def test_with_hyperopt(self):
planned = FunctionTransformer(func=np.log1p) >> LogisticRegression
trained = planned.auto_configure(self.train_X,
self.train_y,
optimizer=Hyperopt,
cv=3,
max_evals=3)
_ = trained.predict(self.test_X)
def test_scorers_np_cat(self):
fairness_info = self.creditg_np_cat["fairness_info"]
train_X = self.creditg_np_cat["train_X"]
train_y = self.creditg_np_cat["train_y"]
cat_columns, num_columns = [], []
for i in range(train_X.shape[1]):
try:
_ = train_X[:, i].astype(np.float64)
num_columns.append(i)
except ValueError:
cat_columns.append(i)
trainable = (
(
(Project(columns=cat_columns) >> OneHotEncoder(handle_unknown="ignore"))
& (
Project(columns=num_columns)
>> FunctionTransformer(func=lambda x: x.astype(np.float64))
)
)
>> ConcatFeatures
>> LogisticRegression(max_iter=1000)
)
trained = trainable.fit(train_X, train_y)
test_X = self.creditg_np_cat["test_X"]
test_y = self.creditg_np_cat["test_y"]
self._attempt_scorers(fairness_info, trained, test_X, test_y)
def test_init_fit_predict(self):
import numpy as np
import lale.datasets
ft = FunctionTransformer(func=np.log1p)
lr = LogisticRegression()
trainable = ft >> 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_predict(self):
(train_X_pd, train_y_pd), (test_X_pd,
test_y_pd) = self.tgt2creditg["pandas"]
to_pd = FunctionTransformer(
func=lambda X: X if isinstance(X, pd.DataFrame) else X.toPandas())
lr = LogisticRegression()
sk_trainable = SkStandardScaler() >> lr
sk_trained = sk_trainable.fit(train_X_pd, train_y_pd)
sk_predicted = sk_trained.predict(test_X_pd)
rasl_trainable = RaslStandardScaler() >> to_pd >> lr
for tgt, dataset in self.tgt2creditg.items():
(train_X, train_y), (test_X, test_y) = dataset
rasl_trained = rasl_trainable.fit(train_X, train_y)
rasl_predicted = rasl_trained.predict(test_X)
self.assertEqual(sk_predicted.shape, rasl_predicted.shape, tgt)
self.assertEqual(sk_predicted.tolist(), rasl_predicted.tolist(),
tgt)
def test_predict(self):
(train_X_pd, train_y_pd), (test_X_pd,
test_y_pd) = self.tgt2creditg["pandas"]
cat_columns = categorical()(train_X_pd)
prefix = Map(columns={c: it[c] for c in cat_columns})
to_pd = FunctionTransformer(
func=lambda X: X if isinstance(X, pd.DataFrame) else X.toPandas())
lr = LogisticRegression()
sk_trainable = prefix >> SkOneHotEncoder(sparse=False) >> lr
sk_trained = sk_trainable.fit(train_X_pd, train_y_pd)
sk_predicted = sk_trained.predict(test_X_pd)
rasl_trainable = prefix >> RaslOneHotEncoder(
sparse=False) >> to_pd >> lr
for tgt, dataset in self.tgt2creditg.items():
(train_X, train_y), (test_X, test_y) = dataset
rasl_trained = rasl_trainable.fit(train_X, train_y)
rasl_predicted = rasl_trained.predict(test_X)
self.assertEqual(sk_predicted.shape, rasl_predicted.shape, tgt)
self.assertEqual(sk_predicted.tolist(), rasl_predicted.tolist(),
tgt)
def test_predict(self):
self._fill_missing_value("age", 36.0, np.nan)
(train_X_pd, train_y_pd), (test_X_pd,
test_y_pd) = self.tgt2adult["pandas"]
num_columns = ["age", "fnlwgt", "education-num"]
prefix = Map(columns={c: it[c] for c in num_columns})
to_pd = FunctionTransformer(
func=lambda X: X if isinstance(X, pd.DataFrame) else X.toPandas())
lr = LogisticRegression()
imputer_args = {"strategy": "mean"}
sk_trainable = prefix >> SkSimpleImputer(**imputer_args) >> lr
sk_trained = sk_trainable.fit(train_X_pd, train_y_pd)
sk_predicted = sk_trained.predict(test_X_pd)
rasl_trainable = prefix >> RaslSimpleImputer(
**imputer_args) >> to_pd >> lr
for tgt, dataset in self.tgt2adult.items():
(train_X, train_y), (test_X, test_y) = dataset
rasl_trained = rasl_trainable.fit(train_X, train_y)
rasl_predicted = rasl_trained.predict(test_X)
self.assertEqual(sk_predicted.shape, rasl_predicted.shape, tgt)
self.assertEqual(sk_predicted.tolist(), rasl_predicted.tolist(),
tgt)
def test_validate(self):
default = FunctionTransformer.hyperparam_defaults()["validate"]
self.assertEqual(default, True)
def test_pass_y(self):
trainable = (FunctionTransformer(func=np.log1p, pass_y=False) >>
LogisticRegression())
trained = trainable.fit(self.train_X, self.train_y)
_ = trained.predict(self.test_X)
def test_with_defaults(self):
trainable = FunctionTransformer(func=np.log1p) >> LogisticRegression()
trained = trainable.fit(self.train_X, self.train_y)
_ = trained.predict(self.test_X)
def test_not_callable(self):
with EnableSchemaValidation():
with self.assertRaises(jsonschema.ValidationError):
_ = FunctionTransformer(func='"not callable"')
def test_pipeline_spark(self):
pipeline = (RaslMinMaxScaler() >> FunctionTransformer(
func=lambda X: X.toPandas()) >> LogisticRegression())
trained = pipeline.fit(self.X_train_spark, self.y_train)
_ = trained.predict(self.X_test_spark)