forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathindex_object.py
347 lines (235 loc) · 9.33 KB
/
index_object.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
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
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
from .pandas_vb_common import *
class datetime_index_intersection(object):
goal_time = 0.2
def setup(self):
self.rng = date_range('1/1/2000', periods=10000, freq='T')
self.rng2 = self.rng[:(-1)]
def time_datetime_index_intersection(self):
self.rng.intersection(self.rng2)
class datetime_index_repr(object):
goal_time = 0.2
def setup(self):
self.dr = pd.date_range('20000101', freq='D', periods=100000)
def time_datetime_index_repr(self):
self.dr._is_dates_only
class datetime_index_union(object):
goal_time = 0.2
def setup(self):
self.rng = date_range('1/1/2000', periods=10000, freq='T')
self.rng2 = self.rng[:(-1)]
def time_datetime_index_union(self):
self.rng.union(self.rng2)
class index_datetime_intersection(object):
goal_time = 0.2
def setup(self):
self.rng = DatetimeIndex(start='1/1/2000', periods=10000, freq=datetools.Minute())
if (self.rng.dtype == object):
self.rng = self.rng.view(Index)
else:
self.rng = self.rng.asobject
self.rng2 = self.rng[:(-1)]
def time_index_datetime_intersection(self):
self.rng.intersection(self.rng2)
class index_datetime_union(object):
goal_time = 0.2
def setup(self):
self.rng = DatetimeIndex(start='1/1/2000', periods=10000, freq=datetools.Minute())
if (self.rng.dtype == object):
self.rng = self.rng.view(Index)
else:
self.rng = self.rng.asobject
self.rng2 = self.rng[:(-1)]
def time_index_datetime_union(self):
self.rng.union(self.rng2)
class index_datetime_set_difference(object):
goal_time = 0.2
def setup(self):
self.N = 100000
self.A = self.N - 20000
self.B = self.N + 20000
self.idx1 = DatetimeIndex(range(self.N))
self.idx2 = DatetimeIndex(range(self.A, self.B))
self.idx3 = DatetimeIndex(range(self.N, self.B))
def time_index_datetime_difference(self):
self.idx1.difference(self.idx2)
def time_index_datetime_difference_disjoint(self):
self.idx1.difference(self.idx3)
def time_index_datetime_symmetric_difference(self):
self.idx1.symmetric_difference(self.idx2)
class index_float64_boolean_indexer(object):
goal_time = 0.2
def setup(self):
self.idx = tm.makeFloatIndex(1000000)
self.mask = ((np.arange(self.idx.size) % 3) == 0)
self.series_mask = Series(self.mask)
def time_index_float64_boolean_indexer(self):
self.idx[self.mask]
class index_float64_boolean_series_indexer(object):
goal_time = 0.2
def setup(self):
self.idx = tm.makeFloatIndex(1000000)
self.mask = ((np.arange(self.idx.size) % 3) == 0)
self.series_mask = Series(self.mask)
def time_index_float64_boolean_series_indexer(self):
self.idx[self.series_mask]
class index_float64_construct(object):
goal_time = 0.2
def setup(self):
self.baseidx = np.arange(1000000.0)
def time_index_float64_construct(self):
Index(self.baseidx)
class index_float64_div(object):
goal_time = 0.2
def setup(self):
self.idx = tm.makeFloatIndex(1000000)
self.mask = ((np.arange(self.idx.size) % 3) == 0)
self.series_mask = Series(self.mask)
def time_index_float64_div(self):
(self.idx / 2)
class index_float64_get(object):
goal_time = 0.2
def setup(self):
self.idx = tm.makeFloatIndex(1000000)
self.mask = ((np.arange(self.idx.size) % 3) == 0)
self.series_mask = Series(self.mask)
def time_index_float64_get(self):
self.idx[1]
class index_float64_mul(object):
goal_time = 0.2
def setup(self):
self.idx = tm.makeFloatIndex(1000000)
self.mask = ((np.arange(self.idx.size) % 3) == 0)
self.series_mask = Series(self.mask)
def time_index_float64_mul(self):
(self.idx * 2)
class index_float64_slice_indexer_basic(object):
goal_time = 0.2
def setup(self):
self.idx = tm.makeFloatIndex(1000000)
self.mask = ((np.arange(self.idx.size) % 3) == 0)
self.series_mask = Series(self.mask)
def time_index_float64_slice_indexer_basic(self):
self.idx[:(-1)]
class index_float64_slice_indexer_even(object):
goal_time = 0.2
def setup(self):
self.idx = tm.makeFloatIndex(1000000)
self.mask = ((np.arange(self.idx.size) % 3) == 0)
self.series_mask = Series(self.mask)
def time_index_float64_slice_indexer_even(self):
self.idx[::2]
