = unigrams["Fisherman"]
youngFishermanF = bigrams["young Fisherman"]
total = sum(unigrams.values())
observationtable = [[youngFishermanF, FishermanF - youngFishermanF],
[
youngF - youngFishermanF,
(total - youngF) - (FishermanF - youngFishermanF)
]]
print(observationtable)
expectationtable = [[
(sum(observationtable[0]) *
(observationtable[0][0] + observationtable[1][0])) / total
], []]
print(expectationtable)
chi2 = (observationtable[0][0] -
expectationtable[0][0])**2 / expectationtable[0][0]
print("Chi2-score:", chi2)
relativizeFP(unigrams)
relativizeFP(bigrams)
print("\n\nProbability ratio:")
print("P(young Fisherman):", bigrams["young Fisherman"])
print("P(young) * P(Fisherman):", unigrams["young"] * unigrams["Fisherman"])
print("P(young Fisherman) / ( P(young) * P(Fisherman) ):",
bigrams["young Fisherman"] / (unigrams["young"] * unigrams["Fisherman"]))
#print(unigrams)
# prettyPrintFRP(bigrams, myreverse=False)
youngF = unigrams["young"]
FishermanF = unigrams["Fisherman"]
youngFishermanF = bigrams["young Fisherman"]
total = sum(unigrams.values())
observationtable = [ [ youngFishermanF, FishermanF - youngFishermanF ],
[ youngF - youngFishermanF, (total - youngF) - (FishermanF - youngFishermanF) ] ]
print(observationtable)
expectationtable = [ [ (sum(observationtable[0]) * (observationtable[0][0] + observationtable[1][0])) / total ],
[] ]
print(expectationtable)
chi2 = (observationtable[0][0] - expectationtable[0][0]) ** 2 / expectationtable[0][0]
print("Chi2-score:", chi2)
relativizeFP(unigrams)
relativizeFP(bigrams)
print("\n\nProbability ratio:")
print("P(young Fisherman):", bigrams["young Fisherman"])
print("P(young) * P(Fisherman):", unigrams["young"] * unigrams["Fisherman"])
print("P(young Fisherman) / ( P(young) * P(Fisherman) ):", bigrams["young Fisherman"] / (unigrams["young"] * unigrams["Fisherman"]))
