def test_ovr(self):
model = OneVsRestClassifier(LogisticRegression())
dump_multiple_classification(
model,
allow_failure="StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')",
target_opset=TARGET_OPSET)
def test_extra_trees_classifier(self):
model = ExtraTreesClassifier(n_estimators=3)
dump_one_class_classification(
model,
allow_failure="StrictVersion(onnx.__version__)"
" < StrictVersion('1.2') or "
"StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')",
)
dump_binary_classification(
model,
allow_failure=(
"StrictVersion(onnx.__version__) < StrictVersion('1.2') or "
"StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')"
),
)
dump_multiple_classification(
model,
# Operator cast-1 is not implemented in onnxruntime
allow_failure=(
"StrictVersion(onnx.__version__) < StrictVersion('1.2') or "
"StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')"
),
)
def test_gradient_boosting_classifier_multi(self):
model = GradientBoostingClassifier(n_estimators=3)
dump_multiple_classification(
model,
allow_failure="StrictVersion(onnxruntime.__version__)"
"<= StrictVersion('%s')" % THRESHOLD,
)
def test_ovr_string(self):
model = OneVsRestClassifier(LogisticRegression())
dump_multiple_classification(model,
verbose=False,
label_string=True,
suffix="String",
target_opset=TARGET_OPSET)
def test_ova_02(self):
model = OneVsRestClassifier(LogisticRegression())
dump_multiple_classification(
model,
first_class=2,
suffix="F2",
allow_failure=
"StrictVersion(onnxruntime.__version__) <= StrictVersion('0.2.1')")
def test_random_forest_classifier(self):
model = RandomForestClassifier(n_estimators=3)
dump_one_class_classification(model,
allow_failure="StrictVersion(onnx.__version__) < StrictVersion('1.2')")
dump_binary_classification(model,
allow_failure="StrictVersion(onnx.__version__) < StrictVersion('1.2')")
dump_multiple_classification(model,
allow_failure="StrictVersion(onnx.__version__) < StrictVersion('1.2')")
def test_ova_string(self):
model = OneVsRestClassifier(LogisticRegression())
dump_multiple_classification(
model,
verbose=False,
label_string=True,
suffix="String",
allow_failure=
"StrictVersion(onnxruntime.__version__) <= StrictVersion('0.2.1')")
def test_lightgbm_classifier(self):
model = LGBMClassifier(n_estimators=3, min_child_samples=1)
dump_binary_classification(
model, allow_failure="StrictVersion(onnx.__version__) < "
"StrictVersion('1.3.0')")
dump_multiple_classification(
model,
allow_failure="StrictVersion(onnx.__version__) < "
"StrictVersion('1.3.0')")
def test_voting_soft_multi(self):
model = VotingClassifier(voting='soft',
flatten_transform=False,
estimators=[('lr', LogisticRegression()),
('lr2', LogisticRegression())])
dump_multiple_classification(
model,
suffix='Soft-OneOffArray',
allow_failure=
"StrictVersion(onnxruntime.__version__) <= StrictVersion('0.2.1')")
def test_voting_soft_multi(self):
model = VotingClassifier(
voting="soft",
flatten_transform=False,
estimators=[
("lr", LogisticRegression()),
("lr2", LogisticRegression()),
],
)
dump_multiple_classification(model,
suffix="Soft",
target_opset=TARGET_OPSET)
def test_lightgbm_classifier(self):
model = LGBMClassifier(n_estimators=3, min_child_samples=1)
dump_binary_classification(model,
target_opset={
'': TARGET_OPSET,
'ai.onnx.ml': TARGET_OPSET_ML
})
dump_multiple_classification(model,
target_opset={
'': TARGET_OPSET,
'ai.onnx.ml': TARGET_OPSET_ML
})
def test_voting_soft_multi_weighted42(self):
model = VotingClassifier(voting='soft',
flatten_transform=False,
weights=numpy.array([27, 0.3, 0.5, 0.5]),
estimators=[('lr', LogisticRegression()),
('lra', LogisticRegression()),
('lrb', LogisticRegression()),
('lr2', LogisticRegression())])
dump_multiple_classification(
model,
suffix='Weighted42Soft-OneOffArray',
allow_failure=
"StrictVersion(onnxruntime.__version__) <= StrictVersion('0.2.1')")
def test_voting_hard_multi(self):
