def test_add_constraint(self):
init = self.sk_pca.hyperparam_schema()
expected = {
'allOf': [{
'type': 'object',
'properties': {}
}, {
'anyOf': [{
'type': 'object',
'properties': {
'n_components': {
'not': {
'enum': ['mle']
},
}
},
}, {
'type': 'object',
'properties': {
'svd_solver': {
'enum': ['full', 'auto']
},
}
}]
}]
}
foo = self.sk_pca.customize_schema(constraint=schemas.AnyOf([
schemas.Object(
{'n_components': schemas.Not(schemas.Enum(['mle']))}),
schemas.Object({'svd_solver': schemas.Enum(['full', 'auto'])})
]))
self.assertEqual(foo.hyperparam_schema(), expected)
helpers.validate_is_schema(foo._schemas)
self.assertEqual(self.sk_pca.hyperparam_schema(), init)
def test_disable_schema_validation_individual_op(self):
os.environ["LALE_DISABLE_SCHEMA_VALIDATION"] = "True"
import lale.schemas as schemas
from lale.lib.sklearn import PCA
pca_input = schemas.Object(
X=schemas.AnyOf(
[
schemas.Array(schemas.Array(schemas.String())),
schemas.Array(schemas.String()),
]
)
)
foo = PCA.customize_schema(input_fit=pca_input)
pca_output = schemas.Object(
X=schemas.AnyOf(
[
schemas.Array(schemas.Array(schemas.String())),
schemas.Array(schemas.String()),
]
)
)
foo = foo.customize_schema(output_transform=pca_output)
abc = foo()
trained_pca = abc.fit(self.X_train)
trained_pca.transform(self.X_test)
os.environ["LALE_DISABLE_SCHEMA_VALIDATION"] = "False"
def test_enable_schema_validation_individual_op(self):
existing_flag = disable_data_schema_validation
set_disable_data_schema_validation(False)
import lale.schemas as schemas
from lale.lib.sklearn import PCA
pca_input = schemas.Object(X=schemas.AnyOf([
schemas.Array(schemas.Array(schemas.String())),
schemas.Array(schemas.String()),
]))
foo = PCA.customize_schema(input_fit=pca_input)
pca_output = schemas.Object(X=schemas.AnyOf([
schemas.Array(schemas.Array(schemas.String())),
schemas.Array(schemas.String()),
]))
foo = foo.customize_schema(output_transform=pca_output)
abc = foo()
with self.assertRaises(ValueError):
trained_pca = abc.fit(self.X_train)
trained_pca.transform(self.X_test)
set_disable_data_schema_validation(existing_flag)
def test_add_constraint(self):
init = self.sk_pca.hyperparam_schema()
init_expected = {
"allOf": [
{
"type": "object",
"relevantToOptimizer": [],
"additionalProperties": False,
"properties": {
"n_components": {"default": None},
"copy": {"default": True},
"whiten": {"default": False},
"svd_solver": {"default": "auto"},
"tol": {"default": 0.0},
"iterated_power": {"default": "auto"},
"random_state": {"default": None},
},
}
]
}
self.assertEqual(init, init_expected)
expected = {
"allOf": [
init_expected["allOf"][0],
{
"anyOf": [
{
"type": "object",
"properties": {
"n_components": {
"not": {"enum": ["mle"]},
}
},
},
{
"type": "object",
"properties": {
"svd_solver": {"enum": ["full", "auto"]},
},
},
]
},
]
}
foo = self.sk_pca.customize_schema(
constraint=schemas.AnyOf(
[
schemas.Object(n_components=schemas.Not(schemas.Enum(["mle"]))),
schemas.Object(svd_solver=schemas.Enum(["full", "auto"])),
]
)
)
self.assertEqual(foo.hyperparam_schema(), expected)
lale.type_checking.validate_is_schema(foo._schemas)
self.assertEqual(self.sk_pca.hyperparam_schema(), init)
def test_add_constraint(self):
init = self.sk_pca.hyperparam_schema()
init_expected = {'allOf': [
{ 'type': 'object',
'relevantToOptimizer': [],
'additionalProperties': False,
'properties': {
'n_components': {'default': None},
'copy': {'default': True},
'whiten': {'default': False},
'svd_solver': {'default': 'auto'},
'tol': {'default': 0.0},
'iterated_power': {'default': 'auto'},
'random_state': {'default': None}}}]}
self.assertEqual(init, init_expected)
expected = {'allOf': [
init_expected['allOf'][0],
{'anyOf': [
{'type': 'object',
'properties': {
'n_components': {
'not': {
'enum': ['mle']},
}},
},
{'type': 'object',
'properties': {
'svd_solver': {
'enum': ['full', 'auto']},
}}]}]}
foo = self.sk_pca.customize_schema(
