-
Notifications
You must be signed in to change notification settings - Fork 89
/
_cif.py
273 lines (242 loc) · 11.9 KB
/
_cif.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
"""CIF classifier.
Interval based CIF classifier extracting catch22 features from random intervals.
"""
__author__ = ["MatthewMiddlehurst"]
__all__ = ["CanonicalIntervalForestClassifier"]
import numpy as np
from aeon.base.estimator.interval_based import BaseIntervalForest
from aeon.classification import BaseClassifier
from aeon.classification.sklearn import ContinuousIntervalTree
from aeon.transformations.collection.feature_based import Catch22
from aeon.utils.numba.stats import row_mean, row_slope, row_std
class CanonicalIntervalForestClassifier(BaseIntervalForest, BaseClassifier):
"""
Canonical Interval Forest Classifier (CIF).
Implementation of the interval-based forest making use of the catch22 feature set
on randomly selected intervals described in Middlehurst et al. (2020). [1]_
Overview: Input "n" series with "d" dimensions of length "m".
For each tree
- Sample n_intervals intervals of random position and length
- Subsample att_subsample_size catch22 or summary statistic attributes randomly
- Randomly select dimension for each interval
- Calculate attributes for each interval, concatenate to form new
data set
- Build a decision tree on new data set
ensemble the trees with averaged probability estimates
Parameters
----------
base_estimator : BaseEstimator or None, default=None
scikit-learn BaseEstimator used to build the interval ensemble. If None, use a
simple decision tree.
n_estimators : int, default=200
Number of estimators to build for the ensemble.
n_intervals : int, str, list or tuple, default="sqrt"
Number of intervals to extract per tree for each series_transformers series.
An int input will extract that number of intervals from the series, while a str
input will return a function of the series length (may differ per
series_transformers output) to extract that number of intervals.
Valid str inputs are:
- "sqrt": square root of the series length.
- "sqrt-div": sqrt of series length divided by the number
of series_transformers.
A list or tuple of ints and/or strs will extract the number of intervals using
the above rules and sum the results for the final n_intervals. i.e. [4, "sqrt"]
will extract sqrt(n_timepoints) + 4 intervals.
Different number of intervals for each series_transformers series can be
specified using a nested list or tuple. Any list or tuple input containing
another list or tuple must be the same length as the number of
series_transformers.
While random interval extraction will extract the n_intervals intervals total
(removing duplicates), supervised intervals will run the supervised extraction
process n_intervals times, returning more intervals than specified.
min_interval_length : int, float, list, or tuple, default=3
Minimum length of intervals to extract from series. float inputs take a
proportion of the series length to use as the minimum interval length.
Different minimum interval lengths for each series_transformers series can be
specified using a list or tuple. Any list or tuple input must be the same length
as the number of series_transformers.
max_interval_length : int, float, list, or tuple, default=np.inf
Maximum length of intervals to extract from series. float inputs take a
proportion of the series length to use as the maximum interval length.
Different maximum interval lengths for each series_transformers series can be
specified using a list or tuple. Any list or tuple input must be the same length
as the number of series_transformers.
Ignored for supervised interval_selection_method inputs.
att_subsample_size : int, float, list, tuple or None, default=None
The number of attributes to subsample for each estimator. If None, use all
If int, use that number of attributes for all estimators. If float, use that
proportion of attributes for all estimators.
Different subsample sizes for each series_transformers series can be specified
using a list or tuple. Any list or tuple input must be the same length as the
number of series_transformers.
time_limit_in_minutes : int, default=0
Time contract to limit build time in minutes, overriding n_estimators.
Default of 0 means n_estimators are used.
contract_max_n_estimators : int, default=500
Max number of estimators when time_limit_in_minutes is set.
use_pycatch22 : bool, optional, default=False
Wraps the C based pycatch22 implementation for aeon.
(https://github.com/DynamicsAndNeuralSystems/pycatch22). This requires the
``pycatch22`` package to be installed if True.
save_transformed_data : bool, default=False
Save the data transformed in fit for use in _get_train_preds and
_get_train_probs.
random_state : int, RandomState instance or None, default=None
If `int`, random_state is the seed used by the random number generator;
If `RandomState` instance, random_state is the random number generator;
If `None`, the random number generator is the `RandomState` instance used
by `np.random`.
n_jobs : int, default=1
The number of jobs to run in parallel for both `fit` and `predict`.
``-1`` means using all processors.
parallel_backend : str, ParallelBackendBase instance or None, default=None
Specify the parallelisation backend implementation in joblib, if None a 'prefer'
value of "threads" is used by default.
Valid options are "loky", "multiprocessing", "threading" or a custom backend.
See the joblib Parallel documentation for more details.
