def test_init_fit_predict_spark_pandas(self):
from lale.datasets import pandas2spark
from lale.datasets.util import spark_installed
if spark_installed:
trainable_cf = ConcatFeatures()
A = [[11, 12, 13], [21, 22, 23], [31, 32, 33]]
B = [[14, 15], [24, 25], [34, 35]]
A = pd.DataFrame(A, columns=["a", "b", "c"])
B = pd.DataFrame(B, columns=["d", "e"])
A = pandas2spark(A, add_index=True)
A = add_table_name(A, "A")
B = add_table_name(B, "B")
trained_cf = trainable_cf.fit(X=[A, B])
transformed = trained_cf.transform([A, B])
expected = [
[11, 12, 13, 14, 15],
[21, 22, 23, 24, 25],
[31, 32, 33, 34, 35],
]
expected = pd.DataFrame(expected,
columns=["a", "b", "c", "d", "e"])
for c in expected.columns:
self.assertEqual(list(transformed[c]), list(expected[c]))
def test_planned_pipeline_3(self) :
plan = (
( MinMaxScaler() & NoOp() ) >> ConcatFeatures() >>
( StandardScaler & ( NoOp() | MinMaxScaler() ) ) >> ConcatFeatures() >>
( LogisticRegression | KNeighborsClassifier )
)
run_hyperopt_on_planned_pipeline(plan)
def test_export_to_sklearn_pipeline2(self):
from sklearn.feature_selection import SelectKBest
from sklearn.pipeline import FeatureUnion
lale_pipeline = (
(
(
(PCA(svd_solver="randomized", random_state=42) & SelectKBest(k=3))
>> ConcatFeatures()
)
& Nystroem(random_state=42)
)
>> ConcatFeatures()
>> KNeighborsClassifier()
)
trained_lale_pipeline = lale_pipeline.fit(self.X_train, self.y_train)
sklearn_pipeline = trained_lale_pipeline.export_to_sklearn_pipeline()
self.assertIsInstance(
sklearn_pipeline.named_steps["featureunion"], FeatureUnion
)
from sklearn.neighbors import KNeighborsClassifier as SklearnKNN
self.assertIsInstance(
sklearn_pipeline.named_steps["kneighborsclassifier"], SklearnKNN
)
self.assert_equal_predictions(sklearn_pipeline, trained_lale_pipeline)
def test_multiple_estimators_predict_predict_proba(self):
pipeline = (StandardScaler() >>
(LogisticRegression() & PCA()) >> ConcatFeatures() >>
(NoOp() & LinearSVC()) >> ConcatFeatures() >>
KNeighborsClassifier())
pipeline.fit(self.X_train, self.y_train)
_ = pipeline.predict_proba(self.X_test)
_ = pipeline.predict(self.X_test)
def test_init_fit_predict(self):
trainable_cf = ConcatFeatures()
A = [[11, 12, 13], [21, 22, 23], [31, 32, 33]]
B = [[14, 15], [24, 25], [34, 35]]
trained_cf = trainable_cf.fit(X=[A, B])
transformed = trained_cf.transform([A, B])
expected = [[11, 12, 13, 14, 15], [21, 22, 23, 24, 25],
[31, 32, 33, 34, 35]]
for i_sample in range(len(transformed)):
for i_feature in range(len(transformed[i_sample])):
self.assertEqual(transformed[i_sample][i_feature],
expected[i_sample][i_feature])
def test_comparison_with_scikit(self):
import warnings
warnings.filterwarnings("ignore")
from lale.lib.sklearn import PCA
import sklearn.datasets
from lale.helpers import cross_val_score
pca = PCA(n_components=3, random_state=42, svd_solver='arpack')
nys = Nystroem(n_components=10, random_state=42)
concat = ConcatFeatures()
lr = LogisticRegression(random_state=42, C=0.1)
trainable = (pca & nys) >> concat >> lr
digits = sklearn.datasets.load_digits()
X, y = sklearn.utils.shuffle(digits.data, digits.target, random_state=42)
cv_results = cross_val_score(trainable, X, y)
cv_results = ['{0:.1%}'.format(score) for score in cv_results]
from sklearn.pipeline import make_pipeline, FeatureUnion
from sklearn.decomposition import PCA as SklearnPCA
from sklearn.kernel_approximation import Nystroem as SklearnNystroem
from sklearn.linear_model import LogisticRegression as SklearnLR
from sklearn.model_selection import cross_val_score
union = FeatureUnion([("pca", SklearnPCA(n_components=3, random_state=42, svd_solver='arpack')),
