mirror of
https://github.com/aykhans/AzSuicideDataVisualization.git
synced 2025-04-22 02:23:48 +00:00
516 lines
15 KiB
Cython
516 lines
15 KiB
Cython
"""
|
|
Template for each `dtype` helper function for hashtable
|
|
|
|
WARNING: DO NOT edit .pxi FILE directly, .pxi is generated from .pxi.in
|
|
"""
|
|
|
|
{{py:
|
|
|
|
# name, dtype, ttype, c_type, to_c_type
|
|
dtypes = [('Complex128', 'complex128', 'complex128',
|
|
'khcomplex128_t', 'to_khcomplex128_t'),
|
|
('Complex64', 'complex64', 'complex64',
|
|
'khcomplex64_t', 'to_khcomplex64_t'),
|
|
('Float64', 'float64', 'float64', 'float64_t', ''),
|
|
('Float32', 'float32', 'float32', 'float32_t', ''),
|
|
('UInt64', 'uint64', 'uint64', 'uint64_t', ''),
|
|
('UInt32', 'uint32', 'uint32', 'uint32_t', ''),
|
|
('UInt16', 'uint16', 'uint16', 'uint16_t', ''),
|
|
('UInt8', 'uint8', 'uint8', 'uint8_t', ''),
|
|
('Object', 'object', 'pymap', 'object', ''),
|
|
('Int64', 'int64', 'int64', 'int64_t', ''),
|
|
('Int32', 'int32', 'int32', 'int32_t', ''),
|
|
('Int16', 'int16', 'int16', 'int16_t', ''),
|
|
('Int8', 'int8', 'int8', 'int8_t', '')]
|
|
|
|
}}
|
|
|
|
{{for name, dtype, ttype, c_type, to_c_type in dtypes}}
|
|
|
|
|
|
@cython.wraparound(False)
|
|
@cython.boundscheck(False)
|
|
{{if dtype == 'object'}}
|
|
cdef value_count_{{dtype}}(ndarray[{{dtype}}] values, bint dropna):
|
|
{{else}}
|
|
cdef value_count_{{dtype}}(const {{dtype}}_t[:] values, bint dropna):
|
|
{{endif}}
|
|
cdef:
|
|
Py_ssize_t i = 0
|
|
Py_ssize_t n = len(values)
|
|
kh_{{ttype}}_t *table
|
|
|
|
# Don't use Py_ssize_t, since table.n_buckets is unsigned
|
|
khiter_t k
|
|
|
|
{{c_type}} val
|
|
|
|
int ret = 0
|
|
|
|
# we track the order in which keys are first seen (GH39009),
|
|
# khash-map isn't insertion-ordered, thus:
|
|
# table maps keys to counts
|
|
# result_keys remembers the original order of keys
|
|
|
|
result_keys = {{name}}Vector()
|
|
table = kh_init_{{ttype}}()
|
|
|
|
{{if dtype == 'object'}}
|
|
kh_resize_{{ttype}}(table, n // 10)
|
|
|
|
for i in range(n):
|
|
val = values[i]
|
|
if not dropna or not checknull(val):
|
|
k = kh_get_{{ttype}}(table, <PyObject*>val)
|
|
if k != table.n_buckets:
|
|
table.vals[k] += 1
|
|
else:
|
|
k = kh_put_{{ttype}}(table, <PyObject*>val, &ret)
|
|
table.vals[k] = 1
|
|
result_keys.append(val)
|
|
{{else}}
|
|
kh_resize_{{ttype}}(table, n)
|
|
|
|
for i in range(n):
|
|
val = {{to_c_type}}(values[i])
|
|
|
|
if not is_nan_{{c_type}}(val) or not dropna:
|
|
k = kh_get_{{ttype}}(table, val)
|
|
if k != table.n_buckets:
|
|
table.vals[k] += 1
|
|
else:
|
|
k = kh_put_{{ttype}}(table, val, &ret)
|
|
table.vals[k] = 1
|
|
result_keys.append(val)
|
|
{{endif}}
|
|
|
|
# collect counts in the order corresponding to result_keys:
|
|
cdef int64_t[:] result_counts = np.empty(table.size, dtype=np.int64)
|
|
for i in range(table.size):
|
|
