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
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
|
import numpy as np
import pandas as pd
class Methods:
params = (
["DataFrame", "Series"],
[10, 1000],
["int", "float"],
["median", "mean", "max", "min", "std", "count", "skew", "kurt", "sum"],
)
param_names = ["constructor", "window", "dtype", "method"]
def setup(self, constructor, window, dtype, method):
N = 10 ** 5
arr = (100 * np.random.random(N)).astype(dtype)
self.roll = getattr(pd, constructor)(arr).rolling(window)
def time_rolling(self, constructor, window, dtype, method):
getattr(self.roll, method)()
def peakmem_rolling(self, constructor, window, dtype, method):
getattr(self.roll, method)()
class Apply:
params = (
["DataFrame", "Series"],
[3, 300],
["int", "float"],
[sum, np.sum, lambda x: np.sum(x) + 5],
[True, False],
)
param_names = ["constructor", "window", "dtype", "function", "raw"]
def setup(self, constructor, window, dtype, function, raw):
N = 10 ** 3
arr = (100 * np.random.random(N)).astype(dtype)
self.roll = getattr(pd, constructor)(arr).rolling(window)
def time_rolling(self, constructor, window, dtype, function, raw):
self.roll.apply(function, raw=raw)
class Engine:
params = (
["DataFrame", "Series"],
["int", "float"],
[np.sum, lambda x: np.sum(x) + 5],
["cython", "numba"],
)
param_names = ["constructor", "dtype", "function", "engine"]
def setup(self, constructor, dtype, function, engine):
N = 10 ** 3
arr = (100 * np.random.random(N)).astype(dtype)
self.data = getattr(pd, constructor)(arr)
def time_rolling_apply(self, constructor, dtype, function, engine):
self.data.rolling(10).apply(function, raw=True, engine=engine)
def time_expanding_apply(self, constructor, dtype, function, engine):
self.data.expanding().apply(function, raw=True, engine=engine)
class ExpandingMethods:
params = (
["DataFrame", "Series"],
["int", "float"],
["median", "mean", "max", "min", "std", "count", "skew", "kurt", "sum"],
)
param_names = ["constructor", "window", "dtype", "method"]
def setup(self, constructor, dtype, method):
N = 10 ** 5
arr = (100 * np.random.random(N)).astype(dtype)
self.expanding = getattr(pd, constructor)(arr).expanding()
def time_expanding(self, constructor, dtype, method):
getattr(self.expanding, method)()
class EWMMethods:
params = (["DataFrame", "Series"], [10, 1000], ["int", "float"], ["mean", "std"])
param_names = ["constructor", "window", "dtype", "method"]
def setup(self, constructor, window, dtype, method):
N = 10 ** 5
arr = (100 * np.random.random(N)).astype(dtype)
times = pd.date_range("1900", periods=N, freq="23s")
self.ewm = getattr(pd, constructor)(arr).ewm(halflife=window)
self.ewm_times = getattr(pd, constructor)(arr).ewm(
halflife="1 Day", times=times
)
def time_ewm(self, constructor, window, dtype, method):
getattr(self.ewm, method)()
def time_ewm_times(self, constructor, window, dtype, method):
self.ewm.mean()
class VariableWindowMethods(Methods):
params = (
["DataFrame", "Series"],
["50s", "1h", "1d"],
["int", "float"],
["median", "mean", "max", "min", "std", "count", "skew", "kurt", "sum"],
)
param_names = ["constructor", "window", "dtype", "method"]
def setup(self, constructor, window, dtype, method):
N = 10 ** 5
arr = (100 * np.random.random(N)).astype(dtype)
index = pd.date_range("2017-01-01", periods=N, freq="5s")
self.roll = getattr(pd, constructor)(arr, index=index).rolling(window)
class Pairwise:
params = ([10, 1000, None], ["corr", "cov"], [True, False])
param_names = ["window", "method", "pairwise"]
def setup(self, window, method, pairwise):
N = 10 ** 4
arr = np.random.random(N)
self.df = pd.DataFrame(arr)
def time_pairwise(self, window, method, pairwise):
if window is None:
r = self.df.expanding()
else:
r = self.df.rolling(window=window)
getattr(r, method)(self.df, pairwise=pairwise)
class Quantile:
params = (
["DataFrame", "Series"],
[10, 1000],
["int", "float"],
[0, 0.5, 1],
["linear", "nearest", "lower", "higher", "midpoint"],
)
param_names = ["constructor", "window", "dtype", "percentile"]
def setup(self, constructor, window, dtype, percentile, interpolation):
N = 10 ** 5
arr = np.random.random(N).astype(dtype)
self.roll = getattr(pd, constructor)(arr).rolling(window)
def time_quantile(self, constructor, window, dtype, percentile, interpolation):
self.roll.quantile(percentile, interpolation=interpolation)
class PeakMemFixedWindowMinMax:
params = ["min", "max"]
def setup(self, operation):
N = int(1e6)
arr = np.random.random(N)
self.roll = pd.Series(arr).rolling(2)
def peakmem_fixed(self, operation):
for x in range(5):
getattr(self.roll, operation)()
class ForwardWindowMethods:
params = (
["DataFrame", "Series"],
[10, 1000],
["int", "float"],
["median", "mean", "max", "min", "kurt", "sum"],
)
param_names = ["constructor", "window_size", "dtype", "method"]
def setup(self, constructor, window_size, dtype, method):
N = 10 ** 5
arr = np.random.random(N).astype(dtype)
indexer = pd.api.indexers.FixedForwardWindowIndexer(window_size=window_size)
self.roll = getattr(pd, constructor)(arr).rolling(window=indexer)
def time_rolling(self, constructor, window_size, dtype, method):
getattr(self.roll, method)()
def peakmem_rolling(self, constructor, window_size, dtype, method):
getattr(self.roll, method)()
class Groupby:
params = ["sum", "median", "mean", "max", "min", "kurt", "sum"]
def setup(self, method):
N = 1000
df = pd.DataFrame(
{
"A": [str(i) for i in range(N)] * 10,
"B": list(range(N)) * 10,
"C": pd.date_range(start="1900-01-01", freq="1min", periods=N * 10),
}
)
self.groupby_roll_int = df.groupby("A").rolling(window=2)
self.groupby_roll_offset = df.groupby("A").rolling(window="30s", on="C")
def time_rolling_int(self, method):
getattr(self.groupby_roll_int, method)()
def time_rolling_offset(self, method):
getattr(self.groupby_roll_offset, method)()
class GroupbyLargeGroups:
# https://github.com/pandas-dev/pandas/issues/38038
# specific example where the rolling operation on a larger dataframe
# is relatively cheap (few but large groups), but creation of
# MultiIndex of result can be expensive
def setup(self):
N = 100000
self.df = pd.DataFrame({"A": [1, 2] * int(N / 2), "B": np.random.randn(N)})
def time_rolling_multiindex_creation(self):
self.df.groupby("A").rolling(3).mean()
from .pandas_vb_common import setup # noqa: F401 isort:skip
|
