Merge branch 'unpickle_list_shim'. Fixes #45.

Author: dukebody

README.rst

@@ -194,6 +194,7 @@ Changelog
 *******************
 
 * Use custom ``TransformerPipeline`` class to allow transformation steps accepting only a X argument. Fixes #46.
+* Add compatibility shim for unpickling mappers with list of transformers created before 1.0.0. Fixes #45.
 
 
 1.0.0 (2015-11-28)

sklearn_pandas/__init__.py

@@ -8,7 +8,7 @@
 from sklearn.base import BaseEstimator, TransformerMixin
 from sklearn import cross_validation
 from sklearn import grid_search
-from pipeline import make_transformer_pipeline
+from pipeline import make_transformer_pipeline, TransformerPipeline
 
 # load in the correct stringtype: str for py3, basestring for py2
 string_types = str if sys.version_info >= (3, 0) else basestring
@@ -96,6 +96,12 @@ def __init__(self, features, sparse=False):
         self.features = features
         self.sparse = sparse
 
+    def __setstate__(self, state):
+        # compatibility shim for pickles created with sklearn-pandas<1.0.0
+        self.features = [(columns, _build_transformer(transformers))
+                         for (columns, transformers) in state['features']]
+        self.sparse = state.get('sparse', False)
+
     def _get_col_subset(self, X, cols):
         """
         Get a subset of columns from the given table X.

tests/test_dataframe_mapper.py

@@ -18,13 +18,15 @@
 from sklearn.base import BaseEstimator, TransformerMixin
 import numpy as np
 from numpy.testing import assert_array_equal
+import pickle
 
 from sklearn_pandas import (
     DataFrameMapper,
     PassthroughTransformer,
     cross_val_score,
     _build_transformer,
     _handle_feature,
+    TransformerPipeline,
 )
 
 
@@ -191,6 +193,18 @@ def test_list_transformers():
     assert (abs(dmatrix.std(axis=0) - 1) <= 1e-6).all()
 
 
+def test_list_transformers_old_unpickle(simple_dataframe):
+    mapper = DataFrameMapper(None)
+    # simulate the mapper was created with < 1.0.0 code
+    mapper.features = [('a', [MockXTransformer()])]
+    mapper_pickled = pickle.dumps(mapper)
+
+    loaded_mapper = pickle.loads(mapper_pickled)
+    transformer = loaded_mapper.features[0][1]
+    assert isinstance(transformer, TransformerPipeline)
+    assert isinstance(transformer.steps[0][1], MockXTransformer)
+
+
 def test_sparse_features(simple_dataframe):
     """
     If any of the extracted features is sparse and "sparse" argument