Java Code Examples for org.jpmml.converter.CategoricalLabel#size()

The following examples show how to use org.jpmml.converter.CategoricalLabel#size() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: MultinomialLogisticRegression.java    From jpmml-lightgbm with GNU Affero General Public License v3.0 6 votes vote down vote up 
@Override
public MiningModel encodeMiningModel(List<Tree> trees, Integer numIteration, Schema schema){
	Schema segmentSchema = schema.toAnonymousRegressorSchema(DataType.DOUBLE);

	List<MiningModel> miningModels = new ArrayList<>();

	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

	for(int i = 0, rows = categoricalLabel.size(), columns = (trees.size() / rows); i < rows; i++){
		MiningModel miningModel = createMiningModel(FortranMatrixUtil.getRow(trees, rows, columns, i), numIteration, segmentSchema)
			.setOutput(ModelUtil.createPredictedOutput(FieldName.create("lgbmValue(" + categoricalLabel.getValue(i) + ")"), OpType.CONTINUOUS, DataType.DOUBLE));

		miningModels.add(miningModel);
	}

	return MiningModelUtil.createClassification(miningModels, RegressionModel.NormalizationMethod.SOFTMAX, true, schema);
}
Example 2
Source File: MultinomialLogisticRegression.java    From jpmml-xgboost with GNU Affero General Public License v3.0 6 votes vote down vote up 
@Override
public MiningModel encodeMiningModel(List<RegTree> trees, List<Float> weights, float base_score, Integer ntreeLimit, Schema schema){
	Schema segmentSchema = schema.toAnonymousRegressorSchema(DataType.FLOAT);

	List<MiningModel> miningModels = new ArrayList<>();

	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

	for(int i = 0, columns = categoricalLabel.size(), rows = (trees.size() / columns); i < columns; i++){
		MiningModel miningModel = createMiningModel(CMatrixUtil.getColumn(trees, rows, columns, i), (weights != null) ? CMatrixUtil.getColumn(weights, rows, columns, i) : null, base_score, ntreeLimit, segmentSchema)
			.setOutput(ModelUtil.createPredictedOutput(FieldName.create("xgbValue(" + categoricalLabel.getValue(i) + ")"), OpType.CONTINUOUS, DataType.FLOAT));

		miningModels.add(miningModel);
	}

	return MiningModelUtil.createClassification(miningModels, RegressionModel.NormalizationMethod.SOFTMAX, true, schema);
}
Example 3
Source File: ScoreDistributionManager.java    From jpmml-sklearn with GNU Affero General Public License v3.0 6 votes vote down vote up 
public List<ScoreDistribution> createScoreDistribution(CategoricalLabel categoricalLabel, double[] recordCounts){
	List<ScoreDistribution> result = new ArrayList<>();

	for(int i = 0; i < categoricalLabel.size(); i++){
		Object value = categoricalLabel.getValue(i);
		double recordCount = recordCounts[i];

		ScoreDistribution scoreDistribution = new InternableScoreDistribution()
			.setValue(value)
			.setRecordCount(recordCount);

		scoreDistribution = intern(scoreDistribution);

		result.add(scoreDistribution);
	}

	return result;
}
Example 4
Source File: MultilayerPerceptronUtil.java    From jpmml-sklearn with GNU Affero General Public License v3.0 4 votes vote down vote up 
static
public NeuralNetwork encodeNeuralNetwork(MiningFunction miningFunction, String activation, List<? extends HasArray> coefs, List<? extends HasArray> intercepts, Schema schema){
	NeuralNetwork.ActivationFunction activationFunction = parseActivationFunction(activation);

	ClassDictUtil.checkSize(coefs, intercepts);

	Label label = schema.getLabel();
	List<? extends Feature> features = schema.getFeatures();

	NeuralInputs neuralInputs = NeuralNetworkUtil.createNeuralInputs(features, DataType.DOUBLE);

	List<? extends NeuralEntity> entities = neuralInputs.getNeuralInputs();

	List<NeuralLayer> neuralLayers = new ArrayList<>();

	for(int layer = 0; layer < coefs.size(); layer++){
		HasArray coef = coefs.get(layer);
		HasArray intercept = intercepts.get(layer);

		int[] shape = coef.getArrayShape();

		int rows = shape[0];
		int columns = shape[1];

		NeuralLayer neuralLayer = new NeuralLayer();

