def test_nmf_with_all_datasets(self):
should_succeed = ['digits']
should_fail = ['irisArr', 'irisDf', 'housing', 'creditG', 'movies', 'drugRev']
for name in should_succeed:
dataset = getattr(self, f'_{name}')
NMF.validate_schema(**dataset)
for name in should_fail:
dataset = getattr(self, f'_{name}')
with self.assertRaises(ValueError):
NMF.validate_schema(**dataset)
def test_nmf_with_all_datasets(self):
should_succeed = ["digits"]
should_fail = ["irisArr", "irisDf", "housing", "creditG", "movies", "drugRev"]
for name in should_succeed:
dataset = getattr(self, f"_{name}")
NMF.validate_schema(**dataset)
for name in should_fail:
dataset = getattr(self, f"_{name}")
with self.assertRaises(ValueError):
NMF.validate_schema(**dataset)
def test_init_fit_predict(self):
import lale.datasets
nmf = NMF()
lr = LogisticRegression()
trainable = nmf >> lr
(train_X, train_y), (test_X, test_y) = lale.datasets.digits_df()
trained = trainable.fit(train_X, train_y)
predicted = trained.predict(test_X)
def test_init_fit_transform(self):
import lale.datasets
from lale.lib.lale import Both
nmf = NMF()
pca = PCA()
trainable = Both(op1=nmf, op2=pca)
(train_X, train_y), (test_X, test_y) = lale.datasets.digits_df()
trained = trainable.fit(train_X, train_y)
transformed = trained.transform(test_X)
def test_input_schema_fit(self):
self.maxDiff = None
self.assertEqual(
LogisticRegression.input_schema_fit(),
LogisticRegression.get_schema("input_fit"),
)
self.assertEqual(
(NMF >> LogisticRegression).input_schema_fit(), NMF.get_schema("input_fit")
)
self.assertEqual(
IdentityWrapper(op=LogisticRegression).input_schema_fit(),
LogisticRegression.get_schema("input_fit"),
)
actual = (TfidfVectorizer | NMF).input_schema_fit()
expected = {
"anyOf": [
{
"type": "object",
"required": ["X"],
"additionalProperties": False,
"properties": {
"X": {
"anyOf": [
{"type": "array", "items": {"type": "string"}},
{
"type": "array",
"items": {
"type": "array",
"minItems": 1,
"maxItems": 1,
"items": {"type": "string"},
},
},
]
},
"y": {},
},
},
{
"type": "object",
"required": ["X"],
"additionalProperties": False,
"properties": {
"X": {
"type": "array",
"items": {
"type": "array",
"items": {"type": "number", "minimum": 0.0},
},
},
"y": {},
},
},
]
}
self.assertEqual(actual, expected)
def test_input_schema_fit(self):
self.maxDiff = None
self.assertEqual(LogisticRegression.input_schema_fit(),
LogisticRegression.get_schema('input_fit'))
self.assertEqual((NMF >> LogisticRegression).input_schema_fit(),
NMF.get_schema('input_fit'))
self.assertEqual(
IdentityWrapper(op=LogisticRegression).input_schema_fit(),
LogisticRegression.get_schema('input_fit'))
actual = (TfidfVectorizer | NMF).input_schema_fit()
expected = {
'anyOf': [{
'type': 'object',
'required': ['X'],
'additionalProperties': False,
'properties': {
'X': {
'anyOf': [{
'type': 'array',
'items': {
'type': 'string'
}
}, {
'type': 'array',
'items': {
'type': 'array',
'minItems': 1,
'maxItems': 1,
'items': {
'type': 'string'
}
}
}]
},
'y': {}
}
}, {
'type': 'object',
'required': ['X'],
'additionalProperties': False,
'properties': {
'X': {
'type': 'array',
'items': {
'type': 'array',
'items': {
'type': 'number',
'minimum': 0.0
}
}
},
'y': {}
}
}]
}
self.assertEqual(actual, expected)
def test_not_randome_state(self):
with EnableSchemaValidation():
with self.assertRaises(jsonschema.ValidationError):
_ = NMF(random_state='"not RandomState"')