("nys", SklearnNystroem(n_components=10, random_state=42))])
lr = SklearnLR(random_state=42, C=0.1)
pipeline = make_pipeline(union, lr)
scikit_cv_results = cross_val_score(pipeline, X, y, cv = 5)
scikit_cv_results = ['{0:.1%}'.format(score) for score in scikit_cv_results]
self.assertEqual(cv_results, scikit_cv_results)
warnings.resetwarnings()
def test_export_to_sklearn_pipeline3(self):
from sklearn.feature_selection import SelectKBest
from sklearn.pipeline import FeatureUnion
lale_pipeline = (
(
(PCA() >> SelectKBest(k=2))
& (Nystroem(random_state=42) >> SelectKBest(k=3))
& (SelectKBest(k=3))
)
>> ConcatFeatures()
>> SelectKBest(k=2)
>> LogisticRegression()
)
trained_lale_pipeline = lale_pipeline.fit(self.X_train, self.y_train)
sklearn_pipeline = trained_lale_pipeline.export_to_sklearn_pipeline()
self.assertIsInstance(
sklearn_pipeline.named_steps["featureunion"], FeatureUnion
)
self.assertIsInstance(sklearn_pipeline.named_steps["selectkbest"], SelectKBest)
from sklearn.linear_model import LogisticRegression as SklearnLR
self.assertIsInstance(
sklearn_pipeline.named_steps["logisticregression"], SklearnLR
)
self.assert_equal_predictions(sklearn_pipeline, trained_lale_pipeline)
def test_two_estimators_predict_proba1(self):
pipeline = StandardScaler() >> (
PCA() & Nystroem() & PassiveAggressiveClassifier()
) >> ConcatFeatures() >> NoOp() >> PassiveAggressiveClassifier()
pipeline.fit(self.X_train, self.y_train)
with self.assertRaises(ValueError):
pipeline.predict_proba(self.X_test)
def test_planned_pipeline_1(self) :
plan = (
( PCA & ( MinMaxScaler | Normalizer ) ) >> ConcatFeatures() >>
( MinMaxScaler | Normalizer ) >>
( LogisticRegression | KNeighborsClassifier)
)
run_hyperopt_on_planned_pipeline(plan)
def test_remove_last4(self):
pipeline = StandardScaler() >> (
PCA() & Nystroem() & PassiveAggressiveClassifier()
) >> ConcatFeatures() >> NoOp() >> PassiveAggressiveClassifier()
new_pipeline = pipeline.remove_last(inplace=True)
self.assertEqual(len(new_pipeline._steps), 6)
self.assertEqual(len(pipeline._steps), 6)
def test_two_estimators_predict1(self):
pipeline = (
StandardScaler() >>
(PCA() & Nystroem() & PassiveAggressiveClassifier()) >>
ConcatFeatures() >> NoOp() >> PassiveAggressiveClassifier())
trained = pipeline.fit(self.X_train, self.y_train)
trained.predict(self.X_test)
def test_remove_last2(self):
pipeline = (StandardScaler() >>
(PCA() & Nystroem() & PassiveAggressiveClassifier()) >>
ConcatFeatures() >> NoOp() >>
(PassiveAggressiveClassifier() & LogisticRegression()))
with self.assertRaises(ValueError):
pipeline.remove_last()
def test_with_concat_features2(self):
import warnings
warnings.filterwarnings("ignore")
from sklearn.datasets import load_iris
from sklearn.metrics import accuracy_score
from lale.lib.lale import Hyperopt
data = load_iris()
X, y = data.data, data.target
pca = PCA(n_components=3)
nys = Nystroem(n_components=10)
concat = ConcatFeatures()
lr = LogisticRegression(random_state=42, C=0.1)
from lale.operators import make_pipeline
pipeline = make_pipeline(
((((SimpleImputer() | NoOp()) >> pca) & nys) >> concat >> lr)
| KNeighborsClassifier()
)
clf = Hyperopt(estimator=pipeline, max_evals=1, handle_cv_failure=True)
trained = clf.fit(X, y)
predictions = trained.predict(X)
print(accuracy_score(y, predictions))
warnings.resetwarnings()
def test_pipeline_1(self):
self.maxDiff = None
from lale.json_operator import from_json, to_json
from lale.lib.lale import ConcatFeatures, NoOp
from lale.lib.sklearn import PCA
from lale.lib.sklearn import LogisticRegression as LR
operator = (PCA & NoOp) >> ConcatFeatures >> LR
json_expected = {
