-
-
Notifications
You must be signed in to change notification settings - Fork 18.4k
/
Copy pathstat_ops.py
205 lines (136 loc) · 5.96 KB
/
stat_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
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
195
196
197
198
199
200
201
202
203
204
205
from .pandas_vb_common import *
def _set_use_bottleneck_False():
try:
pd.options.compute.use_bottleneck = False
except:
from pandas.core import nanops
nanops._USE_BOTTLENECK = False
class FrameOps(object):
goal_time = 0.2
param_names = ['op', 'use_bottleneck', 'dtype', 'axis']
params = [['mean', 'sum', 'median'],
[True, False],
['float', 'int'],
[0, 1]]
def setup(self, op, use_bottleneck, dtype, axis):
if dtype == 'float':
self.df = DataFrame(np.random.randn(100000, 4))
elif dtype == 'int':
self.df = DataFrame(np.random.randint(1000, size=(100000, 4)))
if not use_bottleneck:
_set_use_bottleneck_False()
self.func = getattr(self.df, op)
def time_op(self, op, use_bottleneck, dtype, axis):
self.func(axis=axis)
class stat_ops_level_frame_sum(object):
goal_time = 0.2
def setup(self):
self.index = MultiIndex(levels=[np.arange(10), np.arange(100), np.arange(100)], labels=[np.arange(10).repeat(10000), np.tile(np.arange(100).repeat(100), 10), np.tile(np.tile(np.arange(100), 100), 10)])
random.shuffle(self.index.values)
self.df = DataFrame(np.random.randn(len(self.index), 4), index=self.index)
self.df_level = DataFrame(np.random.randn(100, 4), index=self.index.levels[1])
def time_stat_ops_level_frame_sum(self):
self.df.sum(level=1)
class stat_ops_level_frame_sum_multiple(object):
goal_time = 0.2
def setup(self):
self.index = MultiIndex(levels=[np.arange(10), np.arange(100), np.arange(100)], labels=[np.arange(10).repeat(10000), np.tile(np.arange(100).repeat(100), 10), np.tile(np.tile(np.arange(100), 100), 10)])
random.shuffle(self.index.values)
self.df = DataFrame(np.random.randn(len(self.index), 4), index=self.index)
self.df_level = DataFrame(np.random.randn(100, 4), index=self.index.levels[1])
def time_stat_ops_level_frame_sum_multiple(self):
self.df.sum(level=[0, 1])
class stat_ops_level_series_sum(object):
goal_time = 0.2
def setup(self):
self.index = MultiIndex(levels=[np.arange(10), np.arange(100), np.arange(100)], labels=[np.arange(10).repeat(10000), np.tile(np.arange(100).repeat(100), 10), np.tile(np.tile(np.arange(100), 100), 10)])
random.shuffle(self.index.values)
self.df = DataFrame(np.random.randn(len(self.index), 4), index=self.index)
self.df_level = DataFrame(np.random.randn(100, 4), index=self.index.levels[1])
def time_stat_ops_level_series_sum(self):
self.df[1].sum(level=1)
class stat_ops_level_series_sum_multiple(object):
goal_time = 0.2
def setup(self):
self.index = MultiIndex(levels=[np.arange(10), np.arange(100), np.arange(100)], labels=[np.arange(10).repeat(10000), np.tile(np.arange(100).repeat(100), 10), np.tile(np.tile(np.arange(100), 100), 10)])
random.shuffle(self.index.values)
self.df = DataFrame(np.random.randn(len(self.index), 4), index=self.index)
self.df_level = DataFrame(np.random.randn(100, 4), index=self.index.levels[1])
def time_stat_ops_level_series_sum_multiple(self):
self.df[1].sum(level=[0, 1])
class stat_ops_series_std(object):
goal_time = 0.2
def setup(self):
self.s = Series(np.random.randn(100000), index=np.arange(100000))
self.s[::2] = np.nan
def time_stat_ops_series_std(self):
self.s.std()
class stats_corr_spearman(object):
goal_time = 0.2
def setup(self):
self.df = DataFrame(np.random.randn(1000, 30))
def time_stats_corr_spearman(self):
self.df.corr(method='spearman')
class stats_rank2d_axis0_average(object):
goal_time = 0.2
def setup(self):
self.df = DataFrame(np.random.randn(5000, 50))
def time_stats_rank2d_axis0_average(self):
self.df.rank()
class stats_rank2d_axis1_average(object):
goal_time = 0.2
def setup(self):
self.df = DataFrame(np.random.randn(5000, 50))
def time_stats_rank2d_axis1_average(self):
self.df.rank(1)
class stats_rank_average(object):
goal_time = 0.2
def setup(self):
self.values = np.concatenate([np.arange(100000), np.random.randn(100000), np.arange(100000)])
self.s = Series(self.values)
def time_stats_rank_average(self):
self.s.rank()
class stats_rank_average_int(object):
goal_time = 0.2
def setup(self):
self.values = np.random.randint(0, 100000, size=200000)
self.s = Series(self.values)
def time_stats_rank_average_int(self):
self.s.rank()
class stats_rank_pct_average(object):
goal_time = 0.2
def setup(self):
self.values = np.concatenate([np.arange(100000), np.random.randn(100000), np.arange(100000)])
self.s = Series(self.values)
def time_stats_rank_pct_average(self):
self.s.rank(pct=True)
class stats_rank_pct_average_old(object):
goal_time = 0.2
def setup(self):
self.values = np.concatenate([np.arange(100000), np.random.randn(100000), np.arange(100000)])
self.s = Series(self.values)
def time_stats_rank_pct_average_old(self):
(self.s.rank() / len(self.s))
class stats_rolling_mean(object):
goal_time = 0.2
def setup(self):
self.arr = np.random.randn(100000)
self.win = 100
def time_rolling_mean(self):
rolling_mean(self.arr, self.win)
def time_rolling_median(self):
rolling_median(self.arr, self.win)
def time_rolling_min(self):
rolling_min(self.arr, self.win)
def time_rolling_max(self):
rolling_max(self.arr, self.win)
def time_rolling_sum(self):
rolling_sum(self.arr, self.win)
def time_rolling_std(self):
rolling_std(self.arr, self.win)
def time_rolling_var(self):
rolling_var(self.arr, self.win)
def time_rolling_skew(self):
rolling_skew(self.arr, self.win)
def time_rolling_kurt(self):
rolling_kurt(self.arr, self.win)