# predict_proba is not defined when voting is hard.
model = VotingClassifier(voting='hard',
flatten_transform=False,
estimators=[('lr', LogisticRegression()),
('lr2', DecisionTreeClassifier())
])
dump_multiple_classification(
model,
suffix='Hard-OneOffArray',
comparable_outputs=[0],
allow_failure=
"StrictVersion(onnxruntime.__version__) <= StrictVersion('0.2.1')")
def test_voting_soft_multi_weighted(self):
model = VotingClassifier(
voting="soft",
flatten_transform=False,
weights=numpy.array([1.8, 0.2]),
estimators=[
("lr", LogisticRegression()),
("lr2", LogisticRegression()),
],
)
dump_multiple_classification(model,
suffix="WeightedSoft",
target_opset=TARGET_OPSET)
def test_xgb_classifier_multi(self):
iris = load_iris()
X = iris.data[:, :2]
y = iris.target
xgb = XGBClassifier()
xgb.fit(X, y)
conv_model = convert_sklearn(
xgb, initial_types=[
('input', FloatTensorType(shape=[None, X.shape[1]]))])
self.assertTrue(conv_model is not None)
dump_multiple_classification(
xgb, allow_failure="StrictVersion(onnx.__version__) "
"< StrictVersion('1.3.0')")
def test_voting_hard_multi(self):
# predict_proba is not defined when voting is hard.
model = VotingClassifier(
voting="hard",
flatten_transform=False,
estimators=[
("lr", LogisticRegression()),
("lr2", DecisionTreeClassifier()),
],
)
dump_multiple_classification(model,
suffix="Hard",
comparable_outputs=[0],
target_opset=TARGET_OPSET)
def test_decision_tree_classifier(self):
model = DecisionTreeClassifier()
dump_one_class_classification(
model,
# Operator cast-1 is not implemented in onnxruntime
allow_failure=
"StrictVersion(onnx.__version__) < StrictVersion('1.2')")
dump_binary_classification(
model,
allow_failure=
"StrictVersion(onnx.__version__) < StrictVersion('1.2')")
dump_multiple_classification(
model,
allow_failure=
"StrictVersion(onnx.__version__) < StrictVersion('1.2')")
def test_voting_soft_multi(self):
model = VotingClassifier(
voting="soft",
flatten_transform=False,
estimators=[
("lr", LogisticRegression()),
("lr2", LogisticRegression()),
],
)
dump_multiple_classification(
model,
suffix="Soft-OneOffArray",
allow_failure="StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')",
)
def test_voting_soft_multi_weighted(self):
model = VotingClassifier(
voting="soft",
flatten_transform=False,
weights=numpy.array([1.8, 0.2]),
estimators=[
("lr", LogisticRegression()),
("lr2", LogisticRegression()),
],
)
dump_multiple_classification(
model,
suffix="WeightedSoft",
allow_failure="StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')",
)
def test_xgb_classifier_multi_reglog(self):
iris = load_iris()
X = iris.data[:, :2]
y = iris.target
xgb = XGBClassifier(objective='reg:logistic')
xgb.fit(X, y)
conv_model = convert_sklearn(
xgb, initial_types=[
('input', FloatTensorType(shape=[None, X.shape[1]]))],
target_opset=TARGET_OPSET)
self.assertTrue(conv_model is not None)
dump_multiple_classification(
xgb, suffix="RegLog",
allow_failure="StrictVersion(onnx.__version__) < "
"StrictVersion('1.3.0')")
def test_voting_soft_multi_string(self):
model = VotingClassifier(
voting="soft",
flatten_transform=False,
estimators=[
("lr", LogisticRegression()),
("lr2", LogisticRegression()),
],
)
dump_multiple_classification(
model,
label_string=True,
suffix="Soft",
allow_failure="StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')",
target_opset=TARGET_OPSET)
def test_voting_hard_multi(self):
