def test_glm_classifier(self):
iris = load_iris()
X = iris.data[:, :2]
y = iris.target
y[y == 2] = 1
# scikit-learn has changed the default value for multi_class.
lr = LogisticRegression(multi_class='ovr')
lr.fit(X, y)
lr_coreml = coremltools.converters.sklearn.convert(lr)
lr_onnx = convert(lr_coreml.get_spec())
self.assertTrue(lr_onnx is not None)
self.validate_zipmap(lr_onnx)
dump_data_and_model(X.astype(numpy.float32), lr, lr_onnx, basename="CmlbinLogitisticRegression",
allow_failure="StrictVersion(onnx.__version__) < StrictVersion('1.3.0')")
# Ensure there is a probability output
svm = LinearSVC()
svm.fit(X, y)
svm_coreml = coremltools.converters.sklearn.convert(svm)
svm_onnx = convert(svm_coreml.get_spec())
self.assertTrue(svm_onnx is not None)
self.validate_zipmap(svm_onnx)
dump_data_and_model(X.astype(numpy.float32), svm, svm_onnx, basename="CmlBinLinearSVC-NoProb",
allow_failure=True)
def test_glm_regressor(self):
X, y = make_regression(n_features=4, random_state=0)
lr = LinearRegression()
lr.fit(X, y)
lr_coreml = coremltools.converters.sklearn.convert(lr)
lr_onnx = convert(lr_coreml.get_spec())
self.assertTrue(lr_onnx is not None)
svr = LinearSVR()
svr.fit(X, y)
svr_coreml = coremltools.converters.sklearn.convert(svr)
svr_onnx = convert(svr_coreml.get_spec())
self.assertTrue(svr_onnx is not None)
def test_support_vector_classifier_multiclass_with_prob(self):
svm, X = self._fit_multi_classification(SVC(probability=True, gamma=0.5))
svm_coreml = coremltools.converters.sklearn.convert(svm)
svm_onnx = convert(svm_coreml.get_spec())
self.assertTrue(svm_onnx is not None)
self.validate_zipmap(svm_onnx)
self._check_model_outputs(svm_onnx, ['classLabel', 'classProbability'])
def test_one_hot_encoder(self):
script_dir = os.path.dirname(__file__)
relative_path = "../data/onehot_simple.mlmodel"
abs_file = os.path.join(script_dir, relative_path)
model_coreml = coremltools.utils.load_spec(abs_file)
model_onnx = convert(model_coreml)
self.assertTrue(model_onnx is not None)
def test_scaler(self):
model = StandardScaler()
data = numpy.array([[0, 0, 3], [1, 1, 0], [0, 2, 1], [1, 0, 2]], dtype=numpy.float32)
model.fit(data)
model_coreml = coremltools.converters.sklearn.convert(model)
model_onnx = convert(model_coreml.get_spec())
self.assertTrue(model_onnx is not None)
dump_data_and_model(data, model, model_onnx, basename="CmlStandardScalerFloat32")
def test_support_vector_regressor(self):
X, y = make_regression(n_features=4, random_state=0)
svm = SVR()
svm.fit(X, y)
svm_coreml = coremltools.converters.sklearn.convert(svm)
svm_onnx = convert(svm_coreml.get_spec())
self.assertTrue(svm_onnx is not None)
def test_tree_ensemble_classifier(self):
X = [[0, 1], [1, 1], [2, 0]]
y = [1, 0, 1]
model = RandomForestClassifier().fit(X, y)
model_coreml = coremltools.converters.sklearn.convert(model)
model_onnx = convert(model_coreml.get_spec())
self.assertTrue(model_onnx is not None)
self.validate_zipmap(model_onnx)
def test_support_vector_classifier_multiclass_no_prob(self):
svm, X = self._fit_multi_classification(SVC(gamma=0.5))
svm_coreml = coremltools.converters.sklearn.convert(svm)
svm_onnx = convert(svm_coreml.get_spec())
self.assertTrue(svm_onnx is not None)
nodes = svm_onnx.graph.node
self.assertEqual(len(nodes), 1)
self._check_model_outputs(svm_onnx, ['classLabel'])
def test_support_vector_classifier_binary_no_prob(self):
