/
_single_problem_loaders.py
1438 lines (1231 loc) · 54 KB
/
_single_problem_loaders.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
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"""Utilities for loading datasets."""
__author__ = [
"mloning",
"sajaysurya",
"big-o",
"SebasKoel",
"Emiliathewolf",
"TonyBagnall",
"yairbeer",
"patrickZIB",
"aiwalter",
"jasonlines",
"achieveordie",
"ciaran-g",
"jonathanbechtel",
]
__all__ = [
"load_airline",
"load_plaid",
"load_arrow_head",
"load_gunpoint",
"load_osuleaf",
"load_italy_power_demand",
"load_basic_motions",
"load_japanese_vowels",
"load_solar",
"load_shampoo_sales",
"load_longley",
"load_lynx",
"load_acsf1",
"load_unit_test",
"load_uschange",
"load_UCR_UEA_dataset",
"load_PBS_dataset",
"load_gun_point_segmentation",
"load_electric_devices_segmentation",
"load_macroeconomic",
"load_unit_test_tsf",
"load_covid_3month",
"load_tecator",
]
import os
import zipfile
from urllib.error import HTTPError, URLError
from warnings import warn
import numpy as np
import pandas as pd
from sktime.datasets._data_io import (
_download_and_extract,
_list_available_datasets,
_load_dataset,
_load_provided_dataset,
)
from sktime.datasets._readers_writers.tsf import load_tsf_to_dataframe
from sktime.datasets.tsf_dataset_names import tsf_all, tsf_all_datasets
from sktime.utils.validation._dependencies import _check_soft_dependencies
DIRNAME = "data"
MODULE = os.path.dirname(__file__)
def load_UCR_UEA_dataset(
name, split=None, return_X_y=True, return_type=None, extract_path=None
):
"""Load dataset from UCR UEA time series archive.
Downloads and extracts dataset if not already downloaded. Data is assumed to be
in the standard .ts format: each row is a (possibly multivariate) time series.
Each dimension is separated by a colon, each value in a series is comma
separated. For examples see sktime.datasets.data.tsc. ArrowHead is an example of
a univariate equal length problem, BasicMotions an equal length multivariate
problem.
Parameters
----------
name : str
Name of data set. If a dataset that is listed in tsc_dataset_names is given,
this function will look in the extract_path first, and if it is not present,
attempt to download the data from www.timeseriesclassification.com, saving it to
the extract_path.
split : None or str{"train", "test"}, optional (default=None)
Whether to load the train or test partition of the problem. By default it
loads both into a single dataset, otherwise it looks only for files of the
format <name>_TRAIN.ts or <name>_TEST.ts.
return_X_y : bool, optional (default=False)
it returns two objects, if False, it appends the class labels to the dataframe.
return_type: valid Panel mtype str or None, optional (default=None="nested_univ")
Memory data format specification to return X in, None = "nested_univ" type.
str can be any supported sktime Panel mtype,
for list of mtypes, see datatypes.MTYPE_REGISTER
for specifications, see examples/AA_datatypes_and_datasets.ipynb
commonly used specifications:
"nested_univ: nested pd.DataFrame, pd.Series in cells
"numpy3D"/"numpy3d"/"np3D": 3D np.ndarray (instance, variable, time index)
"numpy2d"/"np2d"/"numpyflat": 2D np.ndarray (instance, time index)
"pd-multiindex": pd.DataFrame with 2-level (instance, time) MultiIndex
Exception is raised if the data cannot be stored in the requested type.
extract_path : str, optional (default=None)
the path to look for the data. If no path is provided, the function
looks in ``sktime/datasets/data/``. If a path is given, it can be absolute,
e.g. C:/Temp or relative, e.g. Temp or ./Temp.
Returns
-------
X: pd.DataFrame
The time series data for the problem with n_cases rows and either
n_dimensions or n_dimensions+1 columns. Columns 1 to n_dimensions are the
series associated with each case. If return_X_y is False, column
n_dimensions+1 contains the class labels/target variable.
y: numpy array, optional
The class labels for each case in X, returned separately if return_X_y is
True, or appended to X if False
Examples
--------
>>> from sktime.datasets import load_UCR_UEA_dataset
>>> X, y = load_UCR_UEA_dataset(name="ArrowHead")
"""
return _load_dataset(name, split, return_X_y, return_type, extract_path)
def load_tecator(split=None, return_X_y=True, return_type=None):
"""Load the Tecator time series regression problem and returns X and y.
