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_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_with_unnecessary_target(self, teardown):
x = Input()
y_t = Input()
logreg = LogisticRegression()
y_p = logreg(x, y_t)
model = Model(x, y_p, y_t)
model.fit(iris.data, iris.target)
# won't require the target is trainable was set to False,
# but won't complain if it was passed to fit
logreg.trainable = False
model.fit(iris.data, iris.target)
def make_naive_stacked_model(n_components, random_state, x_data, y_t_data):
# An unnecessarily complex Model
# Sub-model 1
x1 = Input(name="x1")
y1_t = Input(name="y1_t")
h1 = PCA(n_components=n_components, random_state=random_state, name="pca_sub1")(x1)
y1 = LogisticRegression(
multi_class="multinomial",
solver="lbfgs",
random_state=random_state,
name="logreg_sub1",
)(h1, y1_t)
submodel1 = Model(x1, y1, y1_t, name="submodel1")
# Sub-model 2 (a nested stacked model)
x2 = Input(name="x2")
y2_t = Input(name="y2_t")
y2_1 = RandomForestClassifier(random_state=random_state, name="rforest_sub2")(
x2, y2_t
)
y2_2 = ExtraTreesClassifier(random_state=random_state, name="extrees_sub2")(
x2, y2_t
)
features = Stack(axis=1, name="stack_sub2")([y2_1, y2_2])
y2 = LogisticRegression(
multi_class="multinomial",
solver="lbfgs",
random_state=random_state,
name="logreg_sub2",
)(features, y2_t)
submodel2 = Model(x2, y2, y2_t, name="submodel2")
# Stack of submodels
x = Input(name="x")
y_t = Input(name="y_t")
y1 = submodel1(x, y_t)
y2 = submodel2(x, y_t)
features = Stack(axis=1, name="stack")([y1, y2])
y = LogisticRegression(
multi_class="multinomial",
solver="lbfgs",
random_state=random_state,
name="logreg_stacked",
)(features, y_t)
stacked_model_baikal = Model(x, y, y_t, name="stacked")
stacked_model_baikal.fit(x_data, y_t_data)
return stacked_model_baikal
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_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_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 test_fit_predict_ensemble_with_proba_features(teardown):
mask = iris.target != 2 # Reduce to binary problem to avoid ConvergenceWarning
x_data = iris.data[mask]
y_t_data = iris.target[mask]
random_state = 123
n_estimators = 5
# baikal way
x = Input()
y_t = Input()
y1 = LogisticRegression(random_state=random_state, function="predict_proba")(x, y_t)
y2 = RandomForestClassifier(
n_estimators=n_estimators, random_state=random_state, function="apply"
)(x, y_t)
features = Concatenate(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_proba = logreg.predict_proba(x_data)
random_forest = sklearn.ensemble.RandomForestClassifier(
n_estimators=n_estimators, random_state=random_state
)
random_forest.fit(x_data, y_t_data)
random_forest_leafidx = random_forest.apply(x_data)
features = np.concatenate([logreg_proba, random_forest_leafidx], 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)
ys_t = Split(n_targets, axis=1)(y_t)
ys_p = []
for j, k in enumerate(order):
x_stacked = ColumnStack()(inputs=[x, *ys_p[:j]])
ys_t[k] = squeeze(ys_t[k])
ys_p.append(LogisticRegression(solver="lbfgs")(x_stacked, ys_t[k]))
ys_p = [ys_p[order.index(j)] for j in range(n_targets)]
y_p = ColumnStack()(ys_p)
model = Model(inputs=x, outputs=y_p, targets=y_t)
# This might take a few seconds
plot_model(model, filename="classifier_chain.png", dpi=96)
# ------- Train model
model.fit(X_train, Y_train)
# ------- Evaluate model
Y_train_pred = model.predict(X_train)
Y_test_pred = model.predict(X_test)
print(
"Jaccard score on train data:",
jaccard_score(Y_train, Y_train_pred, average="samples"),
)
print(
"Jaccard score on test data:",
jaccard_score(Y_test, Y_test_pred, average="samples"),
)
y3 = LogisticRegression()(z, y_t)
stacked_features = Stack()([y1, y2, y3])
y_p = SVC()(stacked_features, y_t)
model = Model([x1, x2], y_p, y_t)
plot_model(model,
filename="multiple_input_nonlinear_pipeline_example_plot.png")
# 3. Train the model
dataset = load_breast_cancer()
X_train, X_test, y_train, y_test = train_test_split(dataset.data,
dataset.target,
random_state=0)
# Let's suppose the dataset is originally split in two
X1_train, X2_train = X_train[:, :15], X_train[:, 15:]
X1_test, X2_test = X_test[:, :15], X_test[:, 15:]
model.fit([X1_train, X2_train], y_train)
# 4. Use the model
y_test_pred = model.predict([X1_test, X2_test])
# This also works:
# y_test_pred = model.predict({x1: X1_test, x2: X2_test})
# We can also query any intermediate outputs:
outs = model.predict([X1_test, X2_test],
output_names=["ExtraTreesClassifier_0:0/0", "PCA_0:0/0"])
import sklearn.svm
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from baikal import Input, Model, make_step
from baikal.plot import plot_model
# 1. Define a step
SVC = make_step(sklearn.svm.SVC)
# 2. Build the model
x = Input()
y_t = Input()
y_p = SVC(C=1.0, kernel="rbf", gamma=0.5)(x, y_t)
model = Model(x, y_p, y_t)
plot_model(model, filename="readme_quick_example.png")
# 3. Train the model
dataset = load_breast_cancer()
X_train, X_test, y_train, y_test = train_test_split(dataset.data,
dataset.target,
random_state=0)
model.fit(X_train, y_train)
# 4. Use the model
y_test_pred = model.predict(X_test)
