bantmen commented on a change in pull request #16618: [SPARK-14409][ML][WIP] Add RankingEvaluator URL: https://github.com/apache/spark/pull/16618#discussion_r331115975
########## File path: mllib/src/main/scala/org/apache/spark/ml/evaluation/RankingMetrics.scala ########## @@ -0,0 +1,202 @@ +/* + * 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.ml.evaluation + +import org.apache.spark.annotation.Since +import org.apache.spark.internal.Logging +import org.apache.spark.sql.{Column, DataFrame} +import org.apache.spark.sql.functions.{mean, sum} +import org.apache.spark.sql.functions.udf +import org.apache.spark.sql.types.DoubleType + +@Since("2.2.0") +class RankingMetrics( + predictionAndObservations: DataFrame, predictionCol: String, labelCol: String) + extends Logging with Serializable { + + /** + * Compute the Mean Percentile Rank (MPR) of all the queries. + * + * See the following paper for detail ("Expected percentile rank" in the paper): + * Hu, Y., Y. Koren, and C. Volinsky. “Collaborative Filtering for Implicit Feedback Datasets.” + * In 2008 Eighth IEEE International Conference on Data Mining, 263–72, 2008. + * doi:10.1109/ICDM.2008.22. + * + * @return the mean percentile rank + */ + lazy val meanPercentileRank: Double = { + + def rank = udf((predicted: Seq[Any], actual: Any) => { + val l_i = predicted.indexOf(actual) + + if (l_i == -1) { + 1 + } else { + l_i.toDouble / predicted.size + } + }, DoubleType) + + val R_prime = predictionAndObservations.count() Review comment: Shouldn't this be a sum instead of count? (I know this is old/closed but other people might be referring to this code) ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
