Examples with Discretize org.dmg.pmml.Discretize used on opensource projects

Example 1 with Discretize

use of org.dmg.pmml.Discretize in project jpmml-r by jpmml.

the class FormulaUtil method createDiscretize.

private static 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;
}

Example 2 with Discretize

use of org.dmg.pmml.Discretize in project jpmml-sparkml by jpmml.

the class BucketizerConverter method encodeFeatures.

@Override
public List<Feature> encodeFeatures(SparkMLEncoder encoder) {
    Bucketizer transformer = getTransformer();
    Feature feature = encoder.getOnlyFeature(transformer.getInputCol());
    ContinuousFeature continuousFeature = feature.toContinuousFeature();
    Discretize discretize = new Discretize(continuousFeature.getName());
    List<String> categories = new ArrayList<>();
    double[] splits = transformer.getSplits();
    for (int i = 0; i < (splits.length - 1); i++) {
        String category = String.valueOf(i);
        categories.add(category);
        Interval interval = new Interval((i < (splits.length - 2)) ? Interval.Closure.CLOSED_OPEN : Interval.Closure.CLOSED_CLOSED).setLeftMargin(formatMargin(splits[i])).setRightMargin(formatMargin(splits[i + 1]));
        DiscretizeBin discretizeBin = new DiscretizeBin(category, interval);
        discretize.addDiscretizeBins(discretizeBin);
    }
    DerivedField derivedField = encoder.createDerivedField(formatName(transformer), OpType.CATEGORICAL, DataType.INTEGER, discretize);
    return Collections.<Feature>singletonList(new CategoricalFeature(encoder, derivedField, categories));
}

Example 3 with Discretize

use of org.dmg.pmml.Discretize in project shifu by ShifuML.

the class PMMLLRModelBuilder method adaptMLModelToPMML.

public RegressionModel adaptMLModelToPMML(ml.shifu.shifu.core.LR lr, RegressionModel pmmlModel) {
    pmmlModel.setNormalizationMethod(NormalizationMethod.LOGIT);
    pmmlModel.setMiningFunction(MiningFunction.REGRESSION);
    RegressionTable table = new RegressionTable();
    table.setIntercept(lr.getBias());
    LocalTransformations lt = pmmlModel.getLocalTransformations();
    List<DerivedField> df = lt.getDerivedFields();
    HashMap<FieldName, FieldName> miningTransformMap = new HashMap<FieldName, FieldName>();
    for (DerivedField dField : df) {
        // Apply z-scale normalization on numerical variables
        if (dField.getExpression() instanceof NormContinuous) {
            miningTransformMap.put(((NormContinuous) dField.getExpression()).getField(), dField.getName());
        } else // Apply bin map on categorical variables
        if (dField.getExpression() instanceof MapValues) {
            miningTransformMap.put(((MapValues) dField.getExpression()).getFieldColumnPairs().get(0).getField(), dField.getName());
        } else if (dField.getExpression() instanceof Discretize) {
            miningTransformMap.put(((Discretize) dField.getExpression()).getField(), dField.getName());
        }
    }
    List<MiningField> miningList = pmmlModel.getMiningSchema().getMiningFields();
    int index = 0;
    for (int i = 0; i < miningList.size(); i++) {
        MiningField mField = miningList.get(i);
        if (mField.getUsageType() != UsageType.ACTIVE)
            continue;
        FieldName mFieldName = mField.getName();
        FieldName fName = mFieldName;
        while (miningTransformMap.containsKey(fName)) {
            fName = miningTransformMap.get(fName);
        }
        NumericPredictor np = new NumericPredictor();
        np.setName(fName);
        np.setCoefficient(lr.getWeights()[index++]);
        table.addNumericPredictors(np);
    }
    pmmlModel.addRegressionTables(table);
    return pmmlModel;
}

Example 4 with Discretize

use of org.dmg.pmml.Discretize in project shifu by ShifuML.

the class WoeLocalTransformCreator method createNumericalDerivedField.

