[SPARK-6093] [MLLIB] Add RegressionMetrics in PySpark/MLlib

https://issues.apache.org/jira/browse/SPARK-6093

Author: Yanbo Liang <ybliang8@gmail.com>

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

1 files changed, 76 insertions, 2 deletions

diff --git a/python/pyspark/mllib/evaluation.py b/python/pyspark/mllib/evaluation.py
index 16cb49cc0c..3e11df09da 100644
--- a/python/pyspark/mllib/evaluation.py
+++ b/python/pyspark/mllib/evaluation.py
@@ -27,9 +27,9 @@ class BinaryClassificationMetrics(JavaModelWrapper):
     >>> scoreAndLabels = sc.parallelize([
     ...     (0.1, 0.0), (0.1, 1.0), (0.4, 0.0), (0.6, 0.0), (0.6, 1.0), (0.6, 1.0), (0.8, 1.0)], 2)
     >>> metrics = BinaryClassificationMetrics(scoreAndLabels)
-    >>> metrics.areaUnderROC()
+    >>> metrics.areaUnderROC
     0.70...
-    >>> metrics.areaUnderPR()
+    >>> metrics.areaUnderPR
     0.83...
     >>> metrics.unpersist()
     """
@@ -47,6 +47,7 @@ class BinaryClassificationMetrics(JavaModelWrapper):
         java_model = java_class(df._jdf)
         super(BinaryClassificationMetrics, self).__init__(java_model)
 
+    @property
     def areaUnderROC(self):
         """
         Computes the area under the receiver operating characteristic
@@ -54,6 +55,7 @@ class BinaryClassificationMetrics(JavaModelWrapper):
         """
         return self.call("areaUnderROC")
 
+    @property
     def areaUnderPR(self):
         """
         Computes the area under the precision-recall curve.
@@ -67,6 +69,78 @@ class BinaryClassificationMetrics(JavaModelWrapper):
         self.call("unpersist")
 
 
+class RegressionMetrics(JavaModelWrapper):
+    """
+    Evaluator for regression.
+
+    >>> predictionAndObservations = sc.parallelize([
+    ...     (2.5, 3.0), (0.0, -0.5), (2.0, 2.0), (8.0, 7.0)])
+    >>> metrics = RegressionMetrics(predictionAndObservations)
+    >>> metrics.explainedVariance
+    0.95...
+    >>> metrics.meanAbsoluteError
+    0.5...
+    >>> metrics.meanSquaredError
+    0.37...
+    >>> metrics.rootMeanSquaredError
+    0.61...
+    >>> metrics.r2
+    0.94...
+    """
+
+    def __init__(self, predictionAndObservations):
+        """
+        :param predictionAndObservations: an RDD of (prediction, observation) pairs.
+        """
+        sc = predictionAndObservations.ctx
+        sql_ctx = SQLContext(sc)
+        df = sql_ctx.createDataFrame(predictionAndObservations, schema=StructType([
+            StructField("prediction", DoubleType(), nullable=False),
+            StructField("observation", DoubleType(), nullable=False)]))
+        java_class = sc._jvm.org.apache.spark.mllib.evaluation.RegressionMetrics
+        java_model = java_class(df._jdf)
+        super(RegressionMetrics, self).__init__(java_model)
+
+    @property
+    def explainedVariance(self):
+        """
+        Returns the explained variance regression score.
+        explainedVariance = 1 - variance(y - \hat{y}) / variance(y)
+        """
+        return self.call("explainedVariance")
+
+    @property
+    def meanAbsoluteError(self):
+        """
+        Returns the mean absolute error, which is a risk function corresponding to the
+        expected value of the absolute error loss or l1-norm loss.
+        """
+        return self.call("meanAbsoluteError")
+
+    @property
+    def meanSquaredError(self):
+        """
+        Returns the mean squared error, which is a risk function corresponding to the
+        expected value of the squared error loss or quadratic loss.
+        """
+        return self.call("meanSquaredError")
+
+    @property
+    def rootMeanSquaredError(self):
+        """
+        Returns the root mean squared error, which is defined as the square root of
+        the mean squared error.
+        """
+        return self.call("rootMeanSquaredError")
+
+    @property
+    def r2(self):
+        """
+        Returns R^2^, the coefficient of determination.
+        """
+        return self.call("r2")
+
+
 def _test():
     import doctest
     from pyspark import SparkContext