org.dmg.pmml.Discretize Java Examples

@Override
public VisitorAction visit(DiscretizeBin discretizeBin){
	Discretize discretize = (Discretize)getParent();

	DataType dataType = discretize.getDataType();
	if(dataType != null){
		Object binValue = discretizeBin.getBinValue();
		if(binValue != null){
			binValue = parseOrCast(dataType, binValue);

			discretizeBin.setBinValue(binValue);
		}
	}

	return super.visit(discretizeBin);
}
 

static
private RangeMap<Double, Object> parseDiscretize(Discretize discretize){
	RangeMap<Double, Object> result = TreeRangeMap.create();

	List<DiscretizeBin> discretizeBins = discretize.getDiscretizeBins();
	for(DiscretizeBin discretizeBin : discretizeBins){
		Interval interval = discretizeBin.getInterval();
		if(interval == null){
			throw new MissingElementException(discretizeBin, PMMLElements.DISCRETIZEBIN_INTERVAL);
		}

		Range<Double> range = toRange(interval);

		Object binValue = discretizeBin.getBinValue();
		if(binValue == null){
			throw new MissingAttributeException(discretizeBin, PMMLAttributes.DISCRETIZEBIN_BINVALUE);
		}

		result.put(range, binValue);
	}

	return result;
}
 

static
private Discretize createDiscretize(FieldName name, List<String> categories){
	Discretize discretize = new Discretize(name);

	for(String category : categories){
		Interval interval = ExpressionTranslator.translateInterval(category);

		DiscretizeBin discretizeBin = new DiscretizeBin(category, interval);

		discretize.addDiscretizeBins(discretizeBin);
	}

	return discretize;
}
 

static
public FieldValue evaluateDiscretize(Discretize discretize, EvaluationContext context){
	FieldValue value = context.evaluate(ensureField(discretize));

	if(FieldValueUtil.isMissing(value)){
		return FieldValueUtil.create(discretize.getDataType(DataType.STRING), OpType.CATEGORICAL, discretize.getMapMissingTo());
	}

	return DiscretizationUtil.discretize(discretize, value);
}
 

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

	InOutMode inputMode = getInputMode();

	String[] inputCols;
	double[][] splitsArray;

	if((InOutMode.SINGLE).equals(inputMode)){
		inputCols = inputMode.getInputCols(transformer);
		splitsArray = new double[][]{transformer.getSplits()};
	} else

	if((InOutMode.MULTIPLE).equals(inputMode)){
		inputCols = inputMode.getInputCols(transformer);
		splitsArray = transformer.getSplitsArray();
	} else

	{
		throw new IllegalArgumentException();
	}

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

	for(int i = 0; i < inputCols.length; i++){
		String inputCol = inputCols[i];
		double[] splits = splitsArray[i];

		Feature feature = encoder.getOnlyFeature(inputCol);

		ContinuousFeature continuousFeature = feature.toContinuousFeature();

		Discretize discretize = new Discretize(continuousFeature.getName())
			.setDataType(DataType.INTEGER);

		List<Integer> categories = new ArrayList<>();

		for(int j = 0; j < (splits.length - 1); j++){
			Integer category = j;

			categories.add(category);

			Interval interval = new Interval((j < (splits.length - 2)) ? Interval.Closure.CLOSED_OPEN : Interval.Closure.CLOSED_CLOSED)
				.setLeftMargin(formatMargin(splits[j]))
				.setRightMargin(formatMargin(splits[j + 1]));

			DiscretizeBin discretizeBin = new DiscretizeBin(category, interval);

			discretize.addDiscretizeBins(discretizeBin);
		}

		DerivedField derivedField = encoder.createDerivedField(formatName(transformer, i), OpType.CATEGORICAL, DataType.INTEGER, discretize);

		result.add(new IndexFeature(encoder, derivedField, categories));
	}

	return result;
}
 

@Override
public VisitorAction visit(Discretize discretize){
	process(discretize.getField());

	return super.visit(discretize);
}
 

@Override
public VisitorAction visit(Discretize discretize){
	parseExpressionValues(discretize);

	return super.visit(discretize);
}
 

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 RangeMap<Double, Object> load(Discretize discretize){
	return ImmutableRangeMap.copyOf(parseDiscretize(discretize));
}
 

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

	Discretize discretize = new Discretize(name);

	assertEquals(null, evaluate(discretize, name, null));

	discretize.setMapMissingTo("Missing");

	assertEquals("Missing", evaluate(discretize, name, null));
	assertEquals(null, evaluate(discretize, name, 3));

	discretize.setDefaultValue("Default");

	assertEquals("Default", evaluate(discretize, name, 3));
}