Parameters
----------
split: None or one of "TRAIN", "TEST", optional (default=None)
Whether to load the train or test instances of the problem.
By default it loads both train and test instances (in a single container).
return_X_y: bool, optional (default=True)
If True, returns (features, target) separately instead of a single
dataframe with columns for features and the target.
return_type: valid Panel mtype str or None, optional (default=None="nested_univ")
Memory data format specification to return X in, None = "nested_univ" type.
str can be any supported sktime Panel mtype,
for list of mtypes, see datatypes.MTYPE_REGISTER
for specifications, see examples/AA_datatypes_and_datasets.ipynb
commonly used specifications:
"nested_univ: nested pd.DataFrame, pd.Series in cells
"numpy3D"/"numpy3d"/"np3D": 3D np.ndarray (instance, variable, time index)
"numpy2d"/"np2d"/"numpyflat": 2D np.ndarray (instance, time index)
"pd-multiindex": pd.DataFrame with 2-level (instance, time) MultiIndex
Exception is raised if the data cannot be stored in the requested type.
Returns
-------
X: sktime data container, following mtype specification ``return_type``
The time series data for the problem, with n instances
y: 1D numpy array of length n, only returned if return_X_y if True
The target values for each time series instance in X
If return_X_y is False, y is appended to X instead.
Examples
--------
>>> from sktime.datasets import load_tecator
>>> X, y = load_tecator()
Notes
-----
Dimensionality: univariate
Series length: 100
Train cases: 172
Test cases: 43
The purpose of this dataset is to measure the fat content of meat based off its near
infrared absorbance spectrum.
The absorbance spectrum is measured in the wavelength range of 850 nm to 1050 nm.
The fat content is measured by standard chemical analysis methods.
The dataset contains 215 samples of meat, each with 100 spectral measurements.
For more information see:
https://www.openml.org/search?type=data&sort=runs&id=505&status=active
References
----------
[1] C.Borggaard and H.H.Thodberg, "Optimal Minimal Neural Interpretation of Spectra"
, Analytical Chemistry 64 (1992), p 545-551.
[2] H.H.Thodberg, "Ace of Bayes: Application of Neural Networks with Pruning"
Manuscript 1132, Danish Meat Research Institute (1993), p 1-12.
"""
name = "Tecator"
return _load_dataset(name, split, return_X_y, return_type=return_type)
def load_plaid(split=None, return_X_y=True, return_type=None):
"""Load the PLAID time series classification problem and returns X and y.
Example of a univariate problem with unequal length series.
Parameters
----------
split: None or one of "TRAIN", "TEST", optional (default=None)
Whether to load the train or test instances of the problem.
By default it loads both train and test instances (in a single container).
return_X_y: bool, optional (default=True)
If True, returns (features, target) separately instead of a single
dataframe with columns for features and the target.
return_type: valid Panel mtype str or None, optional (default=None="nested_univ")
Memory data format specification to return X in, None = "nested_univ" type.
str can be any supported sktime Panel mtype,
for list of mtypes, see datatypes.MTYPE_REGISTER
for specifications, see examples/AA_datatypes_and_datasets.ipynb
commonly used specifications:
"nested_univ: nested pd.DataFrame, pd.Series in cells
"numpy3D"/"numpy3d"/"np3D": 3D np.ndarray (instance, variable, time index)
"numpy2d"/"np2d"/"numpyflat": 2D np.ndarray (instance, time index)
"pd-multiindex": pd.DataFrame with 2-level (instance, time) MultiIndex
Exception is raised if the data cannot be stored in the requested type.
Returns
-------
X: sktime data container, following mtype specification ``return_type``
The time series data for the problem, with n instances
y: 1D numpy array of length n, only returned if return_X_y if True
The class labels for each time series instance in X
If return_X_y is False, y is appended to X instead.
Examples
--------
>>> from sktime.datasets import load_plaid
>>> X, y = load_plaid()
"""
name = "PLAID"
return _load_dataset(name, split, return_X_y, return_type=return_type)
def load_gunpoint(split=None, return_X_y=True, return_type=None):
"""Load the GunPoint time series classification problem and returns X and y.
Parameters
----------
split: None or one of "TRAIN", "TEST", optional (default=None)
Whether to load the train or test instances of the problem.
