org.dmg.pmml.Apply Java Examples

@Test
public void translateCaseWhenExpression(){
	String string = "CASE WHEN x1 < 0 THEN x1 WHEN x2 > 0 THEN x2 ELSE 0 END";

	FieldRef first = new FieldRef(FieldName.create("x1"));
	FieldRef second = new FieldRef(FieldName.create("x2"));

	Constant zero = PMMLUtil.createConstant(0, DataType.DOUBLE);

	Apply expected = PMMLUtil.createApply(PMMLFunctions.IF)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.LESSTHAN)
			.addExpressions(first, zero)
		)
		.addExpressions(first)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.IF)
			.addExpressions(PMMLUtil.createApply(PMMLFunctions.GREATERTHAN)
				.addExpressions(second, zero)
			)
			.addExpressions(second)
			.addExpressions(zero)
		);

	checkExpression(expected, string);
}
 

static
private FieldName prepareInputField(FunctionExpression.Argument argument, OpType opType, DataType dataType, RExpEncoder encoder){
	Expression expression = argument.getExpression();

	if(expression instanceof FieldRef){
		FieldRef fieldRef = (FieldRef)expression;

		return fieldRef.getField();
	} else

	if(expression instanceof Apply){
		Apply apply = (Apply)expression;

		DerivedField derivedField = encoder.createDerivedField(FieldName.create((argument.formatExpression()).trim()), opType, dataType, apply);

		return derivedField.getName();
	} else

	{
		throw new IllegalArgumentException();
	}
}
 

static
private Apply createHingeFunction(int dir, Feature feature, double cut){
	Expression expression;

	switch(dir){
		case -1:
			expression = PMMLUtil.createApply(PMMLFunctions.SUBTRACT, PMMLUtil.createConstant(cut), feature.ref());
			break;
		case 1:
			expression = PMMLUtil.createApply(PMMLFunctions.SUBTRACT, feature.ref(), PMMLUtil.createConstant(cut));
			break;
		default:
			throw new IllegalArgumentException();
	}

	return PMMLUtil.createApply(PMMLFunctions.MAX, expression, PMMLUtil.createConstant(0d));
}
 

static
private Expression encodeIfElseExpression(FunctionExpression functionExpression, VariableMap expressionFields, RExpEncoder encoder){
	FunctionExpression.Argument testArgument = functionExpression.getArgument("test", 0);

	expressionFields.putAll(testArgument);

	FunctionExpression.Argument yesArgument = functionExpression.getArgument("yes", 1);
	FunctionExpression.Argument noArgument = functionExpression.getArgument("no", 2);

	expressionFields.putAll(yesArgument);
	expressionFields.putAll(noArgument);

	// XXX: "Missing values in test give missing values in the result"
	Apply apply = PMMLUtil.createApply(PMMLFunctions.IF)
		.addExpressions(prepareExpression(testArgument, expressionFields, encoder))
		.addExpressions(prepareExpression(yesArgument, expressionFields, encoder), prepareExpression(noArgument, expressionFields, encoder));

	return apply;
}
 

@Override
public List<Feature> encodeFeatures(List<Feature> features, SkLearnEncoder encoder){
	String function = getFunction();

	if(features.size() <= 1){
		return features;
	}

	Apply apply = PMMLUtil.createApply(translateFunction(function));

	for(Feature feature : features){
		apply.addExpressions(feature.ref());
	}

	FieldName name = FeatureUtil.createName(function, features);

	DerivedField derivedField = encoder.createDerivedField(name, OpType.CONTINUOUS, DataType.DOUBLE, apply);

	return Collections.singletonList(new ContinuousFeature(encoder, derivedField));
}
 

static
private boolean checkApply(Apply apply, String function, Class<? extends Expression>... expressionClazzes){

	if((function).equals(apply.getFunction())){
		List<Expression> expressions = apply.getExpressions();

		if(expressionClazzes.length == expressions.size()){

			for(int i = 0; i < expressionClazzes.length; i++){
				Class<? extends Expression> expressionClazz = expressionClazzes[i];
				Expression expression = expressions.get(i);

				if(!(expressionClazz).isInstance(expression)){
					return false;
				}
			}

			return true;
		}
	}

	return false;
}
 

@Override
public MiningModel encodeMiningModel(List<RegTree> trees, List<Float> weights, float base_score, Integer ntreeLimit, Schema schema){
	Schema segmentSchema = schema.toAnonymousRegressorSchema(DataType.FLOAT);