		List<?> coefMatrix = coef.getArrayContent();
		List<?> interceptVector = intercept.getArrayContent();

		for(int column = 0; column < columns; column++){
			List<? extends Number> weights = (List)CMatrixUtil.getColumn(coefMatrix, rows, columns, column);
			Number bias = (Number)interceptVector.get(column);

			Neuron neuron = NeuralNetworkUtil.createNeuron(entities, weights, bias)
				.setId(String.valueOf(layer + 1) + "/" + String.valueOf(column + 1));

			neuralLayer.addNeurons(neuron);
		}

		neuralLayers.add(neuralLayer);

		entities = neuralLayer.getNeurons();

		if(layer == (coefs.size() - 1)){
			neuralLayer.setActivationFunction(NeuralNetwork.ActivationFunction.IDENTITY);

			switch(miningFunction){
				case REGRESSION:
					break;
				case CLASSIFICATION:
					CategoricalLabel categoricalLabel = (CategoricalLabel)label;

					// Binary classification
					if(categoricalLabel.size() == 2){
						List<NeuralLayer> transformationNeuralLayers = NeuralNetworkUtil.createBinaryLogisticTransformation(Iterables.getOnlyElement(entities));

						neuralLayers.addAll(transformationNeuralLayers);

						neuralLayer = Iterables.getLast(transformationNeuralLayers);

						entities = neuralLayer.getNeurons();
					} else

					// Multi-class classification
					if(categoricalLabel.size() > 2){
						neuralLayer.setNormalizationMethod(NeuralNetwork.NormalizationMethod.SOFTMAX);
					} else

					{
						throw new IllegalArgumentException();
					}
					break;
				default:
					break;
			}
		}
	}

	NeuralOutputs neuralOutputs = null;

	switch(miningFunction){
		case REGRESSION:
			neuralOutputs = NeuralNetworkUtil.createRegressionNeuralOutputs(entities, (ContinuousLabel)label);
			break;
		case CLASSIFICATION:
			neuralOutputs = NeuralNetworkUtil.createClassificationNeuralOutputs(entities, (CategoricalLabel)label);
			break;
		default:
			break;
	}

	NeuralNetwork neuralNetwork = new NeuralNetwork(miningFunction, activationFunction, ModelUtil.createMiningSchema(label), neuralInputs, neuralLayers)
		.setNeuralOutputs(neuralOutputs);

	return neuralNetwork;
}
Example 5
Source File: LinearDiscriminantAnalysis.java    From jpmml-sklearn with GNU Affero General Public License v3.0 4 votes vote down vote up 
private Model encodeMultinomialModel(Schema schema){
	String sklearnVersion = getSkLearnVersion();
	int[] shape = getCoefShape();

	int numberOfClasses = shape[0];
	int numberOfFeatures = shape[1];

	List<? extends Number> coef = getCoef();
	List<? extends Number> intercept = getIntercept();

	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

	List<? extends Feature> features = schema.getFeatures();

	// See https://github.com/scikit-learn/scikit-learn/issues/6848
	boolean corrected = (sklearnVersion != null && SkLearnUtil.compareVersion(sklearnVersion, "0.21") >= 0);

	if(!corrected){
		return super.encodeModel(schema);
	} // End if

	if(numberOfClasses >= 3){
		SchemaUtil.checkSize(numberOfClasses, categoricalLabel);

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

		List<RegressionModel> regressionModels = new ArrayList<>();

		for(int i = 0, rows = categoricalLabel.size(); i < rows; i++){
			RegressionModel regressionModel = RegressionModelUtil.createRegression(features, CMatrixUtil.getRow(coef, numberOfClasses, numberOfFeatures, i), intercept.get(i), RegressionModel.NormalizationMethod.NONE, segmentSchema)
				.setOutput(ModelUtil.createPredictedOutput(FieldName.create("decisionFunction(" + categoricalLabel.getValue(i) + ")"), OpType.CONTINUOUS, DataType.DOUBLE));

			regressionModels.add(regressionModel);
		}

		return MiningModelUtil.createClassification(regressionModels, RegressionModel.NormalizationMethod.SOFTMAX, true, schema);
	} else

	{
		throw new IllegalArgumentException();
	}
}
Example 6
Source File: GBMConverter.java    From jpmml-r with GNU Affero General Public License v3.0 4 votes vote down vote up 
private MiningModel encodeMultinomialClassification(List<TreeModel> treeModels, Double initF, Schema schema){
	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