By default it loads both train and test instances (in a single container).
return_X_y: bool, optional (default=True)
If True, returns (features, target) separately instead of a single
dataframe with columns for features and the target.
return_type: valid Panel mtype str or None, optional (default=None="nested_univ")
Memory data format specification to return X in, None = "nested_univ" type.
str can be any supported sktime Panel mtype,
for list of mtypes, see datatypes.MTYPE_REGISTER
for specifications, see examples/AA_datatypes_and_datasets.ipynb
commonly used specifications:
"nested_univ: nested pd.DataFrame, pd.Series in cells
"numpy3D"/"numpy3d"/"np3D": 3D np.ndarray (instance, variable, time index)
"numpy2d"/"np2d"/"numpyflat": 2D np.ndarray (instance, time index)
"pd-multiindex": pd.DataFrame with 2-level (instance, time) MultiIndex
Exception is raised if the data cannot be stored in the requested type.
Returns
-------
X: sktime data container, following mtype specification ``return_type``
The time series data for the problem, with n instances
y: 1D numpy array of length n, only returned if return_X_y if True
The class labels for each time series instance in X
If return_X_y is False, y is appended to X instead.
Examples
--------
>>> from sktime.datasets import load_gunpoint
>>> X, y = load_gunpoint()
Notes
-----
Dimensionality: univariate
Series length: 150
Train cases: 50
Test cases: 150
Number of classes: 2
This dataset involves one female actor and one male actor making a
motion with their
hand. The two classes are: Gun-Draw and Point: For Gun-Draw the actors
have their
hands by their sides. They draw a replicate gun from a hip-mounted
holster, point it
at a target for approximately one second, then return the gun to the
holster, and
their hands to their sides. For Point the actors have their gun by their
sides.
They point with their index fingers to a target for approximately one
second, and
then return their hands to their sides. For both classes, we tracked the
centroid
of the actor's right hands in both X- and Y-axes, which appear to be highly
correlated. The data in the archive is just the X-axis.
Dataset details: http://timeseriesclassification.com/description.php
?Dataset=GunPoint
"""
name = "GunPoint"
return _load_dataset(name, split, return_X_y, return_type=return_type)
def load_osuleaf(split=None, return_X_y=True, return_type=None):
"""Load the OSULeaf time series classification problem and returns X and y.
Parameters
----------
split: None or one of "TRAIN", "TEST", optional (default=None)
Whether to load the train or test instances of the problem.
By default it loads both train and test instances (in a single container).
return_X_y: bool, optional (default=True)
If True, returns (features, target) separately instead of a single
dataframe with columns for features and the target.
return_type: valid Panel mtype str or None, optional (default=None="nested_univ")
Memory data format specification to return X in, None = "nested_univ" type.
str can be any supported sktime Panel mtype,
for list of mtypes, see datatypes.MTYPE_REGISTER
for specifications, see examples/AA_datatypes_and_datasets.ipynb
commonly used specifications:
"nested_univ: nested pd.DataFrame, pd.Series in cells
"numpy3D"/"numpy3d"/"np3D": 3D np.ndarray (instance, variable, time index)
"numpy2d"/"np2d"/"numpyflat": 2D np.ndarray (instance, time index)
"pd-multiindex": pd.DataFrame with 2-level (instance, time) MultiIndex
Exception is raised if the data cannot be stored in the requested type.
Returns
-------
X: sktime data container, following mtype specification ``return_type``
The time series data for the problem, with n instances
y: 1D numpy array of length n, only returned if return_X_y if True
The class labels for each time series instance in X
If return_X_y is False, y is appended to X instead.
Examples
--------
>>> from sktime.datasets import load_osuleaf
>>> X, y = load_osuleaf()
Notes
-----
Dimensionality: univariate
Series length: 427
Train cases: 200
Test cases: 242
Number of classes: 6
The OSULeaf data set consist of one dimensional outlines of leaves.
The series were obtained by color image segmentation and boundary
extraction (in the anti-clockwise direction) from digitized leaf images
of six classes: Acer Circinatum, Acer Glabrum, Acer Macrophyllum,
Acer Negundo, Quercus Garryanaand Quercus Kelloggii for the MSc thesis
"Content-Based Image Retrieval: Plant Species Identification" by A Grandhi.
