def test_tokenCleaner(self):
sentence = "Hello I'm very happy 1313"
goldenSentence = "hello"
tokens = tokenize(sentence)
functions.stopwords = load_stopwords("etc/stopwords_en.txt")
newTokens = tokenCleaner(tokens, ["stemming", "toLowerCase", "removePunctuationAndNumbers", "stopwording"])
self.assertEqual(sentenize(newTokens), goldenSentence)
def test_removeSingleChar(self):
sentence = "at 8 o'clock on (Thursday) morning Arthur didn't feel very good."
goldenSentence = "at o'clock on Thursday morning Arthur did n't feel very good"
tokens = tokenize(sentence)
newTokens = []
for token in tokens:
newTokens.append(removeSingleChar(token))
self.assertEqual(sentenize(newTokens), goldenSentence)
def test_removePunctuationAndNumbers(self):
sentence = "at 8 o'clock on (thursday) morning Arthur didn't feel very good."
goldenSentence = "at oclock on thursday morning Arthur did nt feel very good"
tokens = tokenize(sentence)
newTokens = []
for token in tokens:
newTokens.append(removePunctuationAndNumbers(token))
self.assertEqual(sentenize(newTokens), goldenSentence)
def test_toLowerCase(self):
sentence = "bOys WOMEN Homes MeN cARs aRchIvES"
goldenSentence = "boys women homes men cars archives"
tokens = tokenize(sentence)
newTokens = []
for token in tokens:
newTokens.append(toLowerCase(token))
self.assertEqual(sentenize(newTokens), goldenSentence)
def test_stemming(self):
sentence = "boys and women want to have homes, not cars going and archives"
goldenSentence = "boy and woman want to have home , not car go and archive"
tokens = tokenize(sentence)
newTokens = []
for token in tokens:
newTokens.append(stemming(token))
self.assertEqual(sentenize(newTokens), goldenSentence)
def test_stopwording(self):
sentence = "at eight not on thursday morning Arthur didn't feel very good"
goldenSentence = "eight thursday morning Arthur n't feel good"
language = 'english'
stopwords = load_stopwords('etc/stopwords_en.txt')
tokens = tokenize(sentence)
newTokens = []
for token in tokens:
newTokens.append(stopwording(token) )
self.assertEqual(sentenize(newTokens), goldenSentence)
def test_sentenize(self):
sentence = "Hello I'm very happy 1313"
goldenSentence = "Hello I 'm very happy 1313"
tokens = tokenize(sentence)
self.assertEqual(sentenize(tokens), goldenSentence)
def test_tokenize(self):
sentence = "Hello didn't very happy 1313"
goldenTokens = ["Hello", "did", "n't", "very", "happy", "1313"]
tokens = tokenize(sentence)
for i in range(0, len(tokens)):
self.assertEqual(tokens[i][0], goldenTokens[i])