gerbal
1/25/2014 - 6:59 PM
For NLP Presentation about NLTK
For NLP Presentation about NLTK
evaluating single word features
accuracy: 0.728
pos precision: 0.651595744681
pos recall: 0.98
neg precision: 0.959677419355
neg recall: 0.476
Most Informative Features
magnificent = True pos : neg = 15.0 : 1.0
outstanding = True pos : neg = 13.6 : 1.0
insulting = True neg : pos = 13.0 : 1.0
vulnerable = True pos : neg = 12.3 : 1.0
ludicrous = True neg : pos = 11.8 : 1.0
avoids = True pos : neg = 11.7 : 1.0
uninvolving = True neg : pos = 11.7 : 1.0
astounding = True pos : neg = 10.3 : 1.0
fascination = True pos : neg = 10.3 : 1.0
idiotic = True neg : pos = 9.8 : 1.0
evaluating best word features
accuracy: 0.93
pos precision: 0.890909090909
pos recall: 0.98
neg precision: 0.977777777778
neg recall: 0.88
Most Informative Features
magnificent = True pos : neg = 15.0 : 1.0
outstanding = True pos : neg = 13.6 : 1.0
insulting = True neg : pos = 13.0 : 1.0
vulnerable = True pos : neg = 12.3 : 1.0
ludicrous = True neg : pos = 11.8 : 1.0
avoids = True pos : neg = 11.7 : 1.0
uninvolving = True neg : pos = 11.7 : 1.0
fascination = True pos : neg = 10.3 : 1.0
astounding = True pos : neg = 10.3 : 1.0
idiotic = True neg : pos = 9.8 : 1.0
evaluating best words + bigram chi_sq word features
accuracy: 0.922
pos precision: 0.916996047431
pos recall: 0.928
neg precision: 0.927125506073
neg recall: 0.916
Most Informative Features
magnificent = True pos : neg = 15.0 : 1.0
outstanding = True pos : neg = 13.6 : 1.0
insulting = True neg : pos = 13.0 : 1.0
vulnerable = True pos : neg = 12.3 : 1.0
('matt', 'damon') = True pos : neg = 12.3 : 1.0
('give', 'us') = True neg : pos = 12.3 : 1.0
ludicrous = True neg : pos = 11.8 : 1.0
uninvolving = True neg : pos = 11.7 : 1.0
avoids = True pos : neg = 11.7 : 1.0
('absolutely', 'no') = True neg : pos = 10.6 : 1.0
# From http://streamhacker.com/2010/06/16/text-classification-sentiment-analysis-eliminate-low-information-features/
import collections, itertools
import nltk.classify.util, nltk.metrics
from nltk.classify import NaiveBayesClassifier
from nltk.corpus import movie_reviews, stopwords
from nltk.collocations import BigramCollocationFinder
from nltk.metrics import BigramAssocMeasures
from nltk.probability import FreqDist, ConditionalFreqDist
def evaluate_classifier(featx):
negids = movie_reviews.fileids('neg')
posids = movie_reviews.fileids('pos')
negfeats = [(featx(movie_reviews.words(fileids=[f])), 'neg') for f in negids]
posfeats = [(featx(movie_reviews.words(fileids=[f])), 'pos') for f in posids]
negcutoff = len(negfeats)*3/4
poscutoff = len(posfeats)*3/4
trainfeats = negfeats[:negcutoff] + posfeats[:poscutoff]
testfeats = negfeats[negcutoff:] + posfeats[poscutoff:]
classifier = NaiveBayesClassifier.train(trainfeats)
refsets = collections.defaultdict(set)
testsets = collections.defaultdict(set)
for i, (feats, label) in enumerate(testfeats):
refsets[label].add(i)
observed = classifier.classify(feats)
testsets[observed].add(i)
print 'accuracy:', nltk.classify.util.accuracy(classifier, testfeats)
print 'pos precision:', nltk.metrics.precision(refsets['pos'], testsets['pos'])
print 'pos recall:', nltk.metrics.recall(refsets['pos'], testsets['pos'])
print 'neg precision:', nltk.metrics.precision(refsets['neg'], testsets['neg'])
print 'neg recall:', nltk.metrics.recall(refsets['neg'], testsets['neg'])
classifier.show_most_informative_features()
def word_feats(words):
return dict([(word, True) for word in words])
print 'evaluating single word features'
