-
-
Notifications
You must be signed in to change notification settings - Fork 113
/
ForecasterRnn.py
1277 lines (1115 loc) · 49.1 KB
/
ForecasterRnn.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
################################################################################
# ForecasterRnn #
# #
# This work by skforecast team is licensed under the BSD 3-Clause License #
################################################################################
# coding=utf-8
import logging
import sys
import warnings
from copy import deepcopy
from typing import Any, Callable, Dict, List, Optional, Tuple, Union
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn.pipeline import Pipeline
from sklearn.base import clone
from sklearn.preprocessing import MinMaxScaler
import skforecast
from ..exceptions import IgnoredArgumentWarning
from ..ForecasterBase import ForecasterBase
from ..utils import (
check_predict_input,
check_select_fit_kwargs,
check_y,
expand_index,
preprocess_last_window,
preprocess_y,
transform_series,
set_skforecast_warnings,
)
logging.basicConfig(
format="%(name)-10s %(levelname)-5s %(message)s",
level=logging.INFO,
)
# TODO. Test Interval
# TODO. Test Grid search
class ForecasterRnn(ForecasterBase):
"""
This class turns any regressor compatible with the TensorFlow API into a
TensorFlow RNN multi-serie multi-step forecaster. A unique model is created
to forecast all time steps and series. See documentation for more details.
Parameters
----------
regressor : regressor or pipeline compatible with the TensorFlow API
An instance of a regressor or pipeline compatible with the TensorFlow API.
levels : str, list
Name of one or more time series to be predicted. This determine the series
the forecaster will be handling. If `None`, all series used during training
will be available for prediction.
lags : int, list, str, default `'auto'`
Lags used as predictors. If 'auto', lags used are from 1 to N, where N is
extracted from the input layer `self.regressor.layers[0].input_shape[0][1]`.
transformer_series : object, dict, default `sklearn.preprocessing.MinMaxScaler(feature_range=(0, 1))`
An instance of a transformer (preprocessor) compatible with the scikit-learn
preprocessing API with methods: fit, transform, fit_transform and
inverse_transform. Transformation is applied to each `series` before training
the forecaster. ColumnTransformers are not allowed since they do not have
inverse_transform method.
- If single transformer: it is cloned and applied to all series.
- If `dict` of transformers: a different transformer can be used for each series.
fit_kwargs : dict, default `None`
Additional arguments to be passed to the `fit` method of the regressor.
forecaster_id : str, int, default `None`
Name used as an identifier of the forecaster.
steps : int, list, str, default `'auto'`
Steps to be predicted. If 'auto', steps used are from 1 to N, where N is
extracted from the output layer `self.regressor.layers[-1].output_shape[1]`.
lags : Ignored
Not used, present here for API consistency by convention.
transformer_exog : Ignored
Not used, present here for API consistency by convention.
weight_func : Ignored
Not used, present here for API consistency by convention.
n_jobs : Ignored
Not used, present here for API consistency by convention.
Attributes
----------
regressor : regressor or pipeline compatible with the TensorFlow API
An instance of a regressor or pipeline compatible with the TensorFlow API.
An instance of this regressor is trained for each step. All of them
are stored in `self.regressors_`.
levels : str, list
Name of one or more time series to be predicted. This determine the series
the forecaster will be handling. If `None`, all series used during training
will be available for prediction.
steps : numpy ndarray
Number of future steps the forecaster will predict when using method
`predict()`. Since a different model is created for each step, this value
should be defined before training.
lags : numpy ndarray
Lags used as predictors.
transformer_series : object, dict
An instance of a transformer (preprocessor) compatible with the scikit-learn
preprocessing API with methods: fit, transform, fit_transform and
inverse_transform. Transformation is applied to each `series` before training
the forecaster. ColumnTransformers are not allowed since they do not have
inverse_transform method.
transformer_series_ : dict
Dictionary with the transformer for each series. It is created cloning the
objects in `transformer_series` and is used internally to avoid overwriting.
transformer_exog : Ignored
Not used, present here for API consistency by convention.
max_lag : int
Maximum value of lag included in `lags`.
window_size : int
Size of the window needed to create the predictors.
window_size_diff : int
This attribute has the same value as window_size as this Forecaster
doesn't support differentiation. Present here for API consistency.
last_window : pandas Series
Last window seen by the forecaster during training. It stores the values
needed to predict the next `step` immediately after the training data.
index_type : type
Type of index of the input used in training.
index_freq : str
Frequency of Index of the input used in training.
training_range: pandas Index
First and last values of index of the data used during training.
included_exog : bool
If the forecaster has been trained using exogenous variable/s.
exog_type : type
Type of exogenous variable/s used in training.
exog_dtypes : dict
Type of each exogenous variable/s used in training. If `transformer_exog`
is used, the dtypes are calculated after the transformation.
exog_col_names : list
Names of the exogenous variables used during training.
series_col_names : list
Names of the series used during training.
X_train_dim_names : dict
Labels for the multi-dimensional arrays created internally for training.
y_train_dim_names : dict
Labels for the multi-dimensional arrays created internally for training.
fit_kwargs : dict
Additional arguments to be passed to the `fit` method of the regressor.
in_sample_residuals : dict
Residuals of the models when predicting training data. Only stored up to
1000 values per model in the form `{step: residuals}`. If `transformer_series`
is not `None`, residuals are stored in the transformed scale.
out_sample_residuals : dict
Residuals of the models when predicting non training data. Only stored
up to 1000 values per model in the form `{step: residuals}`. If `transformer_series`
is not `None`, residuals are assumed to be in the transformed scale. Use
`set_out_sample_residuals()` method to set values.
fitted : bool
Tag to identify if the regressor has been fitted (trained).
creation_date : str
Date of creation.
fit_date : str
Date of last fit.
skforcast_version : str
Version of skforecast library used to create the forecaster.
python_version : str
Version of python used to create the forecaster.
forecaster_id : str, int
Name used as an identifier of the forecaster.
history : dict
Dictionary with the history of the training of each step. It is created
internally to avoid overwriting.
dropna_from_series : Ignored
Not used, present here for API consistency by convention.
"""
def __init__(
self,
regressor: object,
levels: Union[str, list],
lags: Optional[Union[int, list, str]] = "auto",
steps: Optional[Union[int, list, str]] = "auto",
transformer_series: Optional[Union[object, dict]] = MinMaxScaler(
feature_range=(0, 1)
),
weight_func: Optional[Callable] = None,
fit_kwargs: Optional[dict] = {},
forecaster_id: Optional[Union[str, int]] = None,
n_jobs: Any = None,
transformer_exog: Any = None
) -> None:
self.levels = None
self.transformer_series = transformer_series
self.transformer_series_ = None
self.transformer_exog = None
self.weight_func = weight_func
self.source_code_weight_func = None
self.max_lag = None
self.window_size = None
self.last_window = None
self.index_type = None
self.index_freq = None
self.training_range = None
self.included_exog = False
self.exog_type = None
self.exog_dtypes = None
self.exog_col_names = None
self.series_col_names = None
self.X_train_dim_names = None
self.y_train_dim_names = None
self.fitted = False
self.creation_date = pd.Timestamp.today().strftime("%Y-%m-%d %H:%M:%S")
self.fit_date = None
self.skforecast_version = skforecast.__version__
self.python_version = sys.version.split(" ")[0]
self.forecaster_id = forecaster_id
self.history = None
self.dropna_from_series = False # Ignored in this forecaster
# Infer parameters from the model
self.regressor = regressor
layer_init = self.regressor.layers[0]
if lags == "auto":
self.lags = np.arange(layer_init.input_shape[0][1]) + 1
warnings.warn(
"Setting `lags` = 'auto'. `lags` are inferred from the regressor "
"architecture. Avoid the warning with lags=lags."