Dataset details: http://www.timeseriesclassification.com/description.php
?Dataset=OSULeaf
"""
name = "OSULeaf"
return _load_dataset(name, split, return_X_y, return_type=return_type)
def load_italy_power_demand(split=None, return_X_y=True, return_type=None):
"""Load ItalyPowerDemand time series classification problem.
Parameters
----------
split: None or one of "TRAIN", "TEST", optional (default=None)
Whether to load the train or test instances of the problem.
By default it loads both train and test instances (in a single container).
return_X_y: bool, optional (default=True)
If True, returns (features, target) separately instead of a single
dataframe with columns for features and the target.
return_type: valid Panel mtype str or None, optional (default=None="nested_univ")
Memory data format specification to return X in, None = "nested_univ" type.
str can be any supported sktime Panel mtype,
for list of mtypes, see datatypes.MTYPE_REGISTER
for specifications, see examples/AA_datatypes_and_datasets.ipynb
commonly used specifications:
"nested_univ: nested pd.DataFrame, pd.Series in cells
"numpy3D"/"numpy3d"/"np3D": 3D np.ndarray (instance, variable, time index)
"numpy2d"/"np2d"/"numpyflat": 2D np.ndarray (instance, time index)
"pd-multiindex": pd.DataFrame with 2-level (instance, time) MultiIndex
Exception is raised if the data cannot be stored in the requested type.
Returns
-------
X: sktime data container, following mtype specification ``return_type``
The time series data for the problem, with n instances
y: 1D numpy array of length n, only returned if return_X_y if True
The class labels for each time series instance in X
If return_X_y is False, y is appended to X instead.
Examples
--------
>>> from sktime.datasets import load_italy_power_demand
>>> X, y = load_italy_power_demand()
Notes
-----
Dimensionality: univariate
Series length: 24
Train cases: 67
Test cases: 1029
Number of classes: 2
The data was derived from twelve monthly electrical power demand time series from
Italy and first used in the paper "Intelligent Icons: Integrating Lite-Weight Data
Mining and Visualization into GUI Operating Systems". The classification task is to
distinguish days from Oct to March (inclusive) from April to September.
Dataset details:
http://timeseriesclassification.com/description.php?Dataset=ItalyPowerDemand
"""
name = "ItalyPowerDemand"
return _load_dataset(name, split, return_X_y, return_type=return_type)
def load_unit_test(split=None, return_X_y=True, return_type=None):
"""Load UnitTest data.
This is an equal length univariate time series classification problem. It is a
stripped down version of the ChinaTown problem that is used in correctness tests
for classification. It loads a two class classification problem with number of
cases, n, where n = 42 (if split is None) or 20/22 (if split is "train"/"test")
of series length m = 24
Parameters
----------
split: None or one of "TRAIN", "TEST", optional (default=None)
Whether to load the train or test instances of the problem.
By default it loads both train and test instances (in a single container).
return_X_y: bool, optional (default=True)
If True, returns (features, target) separately instead of a single
dataframe with columns for features and the target.
return_type: valid Panel mtype str or None, optional (default=None="nested_univ")
Memory data format specification to return X in, None = "nested_univ" type.
str can be any supported sktime Panel mtype,
for list of mtypes, see datatypes.MTYPE_REGISTER
for specifications, see examples/AA_datatypes_and_datasets.ipynb
commonly used specifications:
"nested_univ: nested pd.DataFrame, pd.Series in cells
"numpy3D"/"numpy3d"/"np3D": 3D np.ndarray (instance, variable, time index)
"numpy2d"/"np2d"/"numpyflat": 2D np.ndarray (instance, time index)
"pd-multiindex": pd.DataFrame with 2-level (instance, time) MultiIndex
Exception is raised if the data cannot be stored in the requested type.
Returns
-------
X: The time series data for the problem. If return_type is either
"numpy2d"/"numpyflat", it returns 2D numpy array of shape (n,m), if "numpy3d" it
returns 3D numpy array of shape (n,1,m) and if "nested_univ" or None it returns
a nested pandas DataFrame of shape (n,1), where each cell is a pd.Series of
length m.
y: (optional) numpy array shape (n,1). The class labels for each case in X.
If return_X_y is False, y is appended to X.
Examples
--------
>>> from sktime.datasets import load_unit_test
>>> X, y = load_unit_test()
Details
-------
This is the Chinatown problem with a smaller test set, useful for rapid tests.
