def hash_from_ndarray(data):
"""Return a hash from an ndarray
It takes care of the data, shapes, strides and dtype.
"""
# We need to hash the shapes and strides as hash_from_code only hashes
# the data buffer. Otherwise, this will cause problem with shapes like:
# (1, 0) and (2, 0) and problem with inplace transpose.
# We also need to add the dtype to make the distinction between
# uint32 and int32 of zeros with the same shape and strides.
# python hash are not strong, so I always use md5 in order not to have a
# too long hash, I call it again on the concatenation of all parts.
if not data.flags["C_CONTIGUOUS"]:
# Version 1.7.1 and previous of NumPy allowed calling
# hash_from_code on an F-contiguous array, but more recent
# versions need a C-contiguous one.
data = numpy.ascontiguousarray(data)
return hash_from_code(
hash_from_code(data)
+ hash_from_code(str(data.shape))
+ hash_from_code(str(data.strides))
+ hash_from_code(str(data.dtype))
)
def hash_from_ndarray(data):
"""
Return a hash from an ndarray.
It takes care of the data, shapes, strides and dtype.
"""
# We need to hash the shapes and strides as hash_from_code only hashes
# the data buffer. Otherwise, this will cause problem with shapes like:
# (1, 0) and (2, 0) and problem with inplace transpose.
# We also need to add the dtype to make the distinction between
# uint32 and int32 of zeros with the same shape and strides.
# python hash are not strong, so I always use md5 in order not to have a
# too long hash, I call it again on the concatenation of all parts.
if not data.flags["C_CONTIGUOUS"]:
# hash_from_code needs a C-contiguous array.
data = np.ascontiguousarray(data)
return hash_from_code(
hash_from_code(data) + hash_from_code(str(data.shape)) +
hash_from_code(str(data.strides)) + hash_from_code(str(data.dtype)))
def hash_from_ndarray(data):
"""
Return a hash from an ndarray.
It takes care of the data, shapes, strides and dtype.
"""
# We need to hash the shapes and strides as hash_from_code only hashes
# the data buffer. Otherwise, this will cause problem with shapes like:
# (1, 0) and (2, 0) and problem with inplace transpose.
# We also need to add the dtype to make the distinction between
# uint32 and int32 of zeros with the same shape and strides.
# python hash are not strong, so use sha256 (md5 is not
# FIPS compatible). To not have too long of hash, I call it again on
# the concatenation of all parts.
if not data.flags["C_CONTIGUOUS"]:
# hash_from_code needs a C-contiguous array.
data = np.ascontiguousarray(data)
return hash_from_code(hash_from_code(data) +
hash_from_code(str(data.shape)) +
hash_from_code(str(data.strides)) +
hash_from_code(str(data.dtype)))
def hash_from_sparse(data):
# We need to hash the shapes as hash_from_code only hashes
# the data buffer. Otherwise, this will cause problem with shapes like:
# (1, 0) and (2, 0)
# We also need to add the dtype to make the distinction between
# uint32 and int32 of zeros with the same shape.
# Python hash is not strong, so use sha256 instead. To avoid having a too
# long hash, I call it again on the contatenation of all parts.
return hash_from_code(
hash_from_code(data.data) + hash_from_code(data.indices) +
hash_from_code(data.indptr) + hash_from_code(str(data.shape)) +
hash_from_code(str(data.dtype)) + hash_from_code(data.format))
def hash_from_sparse(data):
# We need to hash the shapes as hash_from_code only hashes
# the data buffer. Otherwise, this will cause problem with shapes like:
# (1, 0) and (2, 0)
# We also need to add the dtype to make the distinction between
# uint32 and int32 of zeros with the same shape.
# Python hash is not strong, so I always use md5. To avoid having a too
# long hash, I call it again on the contatenation of all parts.
return hash_from_code(hash_from_code(data.data) +
hash_from_code(data.indices) +
hash_from_code(data.indptr) +
hash_from_code(str(data.shape)) +
hash_from_code(str(data.dtype)) +
hash_from_code(data.format))