forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathindexing_engines.py
183 lines (152 loc) · 6.04 KB
/
indexing_engines.py
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
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
"""
Benchmarks in this file depend mostly on code in _libs/
We have to created masked arrays to test the masked engine though. The
array is unpacked on the Cython level.
If a PR does not edit anything in _libs, it is very unlikely that benchmarks
in this file will be affected.
"""
import numpy as np
from pandas._libs import (
index as libindex,
)
from pandas.core.arrays import (
BaseMaskedArray,
)
def _get_numeric_engines():
engine_names = [
("Int64Engine", np.int64),
("Int32Engine", np.int32),
("Int16Engine", np.int16),
("Int8Engine", np.int8),
("UInt64Engine", np.uint64),
("UInt32Engine", np.uint32),
("UInt16engine", np.uint16),
("UInt8Engine", np.uint8),
("Float64Engine", np.float64),
("Float32Engine", np.float32),
]
return [
(getattr(libindex, engine_name), dtype)
for engine_name, dtype in engine_names
if hasattr(libindex, engine_name)
]
def _get_masked_engines():
engine_names = [
("MaskedInt64Engine", "Int64"),
("MaskedInt32Engine", "Int32"),
("MaskedInt16Engine", "Int16"),
("MaskedInt8Engine", "Int8"),
("MaskedUInt64Engine", "UInt64"),
("MaskedUInt32Engine", "UInt32"),
("MaskedUInt16engine", "UInt16"),
("MaskedUInt8Engine", "UInt8"),
("MaskedFloat64Engine", "Float64"),
("MaskedFloat32Engine", "Float32"),
]
return [
(getattr(libindex, engine_name), dtype)
for engine_name, dtype in engine_names
if hasattr(libindex, engine_name)
]
class NumericEngineIndexing:
params = [
_get_numeric_engines(),
["monotonic_incr", "monotonic_decr", "non_monotonic"],
[True, False],
[10**5, 2 * 10**6], # 2e6 is above SIZE_CUTOFF
]
param_names = ["engine_and_dtype", "index_type", "unique", "N"]
def setup(self, engine_and_dtype, index_type, unique, N):
engine, dtype = engine_and_dtype
if index_type == "monotonic_incr":
if unique:
arr = np.arange(N * 3, dtype=dtype)
else:
values = list([1] * N + [2] * N + [3] * N)
arr = np.array(values, dtype=dtype)
elif index_type == "monotonic_decr":
if unique:
arr = np.arange(N * 3, dtype=dtype)[::-1]
else:
values = list([1] * N + [2] * N + [3] * N)
arr = np.array(values, dtype=dtype)[::-1]
else:
assert index_type == "non_monotonic"
if unique:
arr = np.empty(N * 3, dtype=dtype)
arr[:N] = np.arange(N * 2, N * 3, dtype=dtype)
arr[N:] = np.arange(N * 2, dtype=dtype)
else:
arr = np.array([1, 2, 3] * N, dtype=dtype)
self.data = engine(arr)
# code belows avoids populating the mapping etc. while timing.
self.data.get_loc(2)
self.key_middle = arr[len(arr) // 2]
self.key_early = arr[2]
def time_get_loc(self, engine_and_dtype, index_type, unique, N):
self.data.get_loc(self.key_early)
def time_get_loc_near_middle(self, engine_and_dtype, index_type, unique, N):
# searchsorted performance may be different near the middle of a range
# vs near an endpoint
self.data.get_loc(self.key_middle)
class MaskedNumericEngineIndexing:
params = [
_get_masked_engines(),
["monotonic_incr", "monotonic_decr", "non_monotonic"],
[True, False],
[10**5, 2 * 10**6], # 2e6 is above SIZE_CUTOFF
]
param_names = ["engine_and_dtype", "index_type", "unique", "N"]
def setup(self, engine_and_dtype, index_type, unique, N):
engine, dtype = engine_and_dtype
if index_type == "monotonic_incr":
if unique:
arr = np.arange(N * 3, dtype=dtype.lower())
else:
values = list([1] * N + [2] * N + [3] * N)
arr = np.array(values, dtype=dtype.lower())
mask = np.zeros(N * 3, dtype=np.bool_)
elif index_type == "monotonic_decr":
if unique:
arr = np.arange(N * 3, dtype=dtype.lower())[::-1]
else:
values = list([1] * N + [2] * N + [3] * N)
arr = np.array(values, dtype=dtype.lower())[::-1]
mask = np.zeros(N * 3, dtype=np.bool_)
else:
assert index_type == "non_monotonic"
if unique:
arr = np.zeros(N * 3, dtype=dtype.lower())
arr[:N] = np.arange(N * 2, N * 3, dtype=dtype.lower())
arr[N:] = np.arange(N * 2, dtype=dtype.lower())
else:
arr = np.array([1, 2, 3] * N, dtype=dtype.lower())
mask = np.zeros(N * 3, dtype=np.bool_)
mask[-1] = True
self.data = engine(BaseMaskedArray(arr, mask))
# code belows avoids populating the mapping etc. while timing.
self.data.get_loc(2)
self.key_middle = arr[len(arr) // 2]
self.key_early = arr[2]
def time_get_loc(self, engine_and_dtype, index_type, unique, N):
self.data.get_loc(self.key_early)
def time_get_loc_near_middle(self, engine_and_dtype, index_type, unique, N):
# searchsorted performance may be different near the middle of a range
# vs near an endpoint
self.data.get_loc(self.key_middle)
class ObjectEngineIndexing:
params = [("monotonic_incr", "monotonic_decr", "non_monotonic")]
param_names = ["index_type"]
def setup(self, index_type):
N = 10**5
values = list("a" * N + "b" * N + "c" * N)
arr = {
"monotonic_incr": np.array(values, dtype=object),
"monotonic_decr": np.array(list(reversed(values)), dtype=object),
"non_monotonic": np.array(list("abc") * N, dtype=object),
}[index_type]
self.data = libindex.ObjectEngine(arr)
# code belows avoids populating the mapping etc. while timing.
self.data.get_loc("b")
def time_get_loc(self, index_type):
self.data.get_loc("b")