def get_vocab_counts_from_csv(self):
review_count = 0
with open(self.input_file, "rb") as csvfile:
review_reader = csv.reader(csvfile, delimiter="\t", quotechar='"')
review_reader.next()
for row in review_reader:
rows = row[0].split(",", 1)
review_type = rows[0]
review_content = rows[1]
# print review_content
self.total_sentence_count = self.total_sentence_count + 1
review_type = str(review_type)
# Organizing the reviews based on the review type
self.update_review_number_for_review_type(review_type)
# updating the class counts
if review_type in self.class_counts_hash.keys():
class_count = self.class_counts_hash[review_type]
class_count = class_count + 1
self.class_counts_hash[review_type] = class_count
else:
self.class_counts_hash.update({review_type: 1})
# @depricated POS tagging
# pos_tagging_tokens=preprocessor.tokenize_string_without_punctuations(review_content)
# self.update_pos_tags(pos_tagging_tokens)
final_tokens = preprocessor.pre_process_sentence(review_content)
self.construct_vocabulary_hash(review_type, final_tokens)
csvfile.close()
import naive_bayes_classifier as nb
(script_name,model_file,test_file)=argv
prior_word_conditional_prob_hash=pickle.load(open(model_file,"rb"))
feature_rank_hash=pickle.load(open("feature_ranks.p","rb"))
prior_probabilities=pickle.load(open("prior_class_probabilities.p","rb"))
count=-1
with open(test_file, 'rb') as csvfile:
review_reader = csv.reader(csvfile, delimiter='\t', quotechar='"')
#review_reader.next()
for row in review_reader:
count=count+1
if count==0:
print "Id,Category"
continue
#rows=row[0].split(",",1)
review_content=""
#if len(rows)==2:
# review_content=rows[1]
#elif len(rows)==1:
# review_content=rows[0]
review_content=row[0]
words=preprocessor.pre_process_sentence(review_content)
negative_words=pickle.load(open("negative_words.p","rb"))
positive_words=pickle.load(open("positive_words.p","rb"))
class_data=nb.naive_bayes_classifier(prior_probabilities,prior_word_conditional_prob_hash,words,positive_words,negative_words )
#print str(count)+","+class_data.keys()[0]
print class_data.keys()[0]+","+review_content
#break
