org.dmg.pmml.Expression Java Examples

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;
}
 

@Test
public void translateLogicalExpression(){
	String string = "a >= 0.0 & b >= 0.0 | c <= 0.0";

	Expression expected = PMMLUtil.createApply(PMMLFunctions.OR)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.AND)
			.addExpressions(PMMLUtil.createApply(PMMLFunctions.GREATEROREQUAL)
				.addExpressions(new FieldRef(FieldName.create("a")), PMMLUtil.createConstant("0.0", DataType.DOUBLE))
			)
			.addExpressions(PMMLUtil.createApply(PMMLFunctions.GREATEROREQUAL)
				.addExpressions(new FieldRef(FieldName.create("b")), PMMLUtil.createConstant("0.0", DataType.DOUBLE))
			)
		)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.LESSOREQUAL)
			.addExpressions(new FieldRef(FieldName.create("c")), PMMLUtil.createConstant("0.0", DataType.DOUBLE))
		);

	Expression actual = ExpressionTranslator.translateExpression(string);

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

@Test
public void translateRelationalExpression(){
	String string = "if(x < 0) \"negative\" else if(x > 0) \"positive\" else \"zero\"";

	Expression expected = PMMLUtil.createApply(PMMLFunctions.IF)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.LESSTHAN)
			.addExpressions(new FieldRef(FieldName.create("x")), PMMLUtil.createConstant("0", DataType.INTEGER))
		)
		.addExpressions(PMMLUtil.createConstant("negative", DataType.STRING))
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.IF)
			.addExpressions(PMMLUtil.createApply(PMMLFunctions.GREATERTHAN)
				.addExpressions(new FieldRef(FieldName.create("x")), PMMLUtil.createConstant("0", DataType.INTEGER))
			)
			.addExpressions(PMMLUtil.createConstant("positive", DataType.STRING))
			.addExpressions(PMMLUtil.createConstant("zero", DataType.STRING))
		);

	Expression actual = ExpressionTranslator.translateExpression(string);

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

@Test
public void translateArithmeticExpressionChain(){
	String string = "A + B - X + C";

	Expression expected = PMMLUtil.createApply(PMMLFunctions.ADD)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.SUBTRACT)
			.addExpressions(PMMLUtil.createApply(PMMLFunctions.ADD)
				.addExpressions(new FieldRef(FieldName.create("A")), new FieldRef(FieldName.create("B")))
			)
			.addExpressions(new FieldRef(FieldName.create("X")))
		)
		.addExpressions(new FieldRef(FieldName.create("C")));

	Expression actual = ExpressionTranslator.translateExpression(string);

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

@Test
public void translate(){
	String string = "(1.0 + log(A / B)) ^ 2";

	Expression expected = PMMLUtil.createApply(PMMLFunctions.POW)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.ADD)
			.addExpressions(PMMLUtil.createConstant("1.0", DataType.DOUBLE))
			.addExpressions(PMMLUtil.createApply(PMMLFunctions.LN)
				.addExpressions(PMMLUtil.createApply(PMMLFunctions.DIVIDE)
					.addExpressions(new FieldRef(FieldName.create("A")), new FieldRef(FieldName.create("B")))
				)
			)
		)
		.addExpressions(PMMLUtil.createConstant("2", DataType.INTEGER));

	Expression actual = ExpressionTranslator.translateExpression(string);

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

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 prepareExpression(FunctionExpression.Argument argument, VariableMap expressionFields, RExpEncoder encoder){
	Expression expression = argument.getExpression();

	if(expression instanceof FunctionExpression){
		FunctionExpression functionExpression = (FunctionExpression)expression;

		if(functionExpression.hasId("base", "ifelse")){
			return encodeIfElseExpression(functionExpression, expressionFields, encoder);
		}

		throw new IllegalArgumentException();
	}

	return expression;
}
 

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();
	}
}
 

private <E extends Expression & HasDataType<E> & HasDefaultValue<E, Object> & HasMapMissingTo<E, Object>> void parseExpressionValues(E expression){
	DataType dataType = expression.getDataType();
	if(dataType != null){
		Object defaultValue = expression.getDefaultValue();
		if(defaultValue != null){
			defaultValue = parseOrCast(dataType, defaultValue);

