def run(self):
rev = ReviewParser(open(settings.reviews_path + ReviewParser.map_cid_to_name(self.cid), 'rb',), review_files[choice].split('.')[-1])
rev.parse()
print "Mining", len(rev.reviews), "reviews"
text = rev.get_raw_text()
f = FeatureExtractor(text, ReviewParser.map_cid_to_name(self.cid))
self.features = f.get_frequent_features(self.min_support)
for ftr in self.features:
self.ratings[ftr[0]] = {'positive': 0, 'negative': 0, 'neutral': 0}
o = OpinionSentenceFinder(self.features, f.feature_sentences)
#Extract all sentences which express some opinion
opinion_sents = map(lambda y: y['opinion_sent'], filter(lambda x: len(x['opinion_sent']) > 1, o.feature_sentences))
temp = []
for os in opinion_sents:
temp.extend(os)
opinion_sents = temp
for ftr, sentiment in opinion_sents:
if sentiment[0] is True:
self.ratings[ftr]['positive'] += 1
elif sentiment[0] is False:
self.ratings[ftr]['negative'] += 1
else:
self.ratings[ftr]['neutral'] += 1
pp = pprint.PrettyPrinter(indent = 4)
print "Is this a %s?" % f.product_category
print "%d features are interesting" % len(self.features)
#pp.pprint(opinion_sents)
pp.pprint(self.ratings)
def run(self):
rev = ReviewParser(
open(settings.reviews_path + ReviewParser.map_cid_to_name(self.cid), "rb"),
review_files[choice].split(".")[-1],
)
rev.parse()
print "Mining", len(rev.reviews), "reviews"
text = rev.get_raw_text()
f = FeatureExtractor(text, ReviewParser.map_cid_to_name(self.cid))
self.features = f.get_frequent_features(self.min_support)
for ftr in self.features:
self.ratings[ftr[0]] = {"positive": 0, "negative": 0, "neutral": 0}
o = OpinionSentenceFinder(self.features, f.feature_sentences)
# Extract all sentences which express some opinion
opinion_sents = map(
lambda y: y["opinion_sent"], filter(lambda x: len(x["opinion_sent"]) > 1, o.feature_sentences)
)
temp = []
for os in opinion_sents:
temp.extend(os)
opinion_sents = temp
for ftr, sentiment in opinion_sents:
if sentiment[0] is True:
self.ratings[ftr]["positive"] += 1
elif sentiment[0] is False:
self.ratings[ftr]["negative"] += 1
else:
self.ratings[ftr]["neutral"] += 1
pp = pprint.PrettyPrinter(indent=4)
print "Is this a %s?" % f.product_category
print "%d features are interesting" % len(self.features)
# pp.pprint(opinion_sents)
pp.pprint(self.ratings)
elif sentiment[0] is False:
self.ratings[ftr]['negative'] += 1
else:
self.ratings[ftr]['neutral'] += 1
pp = pprint.PrettyPrinter(indent = 4)
print "Is this a %s?" % f.product_category
print "%d features are interesting" % len(self.features)
#pp.pprint(opinion_sents)
pp.pprint(self.ratings)
if __name__ == "__main__":
try:
min_support = int(sys.argv[1])
except:
min_support = 4
review_files = ReviewParser.get_available_reviews()
for review_file in review_files:
print review_files.index(review_file), ' ' + review_file
choice = int(input('#'))
if choice not in xrange(0, len(review_files)):
print 'Error'
exit(-1)
cid = review_files[choice].split(".")[0].split("_")[-2]
om = OpinionMiner(cid, min_support)
om.run()
from ReviewParser import ReviewParser
from FeatureExtractor import FeatureExtractor
review_file = ['Apple_iPhone_4.csv', 'Blackberry_Torch_9800.csv', 'Nikon_D90.csv', 'Canon_ELPH_300_HS.csv']
rev = ReviewParser(open('../data/reviews/' + review_file[3], 'rb',), 'CSV')
rev.parse()
text = rev.get_raw_text()
f = FeatureExtractor(text)
print f.get_frequent_features(5)
"""
#tokenize_patterns = ['[Nn]ikon ?[dD][0-9]+', '([0-9]+ ?mm)', '(auto[ -_]?focus)', '(Apple)[ ]?(iphone)??[0-5]?[gs]*']
features = [w.lower() for (w,t) in tags if t.startswith('N') and t != 'NNP']
features = p.stemmer(features)
dist = nltk.FreqDist(features)
obs = [ob for ob in dist.iteritems()]
logfile = open('/tmp/log.txt', 'w')
logfile.write("".join(str(obs)).replace("), (", ")\n("))
logfile.close()
"""
self.ratings[ftr]["positive"] += 1
elif sentiment[0] is False:
self.ratings[ftr]["negative"] += 1
else:
self.ratings[ftr]["neutral"] += 1
pp = pprint.PrettyPrinter(indent=4)
print "Is this a %s?" % f.product_category
print "%d features are interesting" % len(self.features)
# pp.pprint(opinion_sents)
pp.pprint(self.ratings)
if __name__ == "__main__":
try:
min_support = int(sys.argv[1])
except:
min_support = 4
review_files = ReviewParser.get_available_reviews()
for review_file in review_files:
print review_files.index(review_file), " " + review_file
choice = int(input("#"))
if choice not in xrange(0, len(review_files)):
print "Error"
exit(-1)
cid = review_files[choice].split(".")[0].split("_")[-2]
om = OpinionMiner(cid, min_support)
om.run()