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

	List<Model> miningModels = new ArrayList<>();

	for(int i = 0, columns = categoricalLabel.size(), rows = (treeModels.size() / columns); i < columns; i++){
		MiningModel miningModel = createMiningModel(CMatrixUtil.getColumn(treeModels, rows, columns, i), initF, segmentSchema)
			.setOutput(ModelUtil.createPredictedOutput(FieldName.create("gbmValue(" + categoricalLabel.getValue(i) + ")"), OpType.CONTINUOUS, DataType.DOUBLE));

		miningModels.add(miningModel);
	}

	return MiningModelUtil.createClassification(miningModels, RegressionModel.NormalizationMethod.SOFTMAX, true, schema);
}
Example 7
Source File: MiningModelUtil.java    From pyramid with Apache License 2.0 4 votes vote down vote up 
static
public MiningModel createClassification(List<? extends Model> models, RegressionModel.NormalizationMethod normalizationMethod, boolean hasProbabilityDistribution, Schema schema){
    CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

    // modified here
    if(categoricalLabel.size() != models.size()){
        throw new IllegalArgumentException();
    } // End if

    if(normalizationMethod != null){

        switch(normalizationMethod){
            case NONE:
            case SIMPLEMAX:
            case SOFTMAX:
                break;
            default:
                throw new IllegalArgumentException();
        }
    }

    MathContext mathContext = null;

    List<RegressionTable> regressionTables = new ArrayList<>();

    for(int i = 0; i < categoricalLabel.size(); i++){
        Model model = models.get(i);

        MathContext modelMathContext = model.getMathContext();
        if(modelMathContext == null){
            modelMathContext = MathContext.DOUBLE;
        } // End if

        if(mathContext == null){
            mathContext = modelMathContext;
        } else

        {
            if(!Objects.equals(mathContext, modelMathContext)){
                throw new IllegalArgumentException();
            }
        }

        Feature feature = MODEL_PREDICTION.apply(model);

        RegressionTable regressionTable = RegressionModelUtil.createRegressionTable(Collections.singletonList(feature), Collections.singletonList(1d), null)
                .setTargetCategory(categoricalLabel.getValue(i));

        regressionTables.add(regressionTable);
    }

    RegressionModel regressionModel = new RegressionModel(MiningFunction.CLASSIFICATION, ModelUtil.createMiningSchema(categoricalLabel), regressionTables)
            .setNormalizationMethod(normalizationMethod)
            .setMathContext(ModelUtil.simplifyMathContext(mathContext))
            .setOutput(hasProbabilityDistribution ? ModelUtil.createProbabilityOutput(mathContext, categoricalLabel) : null);

    List<Model> segmentationModels = new ArrayList<>(models);
    segmentationModels.add(regressionModel);

    return createModelChain(segmentationModels, schema);
}
Example 8
Source File: LinearModelUtil.java    From jpmml-sparkml with GNU Affero General Public License v3.0 3 votes vote down vote up 
static
public <C extends ModelConverter<?> & HasRegressionTableOptions> Model createSoftmaxClassification(C converter, Matrix coefficients, Vector intercepts, Schema schema){
	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

	MatrixUtil.checkRows(categoricalLabel.size(), coefficients);

	List<RegressionTable> regressionTables = new ArrayList<>();

	for(int i = 0; i < categoricalLabel.size(); i++){
		Object targetCategory = categoricalLabel.getValue(i);

		List<Feature> features = new ArrayList<>(schema.getFeatures());
		List<Double> featureCoefficients = new ArrayList<>(MatrixUtil.getRow(coefficients, i));

		RegressionTableUtil.simplify(converter, targetCategory, features, featureCoefficients);

		double intercept = intercepts.apply(i);

		RegressionTable regressionTable = RegressionModelUtil.createRegressionTable(features, featureCoefficients, intercept)
			.setTargetCategory(targetCategory);

		regressionTables.add(regressionTable);
	}

	RegressionModel regressionModel = new RegressionModel(MiningFunction.CLASSIFICATION, ModelUtil.createMiningSchema(categoricalLabel), regressionTables)
		.setNormalizationMethod(RegressionModel.NormalizationMethod.SOFTMAX);

	return regressionModel;
}
Example 9
Source File: ClassificationModelConverter.java    From jpmml-sparkml with GNU Affero General Public License v3.0 2 votes vote down vote up 
@Override
public List<OutputField> registerOutputFields(Label label, Model pmmlModel, SparkMLEncoder encoder){
	T model = getTransformer();

