ENH Add RMSE (root-mean-square error) metric and scorer (#13467)

doc/modules/model_evaluation.rst

@@ -88,6 +88,7 @@ Scoring                           Function
 'max_error'                       :func:`metrics.max_error`
 'neg_mean_absolute_error'         :func:`metrics.mean_absolute_error`
 'neg_mean_squared_error'          :func:`metrics.mean_squared_error`
+'neg_root_mean_squared_error'     :func:`metrics.mean_squared_error`
 'neg_mean_squared_log_error'      :func:`metrics.mean_squared_log_error`
 'neg_median_absolute_error'       :func:`metrics.median_absolute_error`
 'r2'                              :func:`metrics.r2_score`

doc/whats_new/v0.22.rst

@@ -216,6 +216,10 @@ Changelog
   updated to accept the zero and `float('+inf')` value.
   :pr:`13231` by :user:`Dong-hee Na <corona10>`.
 
+- |Enhancement| Added parameter ``squared`` in :func:`metrics.mean_squared_error`
+  to return root mean squared error.
+  :pr:`13467` by :user:`Urvang Patel <urvang96>`.
+
 :mod:`sklearn.model_selection`
 ...............................
 

sklearn/metrics/regression.py

@@ -191,7 +191,7 @@ def mean_absolute_error(y_true, y_pred,
 
 def mean_squared_error(y_true, y_pred,
                        sample_weight=None,
-                       multioutput='uniform_average'):
+                       multioutput='uniform_average', squared=True):
     """Mean squared error regression loss
 
     Read more in the :ref:`User Guide <mean_squared_error>`.
@@ -218,6 +218,9 @@ def mean_squared_error(y_true, y_pred,
         'uniform_average' :
             Errors of all outputs are averaged with uniform weight.
 
+    squared : boolean value, optional (default = True)
+        If True returns MSE value, if False returns RMSE value.
+
     Returns
     -------
     loss : float or ndarray of floats
@@ -231,6 +234,10 @@ def mean_squared_error(y_true, y_pred,
     >>> y_pred = [2.5, 0.0, 2, 8]
     >>> mean_squared_error(y_true, y_pred)
     0.375
+    >>> y_true = [3, -0.5, 2, 7]
+    >>> y_pred = [2.5, 0.0, 2, 8]
+    >>> mean_squared_error(y_true, y_pred, squared=False)
+    0.612...
     >>> y_true = [[0.5, 1],[-1, 1],[7, -6]]
     >>> y_pred = [[0, 2],[-1, 2],[8, -5]]
     >>> mean_squared_error(y_true, y_pred)
@@ -253,7 +260,8 @@ def mean_squared_error(y_true, y_pred,
             # pass None as weights to np.average: uniform mean
             multioutput = None
 
-    return np.average(output_errors, weights=multioutput)
+    mse = np.average(output_errors, weights=multioutput)
+    return mse if squared else np.sqrt(mse)
 
 
 def mean_squared_log_error(y_true, y_pred,

sklearn/metrics/scorer.py

@@ -495,6 +495,9 @@ def make_scorer(score_func, greater_is_better=True, needs_proba=False,
                                              greater_is_better=False)
 neg_median_absolute_error_scorer = make_scorer(median_absolute_error,
                                                greater_is_better=False)
+neg_root_mean_squared_error_scorer = make_scorer(mean_squared_error,
+                                                 greater_is_better=False,
+                                                 squared=False)
 neg_mean_poisson_deviance_scorer = make_scorer(
     mean_tweedie_deviance, p=1., greater_is_better=False
 )
@@ -549,6 +552,7 @@ def make_scorer(score_func, greater_is_better=True, needs_proba=False,
                neg_mean_absolute_error=neg_mean_absolute_error_scorer,
                neg_mean_squared_error=neg_mean_squared_error_scorer,
                neg_mean_squared_log_error=neg_mean_squared_log_error_scorer,
+               neg_root_mean_squared_error=neg_root_mean_squared_error_scorer,
                neg_mean_poisson_deviance=neg_mean_poisson_deviance_scorer,
                neg_mean_gamma_deviance=neg_mean_gamma_deviance_scorer,
                accuracy=accuracy_scorer, roc_auc=roc_auc_scorer,

sklearn/metrics/tests/test_regression.py

@@ -64,6 +64,9 @@ def test_multioutput_regression():
     error = mean_squared_error(y_true, y_pred)
     assert_almost_equal(error, (1. / 3 + 2. / 3 + 2. / 3) / 4.)
 
+    error = mean_squared_error(y_true, y_pred, squared=False)
+    assert_almost_equal(error, 0.645, decimal=2)
+
     error = mean_squared_log_error(y_true, y_pred)
     assert_almost_equal(error, 0.200, decimal=2)
 
@@ -80,6 +83,7 @@ def test_multioutput_regression():
 
 def test_regression_metrics_at_limits():
     assert_almost_equal(mean_squared_error([0.], [0.]), 0.00, 2)
+    assert_almost_equal(mean_squared_error([0.], [0.], squared=False), 0.00, 2)
     assert_almost_equal(mean_squared_log_error([0.], [0.]), 0.00, 2)
     assert_almost_equal(mean_absolute_error([0.], [0.]), 0.00, 2)
     assert_almost_equal(median_absolute_error([0.], [0.]), 0.00, 2)
@@ -231,11 +235,14 @@ def test_regression_custom_weights():
     y_pred = [[1, 1], [2, -1], [5, 4], [5, 6.5]]
 
     msew = mean_squared_error(y_true, y_pred, multioutput=[0.4, 0.6])
+    rmsew = mean_squared_error(y_true, y_pred, multioutput=[0.4, 0.6],
+                               squared=False)
     maew = mean_absolute_error(y_true, y_pred, multioutput=[0.4, 0.6])
     rw = r2_score(y_true, y_pred, multioutput=[0.4, 0.6])
     evsw = explained_variance_score(y_true, y_pred, multioutput=[0.4, 0.6])
 
     assert_almost_equal(msew, 0.39, decimal=2)
+    assert_almost_equal(rmsew, 0.62, decimal=2)
     assert_almost_equal(maew, 0.475, decimal=3)
     assert_almost_equal(rw, 0.94, decimal=2)
     assert_almost_equal(evsw, 0.94, decimal=2)

sklearn/metrics/tests/test_score_objects.py

@@ -41,7 +41,9 @@
 REGRESSION_SCORERS = ['explained_variance', 'r2',
                       'neg_mean_absolute_error', 'neg_mean_squared_error',
                       'neg_mean_squared_log_error',
-                      'neg_median_absolute_error', 'mean_absolute_error',
+                      'neg_median_absolute_error',
+                      'neg_root_mean_squared_error',
+                      'mean_absolute_error',
                       'mean_squared_error', 'median_absolute_error',
                       'max_error', 'neg_mean_poisson_deviance',
                       'neg_mean_gamma_deviance']