{{if dtype == 'object'}}
|
|
k = kh_get_{{ttype}}(table, result_keys.data[i])
|
|
{{else}}
|
|
k = kh_get_{{ttype}}(table, result_keys.data.data[i])
|
|
{{endif}}
|
|
result_counts[i] = table.vals[k]
|
|
|
|
kh_destroy_{{ttype}}(table)
|
|
|
|
return result_keys.to_array(), result_counts.base
|
|
|
|
|
|
@cython.wraparound(False)
|
|
@cython.boundscheck(False)
|
|
{{if dtype == 'object'}}
|
|
cdef duplicated_{{dtype}}(ndarray[{{dtype}}] values, object keep='first'):
|
|
{{else}}
|
|
cdef duplicated_{{dtype}}(const {{dtype}}_t[:] values, object keep='first'):
|
|
{{endif}}
|
|
cdef:
|
|
int ret = 0
|
|
{{if dtype != 'object'}}
|
|
{{c_type}} value
|
|
{{endif}}
|
|
Py_ssize_t i, n = len(values)
|
|
khiter_t k
|
|
kh_{{ttype}}_t *table = kh_init_{{ttype}}()
|
|
ndarray[uint8_t, ndim=1, cast=True] out = np.empty(n, dtype='bool')
|
|
|
|
kh_resize_{{ttype}}(table, min(kh_needed_n_buckets(n), SIZE_HINT_LIMIT))
|
|
|
|
if keep not in ('last', 'first', False):
|
|
raise ValueError('keep must be either "first", "last" or False')
|
|
|
|
if keep == 'last':
|
|
{{if dtype == 'object'}}
|
|
for i in range(n - 1, -1, -1):
|
|
# equivalent: range(n)[::-1], which cython doesn't like in nogil
|
|
kh_put_{{ttype}}(table, <PyObject*>values[i], &ret)
|
|
out[i] = ret == 0
|
|
{{else}}
|
|
with nogil:
|
|
for i in range(n - 1, -1, -1):
|
|
# equivalent: range(n)[::-1], which cython doesn't like in nogil
|
|
value = {{to_c_type}}(values[i])
|
|
kh_put_{{ttype}}(table, value, &ret)
|
|
out[i] = ret == 0
|
|
{{endif}}
|
|
elif keep == 'first':
|
|
{{if dtype == 'object'}}
|
|
for i in range(n):
|
|
kh_put_{{ttype}}(table, <PyObject*>values[i], &ret)
|
|
out[i] = ret == 0
|
|
{{else}}
|
|
with nogil:
|
|
for i in range(n):
|
|
value = {{to_c_type}}(values[i])
|
|
kh_put_{{ttype}}(table, value, &ret)
|
|
out[i] = ret == 0
|
|
{{endif}}
|
|
else:
|
|
{{if dtype == 'object'}}
|
|
for i in range(n):
|
|
value = values[i]
|
|
k = kh_get_{{ttype}}(table, <PyObject*>value)
|
|
if k != table.n_buckets:
|
|
out[table.vals[k]] = 1
|
|
out[i] = 1
|
|
else:
|
|
k = kh_put_{{ttype}}(table, <PyObject*>value, &ret)
|
|
table.vals[k] = i
|
|
out[i] = 0
|
|
{{else}}
|
|
with nogil:
|
|
for i in range(n):
|
|
value = {{to_c_type}}(values[i])
|
|
k = kh_get_{{ttype}}(table, value)
|
|
if k != table.n_buckets:
|
|
out[table.vals[k]] = 1
|
|
out[i] = 1
|
|
else:
|
|
k = kh_put_{{ttype}}(table, value, &ret)
|
|
table.vals[k] = i
|
|
out[i] = 0
|
|
{{endif}}
|
|
kh_destroy_{{ttype}}(table)
|
|
return out
|
|
|
|
|
|
# ----------------------------------------------------------------------
|
|
# Membership
|
|
# ----------------------------------------------------------------------
|
|
|
|
|
|
@cython.wraparound(False)
|
|
@cython.boundscheck(False)
|
|
{{if dtype == 'object'}}
|
|
cdef ismember_{{dtype}}(ndarray[{{c_type}}] arr, ndarray[{{c_type}}] values):