	CategoricalLabel categoricalLabel = (CategoricalLabel)label;

	List<Integer> categories = LabelUtil.createTargetCategories(categoricalLabel.size());

	String predictionCol = model.getPredictionCol();

	Boolean keepPredictionCol = (Boolean)getOption(HasPredictionModelOptions.OPTION_KEEP_PREDICTIONCOL, Boolean.TRUE);

	OutputField pmmlPredictedOutputField = ModelUtil.createPredictedField(FieldName.create("pmml(" + predictionCol + ")"), OpType.CATEGORICAL, categoricalLabel.getDataType())
		.setFinalResult(false);

	DerivedOutputField pmmlPredictedField = encoder.createDerivedField(pmmlModel, pmmlPredictedOutputField, keepPredictionCol);

	MapValues mapValues = PMMLUtil.createMapValues(pmmlPredictedField.getName(), categoricalLabel.getValues(), categories)
		.setDataType(DataType.DOUBLE);

	OutputField predictedOutputField = new OutputField(FieldName.create(predictionCol), OpType.CONTINUOUS, DataType.DOUBLE)
		.setResultFeature(ResultFeature.TRANSFORMED_VALUE)
		.setExpression(mapValues);

	DerivedOutputField predictedField = encoder.createDerivedField(pmmlModel, predictedOutputField, keepPredictionCol);

	encoder.putOnlyFeature(predictionCol, new IndexFeature(encoder, predictedField, categories));

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

	if(model instanceof HasProbabilityCol){
		HasProbabilityCol hasProbabilityCol = (HasProbabilityCol)model;

		String probabilityCol = hasProbabilityCol.getProbabilityCol();

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

		for(int i = 0; i < categoricalLabel.size(); i++){
			Object value = categoricalLabel.getValue(i);

			OutputField probabilityField = ModelUtil.createProbabilityField(FieldName.create(probabilityCol + "(" + value + ")"), DataType.DOUBLE, value);

			result.add(probabilityField);

			features.add(new ContinuousFeature(encoder, probabilityField));
		}

		// XXX
		encoder.putFeatures(probabilityCol, features);
	}

	return result;
}
Example 10
Source File: LinearClassifier.java    From jpmml-sklearn with GNU Affero General Public License v3.0 2 votes vote down vote up 
@Override
public Model encodeModel(Schema schema){
	int[] shape = getCoefShape();

	int numberOfClasses = shape[0];
	int numberOfFeatures = shape[1];

	boolean hasProbabilityDistribution = hasProbabilityDistribution();

	List<? extends Number> coef = getCoef();
	List<? extends Number> intercept = getIntercept();

	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

	List<? extends Feature> features = schema.getFeatures();

	if(numberOfClasses == 1){
		SchemaUtil.checkSize(2, categoricalLabel);

		return RegressionModelUtil.createBinaryLogisticClassification(features, CMatrixUtil.getRow(coef, numberOfClasses, numberOfFeatures, 0), intercept.get(0), RegressionModel.NormalizationMethod.LOGIT, hasProbabilityDistribution, schema);
	} else

	if(numberOfClasses >= 3){
		SchemaUtil.checkSize(numberOfClasses, categoricalLabel);

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

		List<RegressionModel> regressionModels = new ArrayList<>();

		for(int i = 0, rows = categoricalLabel.size(); i < rows; i++){
			RegressionModel regressionModel = RegressionModelUtil.createRegression(features, CMatrixUtil.getRow(coef, numberOfClasses, numberOfFeatures, i), intercept.get(i), RegressionModel.NormalizationMethod.LOGIT, segmentSchema)
				.setOutput(ModelUtil.createPredictedOutput(FieldName.create("decisionFunction(" + categoricalLabel.getValue(i) + ")"), OpType.CONTINUOUS, DataType.DOUBLE));

			regressionModels.add(regressionModel);
		}

		return MiningModelUtil.createClassification(regressionModels, RegressionModel.NormalizationMethod.SIMPLEMAX, hasProbabilityDistribution, schema);
	} else

	{
		throw new IllegalArgumentException();
	}
}