def test_import_from_sklearn_pipeline_feature_union(self):
from sklearn.decomposition import PCA as SklearnPCA
from sklearn.kernel_approximation import Nystroem as SklearnNystroem
from sklearn.neighbors import KNeighborsClassifier as SklearnKNN
from sklearn.pipeline import FeatureUnion
union = FeatureUnion([
("pca", SklearnPCA(n_components=1)),
("nys", SklearnNystroem(n_components=2, random_state=42)),
])
sklearn_pipeline = sklearn.pipeline.make_pipeline(union, SklearnKNN())
lale_pipeline = import_from_sklearn_pipeline(sklearn_pipeline)
self.assertEqual(len(lale_pipeline.edges()), 3)
from lale.lib.lale.concat_features import ConcatFeaturesImpl
from lale.lib.sklearn.k_neighbors_classifier import KNeighborsClassifierImpl
from lale.lib.sklearn.nystroem import NystroemImpl
from lale.lib.sklearn.pca import PCAImpl
self.assertEqual(lale_pipeline.edges()[0][0]._impl_class(), PCAImpl)
self.assertEqual(lale_pipeline.edges()[0][1]._impl_class(),
ConcatFeaturesImpl)
self.assertEqual(lale_pipeline.edges()[1][0]._impl_class(),
NystroemImpl)
self.assertEqual(lale_pipeline.edges()[1][1]._impl_class(),
ConcatFeaturesImpl)
self.assertEqual(lale_pipeline.edges()[2][0]._impl_class(),
ConcatFeaturesImpl)
self.assertEqual(lale_pipeline.edges()[2][1]._impl_class(),
KNeighborsClassifierImpl)
self.assert_equal_predictions(sklearn_pipeline, lale_pipeline)
def test_import_from_sklearn_pipeline_feature_union(self):
from sklearn.decomposition import PCA as SklearnPCA
from sklearn.kernel_approximation import Nystroem as SklearnNystroem
from sklearn.neighbors import KNeighborsClassifier as SklearnKNN
from sklearn.pipeline import FeatureUnion
union = FeatureUnion([
("pca", SklearnPCA(n_components=1)),
("nys", SklearnNystroem(n_components=2, random_state=42)),
])
sklearn_pipeline = sklearn.pipeline.make_pipeline(union, SklearnKNN())
lale_pipeline = typing.cast(
lale.operators.TrainablePipeline,
import_from_sklearn_pipeline(sklearn_pipeline),
)
self.assertEqual(len(lale_pipeline.edges()), 3)
from lale.lib.lale.concat_features import ConcatFeatures
from lale.lib.sklearn.k_neighbors_classifier import KNeighborsClassifier
from lale.lib.sklearn.nystroem import Nystroem
from lale.lib.sklearn.pca import PCA
self.assertIsInstance(lale_pipeline.edges()[0][0], PCA) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[0][1],
ConcatFeatures) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[1][0],
Nystroem) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[1][1],
ConcatFeatures) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[2][0],
ConcatFeatures) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[2][1],
KNeighborsClassifier) # type: ignore
self.assert_equal_predictions(sklearn_pipeline, lale_pipeline)
def test_import_from_sklearn_pipeline_nested_pipeline1(self):
from sklearn.decomposition import PCA as SklearnPCA
from sklearn.feature_selection import SelectKBest
from sklearn.kernel_approximation import Nystroem as SklearnNystroem
from sklearn.neighbors import KNeighborsClassifier as SklearnKNN
from sklearn.pipeline import FeatureUnion
union = FeatureUnion(
[
(
"selectkbest_pca",
sklearn.pipeline.make_pipeline(
SelectKBest(k=3),
FeatureUnion(
[
("pca", SklearnPCA(n_components=1)),
(
"nested_pipeline",
sklearn.pipeline.make_pipeline(
SelectKBest(k=2), SklearnNystroem()
),
),
]
),
),
),
("nys", SklearnNystroem(n_components=2, random_state=42)),
]
)
sklearn_pipeline = sklearn.pipeline.make_pipeline(union, SklearnKNN())
lale_pipeline = typing.cast(
lale.operators.TrainablePipeline,
import_from_sklearn_pipeline(sklearn_pipeline),
)
self.assertEqual(len(lale_pipeline.edges()), 8)
