269 lines
7.2 KiB
Cython
269 lines
7.2 KiB
Cython
from libc.math cimport sqrt, exp
|
|
|
|
from ..utils._typedefs cimport float64_t, float32_t, int32_t, intp_t
|
|
|
|
cdef class DistanceMetric:
|
|
pass
|
|
|
|
######################################################################
|
|
# Inline distance functions
|
|
#
|
|
# We use these for the default (euclidean) case so that they can be
|
|
# inlined. This leads to faster computation for the most common case
|
|
cdef inline float64_t euclidean_dist64(
|
|
const float64_t* x1,
|
|
const float64_t* x2,
|
|
intp_t size,
|
|
) except -1 nogil:
|
|
cdef float64_t tmp, d=0
|
|
cdef intp_t j
|
|
for j in range(size):
|
|
tmp = <float64_t> (x1[j] - x2[j])
|
|
d += tmp * tmp
|
|
return sqrt(d)
|
|
|
|
|
|
cdef inline float64_t euclidean_rdist64(
|
|
const float64_t* x1,
|
|
const float64_t* x2,
|
|
intp_t size,
|
|
) except -1 nogil:
|
|
cdef float64_t tmp, d=0
|
|
cdef intp_t j
|
|
for j in range(size):
|
|
tmp = <float64_t>(x1[j] - x2[j])
|
|
d += tmp * tmp
|
|
return d
|
|
|
|
|
|
cdef inline float64_t euclidean_dist_to_rdist64(const float64_t dist) except -1 nogil:
|
|
return dist * dist
|
|
|
|
|
|
cdef inline float64_t euclidean_rdist_to_dist64(const float64_t dist) except -1 nogil:
|
|
return sqrt(dist)
|
|
|
|
|
|
######################################################################
|
|
# DistanceMetric64 base class
|
|
cdef class DistanceMetric64(DistanceMetric):
|
|
# The following attributes are required for a few of the subclasses.
|
|
# we must define them here so that cython's limited polymorphism will work.
|
|
# Because we don't expect to instantiate a lot of these objects, the
|
|
# extra memory overhead of this setup should not be an issue.
|
|
cdef float64_t p
|
|
cdef const float64_t[::1] vec
|
|
cdef const float64_t[:, ::1] mat
|
|
cdef intp_t size
|
|
cdef object func
|
|
cdef object kwargs
|
|
|
|
cdef float64_t dist(
|
|
self,
|
|
const float64_t* x1,
|
|
const float64_t* x2,
|
|
intp_t size,
|
|
) except -1 nogil
|
|
|
|
cdef float64_t rdist(
|
|
self,
|
|
const float64_t* x1,
|
|
const float64_t* x2,
|
|
intp_t size,
|
|
) except -1 nogil
|
|
|
|
cdef float64_t dist_csr(
|
|
self,
|
|
const float64_t* x1_data,
|
|
const int32_t* x1_indices,
|
|
const float64_t* x2_data,
|
|
const int32_t* x2_indices,
|
|
const int32_t x1_start,
|
|
const int32_t x1_end,
|
|
const int32_t x2_start,
|
|
const int32_t x2_end,
|
|
const intp_t size,
|
|
) except -1 nogil
|
|
|
|
cdef float64_t rdist_csr(
|
|
self,
|
|
const float64_t* x1_data,
|
|
const int32_t* x1_indices,
|
|
const float64_t* x2_data,
|
|
const int32_t* x2_indices,
|
|
const int32_t x1_start,
|
|
const int32_t x1_end,
|
|
const int32_t x2_start,
|
|
const int32_t x2_end,
|
|
const intp_t size,
|
|
) except -1 nogil
|
|
|
|
cdef int pdist(
|
|
self,
|
|
const float64_t[:, ::1] X,
|
|
float64_t[:, ::1] D,
|
|
) except -1
|
|
|
|
cdef int cdist(
|
|
self,
|
|
const float64_t[:, ::1] X,
|
|
const float64_t[:, ::1] Y,
|
|
float64_t[:, ::1] D,
|
|
) except -1
|
|
|
|
cdef int pdist_csr(
|
|
self,
|
|
const float64_t* x1_data,
|
|
const int32_t[::1] x1_indices,
|
|
const int32_t[::1] x1_indptr,
|
|
const intp_t size,
|
|
float64_t[:, ::1] D,
|
|
) except -1 nogil
|
|
|
|
cdef int cdist_csr(
|
|
self,
|
|
const float64_t* x1_data,
|
|
const int32_t[::1] x1_indices,
|
|
const int32_t[::1] x1_indptr,
|
|
const float64_t* x2_data,
|
|
const int32_t[::1] x2_indices,
|
|
const int32_t[::1] x2_indptr,
|
|
const intp_t size,
|
|
float64_t[:, ::1] D,
|
|
) except -1 nogil
|
|
|
|
cdef float64_t _rdist_to_dist(self, float64_t rdist) except -1 nogil
