print
# Train Naive Bayes on all documents.
# To test the accuracy of a classifier, Using 10-fold crossvalidation
# This yields 4 scores: Accuracy, Precision, Recall and F-score.
print 'Bayes Classifier'
print '-------------------------'
print '(Accuracy, Precision,REcall,F-Measure)'
print Bayes.test(corpus,folds=10)
#Crossavalidation on reduced Dataset
nfeatures=10000
f=corpus.feature_selection(top=nfeatures,method=IG)
corpus=corpus.filter(features=f)
print 'Bayes Classifier on Reduced dataset of', nfeatures,' features'
print '-------------------------'
print '(Accuracy, Precision,REcall,F-Measure)'
print Bayes.test(corpus,folds=10)
#Testing Model on sample Dataset
print 'Testing Model on Sample Dataset'
classifier = Bayes()
for document in corpus.documents:
classifier.train(document,type=document.type)
# In the file top 10 are negative tweets and rest are positive tweets
ft=open('test_20','r')
test_lines=ft.readlines()
#print xxx print len(corpus) print len(corpus.features) print len(corpus.documents[0].vector) from time import time t = time() print KNN.test(corpus, folds=10) print time()-t print "filter..." from time import time t = time() f = corpus.feature_selection(150, verbose=False) print f print time()-t corpus = corpus.filter(f) #corpus.reduce(300) #print len(corpus.lsa.vectors[corpus.documents[0].id]) #print corpus.lsa.vectors[corpus.documents[0].id] #print len(corpus) #print len(corpus.lsa.terms) #print corpus.feature_selection(top=100, verbose=True) from time import time t = time() print KNN.test(corpus, folds=10)
print 'Number of Negative Tweets:',len(neg_lines)
print 'Number of Positive Tweets:',len(pos_lines)
documents = []
for line in neg_lines:
document = Document(line,stopword=True,stemmer=PORTER,type='0')
documents.append(document)
for line in pos_lines:
document = Document(line,stopword=True,stemmer=PORTER,type='1')
documents.append(document)
corpus = Corpus(documents,weight=TFIDF)
print "number of documents:", len(corpus)
print "number of words:", len(corpus.vector)
print "number of words (average):", sum(len(d.terms) for d in corpus.documents) / float(len(corpus))
print
#Filtering top 1000 features using Information Gain Criterion
corpus=corpus.filter(features=(corpus.feature_selection(top=1000,method=IG)))
# To test the accuracy of a classifier, Using 10-fold crossvalidation
# This yields 4 scores: Accuracy, Precision, Recall and F-score.
print 'classifying using KNN'
print '-------------------------'
print '(Accuracy, Precision,REcall,F-Measure)'
print KNN.test(corpus,k=100,folds=10,distance=COSINE)
f_neg.close()
f_pos.close()
