Fix typos (scikit-learn#9476)

Author: taehoonlee

sklearn/ensemble/gradient_boosting.py

@@ -448,7 +448,7 @@ class ClassificationLossFunction(six.with_metaclass(ABCMeta, LossFunction)):
     def _score_to_proba(self, score):
         """Template method to convert scores to probabilities.
 
-         the does not support probabilites raises AttributeError.
+         the does not support probabilities raises AttributeError.
         """
         raise TypeError('%s does not support predict_proba' % type(self).__name__)
 

sklearn/ensemble/tests/test_base.py

@@ -109,7 +109,7 @@ def make_steps():
     assert_not_equal(est1.get_params()['sel__estimator__random_state'],
                      est1.get_params()['clf__random_state'])
 
-    # ensure multiple random_state paramaters are invariant to get_params()
+    # ensure multiple random_state parameters are invariant to get_params()
     # iteration order
 
     class AlphaParamPipeline(Pipeline):

sklearn/linear_model/tests/test_logistic.py

@@ -986,7 +986,7 @@ def test_logreg_predict_proba_multinomial():
     X, y = make_classification(n_samples=10, n_features=20, random_state=0,
                                n_classes=3, n_informative=10)
 
-    # Predicted probabilites using the true-entropy loss should give a
+    # Predicted probabilities using the true-entropy loss should give a
     # smaller loss than those using the ovr method.
     clf_multi = LogisticRegression(multi_class="multinomial", solver="lbfgs")
     clf_multi.fit(X, y)
@@ -996,7 +996,7 @@ def test_logreg_predict_proba_multinomial():
     clf_ovr_loss = log_loss(y, clf_ovr.predict_proba(X))
     assert_greater(clf_ovr_loss, clf_multi_loss)
 
-    # Predicted probabilites using the soft-max function should give a
+    # Predicted probabilities using the soft-max function should give a
     # smaller loss than those using the logistic function.
     clf_multi_loss = log_loss(y, clf_multi.predict_proba(X))
     clf_wrong_loss = log_loss(y, clf_multi._predict_proba_lr(X))

sklearn/metrics/ranking.py

@@ -840,7 +840,7 @@ def ndcg_score(y_true, y_score, k=5):
     """
     y_score, y_true = check_X_y(y_score, y_true)
 
-    # Make sure we use all the labels (max between the lenght and the higher
+    # Make sure we use all the labels (max between the length and the higher
     # number in the array)
     lb = LabelBinarizer()
     lb.fit(np.arange(max(np.max(y_true) + 1, len(y_true))))

sklearn/mixture/dpgmm.py

@@ -47,7 +47,7 @@ def gammaln(x):
 @deprecated("The function log_normalize is deprecated in 0.18 and "
             "will be removed in 0.20.")
 def log_normalize(v, axis=0):
-    """Normalized probabilities from unnormalized log-probabilites"""
+    """Normalized probabilities from unnormalized log-probabilities"""
     v = np.rollaxis(v, axis)
     v = v.copy()
     v -= v.max(axis=0)

sklearn/multioutput.py

@@ -316,7 +316,7 @@ def __init__(self, estimator, n_jobs=1):
 
     def predict_proba(self, X):
         """Probability estimates.
-        Returns prediction probabilites for each class of each output.
+        Returns prediction probabilities for each class of each output.
 
         Parameters
         ----------

sklearn/utils/random.py

@@ -184,7 +184,7 @@ def random_choice_csc(n_samples, classes, class_probability=None,
                                                     random_state=random_state)
             indices.extend(ind_sample)
 
-            # Normalize probabilites for the nonzero elements
+            # Normalize probabilities for the nonzero elements
             classes_j_nonzero = classes[j] != 0
             class_probability_nz = class_prob_j[classes_j_nonzero]
             class_probability_nz_norm = (class_probability_nz /