add r2adj into Python API in LinearRegressionSummary

apache · Mar 16, 2018 · 12d18b5 · 12d18b5
1 parent 918fb9b
commit 12d18b5
Show file tree

Hide file tree

Showing 2 changed files with 15 additions and 0 deletions.
diff --git a/python/pyspark/ml/regression.py b/python/pyspark/ml/regression.py
@@ -347,6 +347,20 @@ def r2(self):
         """
         return self._call_java("r2")
 
+    @property
+    @since("2.4.0")
+    def r2adj(self):
+        """
+        Returns Adjusted R^2^, the adjusted coefficient of determination.
+
+        .. seealso:: `Wikipedia coefficient of determination \
+        <https://en.wikipedia.org/wiki/Coefficient_of_determination>`
+
+        .. note:: This ignores instance weights (setting all to 1.0) from
+            `LinearRegression.weightCol`. This will change in later Spark versions.
+        """
+        return self._call_java("r2adj")
+
     @property
     @since("2.0.0")
     def residuals(self):

diff --git a/python/pyspark/ml/tests.py b/python/pyspark/ml/tests.py
@@ -1488,6 +1488,7 @@ def test_linear_regression_summary(self):
         self.assertAlmostEqual(s.meanSquaredError, 0.0)
         self.assertAlmostEqual(s.rootMeanSquaredError, 0.0)
         self.assertAlmostEqual(s.r2, 1.0, 2)
+        self.assertAlmostEqual(s.r2adj, 1.0, 2)
         self.assertTrue(isinstance(s.residuals, DataFrame))
         self.assertEqual(s.numInstances, 2)
         self.assertEqual(s.degreesOfFreedom, 1)