def test_n_features_float_repeatability(self):
X = numpy.arange(20).reshape((5, 4)).astype(numpy.float64)
X2 = _modify_dimension(X, 6)
X3 = _modify_dimension(X, 6)
self.assertEqualArray(X2, X3)
X4 = _modify_dimension(X, 6, seed=20)
self.assertNotEqualArray(X2, X4)
def test_n_features_int(self):
X = numpy.arange(20).reshape((5, 4)).astype(numpy.int64)
X2 = _modify_dimension(X, 2)
self.assertEqualArray(X[:, :2], X2)
X2 = _modify_dimension(X, None)
self.assertEqualArray(X, X2)
X2 = _modify_dimension(X, 4)
self.assertEqualArray(X, X2)
X2 = _modify_dimension(X, 6)
self.assertEqualArray(X[:, 2:4], X2[:, 2:4])
self.assertNotEqualArray(X[:, :2], X2[:, 4:6])
diff = numpy.sum(numpy.abs(numpy.sign( # pylint: disable=E1101
X[:, :2] - X2[:, :2]).ravel())) # pylint: disable=E1101
self.assertLess(diff, 6)
def test_n_features_float(self):
X = numpy.arange(20).reshape((5, 4)).astype(numpy.float64)
X2 = _modify_dimension(X, 2)
self.assertEqualArray(X[:, :2], X2)
X2 = _modify_dimension(X, None)
self.assertEqualArray(X, X2)
X2 = _modify_dimension(X, 4)
self.assertEqualArray(X, X2)
X2 = _modify_dimension(X, 6)
self.assertEqualArray(X[:, 2:4], X2[:, 2:4])
self.assertNotEqualArray(X[:, :2], X2[:, :2])
self.assertNotEqualArray(X[:, :2], X2[:, 4:6])
cor = numpy.corrcoef(X2)
for i in range(0, 2):
cor = numpy.corrcoef(X[:, i], X2[:, i])
self.assertLess(cor[0, 1], 0.9999)
def test_rt_svr_simple_test_double(self):
fLOG(__file__,
self._testMethodName,
OutputPrint=__name__ == "__main__")
logger = getLogger('skl2onnx')
logger.disabled = True
for nf in range(16, 50):
with self.subTest(nf=nf):
iris = load_iris()
X, y = iris.data, iris.target
X = _modify_dimension(X, nf)
X_train, X_test, y_train, _ = train_test_split(X, y)
clr = SVR(kernel='linear')
clr.fit(X_train, y_train)
x2 = X_test.astype(numpy.float64)
onx = to_onnx(clr, x2)
pyrun = OnnxInference(onx, runtime="python")
res = pyrun.run({'X': x2})
self.assertIn('variable', res)
self.assertEqual(res['variable'].shape, (38, ))
self.assertEqualArray(res['variable'],
clr.predict(x2),
decimal=2)
def _get_dataset(self, nf, dtype):
xdtype = self._get_xdtype(dtype)
data = load_iris()
X, y = data.data, data.target
state = numpy.random.RandomState(seed=34) # pylint: disable=E1101
rnd = state.randn(*X.shape) / 3
X += rnd
X = _modify_dimension(X, nf)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
random_state=42)
Xt = X_test.astype(xdtype)
yt = y_test.astype(self.par_ydtype)
return (X_train, y_train), (Xt, yt)
def test_onnxrt_python_SVR_20(self):
iris = load_iris()
X, y = iris.data, iris.target
X = _modify_dimension(X, 20)
X_train, X_test, y_train, _ = train_test_split(X, y, random_state=11)
clr = SVR()
clr.fit(X_train, y_train)
model_def = to_onnx(clr, X_train.astype(numpy.float32))
oinf = OnnxInference(model_def)
text = "\n".join(map(lambda x: str(x.ops_), oinf.sequence_))
self.assertIn("SVMRegressor", text)
y = oinf.run({'X': X_test.astype(numpy.float32)})
self.assertEqual(list(sorted(y)), ['variable'])
lexp = clr.predict(X_test)
self.assertEqual(lexp.shape, y['variable'].shape)
self.assertEqualArray(lexp, y['variable'], decimal=5)
def _get_dataset(self, nf, dtype):
xdtype = self._get_xdtype(dtype)
data = load_iris()
X, y = data.data, data.target
state = numpy.random.RandomState(seed=34) # pylint: disable=E1101
rnd = state.randn(*X.shape) / 3
X += rnd
nbclass = len(set(y))
y_ = numpy.zeros((y.shape[0], nbclass), dtype=y.dtype)
for i, vy in enumerate(y):
y_[i, vy] = 1
y = y_
X = _modify_dimension(X, nf)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
random_state=42)
X = X_test.astype(xdtype)
y = y_test.astype(self.par_ydtype)
return (X_train, y_train), (X, y)
def test_onnxrt_python_SVC_proba_double_20(self):
iris = load_iris()
X, y = iris.data, iris.target
X = _modify_dimension(X, 20)
X_train, X_test, y_train, _ = train_test_split(X, y, random_state=11)
clr = SVC(probability=True)
clr.fit(X_train, y_train)
model_def = to_onnx(clr, X_train.astype(numpy.float64))
oinf = OnnxInference(model_def)
text = "\n".join(map(lambda x: str(x.ops_), oinf.sequence_))
self.assertIn("SVMClassifier", text)
y = oinf.run({'X': X_test.astype(numpy.float64)})
self.assertEqual(list(sorted(y)), [
'output_label', 'output_probability'])
lexp = clr.predict(X_test)
lprob = clr.predict_proba(X_test)
got = y['output_probability'].values
self.assertEqual(lexp.shape, y['output_label'].shape)
self.assertEqual(lprob.shape, got.shape)
self.assertEqualArray(lexp, y['output_label'], decimal=5)
self.assertEqualArray(lprob, got, decimal=5)
