def test_window_size_timedelta(self):
"""window_size accepts Timedelta object."""
# setup
X = self.X
timeseries = self.timeseries
# run
array = cutoff_window_sequences(
X,
timeseries,
window_size=pd.Timedelta(days=3),
)
# assert
expected_array = np.array([[[2, 22], [3, 23], [4, 24]],
[[14, 34], [15, 35], [16, 36]]])
assert_allclose(array, expected_array)
def test_window_size_string(self):
"""window_size accepts string."""
# setup
X = self.X
timeseries = self.timeseries
# run
array = cutoff_window_sequences(
X,
timeseries,
window_size='3d',
)
# assert
expected_array = np.array([[[2, 22], [3, 23], [4, 24]],
[[14, 34], [15, 35], [16, 36]]])
assert_allclose(array, expected_array)
def test_multiple_filter(self):
"""Test X with two identifier columns."""
# setup
X = self.X
X['id2'] = [3, 4]
timeseries = self.timeseries
timeseries['id2'] = [3, 4] * 10
# run
array = cutoff_window_sequences(
X,
timeseries,
window_size=2,
)
# assert
expected_array = np.array([[[1, 21], [3, 23]], [[14, 34], [16, 36]]])
assert_allclose(array, expected_array)
def test_time_index_column(self):
"""Passing time_index. The indicated column will be used as the timeseries index."""
# setup
X = self.X
timeseries = self.timeseries.reset_index()
# run
array = cutoff_window_sequences(
X,
timeseries,
window_size=3,
time_index='timestamp',
)
# assert
expected_array = np.array([[[2, 22], [3, 23], [4, 24]],
[[14, 34], [15, 35], [16, 36]]])
assert_allclose(array, expected_array)
def test_cutoff_time_only(self):
"""Test X without any other column than cutoff_time."""
# setup
X = self.X
del X['id1']
timeseries = self.timeseries
del timeseries['id1']
# run
array = cutoff_window_sequences(
X,
timeseries,
window_size=3,
)
# assert
expected_array = np.array([[[12, 32], [13, 33], [14, 34]],
[[14, 34], [15, 35], [16, 36]]])
assert_allclose(array, expected_array)
def test_not_enough_data(self):
"""If there is not enough data for the given window_size, shape changes."""
# setup
X = self.X
timeseries = self.timeseries
# run
array = cutoff_window_sequences(
X,
timeseries,
window_size=5,
)
# assert
assert len(array) == 2
expected_array = np.array([
np.array([[1, 21], [2, 22], [3, 23], [4, 24]]),
np.array([[12, 32], [13, 33], [14, 34], [15, 35], [16, 36]])
])
assert_allclose(array[0], expected_array[0])
assert_allclose(array[1], expected_array[1])
