def test_none(self):
self.assertTrue(check.arguments_not_none(("A", "B")))
self.assertTrue(check.arguments_not_none(("A", None), num_none=1))
with self.assertRaises(ValueError):
self.assertTrue(check.arguments_not_none((None, None, "A")))
with self.assertRaises(ValueError):
self.assertTrue(
check.arguments_not_none((None, None, "A"), num_none=0))
def get_sample_index(self,
meta_data=None,
sample_ratio=None,
sample_size=None,
min_size=default.DEFAULT_MINIMUM_SAMPLE_SIZE,
stratified_sampling=None):
"""
Produce an integer index to sample data using .iloc. If the self.stratified_sampling flag is True, sample
separately from each group, as defined by the self.stratified_batch_lookup column.
:param meta_data: pd.DataFrame [N x ?]
Data frame to sample from. Use self.meta_data if this is not set.
:param sample_ratio: float
Sample expression_matrix to this proportion of data points
:param sample_size: int
Sample expression matrix to this absolute number of data points. If sampling from each stratified group,
this is the absolute number of data points PER GROUP (not total)
:return new_size, new_idx: int, np.ndarray
Return the total number of
"""
# Sanity check inputs
assert check.arguments_not_none((sample_ratio, sample_size),
num_none=1)
assert check.argument_numeric(sample_ratio, low=0, allow_none=True)
assert check.argument_numeric(sample_size, low=0, allow_none=True)
stratified_sampling = stratified_sampling if stratified_sampling is not None else self.stratified_sampling
if stratified_sampling:
# Use the main meta_data if there's nothing given
meta_data = meta_data if meta_data is not None else self.meta_data
# Copy and reindex the meta_data so that the index can be used with iloc
meta_data = meta_data.copy()
meta_data.index = pd.Index(range(meta_data.shape[0]))
new_idx = np.ndarray(0, dtype=int)
# For each factor in the batch column
for batch in meta_data[
self.stratified_batch_lookup].unique().tolist():
# Get the integer index of the data points in this batch
batch_idx = meta_data.loc[
meta_data[self.stratified_batch_lookup] ==
batch, :].index.tolist()
# Decide how many to collect from this batch
size = sample_size if sample_ratio is None else max(
int(len(batch_idx) * sample_ratio), min_size)
# Resample and append the new sample index to the index array
new_idx = np.append(
new_idx,
np.random.choice(batch_idx,
size=size,
replace=self.sample_with_replacement))
return new_idx
else:
# Decide how many to collect from the total expression matrix or the meta_data
num_samples = self.expression_matrix.shape[
1] if meta_data is None else meta_data.shape[0]
size = sample_size if sample_ratio is None else max(
int(sample_ratio * num_samples), min_size)
return np.random.choice(num_samples,
size=size,
replace=self.sample_with_replacement)