removed cross_val_score as it not required

Author: RJ Agrawal

README.rst

@@ -32,11 +32,11 @@ Import
 Import what you need from the ``sklearn_pandas`` package. The choices are:
 
 * ``DataFrameMapper``, a class for mapping pandas data frame columns to different sklearn transformations
-* ``cross_val_score``, similar to ``sklearn.cross_validation.cross_val_score`` but working on pandas DataFrames
+
 
 For this demonstration, we will import both::
 
-    >>> from sklearn_pandas import DataFrameMapper, cross_val_score
+    >>> from sklearn_pandas import DataFrameMapper
 
 For these examples, we'll also use pandas, numpy, and sklearn::
 

sklearn_pandas/__init__.py

@@ -1,6 +1,5 @@
 __version__ = '2.0.0'
 
 from .dataframe_mapper import DataFrameMapper  # NOQA
-from .cross_validation import cross_val_score, GridSearchCV, RandomizedSearchCV  # NOQA
 from .features_generator import gen_features  # NOQA
 from .transformers import NumericalTransformer # NOQA

sklearn_pandas/cross_validation.py

@@ -1,59 +1,3 @@
-import warnings
-try:
-    from sklearn.model_selection import cross_val_score as sk_cross_val_score
-    from sklearn.model_selection import GridSearchCV as SKGridSearchCV
-    from sklearn.model_selection import RandomizedSearchCV as \
-        SKRandomizedSearchCV
-except ImportError:
-    from sklearn.cross_validation import cross_val_score as sk_cross_val_score
-    from sklearn.grid_search import GridSearchCV as SKGridSearchCV
-    from sklearn.grid_search import RandomizedSearchCV as SKRandomizedSearchCV
-
-DEPRECATION_MSG = '''
-    Custom cross-validation compatibility shims are no longer needed for
-    scikit-learn>=0.16.0 and will be dropped in sklearn-pandas==2.0.
-'''
-
-
-def cross_val_score(model, X, *args, **kwargs):
-    warnings.warn(DEPRECATION_MSG, DeprecationWarning)
-    X = DataWrapper(X)
-    return sk_cross_val_score(model, X, *args, **kwargs)
-
-
-class GridSearchCV(SKGridSearchCV):
-
-    def __init__(self, *args, **kwargs):
-        warnings.warn(DEPRECATION_MSG, DeprecationWarning)
-        super(GridSearchCV, self).__init__(*args, **kwargs)
-
-    def fit(self, X, *params, **kwparams):
-        return super(GridSearchCV, self).fit(
-            DataWrapper(X), *params, **kwparams)
-
-    def predict(self, X, *params, **kwparams):
-        return super(GridSearchCV, self).predict(
-            DataWrapper(X), *params, **kwparams)
-
-
-try:
-    class RandomizedSearchCV(SKRandomizedSearchCV):
-
-        def __init__(self, *args, **kwargs):
-            warnings.warn(DEPRECATION_MSG, DeprecationWarning)
-            super(RandomizedSearchCV, self).__init__(*args, **kwargs)
-
-        def fit(self, X, *params, **kwparams):
-            return super(RandomizedSearchCV, self).fit(
-                DataWrapper(X), *params, **kwparams)
-
-        def predict(self, X, *params, **kwparams):
-            return super(RandomizedSearchCV, self).predict(
-                DataWrapper(X), *params, **kwparams)
-except AttributeError:
-    pass
-
-
 class DataWrapper(object):
 
     def __init__(self, df):

tests/test_dataframe_mapper.py

@@ -14,6 +14,7 @@
 from scipy import sparse
 from sklearn.datasets import load_iris
 from sklearn.pipeline import Pipeline
+from sklearn.model_selection import cross_val_score
 from sklearn.svm import SVC
 from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.feature_extraction import DictVectorizer
@@ -27,7 +28,7 @@
 from numpy.testing import assert_array_equal
 import pickle
 
-from sklearn_pandas import DataFrameMapper, cross_val_score
+from sklearn_pandas import DataFrameMapper
 from sklearn_pandas.dataframe_mapper import _handle_feature, _build_transformer
 from sklearn_pandas.pipeline import TransformerPipeline
 
@@ -882,6 +883,27 @@ def test_with_car_dataframe(cars_dataframe):
     assert scores.mean() > 0.30
 
 
+def test_direct_cross_validation(iris_dataframe):
+    """
+    Starting with sklearn>=0.16.0 we no longer need CV wrappers for dataframes.
+    See https://github.com/paulgb/sklearn-pandas/issues/11
+    """
+    pipeline = Pipeline([
+        ("preprocess", DataFrameMapper([
+            ("petal length (cm)", None),
+            ("petal width (cm)", None),
+            ("sepal length (cm)", None),
+            ("sepal width (cm)", None),
+        ])),
+        ("classify", SVC(kernel='linear'))
+    ])
+    data = iris_dataframe.drop("species", axis=1)
+    labels = iris_dataframe["species"]
+    scores = cross_val_score(pipeline, data, labels)
+    assert scores.mean() > 0.96
+    assert (scores.std() * 2) < 0.04
+
+
 def test_heterogeneous_output_types_input_df():
     """
     Modify feat2, but pass feat1 through unmodified.

tests/test_transformers.py

@@ -5,7 +5,7 @@
 import joblib
 
 from sklearn_pandas import DataFrameMapper
-from sklearn_pandas.transformers import NumericalTransformer
+from sklearn_pandas import NumericalTransformer
 
 
 @pytest.fixture