	Transformation transformation = new FunctionTransformation(PMMLFunctions.THRESHOLD){

		@Override
		public FieldName getName(FieldName name){
			return FieldName.create("hinge(" + name + ")");
		}

		@Override
		public Expression createExpression(FieldRef fieldRef){
			Apply apply = (Apply)super.createExpression(fieldRef);

			apply.addExpressions(PMMLUtil.createConstant(0f));

			return apply;
		}
	};

	MiningModel miningModel = createMiningModel(trees, weights, base_score, ntreeLimit, segmentSchema)
		.setOutput(ModelUtil.createPredictedOutput(FieldName.create("xgbValue"), OpType.CONTINUOUS, DataType.FLOAT, transformation));

	return MiningModelUtil.createBinaryLogisticClassification(miningModel, 1d, 0d, RegressionModel.NormalizationMethod.NONE, true, schema);
}
 

@Test
public void translateIfExpression(){
	String string = "if(status in (-1, 1), x1 != 0, x2 != 0)";

	Apply expected = PMMLUtil.createApply(PMMLFunctions.IF)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.ISIN)
			.addExpressions(new FieldRef(FieldName.create("status")))
			.addExpressions(PMMLUtil.createConstant(-1), PMMLUtil.createConstant(1))
		)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.NOTEQUAL)
			.addExpressions(new FieldRef(FieldName.create("x1")), PMMLUtil.createConstant(0, DataType.DOUBLE))
		)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.NOTEQUAL)
			.addExpressions(new FieldRef(FieldName.create("x2")), PMMLUtil.createConstant(0, DataType.DOUBLE))
		);

	checkExpression(expected, string);
}
 

@Test
public void translateArithmeticExpression(){
	String string = "-((x1 - 1) / (x2 + 1))";

	Apply expected = PMMLUtil.createApply(PMMLFunctions.MULTIPLY)
		.addExpressions(PMMLUtil.createConstant(-1))
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.DIVIDE)
			.addExpressions(PMMLUtil.createApply(PMMLFunctions.SUBTRACT)
				.addExpressions(new FieldRef(FieldName.create("x1")), PMMLUtil.createConstant(1, DataType.DOUBLE))
			)
			.addExpressions(PMMLUtil.createApply(PMMLFunctions.ADD)
				.addExpressions(new FieldRef(FieldName.create("x2")), PMMLUtil.createConstant(1, DataType.DOUBLE))
			)
		);

	checkExpression(expected, string);
}
 

@Override
public List<Feature> encodeFeatures(List<Feature> features, SkLearnEncoder encoder){
	String pattern = getPattern();
	String replacement = getReplacement();

	ClassDictUtil.checkSize(1, features);

	Feature feature = features.get(0);
	if(!(DataType.STRING).equals(feature.getDataType())){
		throw new IllegalArgumentException();
	}

	Apply apply = PMMLUtil.createApply(PMMLFunctions.REPLACE)
		.addExpressions(feature.ref())
		.addExpressions(PMMLUtil.createConstant(pattern, DataType.STRING), PMMLUtil.createConstant(replacement, DataType.STRING));

	DerivedField derivedField = encoder.createDerivedField(FeatureUtil.createName("replace", feature), OpType.CATEGORICAL, DataType.STRING, apply);

	return Collections.singletonList(new StringFeature(encoder, derivedField));
}
 

@Override
public List<Feature> encodeFeatures(List<Feature> features, SkLearnEncoder encoder){
	Integer begin = getBegin();
	Integer end = getEnd();

	if((begin < 0) || (end < begin)){
		throw new IllegalArgumentException();
	}

	ClassDictUtil.checkSize(1, features);