|
|
|
|
cdef float64_t _dist_to_rdist(self, float64_t dist) except -1 nogil
|
|
|
|
######################################################################
|
|
# Inline distance functions
|
|
#
|
|
# We use these for the default (euclidean) case so that they can be
|
|
# inlined. This leads to faster computation for the most common case
|
|
cdef inline float64_t euclidean_dist32(
|
|
const float32_t* x1,
|
|
const float32_t* x2,
|
|
intp_t size,
|
|
) except -1 nogil:
|
|
cdef float64_t tmp, d=0
|
|
cdef intp_t j
|
|
for j in range(size):
|
|
tmp = <float64_t> (x1[j] - x2[j])
|
|
d += tmp * tmp
|
|
return sqrt(d)
|
|
|
|
|
|
cdef inline float64_t euclidean_rdist32(
|
|
const float32_t* x1,
|
|
const float32_t* x2,
|
|
intp_t size,
|
|
) except -1 nogil:
|
|
cdef float64_t tmp, d=0
|
|
cdef intp_t j
|
|
for j in range(size):
|
|
tmp = <float64_t>(x1[j] - x2[j])
|
|
d += tmp * tmp
|
|
return d
|
|
|
|
|
|
cdef inline float64_t euclidean_dist_to_rdist32(const float32_t dist) except -1 nogil:
|
|
return dist * dist
|
|
|
|
|
|
cdef inline float64_t euclidean_rdist_to_dist32(const float32_t dist) except -1 nogil:
|
|
return sqrt(dist)
|
|
|
|
|
|
######################################################################
|
|
# DistanceMetric32 base class
|
|
cdef class DistanceMetric32(DistanceMetric):
|
|
# The following attributes are required for a few of the subclasses.
|
|
# we must define them here so that cython's limited polymorphism will work.
|
|
# Because we don't expect to instantiate a lot of these objects, the
|
|
# extra memory overhead of this setup should not be an issue.
|
|
cdef float64_t p
|
|
cdef const float64_t[::1] vec
|
|
cdef const float64_t[:, ::1] mat
|
|
cdef intp_t size
|
|
cdef object func
|
|
cdef object kwargs
|
|
|
|
cdef float32_t dist(
|
|
self,
|
|
const float32_t* x1,
|
|
const float32_t* x2,
|
|
intp_t size,
|
|
) except -1 nogil
|
|
|
|
cdef float32_t rdist(
|
|
self,
|
|
const float32_t* x1,
|
|
const float32_t* x2,
|
|
intp_t size,
|
|
) except -1 nogil
|
|
|
|
cdef float32_t dist_csr(
|
|
self,
|
|
const float32_t* x1_data,
|
|
const int32_t* x1_indices,
|
|
const float32_t* x2_data,
|
|
const int32_t* x2_indices,
|
|
const int32_t x1_start,
|
|
const int32_t x1_end,
|
|
const int32_t x2_start,
|
|
const int32_t x2_end,
|
|
const intp_t size,
|
|
) except -1 nogil
|
|
|
|
cdef float32_t rdist_csr(
|
|
self,
|
|
const float32_t* x1_data,
|
|
const int32_t* x1_indices,
|
|
const float32_t* x2_data,
|
|
const int32_t* x2_indices,
|
|
const int32_t x1_start,
|
|
const int32_t x1_end,
|
|
const int32_t x2_start,
|
|
const int32_t x2_end,
|
|
const intp_t size,
|
|
) except -1 nogil
|
|
|
|
cdef int pdist(
|
|
self,
|
|
const float32_t[:, ::1] X,
|
|
float32_t[:, ::1] D,
|
|
) except -1
|
|
|
|
cdef int cdist(
|
|
self,
|
|
const float32_t[:, ::1] X,
|
|
const float32_t[:, ::1] Y,
|
|
float32_t[:, ::1] D,
|
|
) except -1
|
|
|
|
cdef int pdist_csr(
|
|
self,
|
|
const float32_t* x1_data,
|
|
const int32_t[::1] x1_indices,
|
|
const int32_t[::1] x1_indptr,
|
|
const intp_t size,
|
|
float32_t[:, ::1] D,
|
|
) except -1 nogil
|
|
|
|
cdef int cdist_csr(
|
|
self,
|
|
const float32_t* x1_data,
|
|
const int32_t[::1] x1_indices,
|
|
const int32_t[::1] x1_indptr,
|
|
const float32_t* x2_data,
|
|
const int32_t[::1] x2_indices,
|
|
const int32_t[::1] x2_indptr,
|
|
const intp_t size,
|
|
float32_t[:, ::1] D,
|
|
) except -1 nogil
|
|
|
|
cdef float32_t _rdist_to_dist(self, float32_t rdist) except -1 nogil
|
|
|
|
cdef float32_t _dist_to_rdist(self, float32_t dist) except -1 nogil
|