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)
timeline = td.extract(stim)
result = timeline[2].to_df()
assert np.isnan(result.iloc[0, 1])
assert result.shape == (1, 4)
assert np.isclose(result['frequency'][0], 11.729, 1e-5)
def test_check_target_type():
audio_dir = join(_get_test_data_path(), 'audio')
stim = AudioStim(join(audio_dir, 'barber.wav'))
td = DictionaryExtractor(join(TEXT_DIR, 'test_lexical_dictionary.txt'),
variables=['length', 'frequency'])
with pytest.raises(TypeError):
stim.extract([td])
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.extract(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.extract(stim2).to_df()
assert np.isnan(result['onset'][0])
assert 'frequency' in result.columns
assert np.isnan(result['frequency'][0])
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)
timeline = stim.extract([td])
df = timeline.to_df()
assert np.isnan(df.iloc[0, 3])
assert df.shape == (12, 4)
target = df.query('name=="frequency" & onset==5')['value'].values
assert target == 10.6