	Feature feature = features.get(0);
	if(!(DataType.STRING).equals(feature.getDataType())){
		throw new IllegalArgumentException();
	}

	Apply apply = PMMLUtil.createApply(PMMLFunctions.SUBSTRING)
		.addExpressions(feature.ref())
		.addExpressions(PMMLUtil.createConstant(begin + 1, DataType.INTEGER), PMMLUtil.createConstant((end - begin), DataType.INTEGER));

	DerivedField derivedField = encoder.createDerivedField(FeatureUtil.createName("substring", feature), OpType.CATEGORICAL, DataType.STRING, apply);

	return Collections.singletonList(new StringFeature(encoder, derivedField));
}
 

@Override
public List<Feature> encodeFeatures(List<Feature> features, SkLearnEncoder encoder){
	String pattern = getPattern();

	ClassDictUtil.checkSize(1, features);

	Feature feature = features.get(0);
	if(!(DataType.STRING).equals(feature.getDataType())){
		throw new IllegalArgumentException();
	}

	Apply apply = PMMLUtil.createApply(PMMLFunctions.MATCHES)
		.addExpressions(feature.ref())
		.addExpressions(PMMLUtil.createConstant(pattern, DataType.STRING));

	DerivedField derivedField = encoder.createDerivedField(FeatureUtil.createName("matches", feature), OpType.CATEGORICAL, DataType.BOOLEAN, apply);

	return Collections.singletonList(new BooleanFeature(encoder, derivedField));
}
 

@Override
public List<Feature> encodeFeatures(SparkMLEncoder encoder){
	RegexTokenizer transformer = getTransformer();

	if(!transformer.getGaps()){
		throw new IllegalArgumentException("Expected splitter mode, got token matching mode");
	} // End if

	if(transformer.getMinTokenLength() != 1){
		throw new IllegalArgumentException("Expected 1 as minimum token length, got " + transformer.getMinTokenLength() + " as minimum token length");
	}

	Feature feature = encoder.getOnlyFeature(transformer.getInputCol());

	Field<?> field = feature.getField();

	if(transformer.getToLowercase()){
		Apply apply = PMMLUtil.createApply(PMMLFunctions.LOWERCASE, feature.ref());

		field = encoder.createDerivedField(FeatureUtil.createName("lowercase", feature), OpType.CATEGORICAL, DataType.STRING, apply);
	}

	return Collections.singletonList(new DocumentFeature(encoder, field, transformer.getPattern()));
}
 

@Override
public VisitorAction visit(Apply apply){
	String function = apply.getFunction();

	switch(function){
		case PMMLFunctions.ERF:
		case PMMLFunctions.NORMALCDF:
		case PMMLFunctions.NORMALIDF:
		case PMMLFunctions.NORMALPDF:
		case PMMLFunctions.STDNORMALCDF:
		case PMMLFunctions.STDNORMALIDF:
		case PMMLFunctions.STDNORMALPDF:
			report(new UnsupportedAttributeException(apply, PMMLAttributes.APPLY_FUNCTION, function));
			break;
		default:
			break;
	}

	return super.visit(apply);
}
 

@Test
public void evaluateApplyJavaFunction(){
	FieldName name = FieldName.create("x");

	FieldRef fieldRef = new FieldRef(name);

	Apply apply = new Apply(EchoFunction.class.getName())
		.addExpressions(fieldRef);

	try {
		evaluate(apply);

		fail();
	} catch(EvaluationException ee){
		assertEquals(fieldRef, ee.getContext());
	}

	assertEquals("Hello World!", evaluate(apply, name, "Hello World!"));
}
 

private void scaleFeatures(RExpEncoder encoder){
	RGenericVector mvr = getObject();

	RDoubleVector scale = mvr.getDoubleElement("scale", false);
	if(scale == null){
		return;
	}

