def test_complex_stim_from_text():
textfile = join(get_test_data_path(), 'text', 'scandal.txt')
text = open(textfile).read().strip()
stim = ComplexTextStim.from_text(text)
target = ['To', 'Sherlock', 'Holmes']
assert [w.text for w in stim.elements[:3]] == target
assert len(stim.elements) == 231
stim = ComplexTextStim.from_text(text, unit='sent')
# Custom tokenizer
stim = ComplexTextStim.from_text(text, tokenizer='(\w+)')
assert len(stim.elements) == 209
def test_complex_stim_from_text(self):
textfile = join(_get_test_data_path(), 'text', 'scandal.txt')
text = open(textfile).read().strip()
stim = ComplexTextStim.from_text(text)
target = ['To', 'Sherlock', 'Holmes']
self.assertEquals([w.text for w in stim.elements[:3]], target)
self.assertEquals(len(stim.elements), 231)
stim = ComplexTextStim.from_text(text, unit='sent')
# Custom tokenizer
stim = ComplexTextStim.from_text(text, tokenizer='(\w+)')
self.assertEquals(len(stim.elements), 209)
def test_complex_stim_from_text():
textfile = join(_get_test_data_path(), 'text', 'scandal.txt')
text = open(textfile).read().strip()
stim = ComplexTextStim.from_text(text)
target = ['To', 'Sherlock', 'Holmes']
assert [w.text for w in stim.elements[:3]] == target
assert len(stim.elements) == 231
stim = ComplexTextStim.from_text(text, unit='sent')
# Custom tokenizer
stim = ComplexTextStim.from_text(text, tokenizer='(\w+)')
assert len(stim.elements) == 209
def test_complex_stim_from_text(self):
textfile = join(_get_test_data_path(), 'text', 'scandal.txt')
text = open(textfile).read().strip()
stim = ComplexTextStim.from_text(text)
target = ['To', 'Sherlock', 'Holmes']
self.assertEquals([w.text for w in stim.elements[:3]], target)
self.assertEquals(len(stim.elements), 231)
stim = ComplexTextStim.from_text(text, unit='sent')
# Custom tokenizer
stim = ComplexTextStim.from_text(text, tokenizer='(\w+)')
self.assertEquals(len(stim.elements), 209)
def test_predefined_dictionary_extractor():
text = """enormous chunks of ice that have been frozen for thousands of
years are breaking apart and melting away"""
stim = ComplexTextStim.from_text(text)
td = PredefinedDictionaryExtractor(['aoa/Freq_pm', 'affect/V.Mean.Sum'])
timeline = stim.extract([td])
df = TimelineExporter.timeline_to_df(timeline)
assert df.shape == (36, 4)
valid_rows = df.query('name == "affect_V.Mean.Sum"').dropna()
assert len(valid_rows) == 3
def _convert(self, audio):
import speech_recognition as sr
with sr.AudioFile(audio.filename) as source:
clip = self.recognizer.record(source)
text = getattr(self.recognizer, self.recognize_method)(clip, self.api_key)
return ComplexTextStim.from_text(text=text)