/**
 * Create @DerivedField for numerical variable
 *
 * @param config
 *            - ColumnConfig for numerical variable
 * @param cutoff
 *            - cutoff of normalization
 * @param normType
 *            - the normalization method that is used to generate DerivedField
 * @return DerivedField for variable
 */
@Override
protected List<DerivedField> createNumericalDerivedField(ColumnConfig config, double cutoff, ModelNormalizeConf.NormType normType) {
    List<Double> binWoeList = (normType.equals(ModelNormalizeConf.NormType.WOE) ? config.getBinCountWoe() : config.getBinWeightedWoe());
    List<Double> binBoundaryList = config.getBinBoundary();
    List<DiscretizeBin> discretizeBinList = new ArrayList<DiscretizeBin>();
    for (int i = 0; i < binBoundaryList.size(); i++) {
        DiscretizeBin discretizeBin = new DiscretizeBin();
        Interval interval = new Interval();
        if (i == 0) {
            if (binBoundaryList.size() == 1) {
                interval.setClosure(Interval.Closure.OPEN_OPEN).setLeftMargin(Double.NEGATIVE_INFINITY).setRightMargin(Double.POSITIVE_INFINITY);
            } else {
                interval.setClosure(Interval.Closure.OPEN_OPEN).setRightMargin(binBoundaryList.get(i + 1));
            }
        } else if (i == binBoundaryList.size() - 1) {
            interval.setClosure(Interval.Closure.CLOSED_OPEN).setLeftMargin(binBoundaryList.get(i));
        } else {
            interval.setClosure(Interval.Closure.CLOSED_OPEN).setLeftMargin(binBoundaryList.get(i)).setRightMargin(binBoundaryList.get(i + 1));
        }
        discretizeBin.setInterval(interval).setBinValue(Double.toString(binWoeList.get(i)));
        discretizeBinList.add(discretizeBin);
    }
    Discretize discretize = new Discretize();
    discretize.setDataType(DataType.DOUBLE).setField(FieldName.create(NormalUtils.getSimpleColumnName(config, columnConfigList, segmentExpansions, datasetHeaders))).setMapMissingTo(Normalizer.normalize(config, null, cutoff, normType).get(0).toString()).setDefaultValue(Normalizer.normalize(config, null, cutoff, normType).get(0).toString()).addDiscretizeBins(discretizeBinList.toArray(new DiscretizeBin[discretizeBinList.size()]));
    // derived field name is consisted of FieldName and "_zscl"
    List<DerivedField> derivedFields = new ArrayList<DerivedField>();
    derivedFields.add(new DerivedField(OpType.CONTINUOUS, DataType.DOUBLE).setName(FieldName.create(genPmmlColumnName(NormalUtils.getSimpleColumnName(config.getColumnName()), normType))).setExpression(discretize));
    return derivedFields;
}

Example 5 with Discretize

use of org.dmg.pmml.Discretize in project shifu by ShifuML.

the class NeuralNetworkModelIntegrator method getNeuralInputs.

private NeuralInputs getNeuralInputs(final NeuralNetwork model) {
    NeuralInputs nnInputs = new NeuralInputs();
    // get HashMap for local transform and MiningSchema fields
    HashMap<FieldName, FieldName> reversMiningTransformMap = new HashMap<FieldName, FieldName>();
    HashMap<FieldName, List<FieldName>> treeMapOfTransform = new HashMap<FieldName, List<FieldName>>();
    for (DerivedField dField : model.getLocalTransformations().getDerivedFields()) {
        // Apply z-scale normalization on numerical variables
        FieldName parentField = null;
        if (dField.getExpression() instanceof NormContinuous) {
            parentField = ((NormContinuous) dField.getExpression()).getField();
            reversMiningTransformMap.put(dField.getName(), parentField);
        } else // Apply bin map on categorical variables
        if (dField.getExpression() instanceof MapValues) {
            parentField = ((MapValues) dField.getExpression()).getFieldColumnPairs().get(0).getField();
            reversMiningTransformMap.put(dField.getName(), parentField);
        } else if (dField.getExpression() instanceof Discretize) {
            parentField = ((Discretize) dField.getExpression()).getField();
            reversMiningTransformMap.put(dField.getName(), parentField);
        }
        List<FieldName> fieldNames = treeMapOfTransform.get(parentField);
        if (fieldNames == null) {
            fieldNames = new ArrayList<FieldName>();
        }
        fieldNames.add(dField.getName());
        treeMapOfTransform.put(parentField, fieldNames);
    }
    // comment here
    List<MiningField> miningList = model.getMiningSchema().getMiningFields();
    int index = 0;
    for (DerivedField dField : model.getLocalTransformations().getDerivedFields()) {
        List<FieldName> list = treeMapOfTransform.get(dField.getName());
        boolean isLeaf = (list == null || list.size() == 0);
        FieldName root = getRoot(dField.getName(), reversMiningTransformMap);
        if (isLeaf && isRootInMiningList(root, miningList)) {
            DerivedField field = new DerivedField(OpType.CONTINUOUS, DataType.DOUBLE).setName(dField.getName()).setExpression(new FieldRef(dField.getName()));
            nnInputs.addNeuralInputs(new NeuralInput("0," + (index++), field));
        }
    }
    DerivedField field = new DerivedField(OpType.CONTINUOUS, DataType.DOUBLE).setName(new FieldName(PluginConstants.biasValue)).setExpression(new FieldRef(new FieldName(PluginConstants.biasValue)));
    nnInputs.addNeuralInputs(new NeuralInput(PluginConstants.biasValue, field));
    return nnInputs;
}