Search in sources :

Example 1 with Field

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

the class ModelConverter method encodeSchema.

public Schema encodeSchema(SparkMLEncoder encoder) {
    T model = getTransformer();
    Label label = null;
    if (model instanceof HasLabelCol) {
        HasLabelCol hasLabelCol = (HasLabelCol) model;
        String labelCol = hasLabelCol.getLabelCol();
        Feature feature = encoder.getOnlyFeature(labelCol);
        MiningFunction miningFunction = getMiningFunction();
        switch(miningFunction) {
            case CLASSIFICATION:
                {
                    if (feature instanceof CategoricalFeature) {
                        CategoricalFeature categoricalFeature = (CategoricalFeature) feature;
                        DataField dataField = encoder.getDataField(categoricalFeature.getName());
                        label = new CategoricalLabel(dataField);
                    } else if (feature instanceof ContinuousFeature) {
                        ContinuousFeature continuousFeature = (ContinuousFeature) feature;
                        int numClasses = 2;
                        if (model instanceof ClassificationModel) {
                            ClassificationModel<?, ?> classificationModel = (ClassificationModel<?, ?>) model;
                            numClasses = classificationModel.numClasses();
                        }
                        List<String> categories = new ArrayList<>();
                        for (int i = 0; i < numClasses; i++) {
                            categories.add(String.valueOf(i));
                        }
                        Field<?> field = encoder.toCategorical(continuousFeature.getName(), categories);
                        encoder.putOnlyFeature(labelCol, new CategoricalFeature(encoder, field, categories));
                        label = new CategoricalLabel(field.getName(), field.getDataType(), categories);
                    } else {
                        throw new IllegalArgumentException("Expected a categorical or categorical-like continuous feature, got " + feature);
                    }
                }
                break;
            case REGRESSION:
                {
                    Field<?> field = encoder.toContinuous(feature.getName());
                    field.setDataType(DataType.DOUBLE);
                    label = new ContinuousLabel(field.getName(), field.getDataType());
                }
                break;
            default:
                throw new IllegalArgumentException("Mining function " + miningFunction + " is not supported");
        }
    }
    if (model instanceof ClassificationModel) {
        ClassificationModel<?, ?> classificationModel = (ClassificationModel<?, ?>) model;
        CategoricalLabel categoricalLabel = (CategoricalLabel) label;
        int numClasses = classificationModel.numClasses();
        if (numClasses != categoricalLabel.size()) {
            throw new IllegalArgumentException("Expected " + numClasses + " target categories, got " + categoricalLabel.size() + " target categories");
        }
    }
    String featuresCol = model.getFeaturesCol();
    List<Feature> features = encoder.getFeatures(featuresCol);
    if (model instanceof PredictionModel) {
        PredictionModel<?, ?> predictionModel = (PredictionModel<?, ?>) model;
        int numFeatures = predictionModel.numFeatures();
        if (numFeatures != -1 && features.size() != numFeatures) {
            throw new IllegalArgumentException("Expected " + numFeatures + " features, got " + features.size() + " features");
        }
    }
    Schema result = new Schema(label, features);
    return result;
}
Also used : Schema(org.jpmml.converter.Schema) ContinuousLabel(org.jpmml.converter.ContinuousLabel) CategoricalLabel(org.jpmml.converter.CategoricalLabel) Label(org.jpmml.converter.Label) ArrayList(java.util.ArrayList) PredictionModel(org.apache.spark.ml.PredictionModel) ContinuousFeature(org.jpmml.converter.ContinuousFeature) Feature(org.jpmml.converter.Feature) CategoricalFeature(org.jpmml.converter.CategoricalFeature) CategoricalFeature(org.jpmml.converter.CategoricalFeature) HasLabelCol(org.apache.spark.ml.param.shared.HasLabelCol) OutputField(org.dmg.pmml.OutputField) Field(org.dmg.pmml.Field) DataField(org.dmg.pmml.DataField) ContinuousFeature(org.jpmml.converter.ContinuousFeature) DataField(org.dmg.pmml.DataField) CategoricalLabel(org.jpmml.converter.CategoricalLabel) MiningFunction(org.dmg.pmml.MiningFunction) ClassificationModel(org.apache.spark.ml.classification.ClassificationModel) ContinuousLabel(org.jpmml.converter.ContinuousLabel)

Aggregations

ArrayList (java.util.ArrayList)1 PredictionModel (org.apache.spark.ml.PredictionModel)1 ClassificationModel (org.apache.spark.ml.classification.ClassificationModel)1 HasLabelCol (org.apache.spark.ml.param.shared.HasLabelCol)1 DataField (org.dmg.pmml.DataField)1 Field (org.dmg.pmml.Field)1 MiningFunction (org.dmg.pmml.MiningFunction)1 OutputField (org.dmg.pmml.OutputField)1 CategoricalFeature (org.jpmml.converter.CategoricalFeature)1 CategoricalLabel (org.jpmml.converter.CategoricalLabel)1 ContinuousFeature (org.jpmml.converter.ContinuousFeature)1 ContinuousLabel (org.jpmml.converter.ContinuousLabel)1 Feature (org.jpmml.converter.Feature)1 Label (org.jpmml.converter.Label)1 Schema (org.jpmml.converter.Schema)1