def test_sentiment(self):
# Assert < 0 for negative adjectives and > 0 for positive adjectives.
self.assertTrue(en.sentiment("wonderful")[0] > 0)
self.assertTrue(en.sentiment("horrible")[0] < 0)
self.assertTrue(
en.sentiment(en.wordnet.synsets("horrible", pos="JJ")[0])[0] < 0)
self.assertTrue(
en.sentiment(en.Text(en.parse("A bad book. Really horrible.")))[0]
< 0)
# Assert that :) and :( are recognized.
self.assertTrue(en.sentiment(":)")[0] > 0)
self.assertTrue(en.sentiment(":(")[0] < 0)
# Assert the accuracy of the sentiment analysis.
# Given are the scores for Pang & Lee's polarity dataset v2.0:
# http://www.cs.cornell.edu/people/pabo/movie-review-data/
# The baseline should increase (not decrease) when the algorithm is modified.
from pattern.db import Datasheet
from pattern.metrics import test
reviews = []
for score, review in Datasheet.load(
os.path.join(PATH, "corpora", "polarity-en-pang&lee.csv")):
reviews.append((review, int(score) > 0))
A, P, R, F = test(lambda review: en.positive(review), reviews)
self.assertTrue(A > 0.71)
self.assertTrue(P > 0.72)
self.assertTrue(R > 0.70)
self.assertTrue(F > 0.71)
print "pattern.en.sentiment()"
def setUp(self):
# Parse sentences to test on.
# Creating a Text creates Sentence, Chunk, PNP and Word.
# Creating a Sentence tests Sentence.append() and
# Sentence.parse_token().
self.text = "I'm eating pizza with a fork. What a tasty pizza!"
self.text = en.Text(en.parse(self.text, relations=True, lemmata=True))
