From 1712a7c7057bf6dd5da8aea1d7fbecdf96ea4b32 Mon Sep 17 00:00:00 2001 From: Yanbo Liang Date: Thu, 7 May 2015 11:18:32 -0700 Subject: [SPARK-6093] [MLLIB] Add RegressionMetrics in PySpark/MLlib https://issues.apache.org/jira/browse/SPARK-6093 Author: Yanbo Liang Closes #5941 from yanboliang/spark-6093 and squashes the following commits: 6934af3 [Yanbo Liang] change to @property aac3bc5 [Yanbo Liang] Add RegressionMetrics in PySpark/MLlib --- .../org/apache/spark/mllib/evaluation/RegressionMetrics.scala | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'mllib') diff --git a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RegressionMetrics.scala b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RegressionMetrics.scala index 693117d820..e577bf87f8 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RegressionMetrics.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RegressionMetrics.scala @@ -22,6 +22,7 @@ import org.apache.spark.rdd.RDD import org.apache.spark.Logging import org.apache.spark.mllib.linalg.Vectors import org.apache.spark.mllib.stat.{MultivariateStatisticalSummary, MultivariateOnlineSummarizer} +import org.apache.spark.sql.DataFrame /** * :: Experimental :: @@ -32,6 +33,14 @@ import org.apache.spark.mllib.stat.{MultivariateStatisticalSummary, Multivariate @Experimental class RegressionMetrics(predictionAndObservations: RDD[(Double, Double)]) extends Logging { + /** + * An auxiliary constructor taking a DataFrame. + * @param predictionAndObservations a DataFrame with two double columns: + * prediction and observation + */ + private[mllib] def this(predictionAndObservations: DataFrame) = + this(predictionAndObservations.map(r => (r.getDouble(0), r.getDouble(1)))) + /** * Use MultivariateOnlineSummarizer to calculate summary statistics of observations and errors. */ -- cgit v1.2.3