"class": "lale.operators.PlannedPipeline",
"state": "planned",
"edges": [
["pca", "concat_features"],
["no_op", "concat_features"],
["concat_features", "lr"],
],
"steps": {
"pca": {
"class": PCA.class_name(),
"state": "planned",
"operator": "PCA",
"label": "PCA",
"documentation_url": "https://lale.readthedocs.io/en/latest/modules/lale.lib.sklearn.pca.html",
},
"no_op": {
"class": NoOp.class_name(),
"state": "trained",
"operator": "NoOp",
"label": "NoOp",
"documentation_url": "https://lale.readthedocs.io/en/latest/modules/lale.lib.lale.no_op.html",
"hyperparams": None,
"coefs": None,
"is_frozen_trainable": True,
"is_frozen_trained": True,
},
"concat_features": {
"class": ConcatFeatures.class_name(),
"state": "trained",
"operator": "ConcatFeatures",
"label": "ConcatFeatures",
"documentation_url": "https://lale.readthedocs.io/en/latest/modules/lale.lib.lale.concat_features.html",
"hyperparams": None,
"coefs": None,
"is_frozen_trainable": True,
"is_frozen_trained": True,
},
"lr": {
"class": LR.class_name(),
"state": "planned",
"operator": "LogisticRegression",
"label": "LR",
"documentation_url": "https://lale.readthedocs.io/en/latest/modules/lale.lib.sklearn.logistic_regression.html",
},
},
}
json = to_json(operator)
self.assertEqual(json, json_expected)
operator_2 = from_json(json)
json_2 = to_json(operator_2)
self.assertEqual(json, json_2)
def test_empty_schema(self):
pca = PCA().customize_schema(whiten=schemas.Schema())
plan = ((pca & (MinMaxScaler | Normalizer)) >> ConcatFeatures() >>
(MinMaxScaler | Normalizer) >>
(LogisticRegression | KNeighborsClassifier))
from lale.search.schema2search_space import OperatorSchemaError
with self.assertRaises(OperatorSchemaError) as ctxt:
run_hyperopt_on_planned_pipeline(plan)
def test_no_max_schema(self):
pca = PCA().customize_schema(n_components=schemas.Float(min=0.0))
plan = ((pca & (MinMaxScaler | Normalizer)) >> ConcatFeatures() >>
(MinMaxScaler | Normalizer) >>
(LogisticRegression | KNeighborsClassifier))
from lale.search.search_space import SearchSpaceError
with self.assertRaises(SearchSpaceError) as ctxt:
run_hyperopt_on_planned_pipeline(plan)
def test_remove_last5(self):
pipeline = (
StandardScaler()
>> (PCA() & Nystroem() & PassiveAggressiveClassifier())
>> ConcatFeatures()
>> NoOp()
>> PassiveAggressiveClassifier()
)
pipeline.remove_last(inplace=True).freeze_trainable()
def test_init_fit_predict_pandas_series(self):
trainable_cf = ConcatFeatures()
A = [[11, 12, 13], [21, 22, 23], [31, 32, 33]]
B = [14, 24, 34]
A = pd.DataFrame(A, columns=["a", "b", "c"])
B = pd.Series(B, name="d")
A = add_table_name(A, "A")
B = add_table_name(B, "B")
trained_cf = trainable_cf.fit(X=[A, B])
transformed = trained_cf.transform([A, B])
expected = [
[11, 12, 13, 14],
[21, 22, 23, 24],
[31, 32, 33, 34],
]
expected = pd.DataFrame(expected, columns=["a", "b", "c", "d"])
for c in expected.columns:
self.assertEqual(list(transformed[c]), list(expected[c]))
def test_two_estimators_predict_proba(self):
pipeline = (
StandardScaler()
>> (PCA() & Nystroem() & LogisticRegression())
>> ConcatFeatures()
>> NoOp()
>> LogisticRegression()
)
trained = pipeline.fit(self.X_train, self.y_train)
trained.predict_proba(self.X_test)
def test_two_estimators_predict_proba1(self):
pipeline = (
StandardScaler()
>> (PCA() & Nystroem() & GaussianNB())
>> ConcatFeatures()
>> NoOp()
>> GaussianNB()
)
pipeline.fit(self.X_train, self.y_train)
pipeline.predict_proba(self.X_test)
def do1DTest(self, trainable, train_X, train_y, test_X, test_y):
#Test for 1-D array as input to the transformers
train_X = train_X[:,0]
test_X = test_X[:,0]