Dimensionality: univariate
Series length: 24
Train cases: 20
Test cases: 22 (full dataset has 345)
Number of classes: 2
See
http://timeseriesclassification.com/description.php?Dataset=Chinatown
for the full dataset
"""
name = "UnitTest"
return _load_provided_dataset(name, split, return_X_y, return_type)
def load_japanese_vowels(split=None, return_X_y=True, return_type=None):
"""Load the JapaneseVowels time series classification problem.
Example of a multivariate problem with unequal length series.
Parameters
----------
split: None or one of "TRAIN", "TEST", optional (default=None)
Whether to load the train or test instances of the problem.
By default it loads both train and test instances (in a single container).
return_X_y: bool, optional (default=True)
If True, returns (features, target) separately instead of a single
dataframe with columns for features and the target.
return_type: valid Panel mtype str or None, optional (default=None="nested_univ")
Memory data format specification to return X in, None = "nested_univ" type.
str can be any supported sktime Panel mtype,
for list of mtypes, see datatypes.MTYPE_REGISTER
for specifications, see examples/AA_datatypes_and_datasets.ipynb
commonly used specifications:
"nested_univ: nested pd.DataFrame, pd.Series in cells
"numpy3D"/"numpy3d"/"np3D": 3D np.ndarray (instance, variable, time index)
"numpy2d"/"np2d"/"numpyflat": 2D np.ndarray (instance, time index)
"pd-multiindex": pd.DataFrame with 2-level (instance, time) MultiIndex
Exception is raised if the data cannot be stored in the requested type.
Returns
-------
X: pd.DataFrame with m rows and c columns
The time series data for the problem with m cases and c dimensions
y: numpy array
The class labels for each case in X
Examples
--------
>>> from sktime.datasets import load_japanese_vowels
>>> X, y = load_japanese_vowels()
Notes
-----
Dimensionality: multivariate, 12
Series length: 7-29
Train cases: 270
Test cases: 370
Number of classes: 9
A UCI Archive dataset. 9 Japanese-male speakers were recorded saying
the vowels 'a' and 'e'. A '12-degree
linear prediction analysis' is applied to the raw recordings to
obtain time-series with 12 dimensions and series lengths between 7 and 29.
The classification task is to predict the speaker. Therefore,
each instance is a transformed utterance,
12*29 values with a single class label attached, [1...9]. The given
training set is comprised of 30
utterances for each speaker, however the test set has a varied
distribution based on external factors of
timing and experimental availability, between 24 and 88 instances per
speaker. Reference: M. Kudo, J. Toyama
and M. Shimbo. (1999). "Multidimensional Curve Classification Using
Passing-Through Regions". Pattern
Recognition Letters, Vol. 20, No. 11--13, pages 1103--1111.
Dataset details: http://timeseriesclassification.com/description.php
?Dataset=JapaneseVowels
"""
name = "JapaneseVowels"
return _load_dataset(name, split, return_X_y, return_type=return_type)
def load_arrow_head(split=None, return_X_y=True, return_type=None):
"""Load the ArrowHead time series classification problem and returns X and y.
Parameters
----------
split: None or one of "TRAIN", "TEST", optional (default=None)
Whether to load the train or test instances of the problem.
By default it loads both train and test instances (in a single container).
return_X_y: bool, optional (default=True)
If True, returns (features, target) separately instead of a single
dataframe with columns for features and the target.
return_type: valid Panel mtype str or None, optional (default=None="nested_univ")
Memory data format specification to return X in, None = "nested_univ" type.
str can be any supported sktime Panel mtype,
for list of mtypes, see datatypes.MTYPE_REGISTER
for specifications, see examples/AA_datatypes_and_datasets.ipynb
commonly used specifications:
"nested_univ: nested pd.DataFrame, pd.Series in cells
"numpy3D"/"numpy3d"/"np3D": 3D np.ndarray (instance, variable, time index)
"numpy2d"/"np2d"/"numpyflat": 2D np.ndarray (instance, time index)
"pd-multiindex": pd.DataFrame with 2-level (instance, time) MultiIndex
Exception is raised if the data cannot be stored in the requested type.
Returns
-------
X: sktime data container, following mtype specification ``return_type``
The time series data for the problem, with n instances
y: 1D numpy array of length n, only returned if return_X_y if True
The class labels for each time series instance in X
If return_X_y is False, y is appended to X instead.
