def test_readability(self):
# Technical jargon should be in the "difficult" range: < 0.30
s = "The Australian platypus is seemingly a hybrid of a mammal and reptilian creature"
v = metrics.readability(s)
self.assertTrue(v < 0.30)
# Dr. Seuss should be in the "easy" range: > 0.70
s = "'I know some good games we could play,' said the cat." + \
"'I know some new tricks,' said the cat in the hat." + \
"'A lot of good tricks. I will show them to you.'" + \
"'Your mother will not mind at all if I do.'"
v = metrics.readability(s)
self.assertTrue(v > 0.70)
def test_readability(self):
# Assert technical jargon in the "difficult" range (< 0.30).
s = "The Australian platypus is seemingly a hybrid of a mammal and reptilian creature"
v = metrics.readability(s)
self.assertTrue(v < 0.30)
# Assert that Dr. Seuss isin the "easy" range (> 0.70).
s = (
"'I know some good games we could play,' said the cat."
+ "'I know some new tricks,' said the cat in the hat."
+ "'A lot of good tricks. I will show them to you.'"
+ "'Your mother will not mind at all if I do.'"
)
v = metrics.readability(s)
self.assertTrue(v > 0.70)
print "pattern.metrics.readability()"
import pandas as pd
import sys
store = 'tweets.csv'
df = pd.read_csv(store,
sep=';',
names=['brand', 'id', 'username', 'date', 'tweet', 'source'])
brand1 = df[df.brand == 'SNCB']
brand2 = df[df.brand == 'SNCF']
from pattern.fr import parse, sentiment, ngrams, pprint
from pattern.web import URL, plaintext
from pattern.metrics import readability
b1_read = 0.0
b1_sent = 0.0
for tweet in brand1.tweet:
b1_sent += sentiment(plaintext(tweet))[0]
b1_read += readability(tweet)
b2_read = 0.0
b2_sent = 0.0
for tweet in brand2.tweet:
b2_sent += sentiment(plaintext(tweet))[0]
b2_read += readability(tweet)
print 'SNCB: %f' % b1_sent
print 'SNCF: %f' % b2_sent