import cPickle as pickle
import random
from nltk.model import NgramModel
from nltk.probability import LidstoneProbDist
import nltk
print "... loading text"
text_train = list(nltk.corpus.gutenberg.words('austen-emma.txt'))
print len(set(text_train))
text_test = list(nltk.corpus.gutenberg.words('austen-sense.txt'))
#with open('./../datasets/t5_train') as f:
# text_train =(' '.join(pickle.load(f))).split(' . ')
# random.shuffle(text_train)
# text_train = (' . '.join(text_train)).split(' ')
#
#with open('./../datasets/t5_test') as f:
# text_test =(' '.join(pickle.load(f))).split(' . ')
# random.shuffle(text_test)
# text_test = (' . '.join(text_test)).split(' ')
print "... training model"
estimator = lambda fdist, bins: LidstoneProbDist(fdist, 0.2)
lm = NgramModel(3, text_train, estimator=estimator)
print "... results"
print lm.generate(50, ['dog'])
print lm.perplexity(text_test)
print lm.entropy(text_test)
#!/usr/bin/env python
import nltk
from nltk import bigrams
from nltk import trigrams
from nltk.probability import LidstoneProbDist
from nltk.model import NgramModel
with open('./austen/persuasion.txt', 'r') as training_file:
raw = training_file.read()
tokens = nltk.word_tokenize(raw)
with open('./austen/sense_and_sensibility.txt', 'r') as test_file:
test = test_file.read()
test_list = nltk.word_tokenize(test)
estimator = lambda fdist, bins: LidstoneProbDist(fdist, 0.2)
model = NgramModel(3, tokens,True,False,estimator)
tri=model.entropy(test_list)
print "tri-gram: " + str(tri)
model = NgramModel(2, tokens,True,False,estimator)
bi=model.entropy(test_list)
print "bi-gram: " + str(bi)
#!/usr/bin/env python
import nltk
from nltk import bigrams
from nltk import trigrams
from nltk.probability import LidstoneProbDist
from nltk.model import NgramModel
with open('./austen/persuasion.txt', 'r') as training_file:
raw = training_file.read()
tokens = nltk.word_tokenize(raw)
with open('./austen/sense_and_sensibility.txt', 'r') as test_file:
test = test_file.read()
test_list = nltk.word_tokenize(test)
estimator = lambda fdist, bins: LidstoneProbDist(fdist, 0.2)
model = NgramModel(3, tokens, True, False, estimator)
tri = model.entropy(test_list)
print "tri-gram: " + str(tri)
model = NgramModel(2, tokens, True, False, estimator)
bi = model.entropy(test_list)
print "bi-gram: " + str(bi)
from nltk.util import ngrams
from nltk.corpus import reuters
from nltk.corpus import genesis
from nltk.probability import LaplaceProbDist
from nltk.model import NgramModel
import nltk
sentence = 'She covered a Bob Dylan song for Amnesty International.'
## http://www.inf.ed.ac.uk/teaching/courses/icl/nltk/probability.pdf
## http://www.nltk.org/book/ch02.html
n = 2
bigrams = ngrams(sentence.split(), n)
print bigrams
## Append starting points and ending points
#for grams in sixgrams:
# print grams
estimator = lambda fdist, bins: LaplaceProbDist(fdist, len(sentence.split())+1)
model = NgramModel(2,sentence.split(),estimator=estimator)
print model.generate(1, ("her","take"))
print
print model.entropy(["she","covered"])
def demo():
from nltk.corpus import treebank
#from nltk.probability import LidstoneProbDist
#from nltk.probability import WittenBellProbDist
from nltk.probability import SimpleGoodTuringProbDist
from nltk.model import NgramModel
estimator = lambda fdist, bins: SimpleGoodTuringProbDist(fdist, len(fdist)+1)
#estimator = lambda fdist, bins: LidstoneProbDist(fdist, 0.2)
#estimator = lambda fdist, bins: WittenBellProbDist(fdist, 0.2)
tag_corpus = []
for (word,tag) in treebank.tagged_words():
tag_corpus.append(tag)
lm = NgramModel(2, tag_corpus, estimator)
print lm
lm1 = NgramModel(1, tag_corpus, estimator)
print lm1
print tag_corpus[:20]
sent = "NN"
print lm1.entropy(sent)
sent = "DT "
print lm1.entropy(sent)
sent = "VBZ"
print lm1.entropy(sent)
sent = "JJ"
print lm1.entropy(sent)
sent = "RB"
print lm1.entropy(sent)
sent = "DT NN"
print lm.entropy(sent)
word = word.lower()
corpus_tokens.append(word)
print "Adding gutenberg"
for word in gutenberg.words():
word = word.lower()
corpus_tokens.append(word)
print "Training Trigram Model"
lm = NgramModel(3,corpus_tokens,True,False,lambda f,b:LidstoneProbDist(f,0.01,f.B()+1))
tweet_entropies = []
count = 1
for sent in useful:
sent = sent.split()
percentage = 100*count/len(useful)
print "\rChecking entropy : " + str(count) + " of " + str(len(useful)) + " " + str(percentage) + "%",
entropy = lm.entropy(sent)
tweet_entropies.append((" ".join(sent), entropy))
count += 1
tweet_entropies.sort(key=lambda x: x[1])
threshold = int(len(tweet_entropies) * 0.8)
list_of_tweets = tweet_entropies[:threshold]
print "\n",
final_tweets = [a for (a,b) in list_of_tweets]
count = 1
for tweet in final_tweets:
percentage = 100*count/len(final_tweets)
print '\rWriting: ' + str(count) + " of " + str(len(final_tweets)) + " " + str(percentage) + "%",
writer.write(tweet + "\n")
tamil2_alpha = []
tamil2_alpha_all = []
for line in tamil1f.readlines()[1:]:
tamil1_alpha.append(["St"]+line.split(",")[-1].replace("\n","").replace("[","").replace("]","").replace("\r","").split("|")+["En"])
tamil1_alpha_all += ["St"]+line.split(",")[-1].replace("\n","").replace("[","").replace("]","").replace("\r","").split("|")+["En"]
for line in tamil2f.readlines()[1:]:
tamil2_alpha.append(["St"]+line.split(",")[-1].replace("\n","").replace("[","").replace("]","").replace("\r","").split("|")+["En"])
tamil2_alpha_all += ["St"]+line.split(",")[-1].replace("\n","").replace("[","").replace("]","").replace("\r","").split("|")+["En"]
s_bg1 = nltk.bigrams(tamil1_alpha_all)
s_bg2 = nltk.bigrams(tamil2_alpha_all)
fdist1 = nltk.FreqDist(s_bg1)
fdist2 = nltk.FreqDist(s_bg2)
estimator1 = lambda fdist, bins: LaplaceProbDist(fdist, len(tamil1_alpha_all)+1)
estimator2 = lambda fdist, bins: LaplaceProbDist(fdist, len(tamil2_alpha_all)+1)
model1 = NgramModel(3,tamil1_alpha_all,estimator=estimator1)
model2 = NgramModel(3,tamil2_alpha_all,estimator=estimator2)
print model1.entropy(tamil1_alpha[0])
print model1.perplexity(tamil1_alpha[0])