	List<Feature> features = encoder.getFeatures();

	if(scale.size() != features.size()){
		throw new IllegalArgumentException();
	}

	for(int i = 0; i < features.size(); i++){
		Feature feature = features.get(i);
		Double factor = scale.getValue(i);

		if(ValueUtil.isOne(factor)){
			continue;
		}

		ContinuousFeature continuousFeature = feature.toContinuousFeature();

		Apply apply = PMMLUtil.createApply(PMMLFunctions.DIVIDE, continuousFeature.ref(), PMMLUtil.createConstant(factor));

		DerivedField derivedField = encoder.createDerivedField(FeatureUtil.createName("scale", feature), OpType.CONTINUOUS, DataType.DOUBLE, apply);

		features.set(i, new ContinuousFeature(encoder, derivedField));
	}
}
 

/**
 * https://docs.scipy.org/doc/scipy/reference/generated/scipy.interpolate.BSpline.html
 */
static
private DefineFunction createBSplineFunction(BSpline bspline, SkLearnEncoder encoder){
	int k = bspline.getK();

	List<Number> c = bspline.getC();
	List<Number> t = bspline.getT();

	int n = (t.size() - k - 1);

	ParameterField paramterField = new ParameterField()
		.setName(FieldName.create("x"))
		.setOpType(OpType.CONTINUOUS)
		.setDataType(DataType.DOUBLE);

	Apply sumApply = PMMLUtil.createApply(PMMLFunctions.SUM);

	for(int i = 0; i < n; i++){

		for(int j = k; j >= 0; j--){
			createBFunction(t, i, j, encoder);
		}

		Apply apply = PMMLUtil.createApply(PMMLFunctions.MULTIPLY)
			.addExpressions(PMMLUtil.createConstant(c.get(i)))
			.addExpressions(PMMLUtil.createApply(formatBFunction(i, k), new FieldRef(paramterField.getName())));

		sumApply.addExpressions(apply);
	}

	DefineFunction defineFunction = new DefineFunction(formatBSplineFunction(k), OpType.CONTINUOUS, DataType.DOUBLE, null, sumApply)
		.addParameterFields(paramterField);

	encoder.addDefineFunction(defineFunction);

	return defineFunction;
}
 

public void addField(Field<?> field){
	RExpEncoder encoder = getEncoder();

	Feature feature = new ContinuousFeature(encoder, field);

	if(field instanceof DerivedField){
		DerivedField derivedField = (DerivedField)field;

		Expression expression = derivedField.getExpression();
		if(expression instanceof Apply){
			Apply apply = (Apply)expression;

			if(checkApply(apply, PMMLFunctions.POW, FieldRef.class, Constant.class)){
				List<Expression> expressions = apply.getExpressions();

				FieldRef fieldRef = (FieldRef)expressions.get(0);
				Constant constant = (Constant)expressions.get(1);

				try {
					String string = ValueUtil.asString(constant.getValue());

					int power = Integer.parseInt(string);

					feature = new PowerFeature(encoder, fieldRef.getField(), DataType.DOUBLE, power);
				} catch(NumberFormatException nfe){
					// Ignored
				}
			}
		}
	}

	putFeature(field.getName(), feature);

	this.fields.add(field);
}
 

@Test
public void translateLogicalExpressionChain(){
	String string = "(x == 0) | ((x == 1) | (x == 2)) | x == 3";

	Apply left = PMMLUtil.createApply(PMMLFunctions.EQUAL)
		.addExpressions(new FieldRef(FieldName.create("x")), PMMLUtil.createConstant("0", DataType.INTEGER));

	Apply middleLeft = PMMLUtil.createApply(PMMLFunctions.EQUAL)
		.addExpressions(new FieldRef(FieldName.create("x")), PMMLUtil.createConstant("1", DataType.INTEGER));

	Apply middleRight = PMMLUtil.createApply(PMMLFunctions.EQUAL)
		.addExpressions(new FieldRef(FieldName.create("x")), PMMLUtil.createConstant("2", DataType.INTEGER));

	Apply right = PMMLUtil.createApply(PMMLFunctions.EQUAL)
		.addExpressions(new FieldRef(FieldName.create("x")), PMMLUtil.createConstant("3", DataType.INTEGER));