Examples
--------
>>> from sktime.datasets import load_arrow_head
>>> X, y = load_arrow_head()
Notes
-----
Dimensionality: univariate
Series length: 251
Train cases: 36
Test cases: 175
Number of classes: 3
The arrowhead data consists of outlines of the images of arrowheads. The
shapes of the
projectile points are converted into a time series using the angle-based
method. The
classification of projectile points is an important topic in
anthropology. The classes
are based on shape distinctions such as the presence and location of a
notch in the
arrow. The problem in the repository is a length normalised version of
that used in
Ye09shapelets. The three classes are called "Avonlea", "Clovis" and "Mix"."
Dataset details: http://timeseriesclassification.com/description.php
?Dataset=ArrowHead
"""
name = "ArrowHead"
return _load_provided_dataset(
name=name, split=split, return_X_y=return_X_y, return_type=return_type
)
def load_acsf1(split=None, return_X_y=True, return_type=None):
"""Load dataset on power consumption of typical appliances.
Parameters
----------
split: None or one of "TRAIN", "TEST", optional (default=None)
Whether to load the train or test instances of the problem.
By default it loads both train and test instances (in a single container).
return_X_y: bool, optional (default=True)
If True, returns (features, target) separately instead of a single
dataframe with columns for features and the target.
return_type: valid Panel mtype str or None, optional (default=None="nested_univ")
Memory data format specification to return X in, None = "nested_univ" type.
str can be any supported sktime Panel mtype,
for list of mtypes, see datatypes.MTYPE_REGISTER
for specifications, see examples/AA_datatypes_and_datasets.ipynb
commonly used specifications:
"nested_univ: nested pd.DataFrame, pd.Series in cells
"numpy3D"/"numpy3d"/"np3D": 3D np.ndarray (instance, variable, time index)
"numpy2d"/"np2d"/"numpyflat": 2D np.ndarray (instance, time index)
"pd-multiindex": pd.DataFrame with 2-level (instance, time) MultiIndex
Exception is raised if the data cannot be stored in the requested type.
Returns
-------
X: sktime data container, following mtype specification ``return_type``
The time series data for the problem, with n instances
y: 1D numpy array of length n, only returned if return_X_y if True
The class labels for each time series instance in X
If return_X_y is False, y is appended to X instead.
Examples
--------
>>> from sktime.datasets import load_acsf1
>>> X, y = load_acsf1()
Notes
-----
Dimensionality: univariate
Series length: 1460
Train cases: 100
Test cases: 100
Number of classes: 10
The dataset contains the power consumption of typical appliances.
The recordings are characterized by long idle periods and some high bursts
of energy consumption when the appliance is active.
The classes correspond to 10 categories of home appliances;
mobile phones (via chargers), coffee machines, computer stations
(including monitor), fridges and freezers, Hi-Fi systems (CD players),
lamp (CFL), laptops (via chargers), microwave ovens, printers, and
televisions (LCD or LED)."
Dataset details: http://www.timeseriesclassification.com/description.php?Dataset
=ACSF1
"""
name = "ACSF1"
return _load_dataset(name, split, return_X_y, return_type=return_type)
def load_basic_motions(split=None, return_X_y=True, return_type=None):
"""Load the BasicMotions time series classification problem and returns X and y.
This is an equal length multivariate time series classification problem. It loads a
4 class classification problem with number of cases, n, where n = 80 (if
split is None) or 40 (if split is "train"/"test") of series length m = 100.
Parameters
----------
split: None or one of "TRAIN", "TEST", optional (default=None)
Whether to load the train or test instances of the problem.
By default it loads both train and test instances (in a single container).
return_X_y: bool, optional (default=True)
If True, returns (features, target) separately instead of a single
dataframe with columns for features and the target.
return_type: valid Panel mtype str or None, optional (default=None="nested_univ")
Memory data format specification to return X in, None = "nested_univ" type.
str can be any supported sktime Panel mtype,
for list of mtypes, see datatypes.MTYPE_REGISTER
for specifications, see examples/AA_datatypes_and_datasets.ipynb
commonly used specifications:
"nested_univ: nested pd.DataFrame, pd.Series in cells
"numpy3D"/"numpy3d"/"np3D": 3D np.ndarray (instance, variable, time index)
"numpy2d"/"np2d"/"numpyflat": 2D np.ndarray (instance, time index)
"pd-multiindex": pd.DataFrame with 2-level (instance, time) MultiIndex
Exception is raised if the data cannot be stored in the requested type.