# These assertions assume topological sort, which may not be unique. So the assertions are brittle.
from lale.lib.lale.concat_features import ConcatFeatures
from lale.lib.sklearn.k_neighbors_classifier import KNeighborsClassifier
from lale.lib.sklearn.nystroem import Nystroem
from lale.lib.sklearn.pca import PCA
from lale.lib.sklearn.select_k_best import SelectKBest
self.assertIsInstance(lale_pipeline.edges()[0][0], SelectKBest) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[0][1], PCA) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[1][0], SelectKBest) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[1][1], SelectKBest) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[2][0], SelectKBest) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[2][1], Nystroem) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[3][0], PCA) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[3][1], ConcatFeatures) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[4][0], Nystroem) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[4][1], ConcatFeatures) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[5][0], ConcatFeatures) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[5][1], ConcatFeatures) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[6][0], Nystroem) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[6][1], ConcatFeatures) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[7][0], ConcatFeatures) # type: ignore
self.assertIsInstance(lale_pipeline.edges()[7][1], KNeighborsClassifier) # type: ignore
self.assert_equal_predictions(sklearn_pipeline, lale_pipeline)
def test_import_from_sklearn_pipeline_nested_pipeline1(self):
from sklearn.pipeline import FeatureUnion
from sklearn.decomposition import PCA as SklearnPCA
from sklearn.kernel_approximation import Nystroem as SklearnNystroem
from sklearn.feature_selection import SelectKBest
from sklearn.neighbors import KNeighborsClassifier as SklearnKNN
union = FeatureUnion([
("selectkbest_pca",
sklearn.pipeline.make_pipeline(
SelectKBest(k=3),
FeatureUnion([
('pca', SklearnPCA(n_components=1)),
('nested_pipeline',
sklearn.pipeline.make_pipeline(SelectKBest(k=2),
SklearnNystroem()))
]))), ("nys", SklearnNystroem(n_components=2,
random_state=42))
])
sklearn_pipeline = sklearn.pipeline.make_pipeline(union, SklearnKNN())
lale_pipeline = import_from_sklearn_pipeline(sklearn_pipeline)
self.assertEqual(len(lale_pipeline.edges()), 8)
#These assertions assume topological sort, which may not be unique. So the assertions are brittle.
from lale.lib.sklearn.pca import PCAImpl
from lale.lib.sklearn.nystroem import NystroemImpl
from lale.lib.lale.concat_features import ConcatFeaturesImpl
from lale.lib.sklearn.k_neighbors_classifier import KNeighborsClassifierImpl
from lale.lib.sklearn.select_k_best import SelectKBestImpl
self.assertEqual(lale_pipeline.edges()[0][0]._impl_class(),
SelectKBestImpl)
self.assertEqual(lale_pipeline.edges()[0][1]._impl_class(), PCAImpl)
self.assertEqual(lale_pipeline.edges()[1][0]._impl_class(),
SelectKBestImpl)
self.assertEqual(lale_pipeline.edges()[1][1]._impl_class(),
SelectKBestImpl)
self.assertEqual(lale_pipeline.edges()[2][0]._impl_class(),
SelectKBestImpl)
self.assertEqual(lale_pipeline.edges()[2][1]._impl_class(),
NystroemImpl)
self.assertEqual(lale_pipeline.edges()[3][0]._impl_class(), PCAImpl)
self.assertEqual(lale_pipeline.edges()[3][1]._impl_class(),
ConcatFeaturesImpl)
self.assertEqual(lale_pipeline.edges()[4][0]._impl_class(),
NystroemImpl)
self.assertEqual(lale_pipeline.edges()[4][1]._impl_class(),
ConcatFeaturesImpl)
self.assertEqual(lale_pipeline.edges()[5][0]._impl_class(),
ConcatFeaturesImpl)
self.assertEqual(lale_pipeline.edges()[5][1]._impl_class(),
ConcatFeaturesImpl)
self.assertEqual(lale_pipeline.edges()[6][0]._impl_class(),
NystroemImpl)
self.assertEqual(lale_pipeline.edges()[6][1]._impl_class(),
