def rate(review):
review = SVM.asciify(review)
inputData = []
# 1st element = bayes with unigram
bayesClassifier.loadData("U")
inputData.append(bayesClassifier.percentPositive(review))
# bayes with adjective
bayesClassifier.loadData("A")
inputData.append(bayesClassifier.percentPositive(review))
# bayes with POS
bayesClassifier.loadData("P")
bayesClassifier.partOfSpeech = True
inputData.append(bayesClassifier.percentPositive(review))
# SVM with unigram
review = review.split()
SVM.loadModule("U")
SVM.loadWords("U")
X = SVM.intersection(SVM.wordList, review)
# SVM with adjective
inputData.append(SVM.movieReviewer.predict(X)[0])
SVM.loadModule("A")
SVM.loadWords("A")
X = SVM.intersection(SVM.wordList, review)
inputData.append(SVM.movieReviewer.predict(X)[0])
return Tree.predict(inputData)[0]
#!/usr/bin/python
import bayesClassifier
import os
from sys import argv
total = 0
done = 0
accurate = 0
keywordList = {}
bayesClassifier.loadData(argv[1])
files = os.listdir('./test/pos')
# comment this line to increase sample size
files = files[:3000]
total = len(files)
progress = 0
for i in files:
done += 1
if ((done * 100 / float(total)) > (progress + 10)):
progress += 10
#os.system("echo -n '='")
f = bayesClassifier.asciify(open('./test/pos/' + i, 'r').read())
print bayesClassifier.percentPositive(f)
if bayesClassifier.percentPositive(f) > 0.5:
accurate += 1