Github user myui commented on a diff in the pull request:
https://github.com/apache/incubator-hivemall/pull/52#discussion_r103403903
--- Diff: core/src/main/java/hivemall/evaluation/AUCUDAF.java ---
@@ -49,35 +51,264 @@
@SuppressWarnings("deprecation")
@Description(
name = "auc",
- value = "_FUNC_(array rankItems, array correctItems [, const int
recommendSize = rankItems.size])"
+ value = "_FUNC_(array rankItems | double score, array correctItems
| int label "
+ + "[, const int recommendSize = rankItems.size ])"
+ " - Returns AUC")
public final class AUCUDAF extends AbstractGenericUDAFResolver {
- // prevent instantiation
- private AUCUDAF() {}
-
@Override
public GenericUDAFEvaluator getEvaluator(@Nonnull TypeInfo[] typeInfo)
throws SemanticException {
if (typeInfo.length != 2 && typeInfo.length != 3) {
throw new UDFArgumentTypeException(typeInfo.length - 1,
"_FUNC_ takes two or three arguments");
}
- ListTypeInfo arg1type = HiveUtils.asListTypeInfo(typeInfo[0]);
- if
(!HiveUtils.isPrimitiveTypeInfo(arg1type.getListElementTypeInfo())) {
- throw new UDFArgumentTypeException(0,
- "The first argument `array rankItems` is invalid form: " +
typeInfo[0]);
+ if (HiveUtils.isNumberTypeInfo(typeInfo[0]) &&
HiveUtils.isIntegerTypeInfo(typeInfo[1])) {
+ return new ClassificationEvaluator();
+ } else {
+ ListTypeInfo arg1type = HiveUtils.asListTypeInfo(typeInfo[0]);
+ if
(!HiveUtils.isPrimitiveTypeInfo(arg1type.getListElementTypeInfo())) {
+ throw new UDFArgumentTypeException(0,
+ "The first argument `array rankItems` is invalid form:
" + typeInfo[0]);
+ }
+
+ ListTypeInfo arg2type = HiveUtils.asListTypeInfo(typeInfo[1]);
+ if
(!HiveUtils.isPrimitiveTypeInfo(arg2type.getListElementTypeInfo())) {
+ throw new UDFArgumentTypeException(1,
+ "The second argument `array correctItems` is invalid
form: " + typeInfo[1]);
+ }
+
+ return new RankingEvaluator();
+ }
+ }
+
+ public static class ClassificationEvaluator extends
GenericUDAFEvaluator {
+
+ private PrimitiveObjectInspector scoreOI;
+ private PrimitiveObjectInspector labelOI;
+
+ private StructObjectInspector internalMergeOI;
+ private StructField aField;
+ private StructField scorePrevField;
+ private StructField fpField;
+ private StructField tpField;
+ private StructField fpPrevField;
+ private StructField tpPrevField;
+
+ public ClassificationEvaluator() {}
+
+ @Override
+ public ObjectInspector init(Mode mode, ObjectInspector[]
parameters) throws HiveException {
+ assert (parameters.length == 2 || parameters.length == 3) :
parameters.length;
+ super.init(mode, parameters);
+
+ // initialize input
+ if (mode == Mode.PARTIAL1 || mode == Mode.COMPLETE) {// from
original data
+ this.scoreOI =
HiveUtils.asDoubleCompatibleOI(parameters[0]);
+ this.labelOI = HiveUtils.asIntegerOI(parameters[1]);
+ } else {// from partial aggregation
+ StructObjectInspector soi = (StructObjectInspector)
parameters[0];
+ this.internalMergeOI = soi;
+ this.aField = soi.getStructFieldRef("a");
+ this.scorePrevField = soi.getStructFieldRef("scorePrev");
+ this.fpField = soi.getStructFieldRef("fp");
+ this.tpField = soi.getStructFieldRef("tp");
+ this.fpPrevField = soi.getStructFieldRef("fpPrev");
+ this.tpPrevField = soi.getStructFieldRef("tpPrev");
+ }
+
+ // initialize output
+ final ObjectInspector outputOI;
+ if (mode == Mode.PARTIAL1 || mode == Mode.PARTIAL2) {//
terminatePartial
+ outputOI = internalMergeOI();
+ } else {// terminate
+ outputOI =
PrimitiveObjectInspectorFactory.writableDoubleObjectInspector;
+ }
+ return outputOI;
+ }
+
+ private static StructObjectInspector internalMergeOI() {
+ ArrayList<String> fieldNames = new ArrayList<String>();
+ ArrayList<ObjectInspector> fieldOIs = new
ArrayList<ObjectInspector>();
+
+ fieldNames.add("a");
+
fieldOIs.add(PrimitiveObjectInspectorFactory.writableDoubleObjectInspector);
+ fieldNames.add("scorePrev");
+
fieldOIs.add(PrimitiveObjectInspectorFactory.writableDoubleObjectInspector);
+ fieldNames.add("fp");
+
fieldOIs.add(PrimitiveObjectInspectorFactory.writableLongObjectInspector);
+ fieldNames.add("tp");
+
fieldOIs.add(PrimitiveObjectInspectorFactory.writableLongObjectInspector);
+ fieldNames.add("fpPrev");
+
fieldOIs.add(PrimitiveObjectInspectorFactory.writableLongObjectInspector);
+ fieldNames.add("tpPrev");
+
fieldOIs.add(PrimitiveObjectInspectorFactory.writableLongObjectInspector);
+
+ return
ObjectInspectorFactory.getStandardStructObjectInspector(fieldNames, fieldOIs);
+ }
+
+ @Override
+ public AggregationBuffer getNewAggregationBuffer() throws
HiveException {
+ AggregationBuffer myAggr = new
ClassificationAUCAggregationBuffer();
+ reset(myAggr);
+ return myAggr;
+ }
+
+ @Override
+ public void reset(AggregationBuffer agg) throws HiveException {
+ ClassificationAUCAggregationBuffer myAggr =
(ClassificationAUCAggregationBuffer) agg;
+ myAggr.reset();
+ }
+
+ @Override
+ public void iterate(AggregationBuffer agg, Object[] parameters)
throws HiveException {
+ ClassificationAUCAggregationBuffer myAggr =
(ClassificationAUCAggregationBuffer) agg;
+
+ if (parameters[0] == null) {
+ return;
+ }
+ if (parameters[1] == null) {
+ return;
+ }
+
+ double score = HiveUtils.getDouble(parameters[0], scoreOI);
--- End diff --
if(score < 0.0d || score > 1.0d) {
throw new UDFArgumentException("score value MUST be in range [0,1]: " +
score);
}
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
