-
-
Notifications
You must be signed in to change notification settings - Fork 1.3k
/
_random_interval_classifier.py
228 lines (192 loc) · 7.74 KB
/
_random_interval_classifier.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
"""Random Interval Classifier.
Pipeline classifier using summary statistics extracted from random intervals and an
estimator.
"""
__author__ = ["MatthewMiddlehurst"]
__all__ = ["RandomIntervalClassifier"]
import numpy as np
from sktime.base._base import _clone_estimator
from sktime.classification.base import BaseClassifier
from sktime.classification.sklearn import RotationForest
from sktime.transformations.panel.catch22 import Catch22
from sktime.transformations.panel.random_intervals import RandomIntervals
class RandomIntervalClassifier(BaseClassifier):
"""Random Interval Classifier.
This classifier simply transforms the input data using the RandomIntervals
transformer and builds a provided estimator using the transformed data.
Parameters
----------
n_intervals : int, default=100,
The number of intervals of random length, position and dimension to be
extracted.
interval_transformers : transformer or list of transformers, default=None,
Transformer(s) used to extract features from each interval. If None, defaults to
the Catch22 transformer.
estimator : sklearn classifier, default=None
An sklearn estimator to be built using the transformed data. Defaults to a
Rotation Forest with 200 trees.
n_jobs : int, default=1
The number of jobs to run in parallel for both ``fit`` and ``predict``.
``-1`` means using all processors.
random_state : int or None, default=None
Seed for random, integer.
Attributes
----------
n_classes_ : int
Number of classes. Extracted from the data.
classes_ : ndarray of shape (n_classes)
Holds the label for each class.
See Also
--------
RandomIntervals
Examples
--------
>>> from sktime.classification.feature_based import RandomIntervalClassifier
>>> from sklearn.ensemble import RandomForestClassifier
>>> from sktime.datasets import load_unit_test
>>> X_train, y_train = load_unit_test(split="train", return_X_y=True)
>>> X_test, y_test = load_unit_test(split="test", return_X_y=True) # doctest: +SKIP
>>> clf = RandomIntervalClassifier(
... estimator=RandomForestClassifier(n_estimators=5)
... ) # doctest: +SKIP
>>> clf.fit(X_train, y_train) # doctest: +SKIP
RandomIntervalClassifier(...)
>>> y_pred = clf.predict(X_test) # doctest: +SKIP
"""
_tags = {
# packaging info
# --------------
"authors": ["MatthewMiddlehurst"],
# estimator type
# --------------
"capability:multivariate": True,
"capability:multithreading": True,
"capability:predict_proba": True,
"classifier_type": "interval",
}
def __init__(
self,
n_intervals=100,
interval_transformers=None,
estimator=None,
n_jobs=1,
random_state=None,
):
self.n_intervals = n_intervals
self.interval_transformers = interval_transformers
self.estimator = estimator
self.n_jobs = n_jobs
self.random_state = random_state
self._transformer = None
self._estimator = None
super().__init__()
def _fit(self, X, y):
"""Fit a pipeline on cases (X,y), where y is the target variable.
Parameters
----------
X : 3D np.array of shape = [n_instances, n_dimensions, series_length]
The training data.
y : array-like, shape = [n_instances]
The class labels.
Returns
-------
self :
Reference to self.
Notes
-----
Changes state by creating a fitted model that updates attributes
ending in "_" and sets is_fitted flag to True.
"""
interval_transformers = (
Catch22(outlier_norm=True, replace_nans=True)
if self.interval_transformers is None
else self.interval_transformers
)
self._transformer = RandomIntervals(
n_intervals=self.n_intervals,
transformers=interval_transformers,
random_state=self.random_state,
n_jobs=self._threads_to_use,
)
self._estimator = _clone_estimator(
RotationForest() if self.estimator is None else self.estimator,
self.random_state,
)
m = getattr(self._estimator, "n_jobs", None)
if m is not None:
self._estimator.n_jobs = self._threads_to_use
X_t = self._transformer.fit_transform(X, y)
self._estimator.fit(X_t, y)
return self
def _predict(self, X) -> np.ndarray:
"""Predict class values of n instances in X.
Parameters
----------
X : 3D np.array of shape = [n_instances, n_dimensions, series_length]
The data to make predictions for.
Returns
-------
y : array-like, shape = [n_instances]
Predicted class labels.
"""
return self._estimator.predict(self._transformer.transform(X))
def _predict_proba(self, X) -> np.ndarray:
"""Predict class probabilities for n instances in X.
Parameters
----------
X : 3D np.array of shape = [n_instances, n_dimensions, series_length]
The data to make predict probabilities for.
Returns
-------
y : array-like, shape = [n_instances, n_classes_]
Predicted probabilities using the ordering in classes_.
"""
m = getattr(self._estimator, "predict_proba", None)
if callable(m):
return self._estimator.predict_proba(self._transformer.transform(X))
else:
dists = np.zeros((X.shape[0], self.n_classes_))
preds = self._estimator.predict(self._transformer.transform(X))
for i in range(0, X.shape[0]):
dists[i, self._class_dictionary[preds[i]]] = 1
return dists
@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.
For classifiers, a "default" set of parameters should be provided for
general testing, and a "results_comparison" set for comparing against
previously recorded results if the general set does not produce suitable
probabilities to compare against.
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``.
"""
from sklearn.ensemble import RandomForestClassifier
from sktime.transformations.series.summarize import SummaryTransformer
if parameter_set == "results_comparison":
return {
"n_intervals": 3,
"estimator": RandomForestClassifier(n_estimators=10),
"interval_transformers": SummaryTransformer(
summary_function=("mean", "std", "min", "max"),
quantiles=(0.25, 0.5, 0.75),
),
}
else:
return {
"n_intervals": 2,
"estimator": RandomForestClassifier(n_estimators=2),
"interval_transformers": SummaryTransformer(
summary_function=("mean", "min", "max"),
),
}