def field_not_in_list(field, values):
mv = pmml.MapValues(outputColumn='output', defaultValue=1)
mv.append(pmml.FieldColumnPair(field=field, column='input'))
it = pmml.InlineTable()
for v in values:
it.append(pmml_row(input=v, output=0))
mv.append(it)
return {
DerivedFeatureTransformations.TRANSFORMATION:
mv,
DerivedFeatureTransformations.FUNCTION:
lambda df: reduce(np.logical_and, [df[field] != _ for _ in values])
}
def transformation_dictionary(self):
"""
Build a transformation dictionary and return a TransformationDictionary element
"""
td = pmml.TransformationDictionary()
# define a schema with all variables available for a model
encoded_schema = []
self.context.schemas[Schema.NUMERIC] = encoded_schema
idx = {}
# First, populate transformation dictionary for _all_ derived fields, because they can be requested later
for f in self.context.schemas[Schema.DERIVED]:
ef = RealNumericFeature(name=f.name)
df = pmml.DerivedField(name=ef.full_name,
optype=ef.optype.value,
dataType=ef.data_type.value)
df.append(f.transformation)
td.append(df)
assert f.name not in idx, 'Duplicate field definition: {}'.format(
f.name)
idx[f.name] = ef
# second, define the numeric transformations for the categorical variables
for f in self.context.schemas[Schema.INPUT]:
assert f.name not in idx, 'Duplicate field definition: {}'.format(
f.name)
if isinstance(f, CategoricalFeature):
ef = RealNumericFeature(name=f.name,
namespace=Schema.NUMERIC.namespace)
# create a record in transformation dictionary with mapping from raw values into numbers
df = pmml.DerivedField(name=ef.full_name,
optype=ef.optype.value,
dataType=ef.data_type.value)
mv = pmml.MapValues(outputColumn='output',
dataType=ef.data_type.value)
mv.append(
pmml.FieldColumnPair(field=f.full_name, column='input'))
it = pmml.InlineTable()
for i, v in enumerate(f.value_list):
it.append(pmml_row(input=v, output=i))
td.append(df.append(mv.append(it)))
idx[f.name] = ef
else:
idx[f.name] = f
# now we can build a mirror of model schema into the numeric schema
self.context.schemas[Schema.NUMERIC] = [
idx[f.name] for f in self.context.schemas[Schema.MODEL]
]
return td
def map_values(field, value_map, default_value):
mv = pmml.MapValues(outputColumn='output', default_value=default_value)
mv.append(pmml.FieldColumnPair(field=field, column='input'))
it = pmml.InlineTable()
for k, v in value_map.items():
it.append(pmml_row(input=k, output=v))
mv.append(it)
return {
DerivedFeatureTransformations.TRANSFORMATION:
mv,
DerivedFeatureTransformations.FUNCTION:
lambda df: np.vectorize(partial(value_map.get, default_value))
(df[field])
}
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()