|
|
{{else}}
|
|
cdef ismember_{{dtype}}(const {{dtype}}_t[:] arr, const {{dtype}}_t[:] values):
|
|
{{endif}}
|
|
"""
|
|
Return boolean of values in arr on an
|
|
element by-element basis
|
|
|
|
Parameters
|
|
----------
|
|
arr : {{dtype}} ndarray
|
|
values : {{dtype}} ndarray
|
|
|
|
Returns
|
|
-------
|
|
boolean ndarry len of (arr)
|
|
"""
|
|
cdef:
|
|
Py_ssize_t i, n
|
|
khiter_t k
|
|
int ret = 0
|
|
ndarray[uint8_t] result
|
|
{{c_type}} val
|
|
kh_{{ttype}}_t *table = kh_init_{{ttype}}()
|
|
|
|
# construct the table
|
|
n = len(values)
|
|
kh_resize_{{ttype}}(table, n)
|
|
|
|
{{if dtype == 'object'}}
|
|
for i in range(n):
|
|
kh_put_{{ttype}}(table, <PyObject*>values[i], &ret)
|
|
{{else}}
|
|
with nogil:
|
|
for i in range(n):
|
|
val = {{to_c_type}}(values[i])
|
|
kh_put_{{ttype}}(table, val, &ret)
|
|
{{endif}}
|
|
|
|
# test membership
|
|
n = len(arr)
|
|
result = np.empty(n, dtype=np.uint8)
|
|
|
|
{{if dtype == 'object'}}
|
|
for i in range(n):
|
|
val = arr[i]
|
|
k = kh_get_{{ttype}}(table, <PyObject*>val)
|
|
result[i] = (k != table.n_buckets)
|
|
{{else}}
|
|
with nogil:
|
|
for i in range(n):
|
|
val = {{to_c_type}}(arr[i])
|
|
k = kh_get_{{ttype}}(table, val)
|
|
result[i] = (k != table.n_buckets)
|
|
{{endif}}
|
|
|
|
kh_destroy_{{ttype}}(table)
|
|
return result.view(np.bool_)
|
|
|
|
# ----------------------------------------------------------------------
|
|
# Mode Computations
|
|
# ----------------------------------------------------------------------
|
|
|
|
|
|
@cython.wraparound(False)
|
|
@cython.boundscheck(False)
|
|
{{if dtype == 'object'}}
|
|
cdef mode_{{dtype}}(ndarray[{{dtype}}] values, bint dropna):
|
|
{{else}}
|
|
cdef mode_{{dtype}}(const {{dtype}}_t[:] values, bint dropna):
|
|
{{endif}}
|
|
cdef:
|
|
{{if dtype == 'object'}}
|
|
ndarray[{{dtype}}] keys
|
|
ndarray[{{dtype}}] modes
|
|
{{else}}
|
|
{{dtype}}_t[:] keys
|
|
ndarray[{{dtype}}_t] modes
|
|
{{endif}}
|
|
int64_t[:] counts
|
|
int64_t count, max_count = -1
|
|
Py_ssize_t k, j = 0
|
|
|
|
keys, counts = value_count_{{dtype}}(values, dropna)
|
|
|
|
{{if dtype == 'object'}}
|
|
modes = np.empty(len(keys), dtype=np.object_)
|
|
{{else}}
|
|
modes = np.empty(len(keys), dtype=np.{{dtype}})
|
|
{{endif}}
|
|
|
|
{{if dtype != 'object'}}
|
|
with nogil:
|
|
for k in range(len(keys)):
|
|
count = counts[k]
|
|
if count == max_count:
|
|
j += 1
|
|
elif count > max_count:
|
|
max_count = count
|
|
j = 0
|
|
else:
|
|
continue
|
|
|
|
modes[j] = keys[k]
|
|
{{else}}
|
|
for k in range(len(keys)):
|
|
count = counts[k]
|
|
if count == max_count:
|
|
j += 1
|
|
elif count > max_count:
|
|
max_count = count
|
|
j = 0
|
|
else:
|
|
continue
|
|
|
|
modes[j] = keys[k]
|
|
{{endif}}
|
|
|
|
return modes[:j + 1]
|
|
|
|
{{endfor}}
|
|
|
|
|
|
ctypedef fused htfunc_t:
|
|
complex128_t
|
|
complex64_t
|
