forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
indexing.py
371 lines (256 loc) · 10.1 KB
/
indexing.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
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
import warnings
import numpy as np
import pandas.util.testing as tm
from pandas import (Series, DataFrame, Panel, MultiIndex, Int64Index,
Float64Index, IntervalIndex, CategoricalIndex,
IndexSlice, concat, date_range)
class NumericSeriesIndexing(object):
goal_time = 0.2
params = [
(Int64Index, Float64Index),
('unique_monotonic_inc', 'nonunique_monotonic_inc'),
]
param_names = ['index_dtype', 'index_structure']
def setup(self, index, index_structure):
N = 10**6
indices = {
'unique_monotonic_inc': index(range(N)),
'nonunique_monotonic_inc': index(
list(range(55)) + [54] + list(range(55, N - 1))),
}
self.data = Series(np.random.rand(N), index=indices[index_structure])
self.array = np.arange(10000)
self.array_list = self.array.tolist()
def time_getitem_scalar(self, index, index_structure):
self.data[800000]
def time_getitem_slice(self, index, index_structure):
self.data[:800000]
def time_getitem_list_like(self, index, index_structure):
self.data[[800000]]
def time_getitem_array(self, index, index_structure):
self.data[self.array]
def time_getitem_lists(self, index, index_structure):
self.data[self.array_list]
def time_iloc_array(self, index, index_structure):
self.data.iloc[self.array]
def time_iloc_list_like(self, index, index_structure):
self.data.iloc[[800000]]
def time_iloc_scalar(self, index, index_structure):
self.data.iloc[800000]
def time_iloc_slice(self, index, index_structure):
self.data.iloc[:800000]
def time_ix_array(self, index, index_structure):
self.data.ix[self.array]
def time_ix_list_like(self, index, index_structure):
self.data.ix[[800000]]
def time_ix_scalar(self, index, index_structure):
self.data.ix[800000]
def time_ix_slice(self, index, index_structure):
self.data.ix[:800000]
def time_loc_array(self, index, index_structure):
self.data.loc[self.array]
def time_loc_list_like(self, index, index_structure):
self.data.loc[[800000]]
def time_loc_scalar(self, index, index_structure):
self.data.loc[800000]
def time_loc_slice(self, index, index_structure):
self.data.loc[:800000]
class NonNumericSeriesIndexing(object):
goal_time = 0.2
params = [
('string', 'datetime'),
('unique_monotonic_inc', 'nonunique_monotonic_inc'),
]
param_names = ['index_dtype', 'index_structure']
def setup(self, index, index_structure):
N = 10**6
indexes = {'string': tm.makeStringIndex(N),
'datetime': date_range('1900', periods=N, freq='s')}
index = indexes[index]
if index_structure == 'nonunique_monotonic_inc':
index = index.insert(item=index[2], loc=2)[:-1]
self.s = Series(np.random.rand(N), index=index)
self.lbl = index[80000]
def time_getitem_label_slice(self, index, index_structure):
self.s[:self.lbl]
def time_getitem_pos_slice(self, index, index_structure):
self.s[:80000]
def time_get_value(self, index, index_structure):
with warnings.catch_warnings(record=True):
self.s.get_value(self.lbl)
def time_getitem_scalar(self, index, index_structure):
self.s[self.lbl]
def time_getitem_list_like(self, index, index_structure):
self.s[[self.lbl]]
class DataFrameStringIndexing(object):
goal_time = 0.2
def setup(self):
index = tm.makeStringIndex(1000)
columns = tm.makeStringIndex(30)
self.df = DataFrame(np.random.randn(1000, 30), index=index,
columns=columns)
self.idx_scalar = index[100]
self.col_scalar = columns[10]
self.bool_indexer = self.df[self.col_scalar] > 0
self.bool_obj_indexer = self.bool_indexer.astype(object)
def time_get_value(self):
with warnings.catch_warnings(record=True):
self.df.get_value(self.idx_scalar, self.col_scalar)
def time_ix(self):
self.df.ix[self.idx_scalar, self.col_scalar]
def time_loc(self):
self.df.loc[self.idx_scalar, self.col_scalar]
def time_getitem_scalar(self):
self.df[self.col_scalar][self.idx_scalar]
def time_boolean_rows(self):
self.df[self.bool_indexer]
def time_boolean_rows_object(self):
self.df[self.bool_obj_indexer]
class DataFrameNumericIndexing(object):
goal_time = 0.2
def setup(self):
self.idx_dupe = np.array(range(30)) * 99
self.df = DataFrame(np.random.randn(10000, 5))
self.df_dup = concat([self.df, 2 * self.df, 3 * self.df])
self.bool_indexer = [True] * 5000 + [False] * 5000
def time_iloc_dups(self):