			expression.setDefaultValue(defaultValue);
		}

		Object mapMissingTo = expression.getMapMissingTo();
		if(mapMissingTo != null){
			mapMissingTo = parseOrCast(dataType, mapMissingTo);

			expression.setMapMissingTo(mapMissingTo);
		}
	}
}
 

static
public Feature encodeIndicatorFeature(Feature feature, Object missingValue, SkLearnEncoder encoder){
	Expression expression = feature.ref();

	if(missingValue != null){
		expression = PMMLUtil.createApply(PMMLFunctions.EQUAL, expression, PMMLUtil.createConstant(missingValue, feature.getDataType()));
	} else

	{
		expression = PMMLUtil.createApply(PMMLFunctions.ISMISSING, expression);
	}

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

	return new BooleanFeature(encoder, derivedField);
}
 

@Override
public DefineFunction encodeDefineFunction(){
	TfidfTransformer transformer = getTransformer();

	DefineFunction defineFunction = super.encodeDefineFunction();

	Expression expression = defineFunction.getExpression();

	Boolean sublinearTf = transformer.getSublinearTf();
	if(sublinearTf){
		expression = PMMLUtil.createApply(PMMLFunctions.ADD, PMMLUtil.createApply(PMMLFunctions.LN, expression), PMMLUtil.createConstant(1d));
	} // End if

	Boolean useIdf = transformer.getUseIdf();
	if(useIdf){
		ParameterField weight = new ParameterField(FieldName.create("weight"));

		defineFunction.addParameterFields(weight);

		expression = PMMLUtil.createApply(PMMLFunctions.MULTIPLY, expression, new FieldRef(weight.getName()));
	}

	defineFunction.setExpression(expression);

	return defineFunction;
}
 

@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);
}
 

@Override
public MiningModel encodeModel(Schema schema){
	LinearSVCModel model = getTransformer();

	Transformation transformation = new AbstractTransformation(){

		@Override
		public Expression createExpression(FieldRef fieldRef){
			return PMMLUtil.createApply(PMMLFunctions.THRESHOLD)
				.addExpressions(fieldRef, PMMLUtil.createConstant(model.getThreshold()));
		}
	};

	Schema segmentSchema = schema.toAnonymousRegressorSchema(DataType.DOUBLE);

	Model linearModel = LinearModelUtil.createRegression(this, model.coefficients(), model.intercept(), segmentSchema)
		.setOutput(ModelUtil.createPredictedOutput(FieldName.create("margin"), OpType.CONTINUOUS, DataType.DOUBLE, transformation));

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

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;
}
 

@Test
public void translateExponentiationExpression(){
	String string = "-2^-3";

	Expression expected = PMMLUtil.createApply(PMMLFunctions.MULTIPLY)
		.addExpressions(PMMLUtil.createConstant(-1))
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.POW)
			.addExpressions(PMMLUtil.createConstant("2", DataType.INTEGER), PMMLUtil.createConstant("-3", DataType.INTEGER))
		);

	Expression actual = ExpressionTranslator.translateExpression(string);

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

	string = "-2^-2*1.5";

	expected = PMMLUtil.createApply(PMMLFunctions.MULTIPLY)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.MULTIPLY)
			.addExpressions(PMMLUtil.createConstant(-1))
			.addExpressions(PMMLUtil.createApply(PMMLFunctions.POW)
				.addExpressions(PMMLUtil.createConstant("2", DataType.INTEGER), PMMLUtil.createConstant("-2", DataType.INTEGER))
			)
		)
		.addExpressions(PMMLUtil.createConstant("1.5", DataType.DOUBLE));

	actual = ExpressionTranslator.translateExpression(string);

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

static
private Expression encodeIdentityExpression(FunctionExpression functionExpression, VariableMap expressionFields, RExpEncoder encoder){
	FunctionExpression.Argument xArgument = functionExpression.getArgument("x", 0);

	expressionFields.putAll(xArgument);

	return prepareExpression(xArgument, expressionFields, encoder);
}
 

@Test
public void translateIfExpression(){
	String string = "if(is.na(x)) TRUE else FALSE";

