def test_tonnetz_extractor():
audio = AudioStim(join(AUDIO_DIR, "barber.wav"))
ext = TonnetzExtractor()
df = ext.transform(audio).to_df()
assert df.shape == (4882, 8)
assert np.isclose(df['onset'][1], 0.01161)
assert np.isclose(df['duration'][0], 0.01161)
assert np.isclose(df['tonal_centroid_0'][0], -0.0264436)
def test_tonnetz_extractor():
audio = AudioStim(join(AUDIO_DIR, 'barber.wav'))
ext = TonnetzExtractor()
df = ext.transform(audio).to_df()
assert df.shape == (1221, 10)
assert np.isclose(df['onset'][1], 0.04644)
assert np.isclose(df['duration'][0], 0.04644)
assert np.isclose(df['tonal_centroid_0'][0], -0.0391266)
def test_tonnetz_extractor():
audio = AudioStim(join(AUDIO_DIR, 'barber.wav'))
ext = TonnetzExtractor()
df = ext.transform(audio).to_df()
assert df.shape == (1221, 10)
assert np.isclose(df['onset'][1], 0.04644)
assert np.isclose(df['duration'][0], 0.04644)
tonal_centroid_answers = SemVerDict({
'>=0.6.3,<0.8.0': -0.0391266,
'>=0.8.0': -0.0804008
})
assert np.isclose(df['tonal_centroid_0'][0],
tonal_centroid_answers[LIBROSA_VERSION])