From e0447111ec30ee7c1f760dfcd496f0315aacbe64 Mon Sep 17 00:00:00 2001
From: Luiz Eduardo Amaral <luizamaral306@gmail.com>
Date: Tue, 12 Oct 2021 16:09:34 -0300
Subject: [PATCH 1/3] [DOC] Remove mae-mse from docstrings

---
 sklearn/ensemble/_forest.py | 3 +--
 sklearn/tree/_classes.py    | 7 +++----
 2 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/sklearn/ensemble/_forest.py b/sklearn/ensemble/_forest.py
index 31ecfa8ee867f..81852677a2e72 100644
--- a/sklearn/ensemble/_forest.py
+++ b/sklearn/ensemble/_forest.py
@@ -2061,8 +2061,7 @@ class ExtraTreesRegressor(ForestRegressor):
            The default value of ``n_estimators`` changed from 10 to 100
            in 0.22.
 
-    criterion : {"squared_error", "mse", "absolute_error", "mae"}, \
-            default="squared_error"
+    criterion : {"squared_error", "absolute_error"}, 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"
diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index 818563f0acf59..c59fcda975a9d 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -1038,8 +1038,8 @@ class DecisionTreeRegressor(RegressorMixin, BaseDecisionTree):
 
     Parameters
     ----------
-    criterion : {"squared_error", "mse", "friedman_mse", "absolute_error", \
-            "mae", "poisson"}, default="squared_error"
+    criterion : {"squared_error", "friedman_mse", "absolute_error", \
+            "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 minimizes the L2
@@ -1630,8 +1630,7 @@ class ExtraTreeRegressor(DecisionTreeRegressor):
 
     Parameters
     ----------
-    criterion : {"squared_error", "mse", "friedman_mse", "mae"}, \
-            default="squared_error"
+    criterion : {"squared_error", "friedman_mse"}, 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 "mae" for the

From 3f52b5cc52c2cb2a8ce1bdfed04a6a7d0a01803e Mon Sep 17 00:00:00 2001
From: Luiz Eduardo Amaral <luizamaral306@gmail.com>
Date: Tue, 12 Oct 2021 16:48:48 -0300
Subject: [PATCH 2/3] [DOC] Remove ls lad least_squares from docstrings

---
 sklearn/ensemble/_gb.py                                     | 4 ++--
 .../ensemble/_hist_gradient_boosting/gradient_boosting.py   | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/sklearn/ensemble/_gb.py b/sklearn/ensemble/_gb.py
index 7b66324d1f08b..783105f4f35c8 100644
--- a/sklearn/ensemble/_gb.py
+++ b/sklearn/ensemble/_gb.py
@@ -1474,8 +1474,8 @@ class GradientBoostingRegressor(RegressorMixin, BaseGradientBoosting):
 
     Parameters
     ----------
-    loss : {'squared_error', 'ls', 'absolute_error', 'lad', 'huber', \
-            'quantile'}, default='squared_error'
+    loss : {'squared_error', 'absolute_error', 'huber', 'quantile'},
+            default='squared_error'
         Loss function to be optimized. 'squared_error' refers to the squared
         error for regression. 'absolute_error' refers to the absolute error of
         regression and is a robust loss function. 'huber' is a
diff --git a/sklearn/ensemble/_hist_gradient_boosting/gradient_boosting.py b/sklearn/ensemble/_hist_gradient_boosting/gradient_boosting.py
index d2a2b1ddde9e4..097ceeeadc588 100644
--- a/sklearn/ensemble/_hist_gradient_boosting/gradient_boosting.py
+++ b/sklearn/ensemble/_hist_gradient_boosting/gradient_boosting.py
@@ -1021,10 +1021,10 @@ class HistGradientBoostingRegressor(RegressorMixin, BaseHistGradientBoosting):
 
     Parameters
     ----------
-    loss : {'squared_error', 'least_squares', 'absolute_error', \
-            'least_absolute_deviation', 'poisson'}, default='squared_error'
+    loss : {'squared_error', 'absolute_error', 'poisson'}, \
+            default='squared_error'
         The loss function to use in the boosting process. Note that the
-        "least squares" and "poisson" losses actually implement
+        "squared error" and "poisson" losses actually implement
         "half least squares loss" and "half poisson deviance" to simplify the
         computation of the gradient. Furthermore, "poisson" loss internally
         uses a log-link and requires ``y >= 0``.

From b2aad98b0119e2d9f667ec684020cb32e4819c6d Mon Sep 17 00:00:00 2001
From: Luiz Eduardo Amaral <luizamaral306@gmail.com>
Date: Tue, 12 Oct 2021 17:51:11 -0300
Subject: [PATCH 3/3] [DOC] fix missing end slash

---
 sklearn/ensemble/_gb.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sklearn/ensemble/_gb.py b/sklearn/ensemble/_gb.py
index 783105f4f35c8..34f651830fc0e 100644
--- a/sklearn/ensemble/_gb.py
+++ b/sklearn/ensemble/_gb.py
@@ -1474,7 +1474,7 @@ class GradientBoostingRegressor(RegressorMixin, BaseGradientBoosting):
 
     Parameters
     ----------
-    loss : {'squared_error', 'absolute_error', 'huber', 'quantile'},
+    loss : {'squared_error', 'absolute_error', 'huber', 'quantile'}, \
             default='squared_error'
         Loss function to be optimized. 'squared_error' refers to the squared
         error for regression. 'absolute_error' refers to the absolute error of