	Expression expected = PMMLUtil.createApply(PMMLFunctions.IF)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.ISMISSING)
			.addExpressions(new FieldRef(FieldName.create("x")))
		)
		.addExpressions(PMMLUtil.createConstant("true", DataType.BOOLEAN), PMMLUtil.createConstant("false", DataType.BOOLEAN));

	Expression actual = ExpressionTranslator.translateExpression(string);

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

@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));
}
 

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);
}
 

static
public FieldValue evaluate(Expression expression, EvaluationContext context){

	try {
		return evaluateExpression(expression, context);
	} catch(PMMLException pe){
		throw pe.ensureContext(expression);
	}
}
 

@Test
public void translateParenthesizedExpression(){
	String string = "TRUE | TRUE & FALSE";

	Constant trueConstant = PMMLUtil.createConstant("true", DataType.BOOLEAN);
	Constant falseConstant = PMMLUtil.createConstant("false", DataType.BOOLEAN);

	Expression expected = PMMLUtil.createApply(PMMLFunctions.OR)
		.addExpressions(trueConstant)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.AND)
			.addExpressions(trueConstant, falseConstant)
		);

	Expression actual = ExpressionTranslator.translateExpression(string);

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

	string = "(TRUE | TRUE) & FALSE";

	expected = PMMLUtil.createApply(PMMLFunctions.AND)
		.addExpressions(PMMLUtil.createApply(PMMLFunctions.OR)
			.addExpressions(trueConstant, trueConstant)
		)
		.addExpressions(falseConstant);

	actual = ExpressionTranslator.translateExpression(string);

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

private Expression getOutputExpression(NeuralOutput neuralOutput){
	DerivedField derivedField = neuralOutput.getDerivedField();
	if(derivedField == null){
		throw new MissingElementException(neuralOutput, PMMLElements.NEURALOUTPUT_DERIVEDFIELD);
	}

	Expression expression = ExpressionUtil.ensureExpression(derivedField);

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

		FieldName name = fieldRef.getField();
		if(name == null){
			throw new MissingAttributeException(fieldRef, org.dmg.pmml.PMMLAttributes.FIELDREF_FIELD);
		}

		Field<?> field = resolveField(name);
		if(field == null){
			throw new MissingFieldException(name, fieldRef);
		} // End if

		if(field instanceof DataField){
			return expression;
		} else

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

			Expression targetExpression = ExpressionUtil.ensureExpression(targetDerivedField);

			return targetExpression;
		} else

		{
			throw new InvalidAttributeException(fieldRef, org.dmg.pmml.PMMLAttributes.FIELDREF_FIELD, name);
		}
	}

	return expression;
}
 

private Map<FieldName, List<NeuralOutput>> parseNeuralOutputs(){
	NeuralNetwork neuralNetwork = getModel();

	ListMultimap<FieldName, NeuralOutput> result = ArrayListMultimap.create();

	NeuralOutputs neuralOutputs = neuralNetwork.getNeuralOutputs();
	for(NeuralOutput neuralOutput : neuralOutputs){
		FieldName name;

		Expression expression = getOutputExpression(neuralOutput);

		if(expression instanceof HasFieldReference){
			HasFieldReference<?> hasFieldReference = (HasFieldReference<?>)expression;

			name = hasFieldReference.getField();
			if(name == null){
				throw new MissingAttributeException(MissingAttributeException.formatMessage(XPathUtil.formatElement((Class)hasFieldReference.getClass()) + "@field"), expression);
			}
		} else

		{
			throw new MisplacedElementException(expression);
		}

		result.put(name, neuralOutput);
	}

	return (Map)result.asMap();
}
 

static
public <E extends Expression & HasFieldReference<E>> FieldName ensureField(E hasField){
	FieldName name = hasField.getField();
	if(name == null){
		throw new MissingAttributeException(MissingAttributeException.formatMessage(XPathUtil.formatElement(hasField.getClass()) + "@field"), hasField);
	}

	return name;
}
 

static
public <E extends PMMLObject & HasExpression<E>> Expression ensureExpression(E hasExpression){
	Expression expression = hasExpression.getExpression();
	if(expression == null){
		throw new MissingElementException(MissingElementException.formatMessage(XPathUtil.formatElement(hasExpression.getClass()) + "/<Expression>"), hasExpression);
	}

	return expression;
}
 

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

	if(function == null && !trimBlanks){
		return features;
	}

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

	for(Feature feature : features){
		Expression expression = feature.ref();

		if(function != null){
			expression = PMMLUtil.createApply(translateFunction(function), expression);
		} // End if

		if(trimBlanks){
			expression = PMMLUtil.createApply(PMMLFunctions.TRIMBLANKS, expression);
		}

