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
184
185
186
187
188
189
190
191
192
193
194
|
import numpy as np
import pandas.util.testing as tm
from pandas import (Series, date_range, DatetimeIndex, Index, RangeIndex,
Float64Index)
from .pandas_vb_common import setup # noqa
class SetOperations(object):
goal_time = 0.2
params = (['datetime', 'date_string', 'int', 'strings'],
['intersection', 'union', 'symmetric_difference'])
param_names = ['dtype', 'method']
def setup(self, dtype, method):
N = 10**5
dates_left = date_range('1/1/2000', periods=N, freq='T')
fmt = '%Y-%m-%d %H:%M:%S'
date_str_left = Index(dates_left.strftime(fmt))
int_left = Index(np.arange(N))
str_left = tm.makeStringIndex(N)
data = {'datetime': {'left': dates_left, 'right': dates_left[:-1]},
'date_string': {'left': date_str_left,
'right': date_str_left[:-1]},
'int': {'left': int_left, 'right': int_left[:-1]},
'strings': {'left': str_left, 'right': str_left[:-1]}}
self.left = data[dtype]['left']
self.right = data[dtype]['right']
def time_operation(self, dtype, method):
getattr(self.left, method)(self.right)
class SetDisjoint(object):
goal_time = 0.2
def setup(self):
N = 10**5
B = N + 20000
self.datetime_left = DatetimeIndex(range(N))
self.datetime_right = DatetimeIndex(range(N, B))
def time_datetime_difference_disjoint(self):
self.datetime_left.difference(self.datetime_right)
class Datetime(object):
goal_time = 0.2
def setup(self):
self.dr = date_range('20000101', freq='D', periods=10000)
def time_is_dates_only(self):
self.dr._is_dates_only
class Ops(object):
sample_time = 0.2
params = ['float', 'int']
param_names = ['dtype']
def setup(self, dtype):
N = 10**6
indexes = {'int': 'makeIntIndex', 'float': 'makeFloatIndex'}
self.index = getattr(tm, indexes[dtype])(N)
def time_add(self, dtype):
self.index + 2
def time_subtract(self, dtype):
self.index - 2
def time_multiply(self, dtype):
self.index * 2
def time_divide(self, dtype):
self.index / 2
def time_modulo(self, dtype):
self.index % 2
class Range(object):
goal_time = 0.2
def setup(self):
self.idx_inc = RangeIndex(start=0, stop=10**7, step=3)
self.idx_dec = RangeIndex(start=10**7, stop=-1, step=-3)
def time_max(self):
self.idx_inc.max()
def time_max_trivial(self):
self.idx_dec.max()
def time_min(self):
self.idx_dec.min()
def time_min_trivial(self):
self.idx_inc.min()
class IndexAppend(object):
goal_time = 0.2
def setup(self):
N = 10000
self.range_idx = RangeIndex(0, 100)
self.int_idx = self.range_idx.astype(int)
self.obj_idx = self.int_idx.astype(str)
self.range_idxs = []
self.int_idxs = []
self.object_idxs = []
for i in range(1, N):
r_idx = RangeIndex(i * 100, (i + 1) * 100)
self.range_idxs.append(r_idx)
i_idx = r_idx.astype(int)
self.int_idxs.append(i_idx)
o_idx = i_idx.astype(str)
self.object_idxs.append(o_idx)
def time_append_range_list(self):
self.range_idx.append(self.range_idxs)
def time_append_int_list(self):
self.int_idx.append(self.int_idxs)
def time_append_obj_list(self):
self.obj_idx.append(self.object_idxs)
class Indexing(object):
goal_time = 0.2
params = ['String', 'Float', 'Int']
param_names = ['dtype']
def setup(self, dtype):
N = 10**6
self.idx = getattr(tm, 'make{}Index'.format(dtype))(N)
self.array_mask = (np.arange(N) % 3) == 0
self.series_mask = Series(self.array_mask)
self.sorted = self.idx.sort_values()
half = N // 2
self.non_unique = self.idx[:half].append(self.idx[:half])
self.non_unique_sorted = self.sorted[:half].append(self.sorted[:half])
self.key = self.sorted[N // 4]
def time_boolean_array(self, dtype):
self.idx[self.array_mask]
def time_boolean_series(self, dtype):
self.idx[self.series_mask]
def time_get(self, dtype):
self.idx[1]
def time_slice(self, dtype):
self.idx[:-1]
def time_slice_step(self, dtype):
self.idx[::2]
def time_get_loc(self, dtype):
self.idx.get_loc(self.key)
def time_get_loc_sorted(self, dtype):
self.sorted.get_loc(self.key)
def time_get_loc_non_unique(self, dtype):
self.non_unique.get_loc(self.key)
def time_get_loc_non_unique_sorted(self, dtype):
self.non_unique_sorted.get_loc(self.key)
class Float64IndexMethod(object):
# GH 13166
goal_time = 0.2
def setup(self):
N = 100000
a = np.arange(N)
self.ind = Float64Index(a * 4.8000000418824129e-08)
def time_get_loc(self):
self.ind.get_loc(0)
|