ConcatFeaturesImpl)
self.assertEqual(lale_pipeline.edges()[7][0]._impl_class(),
ConcatFeaturesImpl)
self.assertEqual(lale_pipeline.edges()[7][1]._impl_class(),
KNeighborsClassifierImpl)
self.assert_equal_predictions(sklearn_pipeline, lale_pipeline)
def test_import_from_sklearn_pipeline1(self):
from sklearn.decomposition import PCA as SklearnPCA
from sklearn.neighbors import KNeighborsClassifier as SklearnKNN
sklearn_pipeline = sklearn.pipeline.make_pipeline(
SklearnPCA(n_components=3), SklearnKNN())
lale_pipeline = import_from_sklearn_pipeline(sklearn_pipeline)
for i, pipeline_step in enumerate(sklearn_pipeline.named_steps):
sklearn_step_params = sklearn_pipeline.named_steps[
pipeline_step].get_params()
lale_sklearn_params = lale_pipeline.steps(
)[i]._impl._wrapped_model.get_params()
self.assertEqual(sklearn_step_params, lale_sklearn_params)
self.assert_equal_predictions(sklearn_pipeline, lale_pipeline)
def test_import_from_sklearn_pipeline_nested_pipeline2(self):
from sklearn.decomposition import PCA as SklearnPCA
from sklearn.feature_selection import SelectKBest
from sklearn.kernel_approximation import Nystroem as SklearnNystroem
from sklearn.neighbors import KNeighborsClassifier as SklearnKNN
from sklearn.pipeline import FeatureUnion
union = FeatureUnion([
(
"selectkbest_pca",
sklearn.pipeline.make_pipeline(
SelectKBest(k=3),
sklearn.pipeline.make_pipeline(SelectKBest(k=2),
SklearnPCA()),
),
),
("nys", SklearnNystroem(n_components=2, random_state=42)),
])
sklearn_pipeline = sklearn.pipeline.make_pipeline(union, SklearnKNN())
lale_pipeline = typing.cast(
lale.operators.TrainablePipeline,
import_from_sklearn_pipeline(sklearn_pipeline),
)
self.assertEqual(len(lale_pipeline.edges()), 5)
from lale.lib.lale.concat_features import ConcatFeaturesImpl
from lale.lib.sklearn.k_neighbors_classifier import KNeighborsClassifierImpl
from lale.lib.sklearn.nystroem import NystroemImpl
from lale.lib.sklearn.pca import PCAImpl
from lale.lib.sklearn.select_k_best import SelectKBestImpl
self.assertEqual(lale_pipeline.edges()[0][0]._impl_class(),
SelectKBestImpl)
self.assertEqual(lale_pipeline.edges()[0][1]._impl_class(),
SelectKBestImpl)
self.assertEqual(lale_pipeline.edges()[1][0]._impl_class(),
SelectKBestImpl)
self.assertEqual(lale_pipeline.edges()[1][1]._impl_class(), PCAImpl)
self.assertEqual(lale_pipeline.edges()[2][0]._impl_class(), PCAImpl)
self.assertEqual(lale_pipeline.edges()[2][1]._impl_class(),
ConcatFeaturesImpl)
self.assertEqual(lale_pipeline.edges()[3][0]._impl_class(),
NystroemImpl)
self.assertEqual(lale_pipeline.edges()[3][1]._impl_class(),
ConcatFeaturesImpl)
self.assertEqual(lale_pipeline.edges()[4][0]._impl_class(),
ConcatFeaturesImpl)
self.assertEqual(lale_pipeline.edges()[4][1]._impl_class(),
KNeighborsClassifierImpl)
self.assert_equal_predictions(sklearn_pipeline, lale_pipeline)
def test_import_from_sklearn_pipeline1(self):
from sklearn.decomposition import PCA as SklearnPCA
from sklearn.neighbors import KNeighborsClassifier as SklearnKNN
sklearn_pipeline = sklearn.pipeline.make_pipeline(
SklearnPCA(n_components=3), SklearnKNN())
lale_pipeline = typing.cast(
lale.operators.TrainablePipeline,
import_from_sklearn_pipeline(sklearn_pipeline),
)
for i, pipeline_step in enumerate(sklearn_pipeline.named_steps):
sklearn_step_params = sklearn_pipeline.named_steps[
pipeline_step].get_params()
lale_sklearn_params = self.get_sklearn_params(
lale_pipeline.steps()[i])
self.assertEqual(sklearn_step_params, lale_sklearn_params)
self.assert_equal_predictions(sklearn_pipeline, lale_pipeline)
def __init__(self):
input_type = NumericalDataTypesEnum.table
output_type = NumericalDataTypesEnum.vector
super().__init__(input_type=input_type, output_type=output_type)
self.__model = SklearnKNN(n_neighbors=15)
def fit(self, X, y):
"""Fit the model according to the given training data.