constraint=schemas.AnyOf([
schemas.Object(n_components=schemas.Not(schemas.Enum(['mle']))),
schemas.Object(svd_solver=schemas.Enum(['full', 'auto']))
]))
self.assertEqual(foo.hyperparam_schema(), expected)
lale.type_checking.validate_is_schema(foo._schemas)
self.assertEqual(self.sk_pca.hyperparam_schema(), init)
def test_override_object_param(self):
init = self.sk_pca.get_schema('input_fit')
expected = {'type': 'object',
'required': ['X'],
'additionalProperties': False,
'properties': {
'X': {'type': 'array',
'items': {
'type': 'number'}}}}
foo = self.sk_pca.customize_schema(
input_fit=schemas.Object(required=['X'],
additionalProperties=False,
X=schemas.Array(schemas.Float())))
self.assertEqual(foo.get_schema('input_fit'), expected)
lale.type_checking.validate_is_schema(foo.get_schema('input_fit'))
self.assertEqual(self.sk_pca.get_schema('input_fit'), init)
def test_override_object_param(self):
init = self.sk_pca.get_schema("input_fit")
expected = {
"type": "object",
"required": ["X"],
"additionalProperties": False,
"properties": {"X": {"type": "array", "items": {"type": "number"}}},
}
foo = self.sk_pca.customize_schema(
input_fit=schemas.Object(
required=["X"],
additionalProperties=False,
X=schemas.Array(schemas.Float()),
)
)
self.assertEqual(foo.get_schema("input_fit"), expected)
lale.type_checking.validate_is_schema(foo.get_schema("input_fit"))
self.assertEqual(self.sk_pca.get_schema("input_fit"), init)
def test_disable_schema_validation_pipeline(self):
os.environ["LALE_DISABLE_SCHEMA_VALIDATION"]='True'
from lale.lib.sklearn import PCA, LogisticRegression
import lale.schemas as schemas
lr_input = schemas.Object(required=['X', 'y'], X=schemas.AnyOf([
schemas.Array(
schemas.Array(
schemas.String())),
schemas.Array(
schemas.String())]),
y=schemas.Array(schemas.String()))
foo = LogisticRegression.customize_schema(input_fit=lr_input)
abc = foo()
pipeline = PCA() >> abc
trained_pipeline = pipeline.fit(self.X_train, self.y_train)
trained_pipeline.predict(self.X_test)
os.environ["LALE_DISABLE_SCHEMA_VALIDATION"]='False'
def test_enable_schema_validation_pipeline(self):
with EnableSchemaValidation():
import lale.schemas as schemas
from lale.lib.sklearn import PCA, LogisticRegression
lr_input = schemas.Object(
required=["X", "y"],
X=schemas.AnyOf([
schemas.Array(schemas.Array(schemas.String())),
schemas.Array(schemas.String()),
]),
y=schemas.Array(schemas.String()),
)
foo = LogisticRegression.customize_schema(input_fit=lr_input)
abc = foo()
pipeline = PCA() >> abc
with self.assertRaises(ValueError):
trained_pipeline = pipeline.fit(self.X_train, self.y_train)
trained_pipeline.predict(self.X_test)
def test_disable_schema_validation_pipeline(self):
existing_flag = disable_data_schema_validation
set_disable_data_schema_validation(True)
import lale.schemas as schemas
from lale.lib.sklearn import PCA, LogisticRegression
lr_input = schemas.Object(
required=["X", "y"],
X=schemas.AnyOf([
schemas.Array(schemas.Array(schemas.String())),
schemas.Array(schemas.String()),
]),
y=schemas.Array(schemas.String()),
)
foo = LogisticRegression.customize_schema(input_fit=lr_input)
abc = foo()
pipeline = PCA() >> abc
trained_pipeline = pipeline.fit(self.X_train, self.y_train)
trained_pipeline.predict(self.X_test)
set_disable_data_schema_validation(existing_flag)
def test_override_object_param(self):
init = self.sk_pca.get_schema('input_fit')
expected = {
'$schema': 'http://json-schema.org/draft-04/schema#',
'type': 'object',
'required': ['X'],
'additionalProperties': False,
'properties': {
'X': {
'type': 'array',
'items': {
'type': 'number'
}
}
}
}
foo = self.sk_pca.customize_schema(input_fit=schemas.Object(
required=['X'],
additionalProperties=False,
properties={'X': schemas.Array(schemas.Float())}))
self.assertEqual(foo.get_schema('input_fit'), expected)
helpers.validate_is_schema(foo.get_schema('input_fit'))
self.assertEqual(self.sk_pca.get_schema('input_fit'), init)
