class RemovePunctTest(unittest.TestCase):
def setUp(self):
self.op = RemovePunct()
def test_run(self):
self.op = RemovePunct()
self.test_data = '''He said,"that's it." *u* Hello, World. O'Rourke is rockin'.'''
self.assertEqual(self.op.run(self.test_data), '''He said that s it Hello World O Rourke is rockin''')
def run(self, data):
results = []
data = RemovePunct().run(data)
for corpus in data:
lxa_object = lxa.from_corpus(corpus.contents)
sigs_to_stems = lxa_object.signatures_to_stems()
results.append(self.output_to_results(sigs_to_stems))
return results
def run(self, data):
corpora = []
for corpus in data:
corpus = corpus.contents.splitlines()
corpus = "\n".join(corpus).split('\n\n')
sentences = [Corpus(str(i), "", sentence.strip()) for i, sentence in
enumerate(corpus) if sentence]
corpora += sentences
print('Num corpora = {}'.format(len(corpora)))
corpora = RemovePunct().run(corpora)
return self.execute(corpora)
def get_operation_handler(operation):
if operation == 'lemmatize_wordnet':
return LemmatizerWordNet()
elif operation == 'pos_tag':
return PosTag()
elif operation == 'removecapsgreedy':
return RemoveCapsGreedy()
elif operation == 'removecapsnnp':
return RemoveCapsPreserveNNP()
elif operation == 'removepunct':
return RemovePunct()
elif operation == 'remove_stopwords':
return RemoveStopwords()
elif operation == 'sentence_tokenize':
return SentenceTokenize()
elif operation == 'stem_porter':
return StemmerPorter()
elif operation == 'stem_lancaster':
return StemmerLancaster()
elif operation == 'stem_snowball':
return StemmerSnowball()
elif operation == 'tfidf':
return Tfidf()
elif operation == 'topic_model':
return TopicModel()
elif operation == 'wordcloudop':
return WordCloudOp()
elif operation == 'word_tokenize_treebank':
return WordTokenizeTreebank()
elif operation == 'word_tokenize_whitespace_punct':
return WordTokenizeWhitespacePunct()
elif operation == 'word_tokenize_stanford':
return WordTokenizeStanford()
elif operation == 'word_tokenize_spaces':
return WordTokenizeSpaces()
elif operation == 'word_tokenize_tabs':
return WordTokenizeTabs()
elif operation == 'nlp-pos':
return StanfordCoreNLP(['pos'])
elif operation == 'nlp-ner':
return StanfordCoreNLP(['pos', 'ner'])
elif operation == 'noop':
return NoOp()
else:
raise TransactionException("The requested operation does not exist.")
def get_operation_handler(operation):
if operation == 'lemmatize_wordnet':
return LemmatizerWordNet()
elif operation == 'removecapsgreedy':
return RemoveCapsGreedy()
elif operation == 'removecapsnnp':
return RemoveCapsPreserveNNP()
elif operation == 'removepunct':
return RemovePunct()
elif operation == 'removesilence':
return RemoveSilence()
elif operation == 'remove_stopwords':
return RemoveStopwords()
elif operation == 'sentence_tokenize':
return SentenceTokenize()
elif operation == 'removehashtags':
return RemoveHashtags()
elif operation == 'removequotes':
return RemoveQuotes()
elif operation == 'stem_porter':
return StemmerPorter()
elif operation == 'stop_words':
return RemoveStopwords()
elif operation == 'tfidf':
return Tfidf()
elif operation == 'wordcloudop':
return WordCloudOp()
elif operation == 'word_tokenize_treebank':
return WordTokenizeTreebank()
elif operation == 'word_tokenize_whitespace_punct':
return WordTokenizeWhitespacePunct()
elif operation == 'word_tokenize_stanford':
return WordTokenizeStanford()
elif operation == 'nlp-pos':
return StanfordCoreNLP('pos')
elif operation == 'nlp-ner':
return StanfordCoreNLP('ner')
elif operation == 'nlp-sentiment':
return StanfordCoreNLP('sentiment')
elif operation == 'nlp-coref':
return StanfordCoreNLP('coref')
elif operation == 'nlp-relation':
return StanfordCoreNLP('relation')
