sentiment2.py

## Read the reviews first.
g = open('reviews.txt','r') # What we know!
reviews = list(map(lambda x:x[:-1],g.readlines()))
g.close()

g = open('labels.txt','r') # What we WANT to know!
labels = list(map(lambda x:x[:-1].upper(),g.readlines()))
g.close()

from collections import Counter
import numpy as np

positive_counts = Counter()
negative_counts = Counter()
total_counts = Counter()

for i in range(len(reviews)):
  # first get count of all words with POSITIVE review.
    if(labels[i] == 'POSITIVE'):
        for word in reviews[i].split(" "):
            positive_counts[word] += 1
            total_counts[word] += 1
    else:
      # get count of all words with NEGATIVE review.
        for word in reviews[i].split(" "):
            negative_counts[word] += 1
            total_counts[word] += 1
            
negative_counts.most_common()
positive_counts.most_common()


pos_neg_ratios = Counter()

for term,cnt in list(total_counts.most_common()):
    if(cnt > 100):
        pos_neg_ratio = positive_counts[term] / float(negative_counts[term]+1)
        pos_neg_ratios[term] = pos_neg_ratio

for word,ratio in pos_neg_ratios.most_common():
    if(ratio > 1):
        pos_neg_ratios[word] = np.log(ratio)
    else:
        pos_neg_ratios[word] = -np.log((1 / (ratio+0.01)))
        
pos_neg_ratios.most_common()
list(reversed(pos_neg_ratios.most_common()))[0:30]