diff --git a/examples/calibration/plot_compare_calibration.py b/examples/calibration/plot_compare_calibration.py
index d935bce4f5bc20f9fc2f3d9ef3d5b1519507d733..bc1f73a06eb1a5531c6d60ab949f617bab2636fb 100644
--- a/examples/calibration/plot_compare_calibration.py
+++ b/examples/calibration/plot_compare_calibration.py
@@ -33,9 +33,9 @@ with different biases per method:
   moving the average prediction of the bagged ensemble away from 0. We observe
   this effect most strongly with random forests because the base-level trees
   trained with random forests have relatively high variance due to feature
-  subseting." As a result, the calibration curve shows a characteristic sigmoid
-  shape, indicating that the classifier could trust its "intuition" more and
-  return probabilities closer to 0 or 1 typically.
+  subsetting." As a result, the calibration curve shows a characteristic
+  sigmoid shape, indicating that the classifier could trust its "intuition"
+  more and return probabilities closer to 0 or 1 typically.
 
 * Support Vector Classification (SVC) shows an even more sigmoid curve as
   the  RandomForestClassifier, which is typical for maximum-margin methods
diff --git a/sklearn/externals/joblib/_parallel_backends.py b/sklearn/externals/joblib/_parallel_backends.py
index 8f3e768abd441aeaa8646887de22a2e3e742800b..7035f66e3845290ff24c2390591717aba4aaaedf 100644
--- a/sklearn/externals/joblib/_parallel_backends.py
+++ b/sklearn/externals/joblib/_parallel_backends.py
@@ -88,7 +88,7 @@ class ParallelBackendBase(with_metaclass(ABCMeta)):
         managed by the backend it-self: if we expect no new tasks, there is no
         point in re-creating a new working pool.
         """
-        # Does nothing by default: to be overriden in subclasses when canceling
+        # Does nothing by default: to be overridden in subclasses when canceling
         # tasks is possible.
         pass
 
diff --git a/sklearn/externals/joblib/parallel.py b/sklearn/externals/joblib/parallel.py
index 73e681b870dd599ba77b0ce78739554687ad1fb9..345697e06241a595b8fea7b0917aaed54c9b09c4 100644
--- a/sklearn/externals/joblib/parallel.py
+++ b/sklearn/externals/joblib/parallel.py
@@ -48,7 +48,7 @@ BACKENDS = {
 DEFAULT_BACKEND = 'multiprocessing'
 DEFAULT_N_JOBS = 1
 
-# Thread local value that can be overriden by the ``parallel_backend`` context
+# Thread local value that can be overridden by the ``parallel_backend`` context
 # manager
 _backend = threading.local()
 
diff --git a/sklearn/utils/testing.py b/sklearn/utils/testing.py
index cfaefc88d23081860f87f448fc5edf8b9a024199..e308a2a7b3305577488a9c90a9f19e6facde56fc 100644
--- a/sklearn/utils/testing.py
+++ b/sklearn/utils/testing.py
@@ -268,7 +268,7 @@ class _IgnoreWarnings(object):
 
     Parameters
     ----------
-    category : tuple of warning class, defaut to Warning
+    category : tuple of warning class, default to Warning
         The category to filter. By default, all the categories will be muted.
 
     """
diff --git a/sklearn/utils/validation.py b/sklearn/utils/validation.py
index e6e98f45ae5d5a3cccb9c782ef9b3b56fdc38c4b..460f20673feafa581815d69dca42131819cf24ce 100644
--- a/sklearn/utils/validation.py
+++ b/sklearn/utils/validation.py
@@ -618,7 +618,7 @@ def has_fit_parameter(estimator, parameter):
     Returns
     -------
     is_parameter: bool
-        Whether the parameter was found to be a a named parameter of the
+        Whether the parameter was found to be a named parameter of the
         estimator's fit method.
 
     Examples