Add a compatibility layer for some modules.

OK, there are a bunch of ``import *``, but I don't see any other
reasonable way ...

scikits/learn/__init__.py

+import warnings
+warnings.warn('scikits.learn namespace is deprecated, please use sklearn instead')
+from sklearn import *

scikits/learn/cluster/__init__.py

+import warnings
+warnings.warn('scikits.learn is deprecated, please use sklearn')
+from sklearn.cluster import *
\ No newline at end of file

scikits/learn/datasets/__init__.py

+import warnings
+warnings.warn('scikits.learn is deprecated, please use sklearn')
+from sklearn.datasets import *
\ No newline at end of file

scikits/learn/decomposition/__init__.py

+import warnings
+warnings.warn('scikits.learn namespace is deprecated, please use sklearn instead')
+from sklearn.decomposition import *
\ No newline at end of file

scikits/learn/grid_search.py

+import warnings
+warnings.warn('scikits.learn namespace is deprecated, please use sklearn instead')
+from sklearn.grid_search import *
\ No newline at end of file

scikits/learn/linear_model/__init__.py

+import warnings
+warnings.warn('scikits.learn is deprecated, please use sklearn')
+from sklearn.linear_model import *
\ No newline at end of file

scikits/learn/svm/__init__.py

+import warnings
+warnings.warn('scikits.learn is deprecated, please use sklearn')
+from sklearn.svm import *
\ No newline at end of file