DOC - Correct a few wording mistakes (skrub-data#1877)

Author: star1327p

examples/FIXME/08_join_aggregation_full.py

@@ -191,9 +191,10 @@ def get_results(model, X_test, y_test, threshold, amount, time_to_fit):
 # Low effort estimator
 # --------------------
 #
-# Next, we use the |TableVectorizer| and a |HGBC| to create a very simple baseline model
-# that uses the sparse dataset directly. Note that due to the large number of high
-# cardinality columns, we can't use an multi-dimensional encoder like the
+# Next, we use the |TableVectorizer| and an |HGBC| to create a very simple
+# baseline model that uses the sparse dataset directly.
+# Note that due to the large number of high
+# cardinality columns, we can't use a multi-dimensional encoder like the
 # |MinHashEncoder|, because the number of columns would then explode.
 #
 # Instead, we encode our categories with a |TargetEncoder|.
@@ -493,7 +494,7 @@ def get_X_y(data):
 
 # %%
 # Now that we get a sense of how the |AggJoiner| can help us, we complete this pipeline
-# with a |HGBC| and evaluate our final model.
+# with an |HGBC| and evaluate our final model.
 
 tic = time()
 agg_join_estimator = make_pipeline(

skrub/_data_ops/_estimator.py

@@ -709,7 +709,7 @@ def train_test_split(
     split_func=model_selection.train_test_split,
     **split_func_kwargs,
 ):
-    """Split an environment into a training an testing environments.
+    """Split an environment into training and testing environments.
 
     This functionality is exposed to users through the
     ``DataOp.skb.train_test_split()`` method. See the corresponding docstring for
@@ -738,7 +738,7 @@ def train_test_split(
 
 
 def iter_cv_splits(data_op, environment, *, keep_subsampling=False, cv=KFOLD_5):
-    """Yield splits of an environment into training an testing environments.
+    """Yield splits of an environment into training and testing environments.
 
     This functionality is exposed to users through the
     ``DataOp.skb.iter_cv_splits()`` method. See the corresponding docstring for

skrub/_data_ops/_skrub_namespace.py

@@ -1777,7 +1777,7 @@ def train_test_split(
         split_func=model_selection.train_test_split,
         **split_func_kwargs,
     ):
-        """Split an environment into a training an testing environments.
+        """Split an environment into training and testing environments.
 
         Parameters
         ----------