|
float64_t
|
|
float32_t
|
|
uint64_t
|
|
uint32_t
|
|
uint16_t
|
|
uint8_t
|
|
int64_t
|
|
int32_t
|
|
int16_t
|
|
int8_t
|
|
object
|
|
|
|
|
|
cpdef value_count(ndarray[htfunc_t] values, bint dropna):
|
|
if htfunc_t is object:
|
|
return value_count_object(values, dropna)
|
|
|
|
elif htfunc_t is int8_t:
|
|
return value_count_int8(values, dropna)
|
|
elif htfunc_t is int16_t:
|
|
return value_count_int16(values, dropna)
|
|
elif htfunc_t is int32_t:
|
|
return value_count_int32(values, dropna)
|
|
elif htfunc_t is int64_t:
|
|
return value_count_int64(values, dropna)
|
|
|
|
elif htfunc_t is uint8_t:
|
|
return value_count_uint8(values, dropna)
|
|
elif htfunc_t is uint16_t:
|
|
return value_count_uint16(values, dropna)
|
|
elif htfunc_t is uint32_t:
|
|
return value_count_uint32(values, dropna)
|
|
elif htfunc_t is uint64_t:
|
|
return value_count_uint64(values, dropna)
|
|
|
|
elif htfunc_t is float64_t:
|
|
return value_count_float64(values, dropna)
|
|
elif htfunc_t is float32_t:
|
|
return value_count_float32(values, dropna)
|
|
|
|
elif htfunc_t is complex128_t:
|
|
return value_count_complex128(values, dropna)
|
|
elif htfunc_t is complex64_t:
|
|
return value_count_complex64(values, dropna)
|
|
|
|
else:
|
|
raise TypeError(values.dtype)
|
|
|
|
|
|
cpdef duplicated(ndarray[htfunc_t] values, object keep="first"):
|
|
if htfunc_t is object:
|
|
return duplicated_object(values, keep)
|
|
|
|
elif htfunc_t is int8_t:
|
|
return duplicated_int8(values, keep)
|
|
elif htfunc_t is int16_t:
|
|
return duplicated_int16(values, keep)
|
|
elif htfunc_t is int32_t:
|
|
return duplicated_int32(values, keep)
|
|
elif htfunc_t is int64_t:
|
|
return duplicated_int64(values, keep)
|
|
|
|
elif htfunc_t is uint8_t:
|
|
return duplicated_uint8(values, keep)
|
|
elif htfunc_t is uint16_t:
|
|
return duplicated_uint16(values, keep)
|
|
elif htfunc_t is uint32_t:
|
|
return duplicated_uint32(values, keep)
|
|
elif htfunc_t is uint64_t:
|
|
return duplicated_uint64(values, keep)
|
|
|
|
elif htfunc_t is float64_t:
|
|
return duplicated_float64(values, keep)
|
|
elif htfunc_t is float32_t:
|
|
return duplicated_float32(values, keep)
|
|
|
|
elif htfunc_t is complex128_t:
|
|
return duplicated_complex128(values, keep)
|
|
elif htfunc_t is complex64_t:
|
|
return duplicated_complex64(values, keep)
|
|
|
|
else:
|
|
raise TypeError(values.dtype)
|
|
|
|
|
|
cpdef ismember(ndarray[htfunc_t] arr, ndarray[htfunc_t] values):
|
|
if htfunc_t is object:
|
|
return ismember_object(arr, values)
|
|
|
|
elif htfunc_t is int8_t:
|
|
return ismember_int8(arr, values)
|
|
elif htfunc_t is int16_t:
|
|
return ismember_int16(arr, values)
|
|
elif htfunc_t is int32_t:
|
|
return ismember_int32(arr, values)
|
|
elif htfunc_t is int64_t:
|
|
return ismember_int64(arr, values)
|
|
|
|
elif htfunc_t is uint8_t:
|
|
return ismember_uint8(arr, values)
