Merge pull request scikit-learn-contrib#177 from ragrawal/astransformer

ActAsTransformer

sklearn_pandas/__init__.py

@@ -4,3 +4,4 @@
 from .cross_validation import cross_val_score, GridSearchCV, RandomizedSearchCV  # NOQA
 from .categorical_imputer import CategoricalImputer  # NOQA
 from .features_generator import gen_features  # NOQA
+from .act_as_transformer import ActAsTransformer  # NOQA

sklearn_pandas/act_as_transformer.py

@@ -0,0 +1,21 @@
+from sklearn.base import BaseEstimator, TransformerMixin
+import numpy as np
+
+
+class ActAsTransformer(BaseEstimator, TransformerMixin):
+    """
+    Use this class to convert a random function into a
+    transformer.
+    """
+
+    def __init__(self, func):
+        self.__func = func
+
+    def fit(self, x, y=None):
+        return self
+
+    def transform(self, x):
+        return np.vectorize(self.__func)(x)
+
+    def __call__(self, *args, **kwargs):
+        return self.__func(*args, **kwargs)

tests/test_dataframe_mapper.py

@@ -32,6 +32,7 @@
 from sklearn_pandas import DataFrameMapper, cross_val_score
 from sklearn_pandas.dataframe_mapper import _handle_feature, _build_transformer
 from sklearn_pandas.pipeline import TransformerPipeline
+from sklearn_pandas import ActAsTransformer
 
 
 class MockXTransformer(object):
@@ -950,3 +951,17 @@ def test_heterogeneous_output_types_input_df():
     dft = M.fit_transform(df)
     assert dft['feat1'].dtype == np.dtype('int64')
     assert dft['feat2'].dtype == np.dtype('float64')
+
+
+def test_actastransformer():
+    """
+    Test whether random transformations works
+    """
+    df = pd.DataFrame({
+        'feat1': [10, 100],
+    })
+    M = DataFrameMapper([
+        ('feat1', ActAsTransformer(np.log10))
+    ], input_df=True, df_out=True, default=None)
+    dft = M.fit_transform(df)
+    assert_array_equal([1., 2.], dft['feat1'].values)