def test_text_extractor():
stim = ComplexTextStim(join(TEXT_DIR, 'sample_text.txt'),
columns='to', default_duration=1)
td = DictionaryExtractor(join(TEXT_DIR, 'test_lexical_dictionary.txt'),
variables=['length', 'frequency'])
assert td.data.shape == (7, 2)
result = td.transform(stim)[2].to_df()
assert result['duration'][0] == 1
assert result.shape == (1, 6)
assert np.isclose(result['frequency'][0], 11.729, 1e-5)
def test_text_extractor():
stim = ComplexTextStim(join(TEXT_DIR, 'sample_text.txt'),
columns='to', default_duration=1)
td = DictionaryExtractor(join(TEXT_DIR, 'test_lexical_dictionary.txt'),
variables=['length', 'frequency'])
assert td.data.shape == (7, 2)
result = td.transform(stim)[2].to_df()
assert result['duration'][0] == 1
assert result.shape == (1, 6)
assert np.isclose(result['frequency'][0], 11.729, 1e-5)
def test_dictionary_extractor():
td = DictionaryExtractor(join(TEXT_DIR, 'test_lexical_dictionary.txt'),
variables=['length', 'frequency'])
assert td.data.shape == (7, 2)
stim = TextStim(text='annotation')
result = td.transform(stim).to_df()
assert np.isnan(result['onset'][0])
assert 'length' in result.columns
assert result['length'][0] == 10
stim2 = TextStim(text='some')
result = td.transform(stim2).to_df()
assert np.isnan(result['onset'][0])
assert 'frequency' in result.columns
assert np.isnan(result['frequency'][0])
def test_dictionary_extractor():
td = DictionaryExtractor(join(TEXT_DIR, 'test_lexical_dictionary.txt'),
variables=['length', 'frequency'])
assert td.data.shape == (7, 2)
stim = TextStim(text='annotation')
result = td.transform(stim).to_df()
assert np.isnan(result['onset'][0])
assert 'length' in result.columns
assert result['length'][0] == 10
stim2 = TextStim(text='some')
result = td.transform(stim2).to_df()
assert np.isnan(result['onset'][0])
assert 'frequency' in result.columns
assert np.isnan(result['frequency'][0])