	Expression expected = PMMLUtil.createApply(PMMLFunctions.OR)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.OR)
			.addExpressions(left)
			.addExpressions(PMMLUtil.createApply(PMMLFunctions.OR)
				.addExpressions(middleLeft, middleRight)
			)
		)
		.addExpressions(right);

	Expression actual = ExpressionTranslator.translateExpression(string, false);

	assertTrue(ReflectionUtil.equals(expected, actual));

	expected = PMMLUtil.createApply(PMMLFunctions.OR)
		.addExpressions(left, middleLeft, middleRight, right);

	actual = ExpressionTranslator.translateExpression(string, true);

	assertTrue(ReflectionUtil.equals(expected, actual));
}
 

@Override
public VisitorAction visit(Apply apply){
	String function = apply.getFunction();

	Version version = VersionInspector.functionVersions.get(function);
	if(version != null){
		updateMinimum(version);
	}

	return super.visit(apply);
}
 

@Override
public Apply encodeApply(String function, Feature feature, int index, String term){
	TfidfTransformer transformer = getTransformer();

	Apply apply = super.encodeApply(function, feature, index, term);

	Boolean useIdf = transformer.getUseIdf();
	if(useIdf){
		Number weight = transformer.getWeight(index);

		apply.addExpressions(PMMLUtil.createConstant(weight));
	}

	return apply;
}
 

@Override
public VisitorAction visit(Apply apply){

	if(apply.hasExpressions()){
		filterAll(apply.getExpressions());
	}

	return super.visit(apply);
}
 

@Test
public void translateLogicalExpression(){
	String string = "isnull(x1) and not(isnotnull(x2))";

	FieldRef first = new FieldRef(FieldName.create("x1"));
	FieldRef second = new FieldRef(FieldName.create("x2"));

	Apply expected = PMMLUtil.createApply(PMMLFunctions.AND)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.ISMISSING)
			.addExpressions(first)
		)
		// "not(isnotnull(..)) -> "isnull(..)"
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.ISMISSING)
			.addExpressions(second)
		);

	checkExpression(expected, string);

	string = "(x1 <= 0) or (x2 >= 0)";

	expected = PMMLUtil.createApply(PMMLFunctions.OR)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.LESSOREQUAL)
			.addExpressions(first, PMMLUtil.createConstant(0, DataType.DOUBLE))
		)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.GREATEROREQUAL)
			.addExpressions(second, PMMLUtil.createConstant(0, DataType.DOUBLE))
		);

	checkExpression(expected, string);
}
 

public Apply createApply(){
	DefineFunction defineFunction = getDefineFunction();
	Feature feature = getFeature();
	String value = getValue();

	Constant constant = PMMLUtil.createConstant(value, DataType.STRING);

	return PMMLUtil.createApply(defineFunction.getName(), feature.ref(), constant);
}
 

@Override
public Apply createApply(){
	Number weight = getWeight();

	Apply apply = super.createApply()
		.addExpressions(PMMLUtil.createConstant(weight));

	return apply;
}
 

static
FieldValue evaluateExpression(Expression expression, EvaluationContext context){

	if(expression instanceof Constant){
		return evaluateConstant((Constant)expression);
	} else

	if(expression instanceof FieldRef){
		return evaluateFieldRef((FieldRef)expression, context);
	} else

	if(expression instanceof NormContinuous){
		return evaluateNormContinuous((NormContinuous)expression, context);
	} else

	if(expression instanceof NormDiscrete){
		return evaluateNormDiscrete((NormDiscrete)expression, context);
	} else

	if(expression instanceof Discretize){
		return evaluateDiscretize((Discretize)expression, context);
	} else

	if(expression instanceof MapValues){
		return evaluateMapValues((MapValues)expression, context);
	} else

	if(expression instanceof TextIndex){
		return evaluateTextIndex((TextIndex)expression, context);
	} else

	if(expression instanceof Apply){
		return evaluateApply((Apply)expression, context);
	} else

	if(expression instanceof Aggregate){
		return evaluateAggregate((Aggregate)expression, context);
	} // End if

	if(expression instanceof JavaExpression){
		return evaluateJavaExpression((JavaExpression)expression, context);
	}

	throw new UnsupportedElementException(expression);
}
 

@Override
public List<Feature> encodeFeatures(List<Feature> features, SkLearnEncoder encoder){
	BSpline bspline = getBSpline();