)
elif isinstance(lags, int):
self.lags = np.arange(lags) + 1
elif isinstance(lags, list):
self.lags = np.array(lags)
else:
raise TypeError(
f"`lags` argument must be an int, list or 'auto'. Got {type(lags)}."
)
self.max_lag = np.max(self.lags)
self.window_size = self.max_lag
self.window_size_diff = self.max_lag
layer_end = self.regressor.layers[-1]
try:
self.series = layer_end.output_shape[-1]
# if does not work, break the and raise an error the input shape should
# be shape=(lags, n_series))
except:
raise TypeError(
"Input shape of the regressor should be Input(shape=(lags, n_series))."
)
if steps == "auto":
self.steps = np.arange(layer_end.output_shape[1]) + 1
warnings.warn(
"`steps` default value = 'auto'. `steps` inferred from regressor "
"architecture. Avoid the warning with steps=steps."
)
elif isinstance(steps, int):
self.steps = np.arange(steps) + 1
elif isinstance(steps, list):
self.steps = np.array(steps)
else:
raise TypeError(
f"`steps` argument must be an int, list or 'auto'. Got {type(steps)}."
)
self.max_step = np.max(self.steps)
self.outputs = layer_end.output_shape[-1]
if not isinstance(levels, (list, str, type(None))):
raise TypeError(
f"`levels` argument must be a string, list or. Got {type(levels)}."
)
if isinstance(levels, str):
self.levels = [levels]
elif isinstance(levels, list):
self.levels = levels
else:
raise TypeError(
f"`levels` argument must be a string or a list. Got {type(levels)}."
)
self.series_val = None
if "series_val" in fit_kwargs:
self.series_val = fit_kwargs["series_val"]
fit_kwargs.pop("series_val")
self.fit_kwargs = check_select_fit_kwargs(
regressor=self.regressor, fit_kwargs=fit_kwargs
)
def __repr__(self) -> str:
"""
Information displayed when a ForecasterRnn object is printed.
"""
if isinstance(self.regressor, Pipeline):
name_pipe_steps = tuple(
name + "__" for name in self.regressor.named_steps.keys()
)
params = {
key: value
for key, value in self.regressor.get_params().items()
if key.startswith(name_pipe_steps)
}
else:
params = self.regressor.get_config()
compile_config = self.regressor.get_compile_config()
info = (
f"{'=' * len(type(self).__name__)} \n"
f"{type(self).__name__} \n"
f"{'=' * len(type(self).__name__)} \n"
f"Regressor: {self.regressor} \n"
f"Lags: {self.lags} \n"
f"Transformer for series: {self.transformer_series} \n"
f"Window size: {self.window_size} \n"
f"Target series, levels: {self.levels} \n"
f"Multivariate series (names): {self.series_col_names} \n"
f"Maximum steps predicted: {self.steps} \n"
f"Training range: {self.training_range.to_list() if self.fitted else None} \n"
f"Training index type: {str(self.index_type).split('.')[-1][:-2] if self.fitted else None} \n"
f"Training index frequency: {self.index_freq if self.fitted else None} \n"
f"Model parameters: {params} \n"
f"Compile parameters: {compile_config} \n"
f"fit_kwargs: {self.fit_kwargs} \n"
f"Creation date: {self.creation_date} \n"
f"Last fit date: {self.fit_date} \n"
f"Skforecast version: {self.skforecast_version} \n"
f"Python version: {self.python_version} \n"
f"Forecaster id: {self.forecaster_id} \n"
)
return info
def _create_lags(
self,
y: np.ndarray
) -> Tuple[np.ndarray, np.ndarray]:
"""
Transforms a 1d array into a 3d array (X) and a 3d array (y). Each row
in X is associated with a value of y and it represents the lags that
precede it.
Notice that, the returned matrix X_data, contains the lag 1 in the first
column, the lag 2 in the second column and so on.