trainable_pipeline = (trainable & NoOp()) >> ConcatFeatures() >> float32_transform() >> LR()
trained_pipeline = trainable_pipeline.fit(train_X, train_y)
trained_pipeline.predict(test_X)
hyperopt = Hyperopt(estimator=trainable_pipeline, max_evals=1)
trained_hyperopt = hyperopt.fit(train_X, train_y)
trained_hyperopt.predict(test_X)
def test_export_to_sklearn_pipeline2(self):
from lale.lib.lale import ConcatFeatures
from lale.lib.sklearn import PCA
from lale.lib.sklearn import KNeighborsClassifier
from sklearn.feature_selection import SelectKBest
from lale.lib.sklearn import Nystroem
from sklearn.pipeline import FeatureUnion
lale_pipeline = (
((PCA() & SelectKBest(k=3)) >> ConcatFeatures())
& Nystroem()) >> ConcatFeatures() >> KNeighborsClassifier()
trained_lale_pipeline = lale_pipeline.fit(self.X_train, self.y_train)
sklearn_pipeline = trained_lale_pipeline.export_to_sklearn_pipeline()
self.assertIsInstance(sklearn_pipeline.named_steps['featureunion'],
FeatureUnion)
from sklearn.neighbors import KNeighborsClassifier
self.assertIsInstance(
sklearn_pipeline.named_steps['kneighborsclassifier'],
KNeighborsClassifier)
self.assert_equal_predictions(sklearn_pipeline, trained_lale_pipeline)
def test_transform_schema_Concat_irisArr(self):
from lale.datasets.data_schemas import to_schema
existing_flag = disable_data_schema_validation
set_disable_data_schema_validation(False)
data_X, data_y = self._irisArr["X"], self._irisArr["y"]
s_in_X, s_in_y = to_schema(data_X), to_schema(data_y)
def check(s_actual, n_expected, s_expected):
assert s_actual["items"]["minItems"] == n_expected, str(s_actual)
assert s_actual["items"]["maxItems"] == n_expected, str(s_actual)
assert s_actual["items"]["items"] == s_expected, str(s_actual)
s_out_X = ConcatFeatures.transform_schema({"items": [s_in_X]})
check(s_out_X, 4, {"type": "number"})
s_out_y = ConcatFeatures.transform_schema({"items": [s_in_y]})
check(s_out_y, 1, {"type": "integer"})
s_out_XX = ConcatFeatures.transform_schema({"items": [s_in_X, s_in_X]})
check(s_out_XX, 8, {"type": "number"})
s_out_yy = ConcatFeatures.transform_schema({"items": [s_in_y, s_in_y]})
check(s_out_yy, 2, {"type": "integer"})
s_out_Xy = ConcatFeatures.transform_schema({"items": [s_in_X, s_in_y]})
check(s_out_Xy, 5, {"type": "number"})
s_out_XXX = ConcatFeatures.transform_schema(
{"items": [s_in_X, s_in_X, s_in_X]})
check(s_out_XXX, 12, {"type": "number"})
set_disable_data_schema_validation(existing_flag)
def test_transform_schema_Concat_irisDf(self):
with EnableSchemaValidation():
from lale.datasets.data_schemas import to_schema
data_X, data_y = self._irisDf["X"], self._irisDf["y"]
s_in_X, s_in_y = to_schema(data_X), to_schema(data_y)
def check(s_actual, n_expected, s_expected):
assert s_actual["items"]["minItems"] == n_expected, str(
s_actual)
assert s_actual["items"]["maxItems"] == n_expected, str(
s_actual)
assert s_actual["items"]["items"] == s_expected, str(s_actual)
s_out_X = ConcatFeatures.transform_schema({"items": [s_in_X]})
check(s_out_X, 4, {"type": "number"})
s_out_y = ConcatFeatures.transform_schema({"items": [s_in_y]})
check(s_out_y, 1, {"description": "target", "type": "integer"})
s_out_XX = ConcatFeatures.transform_schema(
{"items": [s_in_X, s_in_X]})
check(s_out_XX, 8, {"type": "number"})
s_out_yy = ConcatFeatures.transform_schema(
{"items": [s_in_y, s_in_y]})
check(s_out_yy, 2, {"type": "integer"})
s_out_Xy = ConcatFeatures.transform_schema(
{"items": [s_in_X, s_in_y]})
check(s_out_Xy, 5, {"type": "number"})
s_out_XXX = ConcatFeatures.transform_schema(
{"items": [s_in_X, s_in_X, s_in_X]})
check(s_out_XXX, 12, {"type": "number"})
def test_concat_with_hyperopt(self):
from lale.lib.lale import Hyperopt