	ClassDictUtil.checkSize(1, features);

	Feature feature = features.get(0);

	ContinuousFeature continuousFeature = feature.toContinuousFeature();

	DefineFunction defineFunction = createBSplineFunction(bspline, encoder);

	Apply apply = PMMLUtil.createApply(defineFunction.getName())
		.addExpressions(continuousFeature.ref());

	DerivedField derivedField = encoder.createDerivedField(FeatureUtil.createName("bspline", feature), apply);

	return Collections.singletonList(new ContinuousFeature(encoder, derivedField));
}
 

void assertTransformedFeature(Transformer transformer, String function){
	SkLearnEncoder encoder = new SkLearnEncoder();

	DataField dataField = encoder.createDataField(FieldName.create("x"));

	Feature inputFeature = new WildcardFeature(encoder, dataField);
	Feature outputFeature = Iterables.getOnlyElement(transformer.encodeFeatures(Collections.singletonList(inputFeature), encoder));

	assertNotSame(inputFeature, outputFeature);

	DerivedField derivedField = (DerivedField)encoder.getField(outputFeature.getName());

	Apply apply = (Apply)derivedField.getExpression();

	assertEquals(function, apply.getFunction());
}
 

@Override
public List<Feature> encodeFeatures(List<Feature> features, SkLearnEncoder encoder){
	String separator = getSeparator();

	Apply apply = PMMLUtil.createApply(PMMLFunctions.CONCAT);

	List<Expression> expressions = apply.getExpressions();

	for(int i = 0; i < features.size(); i++){
		Feature feature = features.get(i);

		if((i > 0) && !("").equals(separator)){
			expressions.add(PMMLUtil.createConstant(separator, DataType.STRING));
		}

		expressions.add(feature.ref());
	}

	DerivedField derivedField = encoder.createDerivedField(FeatureUtil.createName("concat", features), OpType.CATEGORICAL, DataType.STRING, apply);

	return Collections.singletonList(new StringFeature(encoder, derivedField));
}
 

@Override
public List<Feature> encodeFeatures(List<Feature> features, SkLearnEncoder encoder){
	List<?> classes = getClasses();

	Number negLabel = getNegLabel();
	Number posLabel = getPosLabel();

	ClassDictUtil.checkSize(1, features);

	Feature feature = features.get(0);

	List<Object> categories = new ArrayList<>();
	categories.addAll(classes);

	List<Number> labelCategories = new ArrayList<>();
	labelCategories.add(negLabel);
	labelCategories.add(posLabel);

	List<Feature> result = new ArrayList<>();

	classes = prepareClasses(classes);

	for(int i = 0; i < classes.size(); i++){
		Object value = classes.get(i);

		if(ValueUtil.isZero(negLabel) && ValueUtil.isOne(posLabel)){
			result.add(new BinaryFeature(encoder, feature, value));
		} else

		{
			// "($name == value) ? pos_label : neg_label"
			Apply apply = PMMLUtil.createApply(PMMLFunctions.IF)
				.addExpressions(PMMLUtil.createApply(PMMLFunctions.EQUAL, feature.ref(), PMMLUtil.createConstant(value, feature.getDataType())))
				.addExpressions(PMMLUtil.createConstant(posLabel), PMMLUtil.createConstant(negLabel));

			FieldName name = (classes.size() > 1 ? FeatureUtil.createName("label_binarizer", feature, i) : FeatureUtil.createName("label_binarizer", feature));

			DerivedField derivedField = encoder.createDerivedField(name, apply);

			result.add(new CategoricalFeature(encoder, derivedField, labelCategories));
		}
	}

	encoder.toCategorical(feature.getName(), categories);

	return result;
}