evaluate_classifier(word_feats)
word_fd = FreqDist()
label_word_fd = ConditionalFreqDist()
for word in movie_reviews.words(categories=['pos']):
word_fd.inc(word.lower())
label_word_fd['pos'].inc(word.lower())
for word in movie_reviews.words(categories=['neg']):
word_fd.inc(word.lower())
label_word_fd['neg'].inc(word.lower())
# n_ii = label_word_fd[label][word]
# n_ix = word_fd[word]
# n_xi = label_word_fd[label].N()
# n_xx = label_word_fd.N()
pos_word_count = label_word_fd['pos'].N()
neg_word_count = label_word_fd['neg'].N()
total_word_count = pos_word_count + neg_word_count
word_scores = {}
for word, freq in word_fd.iteritems():
pos_score = BigramAssocMeasures.chi_sq(label_word_fd['pos'][word],
(freq, pos_word_count), total_word_count)
neg_score = BigramAssocMeasures.chi_sq(label_word_fd['neg'][word],
(freq, neg_word_count), total_word_count)
word_scores[word] = pos_score + neg_score
best = sorted(word_scores.iteritems(), key=lambda (w,s): s, reverse=True)[:10000]
bestwords = set([w for w, s in best])
def best_word_feats(words):
return dict([(word, True) for word in words if word in bestwords])
print 'evaluating best word features'
evaluate_classifier(best_word_feats)
def best_bigram_word_feats(words, score_fn=BigramAssocMeasures.chi_sq, n=200):
bigram_finder = BigramCollocationFinder.from_words(words)
bigrams = bigram_finder.nbest(score_fn, n)
d = dict([(bigram, True) for bigram in bigrams])
d.update(best_word_feats(words))
return d
print 'evaluating best words + bigram chi_sq word features'
evaluate_classifier(best_bigram_word_feats)train on 1500 instances, test on 500 instances
('accuracy:', 0.728)
Most Informative Features
magnificent = True pos : neg = 15.0 : 1.0
outstanding = True pos : neg = 13.6 : 1.0
insulting = True neg : pos = 13.0 : 1.0
vulnerable = True pos : neg = 12.3 : 1.0
ludicrous = True neg : pos = 11.8 : 1.0
avoids = True pos : neg = 11.7 : 1.0
uninvolving = True neg : pos = 11.7 : 1.0
astounding = True pos : neg = 10.3 : 1.0
fascination = True pos : neg = 10.3 : 1.0
idiotic = True neg : pos = 9.8 : 1.0import nltk.classify.util
from nltk.classify import NaiveBayesClassifier
from nltk.corpus import movie_reviews
from pprint import pprint
# from http://streamhacker.com/2010/05/10/text-classification-sentiment-analysis-naive-bayes-classifier/
def word_feats(words):
return dict([(word, True) for word in words])
negids = movie_reviews.fileids('neg')
posids = movie_reviews.fileids('pos')
negfeats = [(word_feats(movie_reviews.words(fileids=[f])), 'neg') for f in negids]
posfeats = [(word_feats(movie_reviews.words(fileids=[f])), 'pos') for f in posids]
negcutoff = len(negfeats)*3/4
poscutoff = len(posfeats)*3/4
trainfeats = negfeats[:negcutoff] + posfeats[:poscutoff]
testfeats = negfeats[negcutoff:] + posfeats[poscutoff:]
print( 'train on %d instances, test on %d instances' % (len(trainfeats), len(testfeats)))
classifier = NaiveBayesClassifier.train(trainfeats)
print( 'accuracy:', nltk.classify.util.accuracy(classifier, testfeats))
classifier.show_most_informative_features()
from nltk.grammar import parse_cfg
from nltk.parse import generate2
grammar2 = parse_cfg("""
S -> NP VP
NP -> Det Nom | PropN
Nom -> Adj Nom | N
VP -> V Adj | V NP | V S | V NP PP
PP -> P NP
PropN -> 'Buster' | 'Chatterer' | 'Joe'
Det -> 'the' | 'a'
N -> 'bear' | 'squirrel' | 'tree' | 'fish' | 'log'
Adj -> 'angry' | 'frightened' | 'little' | 'tall'
V -> 'chased' | 'saw' | 'said' | 'thought' | 'was' | 'put'
P -> 'on'
""")
for n in generate2.generate(grammar2, None,5):
print ' '.join(n)