Parameters
----------
y : numpy ndarray
1d numpy ndarray Training time series.
Returns
-------
X_data : numpy ndarray
3d numpy ndarray with the lagged values (predictors).
Shape: (samples - max(lags), len(lags))
y_data : numpy ndarray
3d numpy ndarray with the values of the time series related to each
row of `X_data` for each step.
Shape: (len(max_step), samples - max(lags))
"""
n_splits = len(y) - self.max_lag - self.max_step + 1 # rows of y_data
if n_splits <= 0:
raise ValueError(
(
f"The maximum lag ({self.max_lag}) must be less than the length "
f"of the series minus the maximum of steps ({len(y)-self.max_step})."
)
)
X_data = np.full(
shape=(n_splits, (self.max_lag)), fill_value=np.nan, dtype=float
)
for i, lag in enumerate(range(self.max_lag - 1, -1, -1)):
X_data[:, i] = y[self.max_lag - lag - 1 : -(lag + self.max_step)]
y_data = np.full(
shape=(n_splits, self.max_step), fill_value=np.nan, dtype=float
)
for step in range(self.max_step):
y_data[:, step] = y[self.max_lag + step : self.max_lag + step + n_splits]
# Get lags index
X_data = X_data[:, self.lags - 1]
# Get steps index
y_data = y_data[:, self.steps-1]
return X_data, y_data
def create_train_X_y(
self, series: pd.DataFrame, exog: Any = None
) -> Tuple[np.ndarray, np.ndarray, dict]:
"""
Create training matrices. The resulting multi-dimensional matrices contain
the target variable and predictors needed to train the model.
Parameters
----------
series : pandas DataFrame
Training time series.
exog : Ignored
Not used, present here for API consistency by convention. This type of
forecaster does not allow exogenous variables.
Returns
-------
X_train : np.ndarray
Training values (predictors) for each step. The resulting array has
3 dimensions: (time_points, n_lags, n_series)
y_train : np.ndarray
Values (target) of the time series related to each row of `X_train`.
The resulting array has 3 dimensions: (time_points, n_steps, n_levels)
dimension_names : dict
Labels for the multi-dimensional arrays created internally for training.
"""
if not isinstance(series, pd.DataFrame):
raise TypeError(f"`series` must be a pandas DataFrame. Got {type(series)}.")
series_col_names = list(series.columns)
if not set(self.levels).issubset(set(series.columns)):
raise ValueError(
(
f"`levels` defined when initializing the forecaster must be included "
f"in `series` used for trainng. {set(self.levels) - set(series.columns)} "
f"not found."
)
)
if len(series) < self.max_lag + self.max_step:
raise ValueError(
(
f"Minimum length of `series` for training this forecaster is "
f"{self.max_lag + self.max_step}. Got {len(series)}. Reduce the "
f"number of predicted steps, {self.max_step}, or the maximum "
f"lag, {self.max_lag}, if no more data is available."
)
)
if self.transformer_series is None:
self.transformer_series_ = {serie: None for serie in series_col_names}
elif not isinstance(self.transformer_series, dict):
self.transformer_series_ = {
serie: clone(self.transformer_series) for serie in series_col_names
}
else:
self.transformer_series_ = {serie: None for serie in series_col_names}
# Only elements already present in transformer_series_ are updated
self.transformer_series_.update(
(k, v)
for k, v in deepcopy(self.transformer_series).items()
if k in self.transformer_series_
)
series_not_in_transformer_series = set(series.columns) - set(
self.transformer_series.keys()
)
if series_not_in_transformer_series:
warnings.warn(
(
f"{series_not_in_transformer_series} not present in "
f"`transformer_series`. No transformation is applied to "
f"these series."
