def test_transform():
# minmax
X1 = np.random.randn(100, 32, 128)
scaler = Scaler(normalizer="minmax")
scaler.fit(X1)
X1_scaled = scaler.transform(X1)
assert np.amin(X1_scaled) == -1.0
assert np.amax(X1_scaled) == 1.0
# standard
X2 = np.random.randn(100, 32, 128)
scaler = Scaler(normalizer="standard")
scaler.fit(X2)
X2_scaled = scaler.transform(X2)
X2_scaled_flat = np.reshape(X2_scaled, (-1, X2.shape[-1]))
assert X2_scaled_flat.shape[1] == X2.shape[-1]
mean = np.mean(X2_scaled_flat, axis=0)
std = np.std(X2_scaled_flat, axis=0)
assert np.allclose(mean, np.zeros(128), rtol=0.001, atol=0.001)
assert np.allclose(std, np.ones(128), rtol=0.001, atol=0.001)
# list of scalers
scaler = Scaler(normalizer=["minmax", "standard"])
X_list = [X1, X2]
scaler.fit(X_list)
X_list_scaled = scaler.transform(X_list)
assert type(X_list_scaled) is list
assert len(X_list_scaled) == 2
assert np.allclose(X_list_scaled[0], X1_scaled, rtol=0.001, atol=0.001)
assert np.allclose(X_list_scaled[1], X2_scaled, rtol=0.001, atol=0.001)
# DataGenerator
feature_extractor = MelSpectrogram()
feature_extractor.extract(dataset)
data_generator = DataGenerator(dataset, feature_extractor, folds=["all"])
scaler = Scaler(normalizer="minmax")
scaler.fit(data_generator)
data_generator.set_scaler(scaler)
X, _ = data_generator.get_data()
assert np.amin(X) == -1.0
assert np.amax(X) == 1.0
def test_mel_spectrogram():
feature_extractor = MelSpectrogram(pad_mode="constant")
shape = feature_extractor.get_shape(2.0)
assert shape == (3, 32, 64)
feature_extractor = MelSpectrogram(sequence_time=-1, pad_mode="constant")
shape = feature_extractor.get_shape(2.0)
assert shape == (1, 64, 64)
feature_extractor = MelSpectrogram(sequence_time=1.0,
sequence_hop_time=-1,
pad_mode="constant")
shape = feature_extractor.get_shape(2.0)
assert shape == (1, 32, 64)
def test_fit():
# Array, expect same results than partial_fit
X = np.random.randn(100, 32, 128)
scaler = Scaler(normalizer="minmax")
scaler.fit(X)
assert type(scaler.scaler) is list
assert len(scaler.scaler) == 1
assert scaler.scaler[0][0] == np.amin(X)
assert scaler.scaler[0][1] == np.amax(X)
# DataGenerator
feature_extractor = MelSpectrogram()
feature_extractor.extract(dataset)
data_generator = DataGenerator(dataset, feature_extractor, folds=["all"])
scaler = Scaler(normalizer="minmax")
scaler.fit(data_generator)
X, _ = data_generator.get_data()
assert type(scaler.scaler) is list
assert len(scaler.scaler) == 1
assert scaler.scaler[0][0] == np.amin(X)
assert scaler.scaler[0][1] == np.amax(X)
"""
self.file_lists['all'] = sorted(
glob.glob(os.path.join(self.audio_path, '*.wav')))
print(self.file_lists['all'])
def get_annotations(self, file_path, features, time_resolution):
y = np.zeros((len(features), len(self.label_list)))
class_ix = int(os.path.basename(file_path).split('-')[1])
y[:, class_ix] = 1
return y
dataset_path = './tests/data'
dataset = TestDataset(dataset_path)
feature_extractor = MelSpectrogram()
audio_files = ['147764-4-7-0.wav', '176787-5-0-0.wav', '40722-8-0-7.wav']
features_files = ['147764-4-7-0.npy', '176787-5-0-0.npy', '40722-8-0-7.npy']
classes = [4, 5, 8]
feature_extractor.extract(dataset)
features_path = feature_extractor.get_features_path(dataset)
X_gt = []
Y_gt = []
for j, ff in enumerate(features_files):
feat = np.load(os.path.join(features_path, 'original', ff))
X_gt.append(feat)
ann = np.zeros((len(feat), 10))
ann[:, classes[j]] = 1
Y_gt.append(ann)