def test_itereate_chunks(self):
mat = numpy.array([[1, 2, 3], [4, 5, 6]])
exp = [[[1, 2, 3]], [[4, 5, 6]]]
res = list(iterate_matrix_chunks(mat, chunk_size=1))
assert numpy.all(res[0] == exp[0])
assert numpy.all(res[1] == exp[1])
exp = [[2], [5]]
res = list(iterate_matrix_chunks(mat, chunk_size=1, sample_idx=1))
assert numpy.all(res[0] == exp[0])
assert numpy.all(res[1] == exp[1])
def test_itereate_chunks(self):
mat = numpy.array([[1, 2, 3], [4, 5, 6]])
exp = [[[1, 2, 3]], [[4, 5, 6]]]
res = list(iterate_matrix_chunks(mat, chunk_size=1))
assert numpy.all(res[0] == exp[0])
assert numpy.all(res[1] == exp[1])
exp = [[2], [5]]
res = list(iterate_matrix_chunks(mat, chunk_size=1, sample_idx=1))
assert numpy.all(res[0] == exp[0])
assert numpy.all(res[1] == exp[1])
def _row_value_counter(mat, value, ratio=False, by_chunk=False):
ndims = len(mat.shape)
if ndims == 1:
raise ValueError('The matrix has to have at least 2 dimensions')
elif ndims == 2:
axes = 1
else:
axes = tuple([i + 1 for i in range(ndims - 1)])
if by_chunk:
chunks = iterate_matrix_chunks(mat)
result = numpy.zeros(mat.shape[0])
start = 0
for chunk in chunks:
chunk_result = _row_value_counter_array(chunk, value, axes)
end = start + chunk_result.shape[0]
result[start:end] = chunk_result
start = end
else:
if is_dataset(mat):
mat = mat[...]
result = _row_value_counter_array(mat, value, axes)
if ratio:
num_items_per_row = reduce(operator.mul, mat.shape[1:], 1)
result = result / num_items_per_row
return result
def _row_value_counter(mat, value, ratio=False, by_chunk=False):
ndims = len(mat.shape)
if ndims == 1:
raise ValueError('The matrix has to have at least 2 dimensions')
elif ndims == 2:
axes = 1
else:
axes = tuple([i + 1 for i in range(ndims - 1)])
if by_chunk:
chunks = iterate_matrix_chunks(mat)
result = numpy.zeros(mat.shape[0])
start = 0
for chunk in chunks:
chunk_result = _row_value_counter_array(chunk, value, axes)
end = start + chunk_result.shape[0]
result[start:end] = chunk_result
start = end
else:
if is_dataset(mat):
mat = mat[...]
result = _row_value_counter_array(mat, value, axes)
if ratio:
num_items_per_row = reduce(operator.mul, mat.shape[1:], 1)
result = result / num_items_per_row
return result
def is_variant(chunks):
gts = _get_chunks_gt(chunks)
is_var = numpy.ndarray(gts.shape[0])
start = 0
for chunk in iterate_matrix_chunks(gts):
stop = start + chunk.shape[0]
is_var[start:stop] = numpy.sum(chunk > 0, axis=(1, 2)) >= 1
start = stop
return is_var
def allele_count(chunks, allele=1):
"""Calculate number of observations of the given allele per variant."""
gts = _get_chunks_gt(chunks)
a_count = numpy.ndarray(gts.shape[0])
start = 0
for chunk in iterate_matrix_chunks(gts):
stop = start + chunk.shape[0]
a_count[start:stop] = numpy.sum(chunk == allele, axis=(1, 2))
start = stop
return a_count
def allele_number(chunks):
"""Count the number of non-missing allele calls per variant."""
gts = _get_chunks_gt(chunks)
allele_num = numpy.ndarray(gts.shape[0])
start = 0
for chunk in iterate_matrix_chunks(gts):
stop = start + chunk.shape[0]
allele_num[start:stop] = numpy.sum(chunk >= 0, axis=(1, 2))
start = stop
return allele_num
def is_doubleton(chunks, allele=1):
"""Find variants with only two instance of `allele` observed."""
gts = _get_chunks_gt(chunks)
start = 0
is_double = numpy.ndarray(gts.shape[0])
for chunk in iterate_matrix_chunks(gts):
stop = start + chunk.shape[0]
is_double[start:stop] = numpy.sum(chunk == allele, axis=(1, 2)) == 2
start = stop
return is_double
