def test_get_window(self):
filename_data, filename_labels = get_labeled_txt()
df = AudioDataFile().load(filename_data, formatter=AIFFormatter())
df.load_labels(filename_labels,
labels_formatter=TXTLabelsFormatter(),
label="whale")
st1 = df.data.index[0]
en1 = df.data.index[5]
st2 = df.metadata["labels"][0][0]
en2 = st2 + 4
df.add_window(st1, en1) # Length 6
df.add_window(st2, en2) # Length 4
wdf = df.get_windows_data_frame()
assert len(wdf) == 2
w1, l1 = df.get_window(0)
w2, l2 = df.get_window(1)
assert len(w1) == 6
assert len(w2) == 4
# Out of range index
assert df.get_window(100) is None
# Other label treatments
df.parameters["labels_treatment"] = "mode"
df.get_window(0)
df.parameters["labels_treatment"] = "mean"
_, l1mn = df.get_window(0)
assert type(l1mn) is float
with pytest.raises(ValueError):
df.parameters["labels_treatment"] = "fourier"
# There is actually no labels treatment called fourier
df.get_window(0) # Raises value error
def test_add_windows(self):
filename_data, filename_labels = get_labeled_txt()
df = AudioDataFile().load(filename_data, formatter=AIFFormatter())
df.load_labels(filename_labels,
labels_formatter=TXTLabelsFormatter(),
label="whale")
st1 = df.data.index[0]
en1 = df.data.index[5]
st2 = df.metadata["labels"][0][0]
en2 = st2 + 4
# No windows added yet
assert df.parameters["number_of_windows"] == 0
d = df.get_window(0)
assert all(d == df.data)
# Add windows
# First an incorrect one
with pytest.raises(AttributeError):
df.add_window(st1 + 100, en1 - 1)
df.add_window(st1, en1) # Length 6
df.add_window(st2, en2) # Length 4
assert df.parameters["number_of_windows"] == 2
assert str(df) == "AudioDataFile (2 windows)"
def test_segments_repr(self):
filename_data, filename_labels = get_labeled_txt()
df = AudioDataFile().load(filename_data, formatter=AIFFormatter())
df.load_labels(filename_labels,
labels_formatter=TXTLabelsFormatter(),
label="whale")
# Make 5 windows
st = df.start_time
step = df.duration / 5
out = AudioSegments()
assert str(out) == "AudioSegments"
for i in range(5):
df.add_window(st + i * step, st + (i + 1) * step)
out.add_segment(*df.get_window(i))
assert str(out) == "AudioSegments (5 segments)"
def load_feature_datafile(self):
filename_data, filename_labels = get_labeled_txt()
df = AudioDataFile().load(filename_data, formatter=AIFFormatter())
df.load_labels(filename_labels,
labels_formatter=TXTLabelsFormatter(),
label="whale")
# Make 5 windows
st = df.start_time
step = df.duration / 5
out = AudioSegments()
for i in range(5):
df.add_window(st + i * step, st + (i + 1) * step)
out.add_segment(*df.get_window(i))
df = out
# Get features
f1 = Energy()
f1.parameters["data"] = df
f2 = Kurtosis()
f2.parameters["data"] = df
f1 = f1.transform()
f2 = f2.transform()
return FeatureDataFile().concatenate([f1, f2])