def test_with_improperly_defined_step(self, teardown):
x = Input()
y = DummyImproperlyDefined()(x)
model = Model(x, y)
with pytest.raises(RuntimeError):
model.predict(iris.data)
def test_fit_predict_pipeline(teardown):
x_data = iris.data
y_t_data = iris.target
random_state = 123
n_components = 2
# baikal way
x = Input()
y_t = Input()
x_pca = PCA(n_components=n_components, random_state=random_state, name="pca")(x)
y = LogisticRegression(
multi_class="multinomial",
solver="lbfgs",
random_state=random_state,
name="logreg",
)(x_pca, y_t)
model = Model(x, y, y_t)
y_pred_baikal = model.fit(x_data, y_t_data).predict(x_data)
# traditional way
pca = PCA(n_components=n_components, random_state=random_state)
logreg = LogisticRegression(
multi_class="multinomial", solver="lbfgs", random_state=random_state
)
x_data_transformed = pca.fit_transform(x_data)
y_pred_traditional = logreg.fit(x_data_transformed, y_t_data).predict(
x_data_transformed
)
assert_array_equal(y_pred_baikal, y_pred_traditional)
def test_fit_predict_ensemble(teardown):
mask = iris.target != 2 # Reduce to binary problem to avoid ConvergenceWarning
x_data = iris.data
y_t_data = iris.target
random_state = 123
# baikal way
x = Input()
y_t = Input()
y1 = LogisticRegression(random_state=random_state)(x, y_t)
y2 = RandomForestClassifier(random_state=random_state)(x, y_t)
features = Stack(axis=1)([y1, y2])
y = LogisticRegression(random_state=random_state)(features, y_t)
model = Model(x, y, y_t)
model.fit(x_data, y_t_data)
y_pred_baikal = model.predict(x_data)
# traditional way
logreg = sklearn.linear_model.LogisticRegression(random_state=random_state)
logreg.fit(x_data, y_t_data)
logreg_pred = logreg.predict(x_data)
random_forest = sklearn.ensemble.RandomForestClassifier(random_state=random_state)
random_forest.fit(x_data, y_t_data)
random_forest_pred = random_forest.predict(x_data)
features = np.stack([logreg_pred, random_forest_pred], axis=1)
ensemble = sklearn.linear_model.LogisticRegression(random_state=random_state)
ensemble.fit(features, y_t_data)
y_pred_traditional = ensemble.predict(features)
assert_array_equal(y_pred_baikal, y_pred_traditional)
def test_fit_predict_naive_stack(teardown):
x_data = iris.data
y_t_data = iris.target
random_state = 123
# baikal way
x = Input()
y_t = Input()
y1 = LogisticRegression(random_state=random_state, solver="liblinear")(x, y_t)
y2 = RandomForestClassifier(random_state=random_state)(x, y_t)
features = Stack(axis=1)([y1, y2])
y = LogisticRegression(random_state=random_state, solver="liblinear")(features, y_t)
model = Model(x, y, y_t)
model.fit(x_data, y_t_data)
y_pred_baikal = model.predict(x_data)
# traditional way
logreg = LogisticRegression(random_state=random_state, solver="liblinear")
logreg.fit(x_data, y_t_data)
logreg_pred = logreg.predict(x_data)
random_forest = RandomForestClassifier(random_state=random_state)
random_forest.fit(x_data, y_t_data)
random_forest_pred = random_forest.predict(x_data)
features = np.stack([logreg_pred, random_forest_pred], axis=1)
stacked = LogisticRegression(random_state=random_state, solver="liblinear")
stacked.fit(features, y_t_data)
y_pred_traditional = stacked.predict(features)
assert_array_equal(y_pred_baikal, y_pred_traditional)
def test_nested_model(teardown):
x_data = iris.data
y_t_data = iris.target
# Sub-model
x = Input()
y_t = Input()
h = PCA(n_components=2)(x)
y = LogisticRegression()(h, y_t)
submodel = Model(x, y, y_t)
# Model
x = Input()
y_t = Input()
y = submodel(x, y_t)
model = Model(x, y, y_t)
with raises_with_cause(RuntimeError, NotFittedError):
submodel.predict(x_data)
model.fit(x_data, y_t_data)
y_pred = model.predict(x_data)
y_pred_sub = submodel.predict(x_data)
assert_array_equal(y_pred, y_pred_sub)
def test_fit_params(teardown):
x_data = iris.data
y_t_data = iris.target
random_state = 123
n_components = 2
sample_weight = y_t_data + 1 # Just weigh the classes differently
fit_params = {"logreg__sample_weight": sample_weight}
# baikal way
x = Input()
y_t = Input()
x_pca = PCA(n_components=n_components, random_state=random_state, name="pca")(x)
y = LogisticRegression(
multi_class="multinomial",
solver="lbfgs",
random_state=random_state,
name="logreg",
)(x_pca, y_t)
model = Model(x, y, y_t)
model.fit(x_data, y_t_data, **fit_params)
# traditional way
pca = PCA(n_components=n_components, random_state=random_state)
logreg = LogisticRegression(
multi_class="multinomial", solver="lbfgs", random_state=random_state
)
pipe = Pipeline([("pca", pca), ("logreg", logreg)])
pipe.fit(x_data, y_t_data, **fit_params)