Returns
-------
X: sktime data container, following mtype specification ``return_type``
The time series data for the problem, with n instances
y: 1D numpy array of length n, only returned if return_X_y if True
The class labels for each time series instance in X
If return_X_y is False, y is appended to X instead.
Raises
------
ValueError if argument "numpy2d"/"numpyflat" is passed as return_type
Notes
-----
Dimensionality: multivariate, 6
Series length: 100
Train cases: 40
Test cases: 40
Number of classes: 4
The data was generated as part of a student project where four students performed
four activities whilst wearing a smart watch. The watch collects 3D accelerometer
and a 3D gyroscope It consists of four classes, which are walking, resting,
running and badminton. Participants were required to record motion a total of
five times, and the data is sampled once every tenth of a second, for a ten second
period.
Dataset details: http://www.timeseriesclassification.com/description.php?Dataset
=BasicMotions
"""
name = "BasicMotions"
if return_type == "numpy2d" or return_type == "numpyflat":
raise ValueError(
f"{name} loader: Error, attempting to load into a numpy2d "
f"array, but cannot because it is a multivariate problem. Use "
f"numpy3d instead"
)
return _load_provided_dataset(
name=name, split=split, return_X_y=return_X_y, return_type=return_type
)
# forecasting data sets
def load_shampoo_sales():
"""Load the shampoo sales univariate time series dataset for forecasting.
Returns
-------
y : pd.Series/DataFrame
Shampoo sales dataset
Examples
--------
>>> from sktime.datasets import load_shampoo_sales
>>> y = load_shampoo_sales()
Notes
-----
This dataset describes the monthly number of sales of shampoo over a 3
year period.
The units are a sales count.
Dimensionality: univariate
Series length: 36
Frequency: Monthly
Number of cases: 1
References
----------
.. [1] Makridakis, Wheelwright and Hyndman (1998) Forecasting: methods
and applications,
John Wiley & Sons: New York. Chapter 3.
"""
name = "ShampooSales"
fname = name + ".csv"
path = os.path.join(MODULE, DIRNAME, name, fname)
y = pd.read_csv(path, index_col=0, dtype={1: float}).squeeze("columns")
y.index = pd.PeriodIndex(y.index, freq="M", name="Period")
y.name = "Number of shampoo sales"
return y
def load_longley(y_name="TOTEMP"):
"""Load the Longley dataset for forecasting with exogenous variables.
Parameters
----------
y_name: str, optional (default="TOTEMP")
Name of target variable (y)
Returns
-------
y: pd.Series
The target series to be predicted.
X: pd.DataFrame
The exogenous time series data for the problem.
Examples
--------
>>> from sktime.datasets import load_longley
>>> y, X = load_longley()
Notes
-----
This mulitvariate time series dataset contains various US macroeconomic
variables from 1947 to 1962 that are known to be highly collinear.
Dimensionality: multivariate, 6
Series length: 16
Frequency: Yearly
Number of cases: 1
Variable description:
TOTEMP - Total employment
GNPDEFL - Gross national product deflator
GNP - Gross national product
UNEMP - Number of unemployed
ARMED - Size of armed forces
POP - Population
References
----------
.. [1] Longley, J.W. (1967) "An Appraisal of Least Squares Programs for the
Electronic Computer from the Point of View of the User." Journal of
the American Statistical Association. 62.319, 819-41.
(https://www.itl.nist.gov/div898/strd/lls/data/LINKS/DATA/Longley.dat)
"""
name = "Longley"
fname = name + ".csv"
path = os.path.join(MODULE, DIRNAME, name, fname)
data = pd.read_csv(path, index_col=0)
data = data.set_index("YEAR")
data.index = pd.PeriodIndex(data.index, freq="Y", name="Period")
data = data.astype(float)
# Get target series
y = data.pop(y_name)
return y, data
def load_lynx():
"""Load the lynx univariate time series dataset for forecasting.
Returns
-------
y : pd.Series/DataFrame
Lynx sales dataset
Examples
--------
>>> from sktime.datasets import load_lynx
>>> y = load_lynx()
Notes
-----
The annual numbers of lynx trappings for 1821–1934 in Canada. This
time-series records the number of skins of
predators (lynx) that were collected over several years by the Hudson's
Bay Company. The dataset was
taken from Brockwell & Davis (1991) and appears to be the series
considered by Campbell & Walker (1977).
