pandas@2d2e8b5 (original) (raw)

`@@ -890,15 +890,12 @@ cdef class Int64Factorizer:

890

`return labels

891

892

893

-

894

def value_count_int64(ndarray[int64_t] values):

893

cdef build_count_table_int64(ndarray[int64_t] values, kh_int64_t *table):

895

894

` cdef:

895

int k

896

` Py_ssize_t i, n = len(values)

897

kh_int64_t *table

898

897

`int ret = 0

899

list uniques = []

900

898

901

table = kh_init_int64()

902

899

` kh_resize_int64(table, n)

903

900

904

901

`for i in range(n):

`@@ -910,8 +907,17 @@ def value_count_int64(ndarray[int64_t] values):

910

907

` k = kh_put_int64(table, val, &ret)

911

908

` table.vals[k] = 1

912

909

913

for (k = kh_begin(h); k != kh_end(h); ++k)

914

if (kh_exist(h, k)) kh_value(h, k) = 1;

910

+

911

cpdef value_count_int64(ndarray[int64_t] values):

912

cdef:

913

Py_ssize_t i

914

kh_int64_t *table

915

int ret = 0

916

int k

917

+

918

table = kh_init_int64()

919

build_count_table_int64(values, table)

920

+

915

921

` i = 0

916

922

` result_keys = np.empty(table.n_occupied, dtype=np.int64)

917

923

` result_counts = np.zeros(table.n_occupied, dtype=np.int64)

`@@ -924,15 +930,15 @@ def value_count_int64(ndarray[int64_t] values):

924

930

925

931

`return result_keys, result_counts

926

932

927

def value_count_object(ndarray[object] values,

928

ndarray[uint8_t, cast=True] mask):

933

+

934

cdef build_count_table_object(ndarray[object] values,

935

ndarray[uint8_t, cast=True] mask,

936

kh_pymap_t *table):

929

937

` cdef:

938

int k

930

939

` Py_ssize_t i, n = len(values)

931

kh_pymap_t *table

932

940

`int ret = 0

933

list uniques = []

934

941

935

table = kh_init_pymap()

936

942

` kh_resize_pymap(table, n // 10)

937

943

938

944

`for i in range(n):

`@@ -947,6 +953,17 @@ def value_count_object(ndarray[object] values,

947

953

` k = kh_put_pymap(table, <PyObject*> val, &ret)

948

954

` table.vals[k] = 1

949

955

956

+

957

cpdef value_count_object(ndarray[object] values,

958

ndarray[uint8_t, cast=True] mask):

959

cdef:

960

Py_ssize_t i = len(values)

961

kh_pymap_t *table

962

int k

963

+

964

table = kh_init_pymap()

965

build_count_table_object(values, mask, table)

966

+

950

967

` i = 0

951

968

` result_keys = np.empty(table.n_occupied, dtype=object)

952

969

` result_counts = np.zeros(table.n_occupied, dtype=np.int64)

`@@ -959,3 +976,64 @@ def value_count_object(ndarray[object] values,

959

976

960

977

`return result_keys, result_counts

961

978

979

+

980

def mode_object(ndarray[object] values, ndarray[uint8_t, cast=True] mask):

981

cdef:

982

int count, max_count = 2

983

int j = -1 # so you can do +=

984

int k

985

Py_ssize_t i, n = len(values)

986

kh_pymap_t *table

987

int ret = 0

988

+

989

table = kh_init_pymap()

990

build_count_table_object(values, mask, table)

991

+

992

modes = np.empty(table.n_buckets, dtype=np.object_)

993

for k in range(table.n_buckets):

994

if kh_exist_pymap(table, k):

995

count = table.vals[k]

996

+

997

if count == max_count:

998

j += 1

999

elif count > max_count:

1000

max_count = count

1001

j = 0

1002

else:

1003

continue

1004

modes[j] = table.keys[k]

1005

+

1006

kh_destroy_pymap(table)

1007

+

1008

return modes[:j+1]

1009

+

1010

+

1011

def mode_int64(ndarray[int64_t] values):

1012

cdef:

1013

int val, max_val = 2

1014

int j = -1 # so you can do +=

1015

int k

1016

kh_int64_t *table

1017

list uniques = []

1018

+

1019

table = kh_init_int64()

1020

+

1021

build_count_table_int64(values, table)

1022

+

1023

modes = np.empty(table.n_buckets, dtype=np.int64)

1024

for k in range(table.n_buckets):

1025

if kh_exist_int64(table, k):

1026

val = table.vals[k]

1027

+

1028

if val == max_val:

1029

j += 1

1030

elif val > max_val:

1031

max_val = val

1032

j = 0

1033

else:

1034

continue

1035

modes[j] = table.keys[k]

1036

+

1037

kh_destroy_int64(table)

1038

+

1039

return modes[:j+1]