elif operation == 'splat-disfluency':
print("YOU GOT SPLATTED")
return SplatDisfluency()
elif operation == 'splat-ngrams':
print("YOU GOT SPLATTED")
return SplatNGrams()
elif operation == 'splat-complexity':
print("YOU GOT SPLATTED")
return SplatComplexity()
elif operation == 'splat-pos':
print("YOU GOT SPLATTED")
return SplatPOSFrequencies()
elif operation == 'splat-syllables':
print("YOU GOT SPLATTED")
return SplatSyllables()
elif operation == 'splat-pronouns':
print("YOU GOT SPLATTED")
return SplatPronouns()
elif operation == 'char-ngrams':
return CharNgrams()
elif operation == 'length-stats':
return LengthStatistics()
elif operation == 'topic-model-10':
return TopicModel(10)
elif operation == 'topic-model-30':
return TopicModel(30)
elif operation == 'word-vector':
return WordVector()
elif operation == 'unsup-morph':
return UnsupervisedMorphology()
elif operation == 'bigram-array':
return BigramArray()
elif operation == 'speech-token-stats':
return SpeechTokenStatistics()
elif operation == 'extract_transcript':
return ExtractTranscript()
elif operation == 'noop':
return NoOp()
else:
raise TransactionException(
f'The requested operation "{operation}" does not exist.')
def setUp(self):
self.op = RemovePunct()
def test_run(self):
self.op = RemovePunct()
self.test_data = '''He said,"that's it." *u* Hello, World. O'Rourke is rockin'.'''
self.assertEqual(self.op.run(self.test_data), '''He said that s it Hello World O Rourke is rockin''')
def get_operation_handler(operation):
if operation == 'lemmatize_wordnet':
return LemmatizerWordNet()
elif operation == 'pos_tag':
return PosTag()
elif operation == 'removecapsgreedy':
return RemoveCapsGreedy()
elif operation == 'removecapsnnp':
return RemoveCapsPreserveNNP()
elif operation == 'removepunct':
return RemovePunct()
elif operation == 'removesilence':
return RemoveSilence()
elif operation == 'remove_stopwords':
return RemoveStopwords()
elif operation == 'sentence_tokenize':
return SentenceTokenize()
elif operation == 'stem_porter':
return StemmerPorter()
elif operation == 'stop_words':
return RemoveStopwords()
elif operation == 'tfidf':
return Tfidf()
elif operation == 'topic_model':
return TopicModel()
elif operation == 'wordcloudop':
return WordCloudOp()
elif operation == 'word_tokenize_treebank':
return WordTokenizeTreebank()
elif operation == 'word_tokenize_whitespace_punct':
return WordTokenizeWhitespacePunct()
elif operation == 'word_tokenize_stanford':
return WordTokenizeStanford()
elif operation == 'word_tokenize_spaces':
return WordTokenizeSpaces()
elif operation == 'word_tokenize_tabs':
return WordTokenizeTabs()
elif operation == 'nlp-pos':
return StanfordCoreNLP(['pos'])
elif operation == 'nlp-ner':
return StanfordCoreNLP(['pos', 'ner'])
elif operation == 'nlp-sentiment':
return StanfordCoreNLP(['parse', 'sentiment'])
elif operation == 'nlp-parse':
return StanfordCoreNLP(['parse'])
elif operation == 'nlp-coref':
return StanfordCoreNLP(['tokenize', 'ssplit', 'coref'])
elif operation == 'nlp-relation':
return StanfordCoreNLP(['parse', 'relation'])
elif operation == 'splat-disfluency':
print("YOU GOT SPLATTED")
return SplatDisfluency()
elif operation == 'splat-ngrams':
print("YOU GOT SPLATTED")
return SplatNGrams()
elif operation == 'splat-complexity':
print("YOU GOT SPLATTED")
return SplatComplexity()
elif operation == 'splat-pos':
print("YOU GOT SPLATTED")
return SplatPOSFrequencies()
elif operation == 'splat-syllables':
print("YOU GOT SPLATTED")
return SplatSyllables()
elif operation == 'splat-pronouns':
print("YOU GOT SPLATTED")
return SplatPronouns()
elif operation == 'noop':
return NoOp()
else:
raise TransactionException("The requested operation does not exist.")