# predict_proba is not defined when voting is hard.
model = VotingClassifier(
voting="hard",
flatten_transform=False,
estimators=[
("lr", LogisticRegression()),
("lr2", DecisionTreeClassifier()),
],
)
dump_multiple_classification(
model,
suffix="Hard",
comparable_outputs=[0],
allow_failure="StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.5.0')",
)
def test_voting_hard_multi_weighted(self):
# predict_proba is not defined when voting is hard.
model = VotingClassifier(
voting="hard",
flatten_transform=False,
weights=numpy.array([1000, 1]),
estimators=[
("lr", LogisticRegression()),
("lr2", DecisionTreeClassifier()),
],
)
dump_multiple_classification(
model,
suffix="WeightedHard",
comparable_outputs=[0],
allow_failure="StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.5.0')",
target_opset=TARGET_OPSET)
def test_voting_soft_multi_weighted42(self):
model = VotingClassifier(
voting="soft",
flatten_transform=False,
weights=numpy.array([27, 0.3, 0.5, 0.5]),
estimators=[
("lr", LogisticRegression()),
("lra", LogisticRegression()),
("lrb", LogisticRegression()),
("lr2", LogisticRegression()),
],
)
dump_multiple_classification(
model,
suffix="Weighted42Soft",
allow_failure="StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')",
target_opset=TARGET_OPSET)
def test_xgb_classifier_multi(self):
iris = load_iris()
X = iris.data[:, :2]
y = iris.target
xgb = XGBClassifier()
xgb.fit(X, y)
conv_model = convert_sklearn(
xgb,
initial_types=[('input', FloatTensorType(shape=[None, X.shape[1]]))
],
target_opset={
'': TARGET_OPSET,
'ai.onnx.ml': TARGET_OPSET_ML
})
self.assertTrue(conv_model is not None)
dump_multiple_classification(xgb,
target_opset={
'': TARGET_OPSET,
'ai.onnx.ml': TARGET_OPSET_ML
})
def test_decision_tree_classifier(self):
model = DecisionTreeClassifier()
dump_one_class_classification(model)
dump_binary_classification(model)
dump_multiple_classification(model)
dump_multiple_classification(model, label_uint8=True)
dump_multiple_classification(model, label_string=True)
def test_decision_tree_classifier(self):
model = DecisionTreeClassifier()
dump_one_class_classification(
model,
# Operator cast-1 is not implemented in onnxruntime
allow_failure="StrictVersion(onnx.__version__)"
" < StrictVersion('1.3') or "
"StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')",
)
dump_binary_classification(
model,
allow_failure="StrictVersion(onnx.__version__)"
" < StrictVersion('1.3') or "
"StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')",
)
dump_multiple_classification(
model,
allow_failure="StrictVersion(onnx.__version__)"
" < StrictVersion('1.3') or "
"StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')")
dump_multiple_classification(
model,
label_uint8=True,
allow_failure="StrictVersion(onnx.__version__)"
" < StrictVersion('1.3') or "
"StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')")
dump_multiple_classification(
model,
label_string=True,
allow_failure="StrictVersion(onnx.__version__)"
" < StrictVersion('1.3') or "
"StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')")
def test_random_forest_classifier(self):
model = RandomForestClassifier(n_estimators=3)
dump_one_class_classification(model)
dump_binary_classification(model)
dump_multiple_classification(model)
def test_ovr(self):
model = OneVsRestClassifier(LogisticRegression())
dump_multiple_classification(model, target_opset=TARGET_OPSET)
def test_ovr_02(self):
model = OneVsRestClassifier(LogisticRegression())
dump_multiple_classification(model,
first_class=2,
suffix="F2",
target_opset=TARGET_OPSET)