Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

PMML file missing model element #194

Closed
SunGoodIn opened this issue Jun 18, 2020 · 1 comment
Closed

PMML file missing model element #194

SunGoodIn opened this issue Jun 18, 2020 · 1 comment

Comments

@SunGoodIn
Copy link

Hi author,
this is my PMML file(has TransformationDictionary, no Model)

<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<PMML xmlns="http://www.dmg.org/PMML-4_3" xmlns:data="http://jpmml.org/jpmml-model/InlineTable" version="4.3">
	<Header>
		<Application name="JPMML-SkLearn" version="1.5.29"/>
		<Timestamp>2020-06-16T10:17:57Z</Timestamp>
	</Header>
	<MiningBuildTask>
		<Extension>PMMLPipeline(steps=[('09_MinMaxScaler', DataFrameMapper(default=False, df_out=True,
        features=[(['previous', 'duration', 'balance', 'campaign', 'day', 'age', 'pdays'], MinMaxScaler(copy=True, feature_range=(0, 1)), {})],
        input_df=True, sparse=False))])</Extension>
	</MiningBuildTask>
	<DataDictionary>
		<DataField name="previous" optype="continuous" dataType="double"/>
		<DataField name="duration" optype="continuous" dataType="double"/>
		<DataField name="balance" optype="continuous" dataType="double"/>
		<DataField name="campaign" optype="continuous" dataType="double"/>
		<DataField name="day" optype="continuous" dataType="double"/>
		<DataField name="age" optype="continuous" dataType="double"/>
		<DataField name="pdays" optype="continuous" dataType="double"/>
	</DataDictionary>
	<TransformationDictionary>
		<DerivedField name="mix_max_scaler(previous)" optype="continuous" dataType="double">
			<Apply function="*">
				<FieldRef field="previous"/>
				<Constant dataType="double">0.5</Constant>
			</Apply>
		</DerivedField>
		<DerivedField name="mix_max_scaler(duration)" optype="continuous" dataType="double">
			<Apply function="*">
				<FieldRef field="duration"/>
				<Constant dataType="double">0.3333333333333333</Constant>
			</Apply>
		</DerivedField>
		<DerivedField name="mix_max_scaler(balance)" optype="continuous" dataType="double">
			<Apply function="+">
				<Apply function="*">
					<FieldRef field="balance"/>
					<Constant dataType="double">5.6427039837490125E-5</Constant>
				</Apply>
				<Constant dataType="double">0.047906556822029114</Constant>
			</Apply>
		</DerivedField>
		<DerivedField name="mix_max_scaler(campaign)" optype="continuous" dataType="double">
			<Apply function="+">
				<Apply function="*">
					<FieldRef field="campaign"/>
					<Constant dataType="double">0.058823529411764705</Constant>
				</Apply>
				<Constant dataType="double">-0.058823529411764705</Constant>
			</Apply>
		</DerivedField>
		<DerivedField name="mix_max_scaler(day)" optype="continuous" dataType="double">
			<Apply function="+">
				<Apply function="*">
					<FieldRef field="day"/>
					<Constant dataType="double">0.034482758620689655</Constant>
				</Apply>
				<Constant dataType="double">-0.034482758620689655</Constant>
			</Apply>
		</DerivedField>
		<DerivedField name="mix_max_scaler(age)" optype="continuous" dataType="double">
			<Apply function="*">
				<FieldRef field="age"/>
				<Constant dataType="double">0.01282051282051282</Constant>
			</Apply>
		</DerivedField>
		<DerivedField name="mix_max_scaler(pdays)" optype="continuous" dataType="double">
			<Apply function="+">
				<Apply function="*">
					<FieldRef field="pdays"/>
					<Constant dataType="double">0.0021691973969631237</Constant>
				</Apply>
				<Constant dataType="double">0.0021691973969631237</Constant>
			</Apply>
		</DerivedField>
	</TransformationDictionary>
</PMML>
  • 1.Is a PMMl file available without Model element
  • 2.If the file is available,how to use the PMML file for data preprocessing?(pmml-evaluator)
    What is the API?

thinks

@vruusmann
Copy link
Member

Closing as an exact duplicate of #96

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants