private static org.apache.spark.mllib.tree.model.Node nextNode( double[] featureVector, org.apache.spark.mllib.tree.model.Node node, Split split, int featureIndex) { double featureValue = featureVector[featureIndex]; if (split.featureType().equals(FeatureType.Continuous())) { if (featureValue <= split.threshold()) { return node.leftNode().get(); } else { return node.rightNode().get(); } } else { if (split.categories().contains(featureValue)) { return node.leftNode().get(); } else { return node.rightNode().get(); } } }
private Predicate buildPredicate(Split split, CategoricalValueEncodings categoricalValueEncodings) { if (split == null) { // Left child always applies, but is evaluated second return new True(); } int featureIndex = inputSchema.predictorToFeatureIndex(split.feature()); FieldName fieldName = FieldName.create(inputSchema.getFeatureNames().get(featureIndex)); if (split.featureType().equals(FeatureType.Categorical())) { // Note that categories in MLlib model select the *left* child but the // convention here will be that the predicate selects the *right* child // So the predicate will evaluate "not in" this set // More ugly casting @SuppressWarnings("unchecked") Collection<Double> javaCategories = (Collection<Double>) (Collection<?>) JavaConversions.seqAsJavaList(split.categories()); Set<Integer> negativeEncodings = javaCategories.stream().map(Double::intValue).collect(Collectors.toSet()); Map<Integer,String> encodingToValue = categoricalValueEncodings.getEncodingValueMap(featureIndex); List<String> negativeValues = negativeEncodings.stream().map(encodingToValue::get).collect(Collectors.toList()); String joinedValues = TextUtils.joinPMMLDelimited(negativeValues); return new SimpleSetPredicate(fieldName, SimpleSetPredicate.BooleanOperator.IS_NOT_IN, new Array(Array.Type.STRING, joinedValues)); } else { // For MLlib, left means <= threshold, so right means > return new SimplePredicate(fieldName, SimplePredicate.Operator.GREATER_THAN) .setValue(Double.toString(split.threshold())); } }