# Use assert_allclose instead of all equal due to small numerical differences
# between fit_transform(...) and fit(...).transform(...)
assert_allclose(model.get_step("logreg").coef_, pipe.named_steps["logreg"].coef_)
def test_get_params(teardown):
dummy1 = DummyEstimator(name="dummy1")
dummy2 = DummyEstimator(x=456, y="def", name="dummy2")
concat = Concatenate(name="concat") # a step without get_params/set_params
# a meaningless pipeline that contains shared steps
x1 = Input()
x2 = Input()
h = dummy1(x1)
c = concat([x1, h])
y1 = dummy2(c)
y2 = dummy2(x2, compute_func=lambda X: X * 2, trainable=False)
model = Model([x1, x2], [y1, y2])
expected = {
"dummy1": dummy1,
"dummy2": dummy2,
"concat": concat,
"dummy1__x": 123,
"dummy1__y": "abc",
"dummy2__x": 456,
"dummy2__y": "def",
}
params = model.get_params()
assert params == expected
def test_with_undefined_target(self, teardown):
x = Input()
y = LogisticRegression()(x, trainable=True)
model = Model(inputs=x, outputs=y)
with raises_with_cause(RuntimeError, TypeError):
# LogisticRegression.fit will be called with not enough arguments
# hence the TypeError
model.fit(iris.data)
def test_fit_with_shared_step(self, teardown):
x = Input()
scaler = StandardScaler()
z = scaler(x, compute_func="transform", trainable=True)
y = scaler(z, compute_func="inverse_transform", trainable=False)
model = Model(x, y)
model.fit(np.array([1, 3, 1, 3]).reshape(-1, 1))
assert (scaler.mean_, scaler.var_) == (2.0, 1.0)
def test_predict_with_shared_step(self, teardown):
x1 = Input()
x2 = Input()
doubler = Lambda(lambda x: x * 2)
y1 = doubler(x1)
y2 = doubler(x2)
model = Model([x1, x2], [y1, y2])
assert model.predict([2, 3]) == [4, 6]
def test_lazy_model(teardown):
x_data = np.array([[1, 2], [3, 4]])
x = Input()
model = Model(x, x)
model.fit(x_data) # nothing to fit
x_pred = model.predict(x_data)
assert_array_equal(x_pred, x_data)
def test_with_unnecessarily_defined_but_missing_target(self, teardown):
x = Input()
y_t = Input()
pca = PCA()
# The target passed to PCA is unnecessary (see notes in Step.__call__)
y = pca(x, y_t, trainable=True)
model = Model(inputs=x, outputs=y, targets=y_t)
with pytest.raises(ValueError):
# fails because of the model target specification and trainable=True
model.fit(iris.data)
def test_single_input(step_class, teardown):
x = Input()
y = step_class()(x)
model = Model(x, y)
x_data = np.array([[1, 2], [3, 4]])
if step_class is Stack:
assert_array_equal(x_data.reshape((2, 2, 1)), model.predict(x_data))
else:
assert_array_equal(x_data, model.predict(x_data))
def test_multiedge(teardown):
x = Input()
z1, z2 = DummySIMO()(x)
y = DummyMISO()([z1, z2])
model = Model(x, y)
x_data = np.array([[1], [2]])
y_out = model.predict(x_data)
assert_array_equal(y_out, np.array([[2], [4]]))
def test_predict_with_not_fitted_steps(self, teardown):
x_data = iris.data
x = Input(name="x")
xt = PCA(n_components=2)(x)
