def test_sklearn_estimator_regression_validation():
ds = vaex.ml.datasets.load_iris()
train, test = ds.ml.train_test_split(verbose=False)
features = ['sepal_length', 'sepal_width', 'petal_length']
# Dense features
Xtrain = train[features].values
Xtest = test[features].values
ytrain = train.petal_width.values
for model in models_regression:
# vaex
vaex_model = SKLearnPredictor(model=model,
features=features,
prediction_name='pred')
vaex_model.fit(train, train.petal_width)
test = vaex_model.transform(test)
# sklearn
model.fit(Xtrain, ytrain)
skl_pred = model.predict(Xtest)
np.testing.assert_array_almost_equal(test.pred.values,
skl_pred,
decimal=5)
def test_sklearn_estimator_classification_validation():
ds = vaex.ml.datasets.load_titanic()
train, test = ds.ml.train_test_split(verbose=False)
features = ['pclass', 'parch', 'sibsp']
# Dense features
Xtrain = train[features].values
Xtest = test[features].values
ytrain = train.survived.values
for model in models_classification:
# vaex
vaex_model = SKLearnPredictor(model=model,
features=features,
prediction_name='pred')
vaex_model.fit(train, train.survived)
test = vaex_model.transform(test)
# scikit-learn
model.fit(Xtrain, ytrain)
skl_pred = model.predict(Xtest)
assert np.all(skl_pred == test.pred.values)
def test_sklearn_estimator():
ds = vaex.ml.datasets.load_iris()
features = ['sepal_length', 'sepal_width', 'petal_length']
train, test = ds.ml.train_test_split(verbose=False)
model = SKLearnPredictor(model=LinearRegression(),
features=features,
prediction_name='pred')
model.fit(train, train.petal_width)
prediction = model.predict(test)
test = model.transform(test)
np.testing.assert_array_almost_equal(test.pred.values,
prediction,
decimal=5)
# Transfer the state of train to ds
train = model.transform(train)
state = train.state_get()
ds.state_set(state)
assert ds.pred.values.shape == (150, )
def test_sklearn_estimator_virtual_columns():
ds = vaex.ml.datasets.load_iris()
ds['x'] = ds.sepal_length * 1
ds['y'] = ds.sepal_width * 1
ds['w'] = ds.petal_length * 1
ds['z'] = ds.petal_width * 1
train, test = ds.ml.train_test_split(test_size=0.2, verbose=False)
features = ['x', 'y', 'z']
model = SKLearnPredictor(model=LinearRegression(),
features=features,
prediction_name='pred')
model.fit(ds, ds.w)
ds = model.transform(ds)
assert ds.pred.values.shape == (150, )