Attributes
----------
n_instances_ : int
The number of train cases in the training set.
n_channels_ : int
The number of dimensions per case in the training set.
n_timepoints_ : int
The length of each series in the training set.
n_classes_ : int
Number of classes. Extracted from the data.
classes_ : ndarray of shape (n_classes_)
Holds the label for each class.
total_intervals_ : int
Total number of intervals per tree from all representations.
estimators_ : list of shape (n_estimators) of BaseEstimator
The collections of estimators trained in fit.
intervals_ : list of shape (n_estimators) of TransformerMixin
Stores the interval extraction transformer for all estimators.
transformed_data_ : list of shape (n_estimators) of ndarray with shape
(n_instances_ ,total_intervals * att_subsample_size)
The transformed dataset for all classifiers. Only saved when
save_transformed_data is true.
See Also
--------
CanonicalIntervalForestRegressor
DrCIFClassifier
Notes
-----
For the Java version, see
`TSML <https://github.com/uea-machine-learning/tsml/blob/master/src/main/java
/tsml/classifiers/interval_based/CIF.java>`_.
References
----------
.. [1] Matthew Middlehurst and James Large and Anthony Bagnall. "The Canonical
Interval Forest (CIF) Classifier for Time Series Classification."
IEEE International Conference on Big Data 2020
Examples
--------
>>> from aeon.classification.interval_based import CanonicalIntervalForestClassifier
>>> from aeon.datasets import make_example_3d_numpy
>>> X, y = make_example_3d_numpy(n_cases=10, n_channels=1, n_timepoints=12,
... return_y=True, random_state=0)
>>> clf = CanonicalIntervalForestClassifier(n_estimators=10, random_state=0)
>>> clf.fit(X, y)
CanonicalIntervalForestClassifier(n_estimators=10, random_state=0)
>>> clf.predict(X)
array([0, 1, 0, 1, 0, 0, 1, 1, 1, 0])
"""
_tags = {
"capability:multivariate": True,
"capability:train_estimate": True,
"capability:contractable": True,
"capability:multithreading": True,
"algorithm_type": "interval",
}
def __init__(
self,
base_estimator=None,
n_estimators=200,
n_intervals="sqrt",
min_interval_length=3,
max_interval_length=np.inf,
att_subsample_size=8,
time_limit_in_minutes=None,
contract_max_n_estimators=500,
use_pycatch22=False,
save_transformed_data=False,
random_state=None,
n_jobs=1,
parallel_backend=None,
):
self.use_pycatch22 = use_pycatch22
if use_pycatch22:
self.set_tags(**{"python_dependencies": "pycatch22"})
if isinstance(base_estimator, ContinuousIntervalTree):
replace_nan = "nan"
else:
replace_nan = 0
interval_features = [
Catch22(outlier_norm=True, use_pycatch22=use_pycatch22),
row_mean,
row_std,
row_slope,
]
super(CanonicalIntervalForestClassifier, self).__init__(
base_estimator=base_estimator,
n_estimators=n_estimators,
interval_selection_method="random",
n_intervals=n_intervals,
min_interval_length=min_interval_length,
max_interval_length=max_interval_length,
interval_features=interval_features,
series_transformers=None,
att_subsample_size=att_subsample_size,
replace_nan=replace_nan,
time_limit_in_minutes=time_limit_in_minutes,
contract_max_n_estimators=contract_max_n_estimators,
save_transformed_data=save_transformed_data,
random_state=random_state,
n_jobs=n_jobs,
parallel_backend=parallel_backend,
)
@classmethod
def get_test_params(cls, parameter_set="default"):
"""Return testing parameter settings for the estimator.
Parameters
----------
parameter_set : str, default="default"
Name of the set of test parameters to return, for use in tests. If no
special parameters are defined for a value, will return `"default"` set.
CanonicalIntervalForestClassifier provides the following special sets:
"results_comparison" - used in some classifiers to compare against
previously generated results where the default set of parameters
cannot produce suitable probability estimates
"contracting" - used in classifiers that set the
"capability:contractable" tag to True to test contacting
functionality
"train_estimate" - used in some classifiers that set the
"capability:train_estimate" tag to True to allow for more efficient
testing when relevant parameters are available
Returns
-------
params : dict or list of dict, default={}
Parameters to create testing instances of the class.
Each dict are parameters to construct an "interesting" test instance, i.e.,
`MyClass(**params)` or `MyClass(**params[i])` creates a valid test instance.
`create_test_instance` uses the first (or only) dictionary in `params`.
"""
if parameter_set == "results_comparison":
return {"n_estimators": 10, "n_intervals": 2, "att_subsample_size": 4}
elif parameter_set == "contracting":
return {
"time_limit_in_minutes": 5,
"contract_max_n_estimators": 2,
"n_intervals": 2,
"att_subsample_size": 2,
}
elif parameter_set == "train_estimate":
return {
"n_estimators": 2,
"n_intervals": 2,
"att_subsample_size": 2,
"save_transformed_data": True,
}
else:
return {"n_estimators": 2, "n_intervals": 2, "att_subsample_size": 2}