),
IgnoredArgumentWarning,
)
# Step 1: Create lags for all columns
X_train = []
y_train = []
for i, serie in enumerate(series.columns):
x = series[serie]
check_y(y=x)
x = transform_series(
series=x,
transformer=self.transformer_series_[serie],
fit=True,
inverse_transform=False,
)
X, _ = self._create_lags(x)
X_train.append(X)
for i, serie in enumerate(self.levels):
y = series[serie]
check_y(y=y)
y = transform_series(
series=y,
transformer=self.transformer_series_[serie],
fit=True,
inverse_transform=False,
)
_, y = self._create_lags(y)
y_train.append(y)
X_train = np.stack(X_train, axis=2)
y_train = np.stack(y_train, axis=2)
train_index = series.index.to_list()[
self.max_lag : (len(series.index.to_list()) - self.max_step + 1)
]
dimension_names = {
"X_train": {
0: train_index,
1: ["lag_" + str(l) for l in self.lags],
2: series.columns.to_list(),
},
"y_train": {
0: train_index,
1: ["step_" + str(l) for l in self.steps],
2: self.levels,
},
}
return X_train, y_train, dimension_names
def fit(
self,
series: pd.DataFrame,
store_in_sample_residuals: bool = True,
exog: Any = None,
suppress_warnings: bool=False,
store_last_window: str = "Ignored",
) -> None:
"""
Training Forecaster.
Additional arguments to be passed to the `fit` method of the regressor
can be added with the `fit_kwargs` argument when initializing the forecaster.
Parameters
----------
series : pandas DataFrame
Training time series.
store_in_sample_residuals : bool, default `True`
If `True`, in-sample residuals will be stored in the forecaster object
after fitting.
exog : Ignored
Not used, present here for API consistency by convention.
suppress_warnings : bool, default `False`
If `True`, skforecast warnings will be suppressed during the prediction
process. See skforecast.exceptions.warn_skforecast_categories for more
information.
store_last_window : Ignored
Not used, present here for API consistency by convention.
Returns
-------
None
"""
set_skforecast_warnings(suppress_warnings, action='ignore')
# Reset values in case the forecaster has already been fitted.
self.index_type = None
self.index_freq = None
self.last_window = None
self.included_exog = None
self.exog_type = None
self.exog_dtypes = None
self.exog_col_names = None
self.series_col_names = None
self.X_train_dim_names = None
self.y_train_dim_names = None
self.in_sample_residuals = None
self.fitted = False
self.training_range = None
self.series_col_names = list(series.columns)
X_train, y_train, X_train_dim_names = self.create_train_X_y(series=series)
self.X_train_dim_names = X_train_dim_names["X_train"]
self.y_train_dim_names = X_train_dim_names["y_train"]
if self.series_val is not None:
X_val, y_val, _ = self.create_train_X_y(series=self.series_val)
history = self.regressor.fit(
x=X_train, y=y_train, validation_data=(X_val, y_val), **self.fit_kwargs
)
else:
history = self.regressor.fit(x=X_train, y=y_train, **self.fit_kwargs)
self.history = history.history
self.fitted = True
self.fit_date = pd.Timestamp.today().strftime("%Y-%m-%d %H:%M:%S")
_, y_index = preprocess_y(y=series[self.levels], return_values=False)
self.training_range = y_index[[0, -1]]
self.index_type = type(y_index)
if isinstance(y_index, pd.DatetimeIndex):
self.index_freq = y_index.freqstr
else:
self.index_freq = y_index.step
self.last_window = series.iloc[-self.max_lag :].copy()
set_skforecast_warnings(suppress_warnings, action='default')
def predict(
self,
steps: Optional[Union[int, list]] = None,
levels: Optional[Union[str, list]] = None,
last_window: Optional[pd.DataFrame] = None,
exog: Any = None,
suppress_warnings: bool=False
) -> pd.DataFrame:
"""
Predict n steps ahead
Parameters
----------
steps : int, list, None, default `None`
Predict n steps. The value of `steps` must be less than or equal to the
value of steps defined when initializing the forecaster. Starts at 1.
