def test_main(self):
lexicon_df = pd.DataFrame({'activation': {'a': 1.3846,
'abandon': 2.375,
'abandoned': 2.1,
'abandonment': 2.0,
'abated': 1.3333},
'imagery': {'a': 1.0,
'abandon': 2.4,
'abandoned': 3.0,
'abandonment': 1.4,
'abated': 1.2},
'pleasantness': {'a': 2.0,
'abandon': 1.0,
'abandoned': 1.1429,
'abandonment': 1.0,
'abated': 1.6667}})
with self.assertRaises(AssertionError):
FeatsFromScoredLexicon(3)
feats_from_scored_lexicon = FeatsFromScoredLexicon(lexicon_df)
self.assertEqual(set(feats_from_scored_lexicon.get_top_model_term_lists().keys()),
set(['activation', 'imagery', 'pleasantness']))
features = feats_from_scored_lexicon.get_doc_metadata(whitespace_nlp_with_sentences('I abandoned a wallet.'))
np.testing.assert_almost_equal(features[['activation', 'imagery', 'pleasantness']],
np.array([1.74230, 2.00000, 1.57145]))
def test_get_feats(self):
doc = whitespace_nlp_with_sentences("A a bb cc.")
term_freq = UseFullDocAsFeature().get_feats(doc)
self.assertEqual(Counter({"A a bb cc.": 1}), term_freq)
data = [
{'text': "I don't think you'll want to.", 'category': 'a'},
{'text': "You'll have a didn't a-b #dfs .", 'category': 'a'},
{'text': "You'll shoudn't #have a, didn't a-b #dfs .", 'category': 'a'},
{'text': "Can't not get along to didn't.", 'category': 'b'},
{'text': "Can't try aba-ba alo33ng to didn't.", 'category': 'b'},
{'text': "Can't no't g'e't al33ong 3to5.", 'category': 'b'},
{'text': "You haven't changed a b'it.", 'category': 'c'},
{'text': "You haven't changed a b'it.", 'category': 'c'},
{'text': "You haven't ch5ng3d a bit.", 'category': 'c'}
]
df = pd.DataFrame(data)
df['parse'] = df.text.apply(lambda x: st.whitespace_nlp_with_sentences(x, tok_splitter_re=re.compile('( )')))
corpus = st.CorpusFromParsedDocuments(df, parsed_col='parse', category_col='category').build().get_unigram_corpus()
semiotic_square = st.SemioticSquare(
corpus,
category_a='a',
category_b='b',
neutral_categories=['c'],
scorer=st.RankDifference(),
labels={'not_a_and_not_b': 'Plot Descriptions',
'a_and_b': 'Reviews',
'a_and_not_b': 'Positive',
'b_and_not_a': 'Negative',
'a':'',
'b':'',
'not_a':'',