forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathbinary_ops.py
158 lines (109 loc) · 4.01 KB
/
binary_ops.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
import numpy as np
from pandas import DataFrame, Series, date_range
from pandas.core.algorithms import checked_add_with_arr
try:
import pandas.core.computation.expressions as expr
except ImportError:
import pandas.computation.expressions as expr
class Ops:
params = [[True, False], ["default", 1]]
param_names = ["use_numexpr", "threads"]
def setup(self, use_numexpr, threads):
self.df = DataFrame(np.random.randn(20000, 100))
self.df2 = DataFrame(np.random.randn(20000, 100))
if threads != "default":
expr.set_numexpr_threads(threads)
if not use_numexpr:
expr.set_use_numexpr(False)
def time_frame_add(self, use_numexpr, threads):
self.df + self.df2
def time_frame_mult(self, use_numexpr, threads):
self.df * self.df2
def time_frame_multi_and(self, use_numexpr, threads):
self.df[(self.df > 0) & (self.df2 > 0)]
def time_frame_comparison(self, use_numexpr, threads):
self.df > self.df2
def teardown(self, use_numexpr, threads):
expr.set_use_numexpr(True)
expr.set_numexpr_threads()
class Ops2:
def setup(self):
N = 10 ** 3
self.df = DataFrame(np.random.randn(N, N))
self.df2 = DataFrame(np.random.randn(N, N))
self.df_int = DataFrame(
np.random.randint(
np.iinfo(np.int16).min, np.iinfo(np.int16).max, size=(N, N)
)
)
self.df2_int = DataFrame(
np.random.randint(
np.iinfo(np.int16).min, np.iinfo(np.int16).max, size=(N, N)
)
)
self.s = Series(np.random.randn(N))
# Division
def time_frame_float_div(self):
self.df // self.df2
def time_frame_float_div_by_zero(self):
self.df / 0
def time_frame_float_floor_by_zero(self):
self.df // 0
def time_frame_int_div_by_zero(self):
self.df_int / 0
# Modulo
def time_frame_int_mod(self):
self.df_int % self.df2_int
def time_frame_float_mod(self):
self.df % self.df2
# Dot product
def time_frame_dot(self):
self.df.dot(self.df2)
def time_series_dot(self):
self.s.dot(self.s)
def time_frame_series_dot(self):
self.df.dot(self.s)
class Timeseries:
params = [None, "US/Eastern"]
param_names = ["tz"]
def setup(self, tz):
N = 10 ** 6
halfway = (N // 2) - 1
self.s = Series(date_range("20010101", periods=N, freq="T", tz=tz))
self.ts = self.s[halfway]
self.s2 = Series(date_range("20010101", periods=N, freq="s", tz=tz))
def time_series_timestamp_compare(self, tz):
self.s <= self.ts
def time_timestamp_series_compare(self, tz):
self.ts >= self.s
def time_timestamp_ops_diff(self, tz):
self.s2.diff()
def time_timestamp_ops_diff_with_shift(self, tz):
self.s - self.s.shift()
class AddOverflowScalar:
params = [1, -1, 0]
param_names = ["scalar"]
def setup(self, scalar):
N = 10 ** 6
self.arr = np.arange(N)
def time_add_overflow_scalar(self, scalar):
checked_add_with_arr(self.arr, scalar)
class AddOverflowArray:
def setup(self):
N = 10 ** 6
self.arr = np.arange(N)
self.arr_rev = np.arange(-N, 0)
self.arr_mixed = np.array([1, -1]).repeat(N / 2)
self.arr_nan_1 = np.random.choice([True, False], size=N)
self.arr_nan_2 = np.random.choice([True, False], size=N)
def time_add_overflow_arr_rev(self):
checked_add_with_arr(self.arr, self.arr_rev)
def time_add_overflow_arr_mask_nan(self):
checked_add_with_arr(self.arr, self.arr_mixed, arr_mask=self.arr_nan_1)
def time_add_overflow_b_mask_nan(self):
checked_add_with_arr(self.arr, self.arr_mixed, b_mask=self.arr_nan_1)
def time_add_overflow_both_arg_nan(self):
checked_add_with_arr(
self.arr, self.arr_mixed, arr_mask=self.arr_nan_1, b_mask=self.arr_nan_2
)
from .pandas_vb_common import setup # noqa: F401