- If `int`: Only steps within the range of 1 to int are predicted.
- If `list`: List of ints. Only the steps contained in the list
are predicted.
- If `None`: As many steps are predicted as were defined at
initialization.
levels : str, list, default `None`
Name of one or more time series to be predicted. It must be included
in `levels` defined when initializing the forecaster. If `None`, all
all series used during training will be available for prediction.
last_window : pandas DataFrame, default `None`
Series values used to create the predictors (lags) needed in the
first iteration of the prediction (t + 1).
If `last_window = None`, the values stored in `self.last_window` are
used to calculate the initial predictors, and the predictions start
right after training data.
exog : Ignored
Not used, present here for API consistency by convention.
suppress_warnings : bool, default `False`
If `True`, skforecast warnings will be suppressed during the fitting
process. See skforecast.exceptions.warn_skforecast_categories for more
information.
Returns
-------
predictions : pandas DataFrame
Predicted values.
"""
set_skforecast_warnings(suppress_warnings, action='ignore')
if levels is None:
levels = self.levels
elif isinstance(levels, str):
levels = [levels]
if isinstance(steps, int):
steps = list(np.arange(steps) + 1)
elif steps is None:
if isinstance(self.steps, int):
steps = list(np.arange(self.steps) + 1)
elif isinstance(self.steps, (list, np.ndarray)):
steps = list(np.array(self.steps))
elif isinstance(steps, list):
steps = list(np.array(steps))
for step in steps:
if not isinstance(step, (int, np.int64, np.int32)):
raise TypeError(
(
f"`steps` argument must be an int, a list of ints or `None`. "
f"Got {type(steps)}."
)
)
if last_window is None:
last_window = self.last_window
check_predict_input(
forecaster_name=type(self).__name__,
steps=steps,
fitted=self.fitted,
included_exog=self.included_exog,
index_type=self.index_type,
index_freq=self.index_freq,
window_size=self.window_size,
last_window=last_window,
last_window_exog=None,
exog=None,
exog_type=None,
exog_col_names=None,
interval=None,
alpha=None,
max_steps=self.max_step,
levels=levels,
levels_forecaster=self.levels,
series_col_names=self.series_col_names,
)
last_window = last_window.iloc[-self.window_size :,].copy()
for serie_name in self.series_col_names:
last_window_serie = transform_series(
series=last_window[serie_name],
transformer=self.transformer_series_[serie_name],
fit=False,
inverse_transform=False,
)
last_window_values, last_window_index = preprocess_last_window(
last_window=last_window_serie
)
last_window.loc[:, serie_name] = last_window_values
X = np.reshape(last_window.to_numpy(), (1, self.max_lag, last_window.shape[1]))
predictions = self.regressor.predict(X, verbose=0)
predictions_reshaped = np.reshape(
predictions, (predictions.shape[1], predictions.shape[2])
)
# if len(self.levels) == 1:
# predictions_reshaped = np.reshape(predictions, (predictions.shape[1], 1))
# else:
# predictions_reshaped = np.reshape(
# predictions, (predictions.shape[1], predictions.shape[2])
# )
idx = expand_index(index=last_window_index, steps=max(steps))
predictions = pd.DataFrame(
data=predictions_reshaped[np.array(steps) - 1],
columns=self.levels,
index=idx[np.array(steps) - 1],
)
predictions = predictions[levels]
for serie in levels:
x = predictions[serie]
check_y(y=x)
x = transform_series(
series=x,
transformer=self.transformer_series_[serie],
fit=False,
inverse_transform=True,
)
predictions.loc[:, serie] = x
set_skforecast_warnings(suppress_warnings, action='default')
return predictions
def plot_history(
self, ax: matplotlib.axes.Axes = None, **fig_kw
) -> matplotlib.figure.Figure:
"""
Plots the training and validation loss curves from the given history object stores
in the ForecasterRnn.
