Merge branch 'main' into 1.2.X

Author: reidjohnson

examples/plot_quantile_conformalized.py

@@ -1,9 +1,9 @@
 """
-========================================================================
-Quantile regression forests for conformalized quantile regression (CQR)
-========================================================================
+=================================================================
+Quantile regression forests for conformalized quantile regression
+=================================================================
 
-An example that demonstrates the use of a quantile regression forest to
+An example that demonstrates the use of a quantile regression forest (QRF) to
 construct reliable prediction intervals using conformalized quantile
 regression (CQR). CQR offers prediction intervals that attain valid coverage,
 while QRF may require additional calibration for reliable interval estimates.

quantile_forest/_quantile_forest.py

@@ -772,13 +772,16 @@ class RandomForestQuantileRegressor(BaseForestQuantileRegressor):
         predict. Each quantile must be strictly between 0 and 1. If "mean",
         the model predicts the mean.
 
-    criterion : {"squared_error", "absolute_error", "poisson"}, \
+    criterion : {"squared_error", "absolute_error", "friedman_mse", "poisson"}, \
             default="squared_error"
         The function to measure the quality of a split. Supported criteria
         are "squared_error" for the mean squared error, which is equal to
-        variance reduction as feature selection criterion, "absolute_error"
-        for the mean absolute error, and "poisson" which uses reduction in
-        Poisson deviance to find splits.
+        variance reduction as feature selection criterion and minimizes the L2
+        loss using the mean of each terminal node, "friedman_mse", which uses
+        mean squared error with Friedman's improvement score for potential
+        splits, "absolute_error" for the mean absolute error, which minimizes
+        the L1 loss using the median of each terminal node, and "poisson" which
+        uses reduction in Poisson deviance to find splits.
         Training using "absolute_error" is significantly slower
         than when using "squared_error".
 
@@ -866,9 +869,11 @@ class RandomForestQuantileRegressor(BaseForestQuantileRegressor):
         Whether bootstrap samples are used when building trees. If False, the
         whole dataset is used to build each tree.
 
-    oob_score : bool, default=False
+    oob_score : bool or callable, default=False
         Whether to use out-of-bag samples to estimate the generalization score.
-        Only available if bootstrap=True.
+        By default, :func:`~sklearn.metrics.r2_score` is used.
+        Provide a callable with signature `metric(y_true, y_pred)` to use a
+        custom metric. Only available if `bootstrap=True`.
 
     n_jobs : int, default=None
         The number of jobs to run in parallel. :meth:`fit`, :meth:`predict`,
@@ -901,12 +906,12 @@ class RandomForestQuantileRegressor(BaseForestQuantileRegressor):
 
         - If None (default), then draw `X.shape[0]` samples.
         - If int, then draw `max_samples` samples.
-        - If float, then draw `max_samples * X.shape[0]` samples. Thus,
-          `max_samples` should be in the interval `(0.0, 1.0]`.
+        - If float, then draw `max(round(n_samples * max_samples), 1)` samples.
+          Thus, `max_samples` should be in the interval `(0.0, 1.0]`.
 
     Attributes
     ----------
-    base_estimator_ : DecisionTreeRegressor
+    estimator_ : DecisionTreeRegressor
         The child estimator template used to create the collection of fitted
         sub-estimators.
 
@@ -1054,11 +1059,18 @@ class ExtraTreesQuantileRegressor(BaseForestQuantileRegressor):
         predict. Each quantile must be strictly between 0 and 1. If "mean",
         the model predicts the mean.
 
-    criterion : {"squared_error", "absolute_error"}, default="squared_error"
+    criterion : {"squared_error", "absolute_error", "friedman_mse", "poisson"}, \
+            default="squared_error"
         The function to measure the quality of a split. Supported criteria
         are "squared_error" for the mean squared error, which is equal to
-        variance reduction as feature selection criterion, and "absolute_error"
-        for the mean absolute error.
+        variance reduction as feature selection criterion and minimizes the L2
+        loss using the mean of each terminal node, "friedman_mse", which uses
+        mean squared error with Friedman's improvement score for potential
+        splits, "absolute_error" for the mean absolute error, which minimizes
+        the L1 loss using the median of each terminal node, and "poisson" which
+        uses reduction in Poisson deviance to find splits.
+        Training using "absolute_error" is significantly slower
+        than when using "squared_error".
 
     max_depth : int, default=None
         The maximum depth of the tree. If None, then nodes are expanded until
@@ -1144,9 +1156,11 @@ class ExtraTreesQuantileRegressor(BaseForestQuantileRegressor):
         Whether bootstrap samples are used when building trees. If False, the
         whole dataset is used to build each tree.
 
-    oob_score : bool, default=False
+    oob_score : bool or callable, default=False
         Whether to use out-of-bag samples to estimate the generalization score.
-        Only available if bootstrap=True.
+        By default, :func:`~sklearn.metrics.accuracy_score` is used.
+        Provide a callable with signature `metric(y_true, y_pred)` to use a
+        custom metric. Only available if `bootstrap=True`.
 
     n_jobs : int, default=None
         The number of jobs to run in parallel. :meth:`fit`, :meth:`predict`,
@@ -1187,18 +1201,18 @@ class ExtraTreesQuantileRegressor(BaseForestQuantileRegressor):
 
     Attributes
     ----------
-    base_estimator_ : ExtraTreeQuantileRegressor
+    estimator_ : ExtraTreeRegressor
         The child estimator template used to create the collection of fitted
         sub-estimators.
 
-    estimators_ : list of ForestRegressor
+    estimators_ : list of DecisionTreeRegressor
         The collection of fitted sub-estimators.
 
     feature_importances_ : ndarray of shape (n_features,)
         The impurity-based feature importances.
         The higher, the more important the feature.
         The importance of a feature is computed as the (normalized)
-        total reduction of the criterion brought by that feature.  It is also
+        total reduction of the criterion brought by that feature. It is also
         known as the Gini importance.
 
         Warning: impurity-based feature importances can be misleading for