y = LogisticRegression(multi_class="multinomial", solver="lbfgs")(xt)
model = Model(x, y)
with raises_with_cause(RuntimeError, NotFittedError):
model.predict(x_data)
def test_fit_predict_with_shared_step(teardown):
x = Input()
scaler = StandardScaler()
z = scaler(x, compute_func="transform", trainable=True)
y = scaler(z, compute_func="inverse_transform", trainable=False)
model = Model(x, y)
X_data = np.array([1, 3, 1, 3]).reshape(-1, 1)
model.fit(X_data)
assert_array_equal(model.predict(X_data), X_data)
def test_split(x, indices_or_sections, teardown):
x1 = Input()
ys = Split(indices_or_sections, axis=0)(x1)
model = Model(x1, ys)
y_expected = np.split(x, indices_or_sections, axis=0)
y_pred = model.predict(x)
y_pred = listify(y_pred)
for actual, expected in safezip2(y_pred, y_expected):
assert_array_equal(actual, expected)
def test_with_non_fitted_non_trainable_step(self, teardown):
x = Input()
y_t = Input()
z = PCA()(x, trainable=False)
y = LogisticRegression()(z, y_t)
model = Model(x, y, y_t)
with raises_with_cause(RuntimeError, NotFittedError):
# this will raise an error when calling compute
# on PCA which was flagged as trainable=False but
# hasn't been fitted
model.fit(iris.data, iris.target)
def test_stack(teardown):
x1 = Input()
x2 = Input()
y = Stack(axis=1)([x1, x2])
model = Model([x1, x2], y)
x1_data = np.array([[1, 2], [10, 20]])
x2_data = np.array([[3, 4], [30, 40]])
y_expected = np.stack([x1_data, x2_data], axis=1)
y_pred = model.predict([x1_data, x2_data])
assert_array_equal(y_pred, y_expected)
def test_concatenate(teardown):
x1 = Input()
x2 = Input()
y = Concatenate(axis=1)([x1, x2])
model = Model([x1, x2], y)
x1_data = np.array([[1, 2], [10, 20]])
x2_data = np.array([[3, 4, 5], [30, 40, 50]])
y_expected = np.concatenate([x1_data, x2_data], axis=1)
y_pred = model.predict([x1_data, x2_data])
assert_array_equal(y_pred, y_expected)
def test_with_unnecessary_inputs(self, teardown):
x1 = Input()
x2 = Input()
y_t = Input()
h = PCA()(x1)
y = LogisticRegression()(h, y_t)
with pytest.raises(ValueError):
Model([x1, x2], y, y_t)
with pytest.raises(ValueError):
Model([x1, h], y, y_t) # x1 is an unnecessary input upstream of h
def test_fit_and_predict_model_with_no_fittable_steps(teardown):
X_data = np.array([[1, 2], [3, 4]])
y_expected = np.array([[2, 4], [6, 8]])
x = Input()
y = DummySISO()(x)
model = Model(x, y)
model.fit(X_data) # nothing to fit
y_pred = model.predict(X_data)
assert_array_equal(y_pred, y_expected)
def test_transformed_target(teardown):
x = Input()
y_t = Input()
y_t_mod = Lambda(lambda y: np.log(y))(y_t)
y_p_mod = LinearRegression()(x, y_t_mod)
y_p = Lambda(lambda y: np.exp(y))(y_p_mod)
model = Model(x, y_p, y_t)
x_data = np.arange(4).reshape(-1, 1)
y_t_data = np.exp(2 * x_data).ravel()
model.fit(x_data, y_t_data)
assert_array_equal(model.get_step("LinearRegression_0").coef_, np.array([2.0]))
def test_fit_predict_standard_stack(teardown):