svm = self._fit_binary_classification(SVC())
svm_coreml = coremltools.converters.sklearn.convert(svm)
svm_onnx = convert(svm_coreml.get_spec())
self.assertTrue(svm_onnx is not None)
# This should not have a probability output and will be a single node
nodes = svm_onnx.graph.node
self.assertEqual(len(nodes), 1)
self._check_model_outputs(svm_onnx, ['classLabel'])
def test_support_vector_regressor(self):
X, y = make_regression(n_features=4, random_state=0)
svm = SVR(gamma=1./len(X))
svm.fit(X, y)
svm_coreml = coremltools.converters.sklearn.convert(svm)
svm_onnx = convert(svm_coreml.get_spec())
self.assertTrue(svm_onnx is not None)
dump_data_and_model(X.astype(numpy.float32), svm, svm_onnx, basename="CmlRegSVR-Dec3")
def test_dict_vectorizer(self):
model = DictVectorizer()
data = [{'amy': 1., 'chin': 200.}, {'nice': 3., 'amy': 1.}]
model.fit_transform(data)
model_coreml = coremltools.converters.sklearn.convert(model)
model_onnx = convert(model_coreml.get_spec())
self.assertTrue(model_onnx is not None)
dump_data_and_model(data, model, model_onnx, basename="CmlDictVectorizer-OneOff-SkipDim1",
allow_failure="StrictVersion(onnx.__version__) < StrictVersion('1.3.0')")
def test_tree_ensemble_regressor(self):
X, y = make_regression(n_features=4, random_state=0)
model = RandomForestRegressor().fit(X, y)
model_coreml = coremltools.converters.sklearn.convert(model)
model_onnx = convert(model_coreml.get_spec())
self.assertTrue(model_onnx is not None)
dump_data_and_model(X.astype(numpy.float32),
model,
model_onnx,
basename="CmlRegRandomForestRegressor-Dec3")
def test_glm_classifier(self):
iris = load_iris()
X = iris.data[:, :2]
y = iris.target
y[y == 2] = 1
lr = LogisticRegression()
lr.fit(X, y)
lr_coreml = coremltools.converters.sklearn.convert(lr)
lr_onnx = convert(lr_coreml.get_spec())
self.assertTrue(lr_onnx is not None)
self.validate_zipmap(lr_onnx)
# Ensure there is a probability output
svm = LinearSVC()
svm.fit(X, y)
svm_coreml = coremltools.converters.sklearn.convert(svm)
svm_onnx = convert(svm_coreml.get_spec())
self.assertTrue(svm_onnx is not None)
self.validate_zipmap(svm_onnx)
def test_support_vector_classifier_binary_no_prob(self):
svm, X = self._fit_binary_classification(SVC(gamma=0.5))
svm_coreml = coremltools.converters.sklearn.convert(svm)
svm_onnx = convert(svm_coreml.get_spec())
self.assertTrue(svm_onnx is not None)
# This should not have a probability output and will be a single node
nodes = svm_onnx.graph.node
self.assertEqual(len(nodes), 1)
self._check_model_outputs(svm_onnx, ['classLabel'])
dump_data_and_model(X, svm, svm_onnx, basename="CmlBinSVC-Out0",
allow_failure=True)
def test_imputer(self):
model = Imputer(missing_values='NaN', strategy='mean', axis=0)
data = [[1, 2], [np.nan, 3], [7, 6]]
model.fit(data)
model_coreml = coremltools.converters.sklearn.convert(model)
model_onnx = convert(model_coreml.get_spec())
self.assertTrue(model_onnx is not None)
dump_data_and_model(np.array(data, dtype=np.float32),
model,
model_onnx,
basename="CmlImputerMeanFloat32")
def test_glm_regressor(self):
X, y = make_regression(n_features=4, random_state=0)
lr = LinearRegression()
lr.fit(X, y)
lr_coreml = coremltools.converters.sklearn.convert(lr)
lr_onnx = convert(lr_coreml.get_spec())
self.assertTrue(lr_onnx is not None)
dump_data_and_model(X.astype(numpy.float32),
lr,
lr_onnx,
basename="CmlLinearRegression-Dec4")
