def test_pipe_way4_mixin_fit(self):
X = np.arange(20).reshape(10, 2)
try:
tr = wrap_as_onnx_mixin(make_pipeline(CustomOpTransformer(),
KMeans(n_clusters=2)),
target_opset=TARGET_OPSET)
except KeyError as e:
assert "SklearnGaussianProcessRegressor" in str(e)
return
tr.fit(X)
onx = tr.to_onnx(X.astype(np.float32))
if (TARGET_OPSET == 11
or os.environ.get('TEST_TARGET_OPSET', '') != ''):
sonx = str(onx)
if "version: 11" not in sonx or "ir_version: 6" not in sonx:
raise AssertionError("Issue with TARGET_OPSET: {}\n{}".format(
TARGET_OPSET, sonx))
dump_data_and_model(X.astype(np.float32),
tr,
onx,
basename="MixinPipeWay4OnnxMixin2")
def test_pipe_way3_mixin(self):
X = np.arange(20).reshape(10, 2)
tr = make_pipeline(CustomOpTransformer(op_version=TARGET_OPSET),
KMeans(n_clusters=2))
tr.fit(X)
try:
tr_mixin = wrap_as_onnx_mixin(tr, target_opset=TARGET_OPSET)
except KeyError as e:
assert ("SklearnGaussianProcessRegressor" in str(e)
or "SklearnGaussianProcessClassifier" in str(e))
return
try:
onx = tr_mixin.to_onnx()
except RuntimeError as e:
assert "Method enumerate_initial_types" in str(e)
onx = tr_mixin.to_onnx(X.astype(np.float32))
if TARGET_OPSET == 11:
sonx = str(onx)
if "version: 11" not in sonx or "ir_version: 6" not in sonx:
raise AssertionError("Issue with TARGET_OPSET: {}\n{}".format(
TARGET_OPSET, sonx))
dump_data_and_model(X.astype(np.float32),
tr,
onx,
basename="MixinPipeWay3OnnxMixin")
def test_way3_mixin(self):
X = np.arange(20).reshape(10, 2)
# avoids point of different cluster to be very close
# and avoid a small discrepancy due to double/float
# conversion to change a label.
X[:10] += 100
tr = KMeans(n_clusters=2)
tr.fit(X)
try:
tr_mixin = wrap_as_onnx_mixin(tr, target_opset=TARGET_OPSET)
except KeyError as e:
assert ("SklearnGaussianProcessRegressor" in str(e)
or "SklearnGaussianProcessClassifier" in str(e))
return
try:
onx = tr_mixin.to_onnx()
except RuntimeError as e:
assert "Method enumerate_initial_types" in str(e)
onx = tr_mixin.to_onnx(X.astype(np.float32))
dump_data_and_model(X.astype(np.float32),
tr,
onx,
basename="MixinWay3OnnxMixin")
def test_way4_mixin_fit(self):
X = np.arange(20).reshape(10, 2)
tr = wrap_as_onnx_mixin(KMeans(n_clusters=2))
tr.fit(X)
onx = tr.to_onnx(X.astype(np.float32))
dump_data_and_model(X.astype(np.float32),
tr,
onx,
basename="MixinWay4OnnxMixin2")
def test_pipe_way4_mixin_fit(self):
X = np.arange(20).reshape(10, 2)
tr = wrap_as_onnx_mixin(
make_pipeline(CustomOpTransformer(), KMeans(n_clusters=2)))
tr.fit(X)
onx = tr.to_onnx(X.astype(np.float32))
dump_data_and_model(X.astype(np.float32),
tr,
onx,
basename="MixinPipeWay4OnnxMixin2")
def test_way4_mixin_fit(self):
X = np.arange(20).reshape(10, 2)
try:
tr = wrap_as_onnx_mixin(KMeans(n_clusters=2))
except KeyError as e:
assert "SklearnGaussianProcessRegressor" in str(e)
return
tr.fit(X)
onx = tr.to_onnx(X.astype(np.float32))
dump_data_and_model(
X.astype(np.float32), tr, onx,
basename="MixinWay4OnnxMixin2")
def test_pipe_way4_mixin_fit(self):
X = np.arange(20).reshape(10, 2)
try:
tr = wrap_as_onnx_mixin(
make_pipeline(CustomOpTransformer(), KMeans(n_clusters=2)),
target_opset=TARGET_OPSET)
except KeyError as e:
assert "SklearnGaussianProcessRegressor" in str(e)
return
tr.fit(X)
onx = tr.to_onnx(X.astype(np.float32))
dump_data_and_model(
X.astype(np.float32), tr, onx,
basename="MixinPipeWay4OnnxMixin2")
def test_way3_mixin(self):
X = np.arange(20).reshape(10, 2)
tr = KMeans(n_clusters=2)
tr.fit(X)
tr_mixin = wrap_as_onnx_mixin(tr)
try:
onx = tr_mixin.to_onnx()
except RuntimeError as e:
assert "Method enumerate_initial_types" in str(e)
onx = tr_mixin.to_onnx(X.astype(np.float32))
dump_data_and_model(X.astype(np.float32),
tr,
onx,
basename="MixinWay3OnnxMixin")
def test_pipe_way3_mixin(self):
X = np.arange(20).reshape(10, 2)
tr = make_pipeline(CustomOpTransformer(), KMeans(n_clusters=2))
tr.fit(X)
try:
tr_mixin = wrap_as_onnx_mixin(tr)
except KeyError as e:
assert "SklearnGaussianProcessRegressor" in str(e)
return
try:
onx = tr_mixin.to_onnx()
