by Andrew Trask
In [11]:
def pretty_print_review_and_label(i):
print(labels[i] + "\t:\t" + reviews[i][:80] + "...")
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()
In [12]:
len(reviews)
Out[12]:
In [13]:
reviews[0]
Out[13]:
In [14]:
labels[0:2]
Out[14]:
In [15]:
print("labels.txt \t : \t reviews.txt\n")
pretty_print_review_and_label(2137)
pretty_print_review_and_label(12816)
pretty_print_review_and_label(6267)
pretty_print_review_and_label(21934)
pretty_print_review_and_label(5297)
pretty_print_review_and_label(4998)
In [25]:
from collections import Counter
negcnt = 0
poscnt = 0
for line in reviews:
poscnt = poscnt + line.count("excellent")
negcnt = negcnt + line.count("terrible")
print (poscnt, negcnt)
print(labels.count("POSITIVE"), labels.count("NEGATIVE"))
len(labels)
Out[25]:
In [ ]: