def _filter_samples_by_index(variations,
sample_cols,
filtered_vars=None,
reverse=False):
if filtered_vars is None:
filtered_vars = VariationsArrays()
samples = variations.samples
try:
dtype = sample_cols.dtype
is_bool = numpy.issubdtype(dtype, numpy.dtype(bool))
except AttributeError:
item = first(iter(sample_cols))
is_bool = isinstance(item, bool)
if not is_bool:
sample_cols = [idx in sample_cols for idx in range(len(samples))]
if 'shape' not in dir(sample_cols):
sample_cols = numpy.array(sample_cols, dtype=numpy.bool)
if reverse:
sample_cols = numpy.logical_not(sample_cols)
for path in variations.keys():
matrix = variations[path]
if is_dataset(matrix):
matrix = matrix[:]
if 'calls' in path:
flt_data = matrix[:, sample_cols]
# flt_data = numpy.compress(sample_cols, , axis=1)
filtered_vars[path] = flt_data
else:
filtered_vars[path] = matrix
filtered_vars.metadata = variations.metadata
kept_samples = [
samples[idx] for idx, keep in enumerate(sample_cols) if keep
]
filtered_vars.samples = kept_samples
return filtered_vars
def _filter_samples_by_index(variations, sample_cols, filtered_vars=None,
reverse=False):
if filtered_vars is None:
filtered_vars = VariationsArrays()
samples = variations.samples
try:
dtype = sample_cols.dtype
is_bool = numpy.issubdtype(dtype, numpy.bool)
except AttributeError:
item = first(iter(sample_cols))
is_bool = isinstance(item, bool)
if not is_bool:
sample_cols = [idx in sample_cols for idx in range(len(samples))]
if 'shape' not in dir(sample_cols):
sample_cols = numpy.array(sample_cols, dtype=numpy.bool)
if reverse:
sample_cols = numpy.logical_not(sample_cols)
for path in variations.keys():
matrix = variations[path]
if is_dataset(matrix):
matrix = matrix[:]
if 'calls' in path:
flt_data = matrix[:, sample_cols]
# flt_data = numpy.compress(sample_cols, , axis=1)
filtered_vars[path] = flt_data
else:
filtered_vars[path] = matrix
filtered_vars.metadata = variations.metadata
kept_samples = [samples[idx] for idx, keep in enumerate(sample_cols)
if keep]
filtered_vars.samples = kept_samples
return filtered_vars