# This uses the "standard" protocol where the 2nd level features
# are the out-of-fold predictions of the 1st. It also appends the
# original data to the 2nd level features.
# See for example: https://www.kdnuggets.com/2017/02/stacking-models-imropved-predictions.html
X_data, y_t_data = breast_cancer.data, breast_cancer.target
X_train, X_test, y_t_train, y_t_test = train_test_split(X_data,
y_t_data,
test_size=0.2,
random_state=0)
random_state = 42
# baikal way
x = Input()
y_t = Input()
y_p1 = RandomForestClassifierOOF(n_estimators=10,
random_state=random_state)(
x, y_t, compute_func="predict_proba")
y_p1 = Lambda(lambda array: array[:, 1:])(y_p1) # remove collinear feature
x_scaled = StandardScaler()(x)
y_p2 = LinearSVCOOF(random_state=random_state)(
x_scaled, y_t, compute_func="decision_function")
stacked_features = ColumnStack()([x, y_p1, y_p2])
y_p = LogisticRegression(solver="liblinear",
random_state=random_state)(stacked_features, y_t)
model = Model(x, y_p, y_t)
model.fit(X_train, y_t_train)
y_pred_baikal = model.predict(X_test)
# traditional way
estimators = [
("rf",
RandomForestClassifier(n_estimators=10, random_state=random_state)),
("svr",
make_pipeline(StandardScaler(),
LinearSVC(random_state=random_state))),
]
clf = sklearn.ensemble.StackingClassifier(
estimators=estimators,
final_estimator=LogisticRegression(solver="liblinear",
random_state=random_state),
passthrough=True,
)
y_pred_traditional = clf.fit(X_train, y_t_train).predict(X_test)
assert_array_equal(y_pred_baikal, y_pred_traditional)
def test_columnstack(teardown):
x1 = Input()
x2 = Input()
y = ColumnStack()([x1, x2])
model = Model([x1, x2], y)
x1_data = np.array([1, 10, 100])
x2_data = np.array([2, 20, 200])
y_expected = np.column_stack([x1_data, x2_data])
y_pred = model.predict([x1_data, x2_data])
assert_array_equal(y_pred, y_expected)
def test_fit_params_unhashable_step():
class UnhashableStep(Step, sklearn.linear_model.LogisticRegression):
def __eq__(self, other):
pass
x = Input()
y_t = Input()
y = UnhashableStep()(x, y_t)
model = Model(x, y, y_t)
mask = iris.target != 2 # Reduce to binary problem to avoid ConvergenceWarning
x_data = iris.data[mask]
y_t_data = iris.target[mask]
model.fit(x_data, y_t_data)
def test_with_wrong_type(self, teardown):
x = Input()
y_t = Input()
y = LogisticRegression()(x, y_t)
wrong = np.zeros((10,))
with pytest.raises(ValueError):
Model(wrong, y, y_t)
with pytest.raises(ValueError):
Model(x, wrong, y_t)
with pytest.raises(ValueError):
Model(x, y, wrong)
def test_fit_compute(self, teardown):
dummy_estimator_1 = DummyEstimator()
dummy_estimator_2 = DummyEstimator()
x = Input()
y_t = Input()
y_p1 = dummy_estimator_1(x, y_t, fit_compute_func=None)
y_p2 = dummy_estimator_2(x, y_t)
model = Model(x, [y_p1, y_p2], y_t)
model.fit(iris.data, iris.target)
assert dummy_estimator_1.fit_calls == 1
assert dummy_estimator_1.fit_predict_calls == 0
assert dummy_estimator_2.fit_calls == 0
assert dummy_estimator_2.fit_predict_calls == 1
def test_fit_and_predict_model_with_no_fittable_steps(teardown):
X1_data = np.array([[1, 2], [3, 4]])
X2_data = np.array([[5, 6], [7, 8]])
y_expected = np.array([[12, 16], [20, 24]])
x1 = Input()
x2 = Input()
z = DummyMISO()([x1, x2])
y = DummySISO()(z)
model = Model([x1, x2], y)
model.fit([X1_data, X2_data]) # nothing to fit
y_pred = model.predict([X1_data, X2_data])
assert_array_equal(y_pred, y_expected)
def build_model(step):
x1 = Input()
x2 = Input()
y_t1 = Input()
y_t2 = Input()
y_p = step([x1, x2], [y_t1, y_t2])
return Model([x1, x2], y_p, [y_t1, y_t2])