class index_int64_intersection(object):
goal_time = 0.2
def setup(self):
self.N = 1000000
self.options = np.arange(self.N)
self.left = Index(self.options.take(np.random.permutation(self.N)[:(self.N // 2)]))
self.right = Index(self.options.take(np.random.permutation(self.N)[:(self.N // 2)]))
def time_index_int64_intersection(self):
self.left.intersection(self.right)
class index_int64_union(object):
goal_time = 0.2
def setup(self):
self.N = 1000000
self.options = np.arange(self.N)
self.left = Index(self.options.take(np.random.permutation(self.N)[:(self.N // 2)]))
self.right = Index(self.options.take(np.random.permutation(self.N)[:(self.N // 2)]))
def time_index_int64_union(self):
self.left.union(self.right)
class index_int64_set_difference(object):
goal_time = 0.2
def setup(self):
self.N = 500000
self.options = np.arange(self.N)
self.left = Index(self.options.take(
np.random.permutation(self.N)[:(self.N // 2)]))
self.right = Index(self.options.take(
np.random.permutation(self.N)[:(self.N // 2)]))
def time_index_int64_difference(self):
self.left.difference(self.right)
def time_index_int64_symmetric_difference(self):
self.left.symmetric_difference(self.right)
class index_str_set_difference(object):
goal_time = 0.2
def setup(self):
self.N = 10000
self.strs = tm.rands_array(10, self.N)
self.left = Index(self.strs[:self.N * 2 // 3])
self.right = Index(self.strs[self.N // 3:])
def time_str_difference(self):
self.left.difference(self.right)
def time_str_symmetric_difference(self):
self.left.symmetric_difference(self.right)
class index_str_boolean_indexer(object):
goal_time = 0.2
def setup(self):
self.idx = tm.makeStringIndex(1000000)
self.mask = ((np.arange(1000000) % 3) == 0)
self.series_mask = Series(self.mask)
def time_index_str_boolean_indexer(self):
self.idx[self.mask]
class index_str_boolean_series_indexer(object):
goal_time = 0.2
def setup(self):
self.idx = tm.makeStringIndex(1000000)
self.mask = ((np.arange(1000000) % 3) == 0)
self.series_mask = Series(self.mask)
def time_index_str_boolean_series_indexer(self):
self.idx[self.series_mask]
class index_str_slice_indexer_basic(object):
goal_time = 0.2
def setup(self):
self.idx = tm.makeStringIndex(1000000)
self.mask = ((np.arange(1000000) % 3) == 0)
self.series_mask = Series(self.mask)
def time_index_str_slice_indexer_basic(self):
self.idx[:(-1)]
class index_str_slice_indexer_even(object):
goal_time = 0.2
def setup(self):
self.idx = tm.makeStringIndex(1000000)
self.mask = ((np.arange(1000000) % 3) == 0)
self.series_mask = Series(self.mask)
def time_index_str_slice_indexer_even(self):
self.idx[::2]
class multiindex_duplicated(object):
goal_time = 0.2
def setup(self):
(n, k) = (200, 5000)
self.levels = [np.arange(n), tm.makeStringIndex(n).values, (1000 + np.arange(n))]
self.labels = [np.random.choice(n, (k * n)) for lev in self.levels]
self.mi = MultiIndex(levels=self.levels, labels=self.labels)
def time_multiindex_duplicated(self):
self.mi.duplicated()
class multiindex_from_product(object):
goal_time = 0.2
def setup(self):
self.iterables = [tm.makeStringIndex(10000), range(20)]
def time_multiindex_from_product(self):
MultiIndex.from_product(self.iterables)
class multiindex_sortlevel_int64(object):
goal_time = 0.2
def setup(self):
self.n = ((((3 * 5) * 7) * 11) * (1 << 10))
(low, high) = (((-1) << 12), (1 << 12))
self.f = (lambda k: np.repeat(np.random.randint(low, high, (self.n // k)), k))
self.i = np.random.permutation(self.n)
self.mi = MultiIndex.from_arrays([self.f(11), self.f(7), self.f(5), self.f(3), self.f(1)])[self.i]
def time_multiindex_sortlevel_int64(self):
self.mi.sortlevel()
class multiindex_with_datetime_level_full(object):
goal_time = 0.2
def setup(self):
self.level1 = range(1000)
self.level2 = date_range(start='1/1/2012', periods=100)
self.mi = MultiIndex.from_product([self.level1, self.level2])
def time_multiindex_with_datetime_level_full(self):
self.mi.copy().values
class multiindex_with_datetime_level_sliced(object):
goal_time = 0.2
def setup(self):
self.level1 = range(1000)
self.level2 = date_range(start='1/1/2012', periods=100)
self.mi = MultiIndex.from_product([self.level1, self.level2])
def time_multiindex_with_datetime_level_sliced(self):
self.mi[:10].values