Parameters
----------
ax : matplotlib.axes.Axes, default `None`
Pre-existing ax for the plot. Otherwise, call matplotlib.pyplot.subplots()
internally.
fig_kw : dict
Other keyword arguments are passed to matplotlib.pyplot.subplots().
Returns
-------
fig: matplotlib.figure.Figure
Matplotlib Figure.
"""
if ax is None:
fig, ax = plt.subplots(1, 1, **fig_kw)
else:
fig = ax.get_figure()
# Setting up the plot style
if self.history is None:
raise ValueError("ForecasterRnn has not been fitted yet.")
# Plotting training loss
ax.plot(
range(1, len(self.history["loss"]) + 1),
self.history["loss"],
color="b",
label="Training Loss",
)
# Plotting validation loss
if "val_loss" in self.history:
ax.plot(
range(1, len(self.history["val_loss"]) + 1),
self.history["val_loss"],
color="r",
label="Validation Loss",
)
# Labeling the axes and adding a title
ax.set_xlabel("Epochs")
ax.set_ylabel("Loss")
ax.set_title("Training and Validation Loss")
# Adding a legend
ax.legend()
# Displaying grid for better readability
ax.grid(True, linestyle="--", alpha=0.7)
# Setting x-axis ticks to integers only
ax.set_xticks(range(1, len(self.history["loss"]) + 1))