except RuntimeError as e:
assert "Method enumerate_initial_types" in str(e)
onx = tr_mixin.to_onnx(X.astype(np.float32))
dump_data_and_model(
X.astype(np.float32), tr, onx,
basename="MixinPipeWay3OnnxMixin")
def test_way3_mixin(self):
X = np.arange(20).reshape(10, 2)
tr = KMeans(n_clusters=2)
tr.fit(X)
try:
tr_mixin = wrap_as_onnx_mixin(tr, target_opset=TARGET_OPSET)
except KeyError as e:
assert "SklearnGaussianProcessRegressor" in str(e)
return
try:
onx = tr_mixin.to_onnx()
except RuntimeError as e:
assert "Method enumerate_initial_types" in str(e)
onx = tr_mixin.to_onnx(X.astype(np.float32))
dump_data_and_model(
X.astype(np.float32), tr, onx,
basename="MixinWay3OnnxMixin")
def test_algebra_converter(self):
X = numpy.array([[1, 2], [2, 3]])
op = OnnxSklearnStandardScaler()
op.fit(X)
onx = op.to_onnx(X.astype(numpy.float32))
assert onx is not None
import onnxruntime as ort
try:
sess = ort.InferenceSession(onx.SerializeToString())
except RuntimeError as e:
raise RuntimeError("Unable to read\n{}".format(onx)) from e
X = numpy.array([[0, 1], [-1, -2]])
try:
Y = sess.run(None, {'X': X.astype(numpy.float32)})[0]
except RuntimeError as e:
raise RuntimeError("Unable to run\n{}".format(onx)) from e
assert_almost_equal(Y, op.transform(X))
onx1 = str(onx)
op = wrap_as_onnx_mixin(StandardScaler())
op = OnnxSklearnStandardScaler()
op.fit(X)
onx = op.to_onnx(X.astype(numpy.float32))
onx2 = str(onx)
assert 'domain: "ai.onnx.ml"' in onx1
assert 'domain: "ai.onnx.ml"' in onx2
try:
sess = ort.InferenceSession(onx.SerializeToString())
except RuntimeError as e:
raise RuntimeError("Unable to read\n{}".format(onx)) from e
X = numpy.array([[0, 1], [-1, -2]])
try:
Y = sess.run(None, {'X': X.astype(numpy.float32)})[0]
except RuntimeError as e:
raise RuntimeError("Unable to run\n{}".format(onx)) from e
assert_almost_equal(Y, op.transform(X))
def test_way4_mixin_fit(self):
X = np.arange(20).reshape(10, 2)
try:
tr = wrap_as_onnx_mixin(KMeans(n_clusters=2),
target_opset=TARGET_OPSET)
except KeyError as e:
assert ("SklearnGaussianProcessRegressor" in str(e) or
"SklearnGaussianProcessClassifier" in str(e))
return
tr.fit(X)
onx = tr.to_onnx(X.astype(np.float32))
if TARGET_OPSET == 11:
sonx = str(onx)
if "version: 11" not in sonx or "ir_version: 6" not in sonx:
raise AssertionError("Issue with TARGET_OPSET: {}\n{}".format(
TARGET_OPSET, sonx))
dump_data_and_model(
X.astype(np.float32), tr, onx,
basename="MixinWay4OnnxMixin2")
tr.fit(X)
onx = to_onnx(tr, X.astype(np.float32), target_opset=12)
print(predict_with_onnxruntime(onx, X))
#################################
# The third way: :func:`wrap_as_onnx_mixin`: wraps
# the machine learned model into a new class
# inheriting from :class:`OnnxOperatorMixin`.
X = np.arange(20).reshape(10, 2)
tr = KMeans(n_clusters=2)
tr.fit(X)
tr_mixin = wrap_as_onnx_mixin(tr, target_opset=12)
onx = tr_mixin.to_onnx(X.astype(np.float32))
print(predict_with_onnxruntime(onx, X))
#################################
# The fourth way: :func:`wrap_as_onnx_mixin`: can be called
# before fitting the model.
X = np.arange(20).reshape(10, 2)
tr = wrap_as_onnx_mixin(KMeans(n_clusters=2),
target_opset=12)
tr.fit(X)
onx = tr.to_onnx(X.astype(np.float32))
print(predict_with_onnxruntime(onx, X))
tr = KMeans(n_clusters=2) tr.fit(X) onx = to_onnx(tr, X.astype(np.float32)) print(predict_with_onnxruntime(onx, X)) ################################# # The third way: :func:`wrap_as_onnx_mixin`: wraps # the machine learned model into a new class # inheriting from :class:`OnnxOperatorMixin`. X = np.arange(20).reshape(10, 2) tr = KMeans(n_clusters=2) tr.fit(X) tr_mixin = wrap_as_onnx_mixin(tr) onx = tr_mixin.to_onnx(X.astype(np.float32)) print(predict_with_onnxruntime(onx, X)) ################################# # The fourth way: :func:`wrap_as_onnx_mixin`: can be called # before fitting the model. X = np.arange(20).reshape(10, 2) tr = wrap_as_onnx_mixin(KMeans(n_clusters=2)) tr.fit(X) onx = tr.to_onnx(X.astype(np.float32)) print(predict_with_onnxruntime(onx, X))