pca = PCA(n_components=3)
nys = Nystroem(n_components=10)
concat = ConcatFeatures()
lr = LogisticRegression(random_state=42, C=0.1)
trainable = (pca & nys) >> concat >> lr
clf = Hyperopt(estimator=trainable, max_evals=2)
from sklearn.datasets import load_iris
iris_data = load_iris()
clf.fit(iris_data.data, iris_data.target)
clf.predict(iris_data.data)
def test_with_pandas(self):
from lale.datasets import load_iris_df
import warnings
warnings.filterwarnings("ignore")
pca = PCA(n_components=3)
nys = Nystroem(n_components=10)
concat = ConcatFeatures()
lr = LogisticRegression(random_state=42, C=0.1)
trainable = (pca & nys) >> concat >> lr
(X_train, y_train), (X_test, y_test) = load_iris_df()
trained = trainable.fit(X_train, y_train)
predicted = trained.predict(X_test)
def test_with_concat_features1(self):
import warnings
warnings.filterwarnings("ignore")
from sklearn.datasets import load_iris
from lale.lib.lale import Hyperopt
from sklearn.metrics import accuracy_score
data = load_iris()
X, y = data.data, data.target
pca = PCA(n_components=3)
nys = Nystroem(n_components=10)
concat = ConcatFeatures()
lr = LogisticRegression(random_state=42, C=0.1)
pipeline = ((pca & nys) >> concat >> lr) | KNeighborsClassifier()
clf = Hyperopt(estimator=pipeline, max_evals=1)
trained = clf.fit(X, y)
predictions = trained.predict(X)
print(accuracy_score(y, predictions))
warnings.resetwarnings()
def test_export_to_sklearn_pipeline3(self):
from lale.lib.lale import ConcatFeatures
from lale.lib.sklearn import PCA
from lale.lib.sklearn import KNeighborsClassifier, LogisticRegression, SVC
from sklearn.feature_selection import SelectKBest
from lale.lib.sklearn import Nystroem
from sklearn.pipeline import FeatureUnion
lale_pipeline = (
(PCA() >> SelectKBest(k=2)) &
(Nystroem(random_state=42) >> SelectKBest(k=3))
& (SelectKBest(k=3))) >> ConcatFeatures() >> SelectKBest(
k=2) >> LogisticRegression()
trained_lale_pipeline = lale_pipeline.fit(self.X_train, self.y_train)
sklearn_pipeline = trained_lale_pipeline.export_to_sklearn_pipeline()
self.assertIsInstance(sklearn_pipeline.named_steps['featureunion'],
FeatureUnion)
self.assertIsInstance(sklearn_pipeline.named_steps['selectkbest'],
SelectKBest)
from sklearn.linear_model import LogisticRegression
self.assertIsInstance(
sklearn_pipeline.named_steps['logisticregression'],
LogisticRegression)
self.assert_equal_predictions(sklearn_pipeline, trained_lale_pipeline)
def test_transform_schema_Concat_irisDf(self):
from lale.datasets.data_schemas import to_schema
data_X, data_y = self._irisDf['X'], self._irisDf['y']
s_in_X, s_in_y = to_schema(data_X), to_schema(data_y)
def check(s_actual, n_expected, s_expected):
assert s_actual['items']['minItems'] == n_expected, str(s_actual)
assert s_actual['items']['maxItems'] == n_expected, str(s_actual)
assert s_actual['items']['items'] == s_expected, str(s_actual)
s_out_X = ConcatFeatures.transform_schema({'items': [s_in_X]})
check(s_out_X, 4, {'type': 'number'})
s_out_y = ConcatFeatures.transform_schema({'items': [s_in_y]})
check(s_out_y, 1, {'description': 'target', 'type': 'integer'})
s_out_XX = ConcatFeatures.transform_schema({'items': [s_in_X, s_in_X]})
check(s_out_XX, 8, {'type': 'number'})
s_out_yy = ConcatFeatures.transform_schema({'items': [s_in_y, s_in_y]})
check(s_out_yy, 2, {'type': 'integer'})
s_out_Xy = ConcatFeatures.transform_schema({'items': [s_in_X, s_in_y]})
check(s_out_Xy, 5, {'type': 'number'})
s_out_XXX = ConcatFeatures.transform_schema({
'items': [s_in_X, s_in_X, s_in_X]})
check(s_out_XXX, 12, {'type': 'number'})
def test_hyperparam_defaults(self):
cf = ConcatFeatures()
