Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/1155#discussion_r14890904
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala
---
@@ -0,0 +1,182 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.mllib.evaluation
+
+import scala.collection.Map
+
+import org.apache.spark.SparkContext._
+import org.apache.spark.annotation.Experimental
+import org.apache.spark.mllib.linalg.{Matrices, Matrix}
+import org.apache.spark.rdd.RDD
+
+/**
+ * ::Experimental::
+ * Evaluator for multiclass classification.
+ *
+ * @param predictionAndLabels an RDD of (prediction, label) pairs.
+ */
+@Experimental
+class MulticlassMetrics(predictionAndLabels: RDD[(Double, Double)]) {
+
+ private lazy val labelCountByClass: Map[Double, Long] =
predictionAndLabels.values.countByValue()
+ private lazy val labelCount: Long = labelCountByClass.values.sum
+ private lazy val tpByClass: Map[Double, Int] = predictionAndLabels
+ .map { case (prediction, label) =>
+ (label, if (label == prediction) 1 else 0)
+ }.reduceByKey(_ + _)
+ .collectAsMap()
+ private lazy val fpByClass: Map[Double, Int] = predictionAndLabels
+ .map { case (prediction, label) =>
+ (prediction, if (prediction != label) 1 else 0)
+ }.reduceByKey(_ + _)
+ .collectAsMap()
+ private lazy val confusions = predictionAndLabels.map {
+ case (prediction, label) => ((prediction, label), 1)
+ }.reduceByKey(_ + _).collectAsMap()
+
+ /**
+ * Returns confusion matrix:
+ * predicted classes are in columns,
+ * they are ordered by class label ascending,
+ * as in "labels"
+ */
+ lazy val confusionMatrix: Matrix = {
+ val transposedFlatMatrix = Array.ofDim[Double](labels.size *
labels.size)
--- End diff --
Save `labels.size` to `n`? Btw, I'm not sure whether we should use `lazy
val` here because the result matrix could be 1000x1000, different from other
lazy vals used here.
---
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.
---