Dimensionality: univariate
Series length: 114
Frequency: Yearly
Number of cases: 1
This data shows aperiodic, cyclical patterns, as opposed to periodic,
seasonal patterns.
References
----------
.. [1] Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988). The New S
Language. Wadsworth & Brooks/Cole.
.. [2] Campbell, M. J. and Walker, A. M. (1977). A Survey of statistical
work on the Mackenzie River series of
annual Canadian lynx trappings for the years 1821–1934 and a new
analysis. Journal of the Royal Statistical Society
series A, 140, 411–431.
"""
name = "Lynx"
fname = name + ".csv"
path = os.path.join(MODULE, DIRNAME, name, fname)
y = pd.read_csv(path, index_col=0, dtype={1: float}).squeeze("columns")
y.index = pd.PeriodIndex(y.index, freq="Y", name="Period")
y.name = "Number of Lynx trappings"
return y
def load_airline():
"""Load the airline univariate time series dataset [1].
Returns
-------
y : pd.Series
Time series
Examples
--------
>>> from sktime.datasets import load_airline
>>> y = load_airline()
Notes
-----
The classic Box & Jenkins airline data. Monthly totals of international
airline passengers, 1949 to 1960.
Dimensionality: univariate
Series length: 144
Frequency: Monthly
Number of cases: 1
This data shows an increasing trend, non-constant (increasing) variance
and periodic, seasonal patterns.
References
----------
.. [1] Box, G. E. P., Jenkins, G. M. and Reinsel, G. C. (1976) Time Series
Analysis, Forecasting and Control. Third Edition. Holden-Day.
Series G.
"""
name = "Airline"
fname = name + ".csv"
path = os.path.join(MODULE, DIRNAME, name, fname)
y = pd.read_csv(path, index_col=0, dtype={1: float}).squeeze("columns")
# make sure time index is properly formatted
y.index = pd.PeriodIndex(y.index, freq="M", name="Period")
y.name = "Number of airline passengers"
return y
def load_uschange(y_name="Consumption"):
"""Load MTS dataset for forecasting Growth rates of personal consumption and income.
Returns
-------
y : pd.Series
selected column, default consumption
X : pd.DataFrame
columns with explanatory variables
Examples
--------
>>> from sktime.datasets import load_uschange
>>> y, X = load_uschange()
Notes
-----
Percentage changes in quarterly personal consumption expenditure,
personal disposable income, production, savings and the
unemployment rate for the US, 1960 to 2016.
Dimensionality: multivariate
Columns: ['Quarter', 'Consumption', 'Income', 'Production',
'Savings', 'Unemployment']
Series length: 188
Frequency: Quarterly
Number of cases: 1
This data shows an increasing trend, non-constant (increasing) variance
and periodic, seasonal patterns.
References
----------
.. [1] Data for "Forecasting: Principles and Practice" (2nd Edition)
"""
name = "Uschange"
fname = name + ".csv"
path = os.path.join(MODULE, DIRNAME, name, fname)
data = pd.read_csv(path, index_col=0).squeeze("columns")
# Sort by Quarter then set simple numeric index
# TODO add support for period/datetime indexing
# data.index = pd.PeriodIndex(data.index, freq='Y')
data = data.sort_values("Quarter")
data = data.reset_index(drop=True)
data.index = pd.Index(data.index, dtype=int)
data.name = name
y = data[y_name]
if y_name != "Quarter":
data = data.drop("Quarter", axis=1)
X = data.drop(y_name, axis=1)
return y, X
def load_gun_point_segmentation():
"""Load the GunPoint time series segmentation problem and returns X.
We group TS of the UCR GunPoint dataset by class label and concatenate
all TS to create segments with repeating temporal patterns and
characteristics. The location at which different classes were
concatenated are marked as change points.
We resample the resulting TS to control the TS resolution.
The window sizes for these datasets are hand-selected to capture
temporal patterns but are approximate and limited to the values
[10,20,50,100] to avoid over-fitting.
Returns
-------
X : pd.Series
Single time series for segmentation
period_length : int
The annotated period length by a human expert
change_points : numpy array
The change points annotated within the dataset