def test_againstLIBROSA_beethoven(self):
my_val = extractor.rms(beet, win_length=n_fft / sr, decomposition=True)
lib_val = librosa.feature.rmse(y=beet,
n_fft=n_fft,
hop_length=n_fft / 2)
corr = calculateZcorr(my_val, retrieveLibrosaValue(lib_val))
assert corr >= 0.95 # assert 95% correlation b/w zscores
def test_againstMIR_testalt(self):
val = extractor.rms(test_alt, decomposition=False)
npt.assert_almost_equal(
val,
0.61381,
decimal=4,
err_msg='Returned value not within 4 decimal places of MIR output')
def test_againstMIR_beethoven(self):
val = extractor.rms(beet, decomposition=False)
npt.assert_almost_equal(
val,
0.073394,
decimal=4,
err_msg='Returned value not within 4 decimal places of MIR output')
def rms(self, use_librosa=False, decomposition=True, hop_length=None,
n_fft=None):
"""
Get the root mean square (RMS) energy feature.
:parameters:
- use_librosa : boolean. Whether to use librosa or extractor
feature extraction function. Default False.
- decomposition : boolean. Whether to look at a time-series or
an overall root mean square analysis of the piece.
- win_length : float. Window length for the frames in the
time series analysis. [seconds]. Default is 0.05 s.
- hop_length : float. Hop length (i.e. overlap) between the
frames in the time series analysis [samples].
Default is half-overlap.
- n_fft : integer. The window length [samples].
Default 2048 [samples].
"""
if n_fft is None:
n_fft = self.n_fft
if hop_length is None:
hop_length = int(n_fft / 2)
if use_librosa:
tmp = librosa.feature.rmse(self.audio, n_fft=n_fft,
hop_length=hop_length)
self.insertFeature(tmp, 'RMS', hop_length, full=False)
self.insertExtractionParameters('RMS',
dict(n_fft=n_fft, librosa=use_librosa,
hop_length=hop_length, decomposition=True))
else:
tmp = extractor.rms(self.audio, sr=self.sr, n_fft=n_fft, hop_length=hop_length,
pad=self.pad, decomposition=decomposition)
self.insertFeature(tmp, 'RMS', hop_length, full=not decomposition)
self.insertExtractionParameters('RMS',
dict(n_fft=n_fft, hop_length=hop_length,
pad=self.pad, decomposition=decomposition,
librosa=use_librosa))
return tmp
def test_simple_array(self):
val = extractor.rms(np.array([1, 2, 3, 4, 5]), decomposition=False)
npt.assert_equal(val, 3.3166247903554)
def test_ones(self):
npt.assert_equal(extractor.rms(np.ones(100), decomposition=False), 1)