self.df_dup.iloc[self.idx_dupe]
def time_loc_dups(self):
self.df_dup.loc[self.idx_dupe]
def time_iloc(self):
self.df.iloc[:100, 0]
def time_loc(self):
self.df.loc[:100, 0]
def time_bool_indexer(self):
self.df[self.bool_indexer]
class Take(object):
goal_time = 0.2
params = ['int', 'datetime']
param_names = ['index']
def setup(self, index):
N = 100000
indexes = {'int': Int64Index(np.arange(N)),
'datetime': date_range('2011-01-01', freq='S', periods=N)}
index = indexes[index]
self.s = Series(np.random.rand(N), index=index)
self.indexer = [True, False, True, True, False] * 20000
def time_take(self, index):
self.s.take(self.indexer)
class MultiIndexing(object):
goal_time = 0.2
def setup(self):
mi = MultiIndex.from_product([range(1000), range(1000)])
self.s = Series(np.random.randn(1000000), index=mi)
self.df = DataFrame(self.s)
n = 100000
self.mdt = DataFrame({'A': np.random.choice(range(10000, 45000, 1000),
n),
'B': np.random.choice(range(10, 400), n),
'C': np.random.choice(range(1, 150), n),
'D': np.random.choice(range(10000, 45000), n),
'x': np.random.choice(range(400), n),
'y': np.random.choice(range(25), n)})
self.idx = IndexSlice[20000:30000, 20:30, 35:45, 30000:40000]
self.mdt = self.mdt.set_index(['A', 'B', 'C', 'D']).sort_index()
def time_series_ix(self):
self.s.ix[999]
def time_frame_ix(self):
self.df.ix[999]
def time_index_slice(self):
self.mdt.loc[self.idx, :]
class IntervalIndexing(object):
goal_time = 0.2
def setup_cache(self):
idx = IntervalIndex.from_breaks(np.arange(1000001))
monotonic = Series(np.arange(1000000), index=idx)
return monotonic
def time_getitem_scalar(self, monotonic):
monotonic[80000]
def time_loc_scalar(self, monotonic):
monotonic.loc[80000]
def time_getitem_list(self, monotonic):
monotonic[80000:]
def time_loc_list(self, monotonic):
monotonic.loc[80000:]
class CategoricalIndexIndexing(object):
goal_time = 0.2
params = ['monotonic_incr', 'monotonic_decr', 'non_monotonic']
param_names = ['index']
def setup(self, index):
N = 10**5
values = list('a' * N + 'b' * N + 'c' * N)
indices = {
'monotonic_incr': CategoricalIndex(values),
'monotonic_decr': CategoricalIndex(reversed(values)),
'non_monotonic': CategoricalIndex(list('abc' * N))}
self.data = indices[index]
self.int_scalar = 10000
self.int_list = list(range(10000))
self.cat_scalar = 'b'
self.cat_list = ['a', 'c']
def time_getitem_scalar(self, index):
self.data[self.int_scalar]
def time_getitem_slice(self, index):
self.data[:self.int_scalar]
def time_getitem_list_like(self, index):
self.data[[self.int_scalar]]
def time_getitem_list(self, index):
self.data[self.int_list]
def time_getitem_bool_array(self, index):
self.data[self.data == self.cat_scalar]
def time_get_loc_scalar(self, index):
self.data.get_loc(self.cat_scalar)
def time_get_indexer_list(self, index):
self.data.get_indexer(self.cat_list)
class PanelIndexing(object):
goal_time = 0.2
def setup(self):
with warnings.catch_warnings(record=True):
self.p = Panel(np.random.randn(100, 100, 100))
self.inds = range(0, 100, 10)
def time_subset(self):
with warnings.catch_warnings(record=True):
self.p.ix[(self.inds, self.inds, self.inds)]
class MethodLookup(object):
goal_time = 0.2
def setup_cache(self):
s = Series()
return s
def time_lookup_iloc(self, s):
s.iloc
def time_lookup_ix(self, s):
s.ix
def time_lookup_loc(self, s):
s.loc
class GetItemSingleColumn(object):
goal_time = 0.2
def setup(self):
self.df_string_col = DataFrame(np.random.randn(3000, 1), columns=['A'])
self.df_int_col = DataFrame(np.random.randn(3000, 1))
def time_frame_getitem_single_column_label(self):
self.df_string_col['A']
def time_frame_getitem_single_column_int(self):
self.df_int_col[0]
class AssignTimeseriesIndex(object):
goal_time = 0.2
def setup(self):
N = 100000
idx = date_range('1/1/2000', periods=N, freq='H')
self.df = DataFrame(np.random.randn(N, 1), columns=['A'], index=idx)
def time_frame_assign_timeseries_index(self):
self.df['date'] = self.df.index
class InsertColumns(object):
goal_time = 0.2
def setup(self):
self.N = 10**3
self.df = DataFrame(index=range(self.N))
def time_insert(self):
np.random.seed(1234)
for i in range(100):
self.df.insert(0, i, np.random.randn(self.N),
allow_duplicates=True)
def time_assign_with_setitem(self):
np.random.seed(1234)
for i in range(100):
self.df[i] = np.random.randn(self.N)
from .pandas_vb_common import setup # noqa: F401