Skip to content

CLN: Clean up unnecessary templating in hashtable #57574

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

CLN: Clean up unnecessary templating in hashtable #57574

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
42 changes: 15 additions & 27 deletions pandas/_libs/hashtable_class_helper.pxi.in
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,18 +82,6 @@ cimported_types = ['complex64',
'uint64']
}}

{{for name in cimported_types}}
from pandas._libs.khash cimport (
kh_destroy_{{name}},
kh_exist_{{name}},
kh_get_{{name}},
kh_init_{{name}},
kh_put_{{name}},
kh_resize_{{name}},
)

{{endfor}}

# ----------------------------------------------------------------------
# VectorData
# ----------------------------------------------------------------------
Expand Down Expand Up @@ -398,9 +386,9 @@ dtypes = [('Complex128', 'complex128', 'khcomplex128_t', 'to_khcomplex128_t'),
cdef class {{name}}HashTable(HashTable):

def __cinit__(self, int64_t size_hint=1, bint uses_mask=False):
self.table = kh_init_{{dtype}}()
self.table = kh_init({{dtype}})
size_hint = min(kh_needed_n_buckets(size_hint), SIZE_HINT_LIMIT)
kh_resize_{{dtype}}(self.table, size_hint)
kh_resize({{dtype}}, self.table, size_hint)

self.uses_mask = uses_mask
self.na_position = -1
Expand All @@ -410,7 +398,7 @@ cdef class {{name}}HashTable(HashTable):

def __dealloc__(self):
if self.table is not NULL:
kh_destroy_{{dtype}}(self.table)
kh_destroy({{dtype}}, self.table)
self.table = NULL

def __contains__(self, object key) -> bool:
Expand All @@ -424,7 +412,7 @@ cdef class {{name}}HashTable(HashTable):
return -1 != self.na_position

ckey = {{to_c_type}}(key)
k = kh_get_{{dtype}}(self.table, ckey)
k = kh_get({{dtype}}, self.table, ckey)
return k != self.table.n_buckets

def sizeof(self, deep: bool = False) -> int:
Expand Down Expand Up @@ -464,7 +452,7 @@ cdef class {{name}}HashTable(HashTable):
{{c_type}} cval

cval = {{to_c_type}}(val)
k = kh_get_{{dtype}}(self.table, cval)
k = kh_get({{dtype}}, self.table, cval)
if k != self.table.n_buckets:
return self.table.vals[k]
else:
Expand Down Expand Up @@ -494,8 +482,8 @@ cdef class {{name}}HashTable(HashTable):
{{c_type}} ckey

ckey = {{to_c_type}}(key)
k = kh_put_{{dtype}}(self.table, ckey, &ret)
if kh_exist_{{dtype}}(self.table, k):
k = kh_put({{dtype}}, self.table, ckey, &ret)
if kh_exist({{dtype}}, self.table, k):
self.table.vals[k] = val
else:
raise KeyError(key)
Expand Down Expand Up @@ -528,7 +516,7 @@ cdef class {{name}}HashTable(HashTable):
with nogil:
for i in range(n):
key = {{to_c_type}}(keys[i])
k = kh_put_{{dtype}}(self.table, key, &ret)
k = kh_put({{dtype}}, self.table, key, &ret)
self.table.vals[k] = <Py_ssize_t>values[i]
{{endif}}

Expand All @@ -552,12 +540,12 @@ cdef class {{name}}HashTable(HashTable):
na_position = i
else:
val= {{to_c_type}}(values[i])
k = kh_put_{{dtype}}(self.table, val, &ret)
k = kh_put({{dtype}}, self.table, val, &ret)
self.table.vals[k] = i
else:
for i in range(n):
val= {{to_c_type}}(values[i])
k = kh_put_{{dtype}}(self.table, val, &ret)
k = kh_put({{dtype}}, self.table, val, &ret)
self.table.vals[k] = i
self.na_position = na_position

Expand All @@ -582,7 +570,7 @@ cdef class {{name}}HashTable(HashTable):
locs[i] = na_position
else:
val = {{to_c_type}}(values[i])
k = kh_get_{{dtype}}(self.table, val)
k = kh_get({{dtype}}, self.table, val)
if k != self.table.n_buckets:
locs[i] = self.table.vals[k]
else:
Expand Down Expand Up @@ -716,11 +704,11 @@ cdef class {{name}}HashTable(HashTable):
append_data_uint8(rmd, 1)
continue

k = kh_get_{{dtype}}(self.table, val)
k = kh_get({{dtype}}, self.table, val)

if k == self.table.n_buckets:
# k hasn't been seen yet
k = kh_put_{{dtype}}(self.table, val, &ret)
k = kh_put({{dtype}}, self.table, val, &ret)

if needs_resize(ud):
with gil:
Expand Down Expand Up @@ -857,12 +845,12 @@ cdef class {{name}}HashTable(HashTable):
labels[i] = -1
continue

k = kh_get_{{dtype}}(self.table, val)
k = kh_get({{dtype}}, self.table, val)
if k != self.table.n_buckets:
idx = self.table.vals[k]
labels[i] = idx
else:
k = kh_put_{{dtype}}(self.table, val, &ret)
k = kh_put({{dtype}}, self.table, val, &ret)
self.table.vals[k] = count

if needs_resize(ud):
Expand Down