DOC fix typos found by codespell (scikit-learn#27457)

Author: DimitriPapadopoulos

asv_benchmarks/asv.conf.json

@@ -72,7 +72,7 @@
     // followed by the pip installed packages).
     //
     // The versions of the dependencies should be bumped in a dedicated commit
-    // to easily identify regressions/imrovements due to code changes from
+    // to easily identify regressions/improvements due to code changes from
     // those due to dependency changes.
     //
     "matrix": {

doc/modules/clustering.rst

@@ -1780,7 +1780,7 @@ mean of homogeneity and completeness**:
    measure <https://aclweb.org/anthology/D/D07/D07-1043.pdf>`_
    Andrew Rosenberg and Julia Hirschberg, 2007
 
- .. [B2011] `Identication and Characterization of Events in Social Media
+ .. [B2011] `Identification and Characterization of Events in Social Media
    <http://www.cs.columbia.edu/~hila/hila-thesis-distributed.pdf>`_, Hila
    Becker, PhD Thesis.
 

doc/whats_new/v0.23.rst

@@ -784,7 +784,7 @@ Miscellaneous
 .............
 
 - |MajorFeature| Adds a HTML representation of estimators to be shown in
-  a jupyter notebook or lab. This visualization is acitivated by setting the
+  a jupyter notebook or lab. This visualization is activated by setting the
   `display` option in :func:`sklearn.set_config`. :pr:`14180` by
   `Thomas Fan`_.
 

doc/whats_new/v1.3.rst

@@ -432,7 +432,7 @@ Changelog
   the pandas parser. The parameter `read_csv_kwargs` allows to overwrite this behaviour.
   :pr:`26551` by :user:`Guillaume Lemaitre <glemaitre>`.
 
-- |Fix| :func:`datasets.fetch_openml` will consistenly use `np.nan` as missing marker
+- |Fix| :func:`datasets.fetch_openml` will consistently use `np.nan` as missing marker
   with both parsers `"pandas"` and `"liac-arff"`.
   :pr:`26579` by :user:`Guillaume Lemaitre <glemaitre>`.
 
@@ -724,7 +724,7 @@ Changelog
 
 - |API| The parameter `log_scale` in the class
   :class:`model_selection.LearningCurveDisplay` has been deprecated in 1.3 and
-  will be removed in 1.5. The default scale can be overriden by setting it
+  will be removed in 1.5. The default scale can be overridden by setting it
   directly on the `ax` object and will be set automatically from the spacing
   of the data points otherwise.
   :pr:`25120` by :user:`Guillaume Lemaitre <glemaitre>`.
@@ -837,7 +837,7 @@ Changelog
 - |Fix| :class:`preprocessing.PowerTransformer` now correctly preserves the Pandas
   Index when the `set_config(transform_output="pandas")`. :pr:`26454` by `Thomas Fan`_.
 
-- |Fix| :class:`preprocessing.PowerTransformer` now correcly raises error when
+- |Fix| :class:`preprocessing.PowerTransformer` now correctly raises error when
   using `method="box-cox"` on data with a constant `np.nan` column.
   :pr:`26400` by :user:`Yao Xiao <Charlie-XIAO>`.
 

examples/applications/plot_cyclical_feature_engineering.py

@@ -631,7 +631,7 @@ def periodic_spline_transformer(period, n_splines=None, degree=3):
 
 # %%
 # Those features are then combined with the ones already computed in the
-# previous spline-base pipeline. We can observe a nice performance improvemnt
+# previous spline-base pipeline. We can observe a nice performance improvement
 # by modeling this pairwise interaction explicitly:
 
 cyclic_spline_interactions_pipeline = make_pipeline(

examples/ensemble/plot_voting_probas.py

@@ -9,7 +9,7 @@
 three different classifiers and averaged by the
 :class:`~ensemble.VotingClassifier`.
 
-First, three examplary classifiers are initialized
+First, three exemplary classifiers are initialized
 (:class:`~linear_model.LogisticRegression`, :class:`~naive_bayes.GaussianNB`,
 and :class:`~ensemble.RandomForestClassifier`) and used to initialize a
 soft-voting :class:`~ensemble.VotingClassifier` with weights `[1, 1, 5]`, which

examples/linear_model/plot_poisson_regression_non_normal_loss.py

@@ -209,7 +209,7 @@ def score_estimator(estimator, df_test):
 # ---------------------------
 #
 # We start by modeling the target variable with the (l2 penalized) least
-# squares linear regression model, more comonly known as Ridge regression. We
+# squares linear regression model, more commonly known as Ridge regression. We
 # use a low penalization `alpha`, as we expect such a linear model to under-fit
 # on such a large dataset.
 

examples/manifold/plot_lle_digits.py

@@ -145,7 +145,7 @@ def plot_embedding(X, title):
     "Spectral embedding": SpectralEmbedding(
         n_components=2, random_state=0, eigen_solver="arpack"
     ),
-    "t-SNE embeedding": TSNE(
+    "t-SNE embedding": TSNE(
         n_components=2,
         n_iter=500,
         n_iter_without_progress=150,
@@ -158,7 +158,7 @@ def plot_embedding(X, title):
 }
 
 # %%
-# Once we declared all the methodes of interest, we can run and perform the projection
+# Once we declared all the methods of interest, we can run and perform the projection
 # of the original data. We will store the projected data as well as the computational
 # time needed to perform each projection.
 from time import time

examples/svm/plot_svm_kernels.py

@@ -184,7 +184,7 @@ def plot_training_data_with_decision_boundary(kernel):
 # (`gamma`) controls the influence of each individual training sample on the
 # decision boundary and :math:`{r}` is the bias term (`coef0`) that shifts the
 # data up or down. Here, we use the default value for the degree of the
-# polynomal in the kernel funcion (`degree=3`). When `coef0=0` (the default),
+# polynomial in the kernel function (`degree=3`). When `coef0=0` (the default),
 # the data is only transformed, but no additional dimension is added. Using a
 # polynomial kernel is equivalent to creating
 # :class:`~sklearn.preprocessing.PolynomialFeatures` and then fitting a

sklearn/ensemble/_gb.py

@@ -87,7 +87,7 @@ def _init_raw_predictions(X, estimator, loss, use_predict_proba):
     estimator : object
         The estimator to use to compute the predictions.
     loss : BaseLoss
-        An instace of a loss function class.
+        An instance of a loss function class.
     use_predict_proba : bool
         Whether estimator.predict_proba is used instead of estimator.predict.