1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
| """
| Numba 1D sum kernels that can be shared by
| * Dataframe / Series
| * groupby
| * rolling / expanding
|
| Mirrors pandas/_libs/window/aggregation.pyx
| """
| from __future__ import annotations
|
| import numba
| import numpy as np
|
| from pandas.core._numba.kernels.shared import is_monotonic_increasing
|
|
| @numba.jit(nopython=True, nogil=True, parallel=False)
| def add_sum(
| val: float,
| nobs: int,
| sum_x: float,
| compensation: float,
| num_consecutive_same_value: int,
| prev_value: float,
| ) -> tuple[int, float, float, int, float]:
| if not np.isnan(val):
| nobs += 1
| y = val - compensation
| t = sum_x + y
| compensation = t - sum_x - y
| sum_x = t
|
| if val == prev_value:
| num_consecutive_same_value += 1
| else:
| num_consecutive_same_value = 1
| prev_value = val
|
| return nobs, sum_x, compensation, num_consecutive_same_value, prev_value
|
|
| @numba.jit(nopython=True, nogil=True, parallel=False)
| def remove_sum(
| val: float, nobs: int, sum_x: float, compensation: float
| ) -> tuple[int, float, float]:
| if not np.isnan(val):
| nobs -= 1
| y = -val - compensation
| t = sum_x + y
| compensation = t - sum_x - y
| sum_x = t
| return nobs, sum_x, compensation
|
|
| @numba.jit(nopython=True, nogil=True, parallel=False)
| def sliding_sum(
| values: np.ndarray,
| start: np.ndarray,
| end: np.ndarray,
| min_periods: int,
| ) -> np.ndarray:
| N = len(start)
| nobs = 0
| sum_x = 0.0
| compensation_add = 0.0
| compensation_remove = 0.0
|
| is_monotonic_increasing_bounds = is_monotonic_increasing(
| start
| ) and is_monotonic_increasing(end)
|
| output = np.empty(N, dtype=np.float64)
|
| for i in range(N):
| s = start[i]
| e = end[i]
| if i == 0 or not is_monotonic_increasing_bounds:
| prev_value = values[s]
| num_consecutive_same_value = 0
|
| for j in range(s, e):
| val = values[j]
| (
| nobs,
| sum_x,
| compensation_add,
| num_consecutive_same_value,
| prev_value,
| ) = add_sum(
| val,
| nobs,
| sum_x,
| compensation_add,
| num_consecutive_same_value,
| prev_value,
| )
| else:
| for j in range(start[i - 1], s):
| val = values[j]
| nobs, sum_x, compensation_remove = remove_sum(
| val, nobs, sum_x, compensation_remove
| )
|
| for j in range(end[i - 1], e):
| val = values[j]
| (
| nobs,
| sum_x,
| compensation_add,
| num_consecutive_same_value,
| prev_value,
| ) = add_sum(
| val,
| nobs,
| sum_x,
| compensation_add,
| num_consecutive_same_value,
| prev_value,
| )
|
| if nobs == 0 == min_periods:
| result = 0.0
| elif nobs >= min_periods:
| if num_consecutive_same_value >= nobs:
| result = prev_value * nobs
| else:
| result = sum_x
| else:
| result = np.nan
|
| output[i] = result
|
| if not is_monotonic_increasing_bounds:
| nobs = 0
| sum_x = 0.0
| compensation_remove = 0.0
|
| return output
|
|
