def init_data(self):
np.random.seed(12363)
self.x = pd.DataFrame(np.random.randn(500, 10))
self.y = pd.DataFrame({
_TARGET_NAME:
[np.random.choice([0, 1, 2]) for _ in range(self.x.shape[0])]
})
self._model.fit(self.x, np.ravel(self.y))
self.ctx = TransformationContext(
input=[RealNumericFeature(col) for col in list(self.x)],
derived=[],
model=[RealNumericFeature(col) for col in list(self.x)],
output=[self.output])
def init_data_one_label(self):
np.random.seed(12363)
self.x = pd.DataFrame(np.random.randn(500, 4),
columns=['col_' + str(_) for _ in range(4)])
self.y = pd.DataFrame({
TARGET_NAME:
[np.random.choice([0, 1]) for _ in range(self.x.shape[0])]
})
self._model.fit(self.x, np.ravel(self.y))
self.ctx = TransformationContext()
self.ctx.schemas[Schema.INPUT] = [
RealNumericFeature(col) for col in list(self.x)
]
self.ctx.schemas[Schema.DERIVED] = []
self.ctx.schemas[Schema.MODEL] = [
RealNumericFeature(col) for col in list(self.x)
]
self.ctx.schemas[Schema.OUTPUT] = [self.output]
def setUp(self):
np.random.seed(1)
self.est = GradientBoostingClassifier(max_depth=2, n_estimators=10)
self.est.fit([
[0, 0],
[0, 1],
[1, 0],
[1, 1],
], [0, 1, 1, 1])
self.ctx = TransformationContext(
input=[IntegerNumericFeature('x1'), StringCategoricalFeature('x2', ['zero', 'one'])],
derived=[],
model=[IntegerNumericFeature('x1'), StringCategoricalFeature('x2', ['zero', 'one'])],
output=[RealNumericFeature('output')]
)
self.converter = GradientBoostingConverter(
estimator=self.est,
context=self.ctx
)
def test_transform_with_derived_field(self):
self.est = DecisionTreeClassifier(max_depth=2)
self.est.fit([
[0, 0, 0],
[0, 1, 0],
[1, 0, 0],
[1, 1, 1],
], [0, 1, 1, 1])
mapping = pmml.MapValues(dataType="double", outputColumn="output")
mapping.append(pmml.FieldColumnPair(column="x1", field="x1"))
mapping.append(pmml.FieldColumnPair(column="x2", field="x2"))
it = pmml.InlineTable()
it.append(pmml_row(x1=0, x2='zero', output=0))
it.append(pmml_row(x1=0, x2='one', output=0))
it.append(pmml_row(x1=1, x2='zero', output=0))
it.append(pmml_row(x1=1, x2='one', output=1))
mapping.append(it)
self.ctx = TransformationContext({
Schema.INPUT: [
IntegerNumericFeature('x1'),
StringCategoricalFeature('x2', ['zero', 'one'])
],
Schema.DERIVED: [
DerivedFeature(feature=RealNumericFeature(name='x3'),
transformation=mapping)
],
Schema.MODEL: [
IntegerNumericFeature('x1'),
StringCategoricalFeature('x2', ['zero', 'one']),
RealNumericFeature(name='x3')
],
Schema.OUTPUT:
[IntegerCategoricalFeature('output', ['neg', 'pos'])]
})
self.converter = DecisionTreeConverter(estimator=self.est,
context=self.ctx,
mode=ModelMode.CLASSIFICATION)
self.converter.pmml().toxml()
def setUp(self):
np.random.seed(1)
self.est = GradientBoostingClassifier(max_depth=2, n_estimators=10)
self.est.fit([
[0, 0],
[0, 1],
[1, 0],
[1, 1],
], [0, 1, 1, 1])
self.ctx = TransformationContext({
Schema.INPUT: [
IntegerNumericFeature('x1'),
StringCategoricalFeature('x2', ['zero', 'one'])
],
Schema.MODEL: [
IntegerNumericFeature('x1'),
StringCategoricalFeature('x2', ['zero', 'one'])
],
Schema.DERIVED: [],
Schema.OUTPUT: [IntegerCategoricalFeature('output', [0, 1])]
})
self.converter = GradientBoostingConverter(estimator=self.est,
context=self.ctx)
def setUp(self):
np.random.seed(1)
self.est = DecisionTreeRegressor(max_depth=2)
self.est.fit([
[0, 0],
[0, 1],
[1, 0],
[1, 1],
], [0, 1, 1, 1])
self.ctx = TransformationContext({
Schema.INPUT: [
IntegerNumericFeature('x1'),
StringCategoricalFeature('x2', ['zero', 'one'])
],
Schema.MODEL: [
IntegerNumericFeature('x1'),
StringCategoricalFeature('x2', ['zero', 'one'])
],
Schema.DERIVED: [],
Schema.OUTPUT: [IntegerNumericFeature('output')]
})
self.converter = DecisionTreeConverter(estimator=self.est,
context=self.ctx,
mode=ModelMode.REGRESSION)
def setUp(self):
np.random.seed(1)
self.est = DecisionTreeRegressor(max_depth=2)
self.est.fit([
[0, 0],
[0, 1],
[1, 0],
[1, 1],
], [0, 1, 1, 1])
self.ctx = TransformationContext(
input=[
IntegerNumericFeature('x1'),
StringCategoricalFeature('x2', ['zero', 'one'])
],
model=[
IntegerNumericFeature('x1'),
StringCategoricalFeature('x2', ['zero', 'one'])
],
derived=[],
output=[IntegerNumericFeature('output')])
self.converter = DecisionTreeConverter(
estimator=self.est,
context=self.ctx,
mode=DecisionTreeConverter.MODE_REGRESSION)