|
|
elif htfunc_t is uint16_t:
|
|
return ismember_uint16(arr, values)
|
|
elif htfunc_t is uint32_t:
|
|
return ismember_uint32(arr, values)
|
|
elif htfunc_t is uint64_t:
|
|
return ismember_uint64(arr, values)
|
|
|
|
elif htfunc_t is float64_t:
|
|
return ismember_float64(arr, values)
|
|
elif htfunc_t is float32_t:
|
|
return ismember_float32(arr, values)
|
|
|
|
elif htfunc_t is complex128_t:
|
|
return ismember_complex128(arr, values)
|
|
elif htfunc_t is complex64_t:
|
|
return ismember_complex64(arr, values)
|
|
|
|
else:
|
|
raise TypeError(values.dtype)
|
|
|
|
|
|
cpdef mode(ndarray[htfunc_t] values, bint dropna):
|
|
if htfunc_t is object:
|
|
return mode_object(values, dropna)
|
|
|
|
elif htfunc_t is int8_t:
|
|
return mode_int8(values, dropna)
|
|
elif htfunc_t is int16_t:
|
|
return mode_int16(values, dropna)
|
|
elif htfunc_t is int32_t:
|
|
return mode_int32(values, dropna)
|
|
elif htfunc_t is int64_t:
|
|
return mode_int64(values, dropna)
|
|
|
|
elif htfunc_t is uint8_t:
|
|
return mode_uint8(values, dropna)
|
|
elif htfunc_t is uint16_t:
|
|
return mode_uint16(values, dropna)
|
|
elif htfunc_t is uint32_t:
|
|
return mode_uint32(values, dropna)
|
|
elif htfunc_t is uint64_t:
|
|
return mode_uint64(values, dropna)
|
|
|
|
elif htfunc_t is float64_t:
|
|
return mode_float64(values, dropna)
|
|
elif htfunc_t is float32_t:
|
|
return mode_float32(values, dropna)
|
|
|
|
elif htfunc_t is complex128_t:
|
|
return mode_complex128(values, dropna)
|
|
elif htfunc_t is complex64_t:
|
|
return mode_complex64(values, dropna)
|
|
|
|
else:
|
|
raise TypeError(values.dtype)
|
|
|
|
|
|
{{py:
|
|
|
|
# name, dtype, ttype, c_type
|
|
dtypes = [('Int64', 'int64', 'int64', 'int64_t'),
|
|
('Int32', 'int32', 'int32', 'int32_t'), ]
|
|
|
|
}}
|
|
|
|
{{for name, dtype, ttype, c_type in dtypes}}
|
|
|
|
|
|
@cython.wraparound(False)
|
|
@cython.boundscheck(False)
|
|
def _unique_label_indices_{{dtype}}(const {{c_type}}[:] labels) -> ndarray:
|
|
"""
|
|
Indices of the first occurrences of the unique labels
|
|
*excluding* -1. equivalent to:
|
|
np.unique(labels, return_index=True)[1]
|
|
"""
|
|
cdef:
|
|
int ret = 0
|
|
Py_ssize_t i, n = len(labels)
|
|
kh_{{ttype}}_t *table = kh_init_{{ttype}}()
|
|
{{name}}Vector idx = {{name}}Vector()
|
|
ndarray[{{c_type}}, ndim=1] arr
|
|
{{name}}VectorData *ud = idx.data
|
|
|
|
kh_resize_{{ttype}}(table, min(kh_needed_n_buckets(n), SIZE_HINT_LIMIT))
|
|
|
|
with nogil:
|
|
for i in range(n):
|
|
kh_put_{{ttype}}(table, labels[i], &ret)
|
|
if ret != 0:
|
|
if needs_resize(ud):
|
|
with gil:
|
|
idx.resize()
|
|
append_data_{{ttype}}(ud, i)
|
|
|
|
kh_destroy_{{ttype}}(table)
|
|
|
|
arr = idx.to_array()
|
|
arr = arr[np.asarray(labels)[arr].argsort()]
|
|
|
|
return arr[1:] if arr.size != 0 and labels[arr[0]] == -1 else arr
|
|
|
|
{{endfor}}
|