# def predict_bootstrapping(
# self,
# steps: Optional[Union[int, list]] = None,
# last_window: Optional[pd.DataFrame] = None,
# exog: Optional[Union[pd.Series, pd.DataFrame]] = None,
# n_boot: int = 500,
# random_state: int = 123,
# in_sample_residuals: bool = True,
# levels: Any = None,
# ) -> pd.DataFrame:
# """
# Generate multiple forecasting predictions using a bootstrapping process.
# By sampling from a collection of past observed errors (the residuals),
# each iteration of bootstrapping generates a different set of predictions.
# See the Notes section for more information.
# Parameters
# ----------
# steps : int, list, None, default `None`
# Predict n steps. The value of `steps` must be less than or equal to the
# value of steps defined when initializing the forecaster. Starts at 1.
# - If `int`: Only steps within the range of 1 to int are predicted.
# - If `list`: List of ints. Only the steps contained in the list
# are predicted.
# - If `None`: As many steps are predicted as were defined at
# initialization.
# last_window : pandas DataFrame, default `None`
# Series values used to create the predictors (lags) needed in the
# first iteration of the prediction (t + 1).
# If `last_window = None`, the values stored in` self.last_window` are
# used to calculate the initial predictors, and the predictions start
# right after training data.
# exog : pandas Series, pandas DataFrame, default `None`
# Exogenous variable/s included as predictor/s.
# n_boot : int, default `500`
# Number of bootstrapping iterations used to estimate prediction
# intervals.
# random_state : int, default `123`
# Sets a seed to the random generator, so that boot intervals are always
# deterministic.
# in_sample_residuals : bool, default `True`
# If `True`, residuals from the training data are used as proxy of
# prediction error to create prediction intervals. If `False`, out of
# sample residuals are used. In the latter case, the user should have
# calculated and stored the residuals within the forecaster (see
# `set_out_sample_residuals()`).
# levelss : Ignored
# Not used, present here for API consistency by convention.
# Returns
# -------
# boot_predictions : pandas DataFrame
# Predictions generated by bootstrapping.
# Shape: (steps, n_boot)
# Notes
# -----
# More information about prediction intervals in forecasting:
# https://otexts.com/fpp3/prediction-intervals.html#prediction-intervals-from-bootstrapped-residuals
# Forecasting: Principles and Practice (3nd ed) Rob J Hyndman and George Athanasopoulos.
# """
# if isinstance(steps, int):
# steps = list(np.arange(steps) + 1)
# elif steps is None:
# steps = list(np.arange(self.steps) + 1)
# elif isinstance(steps, list):
# steps = list(np.array(steps))
# if in_sample_residuals:
# if not set(steps).issubset(set(self.in_sample_residuals.keys())):
# raise ValueError(
# (
# f"Not `forecaster.in_sample_residuals` for steps: "
# f"{set(steps) - set(self.in_sample_residuals.keys())}."
# )
# )
# residuals = self.in_sample_residuals
# else:
# if self.out_sample_residuals is None:
# raise ValueError(
# (
# "`forecaster.out_sample_residuals` is `None`. Use "
# "`in_sample_residuals=True` or method `set_out_sample_residuals()` "
# "before `predict_interval()`, `predict_bootstrapping()` or "
# "`predict_dist()`."
# )
# )
# else:
# if not set(steps).issubset(set(self.out_sample_residuals.keys())):
# raise ValueError(
# (
# f"Not `forecaster.out_sample_residuals` for steps: "
# f"{set(steps) - set(self.out_sample_residuals.keys())}. "
# f"Use method `set_out_sample_residuals()`."
# )
# )
# residuals = self.out_sample_residuals
# check_residuals = (
# "forecaster.in_sample_residuals"
# if in_sample_residuals
# else "forecaster.out_sample_residuals"
# )
# for step in steps:
# if residuals[step] is None:
# raise ValueError(
# (
# f"forecaster residuals for step {step} are `None`. "
# f"Check {check_residuals}."
# )
# )
# elif (residuals[step] == None).any():
# raise ValueError(
# (
# f"forecaster residuals for step {step} contains `None` values. "
# f"Check {check_residuals}."
# )
# )
# predictions = self.predict(steps=steps, last_window=last_window, exog=exog)
# # Predictions must be in the transformed scale before adding residuals
# predictions = transform_dataframe(
# df=predictions,
# transformer=self.transformer_series_[self.levels],
# fit=False,
# inverse_transform=False,
# )
# boot_predictions = pd.concat([predictions] * n_boot, axis=1)
# boot_predictions.columns = [f"pred_boot_{i}" for i in range(n_boot)]
# for i, step in enumerate(steps):
# rng = np.random.default_rng(seed=random_state)
# sample_residuals = rng.choice(a=residuals[step], size=n_boot, replace=True)
# boot_predictions.iloc[i, :] = boot_predictions.iloc[i, :] + sample_residuals
# if self.transformer_series_[self.levels]:
# for col in boot_predictions.columns:
# boot_predictions[col] = transform_series(
# series=boot_predictions[col],
# transformer=self.transformer_series_[self.levels],
# fit=False,
# inverse_transform=True,
# )
# return boot_predictions
# def predict_interval(
# self,
# steps: Optional[Union[int, list]] = None,
# last_window: Optional[pd.DataFrame] = None,
# exog: Optional[Union[pd.Series, pd.DataFrame]] = None,
# interval: list = [5, 95],
# n_boot: int = 500,
# random_state: int = 123,
# in_sample_residuals: bool = True,
# levelss: Any = None,
# ) -> pd.DataFrame:
# """
# Bootstrapping based prediction intervals.
# Both predictions and intervals are returned.
# Parameters
# ----------
# steps : int, list, None, default `None`
# Predict n steps. The value of `steps` must be less than or equal to the
# value of steps defined when initializing the forecaster. Starts at 1.
# - If `int`: Only steps within the range of 1 to int are predicted.
# - If `list`: List of ints. Only the steps contained in the list
# are predicted.
# - If `None`: As many steps are predicted as were defined at
# initialization.
# last_window : pandas DataFrame, default `None`
# Series values used to create the predictors (lags) needed in the
# first iteration of the prediction (t + 1).
# If `last_window = None`, the values stored in` self.last_window` are
# used to calculate the initial predictors, and the predictions start
# right after training data.
# exog : pandas Series, pandas DataFrame, default `None`
# Exogenous variable/s included as predictor/s.
# interval : list, default `[5, 95]`