svr = LinearSVR()
svr.fit(X, y)
svr_coreml = coremltools.converters.sklearn.convert(svr)
svr_onnx = convert(svr_coreml.get_spec())
self.assertTrue(svr_onnx is not None)
dump_data_and_model(X.astype(numpy.float32),
svr,
svr_onnx,
basename="CmlLinearSvr-Dec4")
def test_tree_ensemble_classifier(self):
X = numpy.array([[0, 1], [1, 1], [2, 0]], dtype=numpy.float32)
y = [1, 0, 1]
model = RandomForestClassifier().fit(X, y)
model_coreml = coremltools.converters.sklearn.convert(model)
model_onnx = convert(model_coreml.get_spec())
self.assertTrue(model_onnx is not None)
self.validate_zipmap(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="CmlBinRandomForestClassifier",
allow_failure=
"StrictVersion(onnx.__version__) < StrictVersion('1.3.0')")
def test_conversion_one_column(self):
scikit_data = [[0], [1], [2], [4], [3], [2], [4], [5], [6], [7]]
scikit_data = numpy.asarray(scikit_data, dtype='d')
scikit_data_multiple_cols = [[0, 1], [1, 0], [2, 2], [3, 3], [4, 4]]
scikit_data_multiple_cols = numpy.asarray(scikit_data_multiple_cols, dtype='d')
scikit_model = OneHotEncoder()
# scikit_model.fit(scikit_data)
# model_coreml = coremltools.converters.sklearn.convert(scikit_model, 'single_feature', 'out')
scikit_model.fit(scikit_data_multiple_cols)
try:
model_coreml = coremltools.converters.sklearn.convert(scikit_model, ['feature_1', 'feature_2'], 'out')
except Exception as e:
warnings.warn("Unable to run convert OneHotEncoder with coreml.")
return
model_onnx = convert(model_coreml)
self.assertTrue(model_onnx is not None)
dump_data_and_model(scikit_data, scikit_model, model_onnx, basename="CmlOneHotEncoder-SkipDim1")
def test_imputer(self):
try:
model = Imputer(missing_values='NaN', strategy='mean', axis=0)
except TypeError:
model = Imputer(missing_values=np.nan, strategy='mean')
model.axis = 0
data = [[1, 2], [np.nan, 3], [7, 6]]
model.fit(data)
from onnxmltools.convert.coreml.convert import convert
import coremltools # noqa
try:
model_coreml = coremltools.converters.sklearn.convert(model)
except ValueError as e:
if 'not supported' in str(e):
# Python 2.7 + scikit-learn 0.22
return
model_onnx = convert(model_coreml.get_spec())
self.assertTrue(model_onnx is not None)
dump_data_and_model(np.array(data, dtype=np.float32),
model, model_onnx, basename="CmlImputerMeanFloat32")
def test_dict_vectorizer(self):
model = DictVectorizer()
model.fit_transform([{'amy': 1, 'chin': 200}, {'nice': 3, 'amy': 1}])
model_coreml = coremltools.converters.sklearn.convert(model)
model_onnx = convert(model_coreml.get_spec())
self.assertTrue(model_onnx is not None)
def test_imputer(self):
model = Imputer(missing_values='NaN', strategy='mean', axis=0)
model.fit([[1, 2], [np.nan, 3], [7, 6]])
model_coreml = coremltools.converters.sklearn.convert(model)
model_onnx = convert(model_coreml.get_spec())
self.assertTrue(model_onnx is not None)
def test_scaler(self):
model = StandardScaler()
model.fit([[0, 0, 3], [1, 1, 0], [0, 2, 1], [1, 0, 2]])
model_coreml = coremltools.converters.sklearn.convert(model)
model_onnx = convert(model_coreml.get_spec())
self.assertTrue(model_onnx is not None)
def test_tree_ensemble_regressor(self):
X, y = make_regression(n_features=4, random_state=0)
model = RandomForestRegressor().fit(X, y)
model_coreml = coremltools.converters.sklearn.convert(model)
model_onnx = convert(model_coreml.get_spec())
self.assertTrue(model_onnx is not None)