Parameters
----------
X : array-like, shape = (n_samples, n_timestamps)
Training vector.
y : array-like, shape = (n_samples,)
Class labels for each data sample.
Returns
-------
self : object
"""
X, y = check_X_y(X, y)
self._le = LabelEncoder().fit(y)
self.classes_ = self._le.classes_
if self.metric == 'dtw':
self._clf = SklearnKNN(
n_neighbors=self.n_neighbors, weights=self.weights,
algorithm='brute', metric=dtw,
metric_params=self.metric_params,
n_jobs=self.n_jobs, **self.kwargs
)
elif self.metric == 'dtw_classic':
self._clf = SklearnKNN(
n_neighbors=self.n_neighbors, weights=self.weights,
algorithm='brute', metric=dtw_classic,
metric_params=self.metric_params,
n_jobs=self.n_jobs, **self.kwargs
)
elif self.metric == 'dtw_sakoechiba':
n_timestamps = X.shape[1]
if self.metric_params is None:
region = sakoe_chiba_band(n_timestamps)
else:
if 'window_size' not in self.metric_params.keys():
window_size = 0.1
else:
window_size = self.metric_params['window_size']
region = sakoe_chiba_band(n_timestamps, window_size)
self._clf = SklearnKNN(
n_neighbors=self.n_neighbors, weights=self.weights,
algorithm='brute', metric=dtw_region,
metric_params={'region': region},
n_jobs=self.n_jobs, **self.kwargs
)
elif self.metric == 'dtw_itakura':
n_timestamps = X.shape[1]
if self.metric_params is None:
region = itakura_parallelogram(n_timestamps)
else:
if 'max_slope' not in self.metric_params.keys():
max_slope = 2.
else:
max_slope = self.metric_params['max_slope']
region = itakura_parallelogram(n_timestamps, max_slope)
self._clf = SklearnKNN(
n_neighbors=self.n_neighbors, weights=self.weights,
algorithm='brute', metric=dtw_region,
metric_params={'region': region},
n_jobs=self.n_jobs, **self.kwargs
)
elif self.metric == 'dtw_multiscale':
self._clf = SklearnKNN(
n_neighbors=self.n_neighbors, weights=self.weights,
algorithm='brute', metric=dtw_multiscale,
metric_params=self.metric_params,
n_jobs=self.n_jobs, **self.kwargs
)
elif self.metric == 'dtw_fast':
self._clf = SklearnKNN(
n_neighbors=self.n_neighbors, weights=self.weights,
algorithm='brute', metric=dtw_fast,
metric_params=self.metric_params,
n_jobs=self.n_jobs, **self.kwargs
)
elif self.metric == 'boss':
self._clf = SklearnKNN(
n_neighbors=self.n_neighbors, weights=self.weights,
algorithm='brute', metric=boss,
metric_params=self.metric_params,
n_jobs=self.n_jobs, **self.kwargs
)
else:
self._clf = SklearnKNN(
n_neighbors=self.n_neighbors, weights=self.weights,
algorithm=self.algorithm, leaf_size=self.leaf_size,
p=self.p, metric=self.metric, metric_params=self.metric_params,
n_jobs=self.n_jobs, **self.kwargs
)
self._clf.fit(X, y)
return self