		Field<?> field = encoder.toCategorical(feature.getName(), Collections.emptyList());

		// XXX: Should have been set by the previous transformer
		field.setDataType(DataType.STRING);

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

		feature = new StringFeature(encoder, derivedField);

		result.add(feature);
	}

	return result;
}
 

static
private Object evaluate(Expression expression, Map<FieldName, ?> arguments){
	EvaluationContext context = new VirtualEvaluationContext();
	context.declareAll(arguments);

	FieldValue result = ExpressionUtil.evaluate(expression, context);

	return FieldValueUtil.getValue(result);
}
 

@Override
public SupportVectorMachineModel encodeModel(Schema schema){
	Transformation outlier = new OutlierTransformation(){

		@Override
		public Expression createExpression(FieldRef fieldRef){
			return PMMLUtil.createApply(PMMLFunctions.LESSOREQUAL, fieldRef, PMMLUtil.createConstant(0d));
		}
	};

	SupportVectorMachineModel supportVectorMachineModel = super.encodeModel(schema)
		.setOutput(ModelUtil.createPredictedOutput(FieldName.create("decisionFunction"), OpType.CONTINUOUS, DataType.DOUBLE, outlier));

	Output output = supportVectorMachineModel.getOutput();

	List<OutputField> outputFields = output.getOutputFields();
	if(outputFields.size() != 2){
		throw new IllegalArgumentException();
	}

	OutputField decisionFunctionOutputField = outputFields.get(0);

	if(!decisionFunctionOutputField.isFinalResult()){
		decisionFunctionOutputField.setFinalResult(true);
	}

	return supportVectorMachineModel;
}
 

@Override
public List<Feature> encodeFeatures(List<Feature> features, SkLearnEncoder encoder){
	Object dtype = getDType();
	String expr = getExpr();

	Scope scope = new DataFrameScope(FieldName.create("X"), features);

	Expression expression = ExpressionTranslator.translate(expr, scope);

	DataType dataType;

	if(dtype != null){
		dataType = TransformerUtil.getDataType(dtype);
	} else

	{
		if(ExpressionTranslator.isString(expression, scope)){
			dataType = DataType.STRING;
		} else

		{
			dataType = DataType.DOUBLE;
		}
	}

	OpType opType = TransformerUtil.getOpType(dataType);

	DerivedField derivedField = encoder.createDerivedField(FieldName.create("eval(" + expr + ")"), opType, dataType, expression);

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

private Expression encodeExpression(FieldName name, Expression expression){
	List<Double> ranges = this.ranges.get(name);
	if(ranges != null){
		Double min = ranges.get(0);
		Double max = ranges.get(1);

		if(!ValueUtil.isZero(min)){
			expression = PMMLUtil.createApply(PMMLFunctions.SUBTRACT, expression, PMMLUtil.createConstant(min));
		} // End if

		if(!ValueUtil.isOne(max - min)){
			expression = PMMLUtil.createApply(PMMLFunctions.DIVIDE, expression, PMMLUtil.createConstant(max - min));
		}
	}

	Double mean = this.mean.get(name);
	if(mean != null && !ValueUtil.isZero(mean)){
		expression = PMMLUtil.createApply(PMMLFunctions.SUBTRACT, expression, PMMLUtil.createConstant(mean));
	}

	Double std = this.std.get(name);
	if(std != null && !ValueUtil.isOne(std)){
		expression = PMMLUtil.createApply(PMMLFunctions.DIVIDE, expression, PMMLUtil.createConstant(std));
	}

	Double median = this.median.get(name);
	if(median != null){
		expression = PMMLUtil.createApply(PMMLFunctions.IF)
			.addExpressions(PMMLUtil.createApply(PMMLFunctions.ISNOTMISSING, new FieldRef(name)))
			.addExpressions(expression, PMMLUtil.createConstant(median));
	}

	return expression;
}