def test_predict(self, data):
raw_model = VW()
raw_model.fit(data.x, data.y)
model = VWRegressor()
model.fit(data.x, data.y)
assert np.allclose(raw_model.predict(data.x), model.predict(data.x))
# ensure model can make multiple calls to predict
assert np.allclose(raw_model.predict(data.x), model.predict(data.x))
def test_predict(self, data):
raw_model = VW()
raw_model.fit(data.x, data.y)
model = VWRegressor()
model.fit(data.x, data.y)
assert np.allclose(raw_model.predict(data.x), model.predict(data.x))
# ensure model can make multiple calls to predict
assert np.allclose(raw_model.predict(data.x), model.predict(data.x))
def test_save_load(tmp_path):
train_file = str(tmp_path / "train.model")
X = [[1, 2], [3, 4], [5, 6], [7, 8]]
y = [1, 2, 3, 4]
model_before = VWRegressor(l=100)
model_before.fit(X, y)
before_saving = model_before.predict(X)
model_before.save(train_file)
model_after = VWRegressor(l=100)
model_after.load(train_file)
after_loading = model_after.predict(X)
assert all([a == b for a, b in zip(before_saving, after_loading)])
from vowpalwabbit.sklearn_vw import VWRegressor
X = [[1, 2], [3, 4], [5, 6], [7, 8]]
y = [1, 2, 3, 4]
model = VWRegressor(l=100)
model.fit(X, y)
print(model.predict(X))
model.save("/tmp/train.model")
model2 = VWRegressor(l=100)
model2.load("/tmp/train.model")
print(model2.predict(X))