raghavrv
diff --git a/‎sklearn/preprocessing/data.py
Lines changed: 33 additions & 2 deletions b/‎sklearn/preprocessing/data.py
Lines changed: 33 additions & 2 deletions
diff --git a/‎sklearn/preprocessing/tests/test_data.py
Lines changed: 25 additions & 0 deletions b/‎sklearn/preprocessing/tests/test_data.py
Lines changed: 25 additions & 0 deletions
@@ -20,6 +20,7 @@
 from ..utils.extmath import row_norms
 from ..utils.extmath import _incremental_mean_and_var
 from ..utils.fixes import combinations_with_replacement as combinations_w_r
+from ..utils.fixes import bincount
 from ..utils.sparsefuncs_fast import (inplace_csr_row_normalize_l1,
                                       inplace_csr_row_normalize_l2)
 from ..utils.sparsefuncs import (inplace_column_scale,
@@ -1140,7 +1141,7 @@ class PolynomialFeatures(BaseEstimator, TransformerMixin):
 
     Attributes
     ----------
-    powers_ : array, shape (n_input_features, n_output_features)
+    powers_ : array, shape (n_output_features, n_input_features)
         powers_[i, j] is the exponent of the jth input in the ith output.
 
     n_input_features_ : int
@@ -1179,9 +1180,39 @@ def powers_(self):
         combinations = self._combinations(self.n_input_features_, self.degree,
                                           self.interaction_only,
                                           self.include_bias)
-        return np.vstack(np.bincount(c, minlength=self.n_input_features_)
+        return np.vstack(bincount(c, minlength=self.n_input_features_)
                          for c in combinations)
 
+    def get_feature_names(self, input_features=None):
+        """
+        Return feature names for output features
+
+        Parameters
+        ----------
+        input_features : list of string, length n_features, optional
+            String names for input features if available. By default,
+            "x0", "x1", ... "xn_features" is used.
+
+        Returns
+        -------
+        output_feature_names : list of string, length n_output_features
+
+        """
+        powers = self.powers_
+        if input_features is None:
+            input_features = ['x%d' % i for i in range(powers.shape[1])]
+        feature_names = []
+        for row in powers:
+            inds = np.where(row)[0]
+            if len(inds):
+                name = " ".join("%s^%d" % (input_features[ind], exp)
+                                if exp != 1 else input_features[ind]
+                                for ind, exp in zip(inds, row[inds]))
+            else:
+                name = "1"
+            feature_names.append(name)
+        return feature_names
+
     def fit(self, X, y=None):
         """
         Compute number of output features.
 
@@ -10,6 +10,7 @@
 import numpy.linalg as la
 from scipy import sparse
 from distutils.version import LooseVersion
+from sklearn.externals.six import u
 
 from sklearn.utils import gen_batches
 
@@ -118,6 +119,30 @@ def test_polynomial_features():
     X_poly = interact.fit_transform(X)
     assert_array_almost_equal(X_poly, P2[:, [0, 1, 2, 4]])
 
+    assert_equal(interact.powers_.shape, (interact.n_output_features_,
+                 interact.n_input_features_))
+
+
+def test_polynomial_feature_names():
+    X = np.arange(30).reshape(10, 3)
+    poly = PolynomialFeatures(degree=2, include_bias=True).fit(X)
+    feature_names = poly.get_feature_names()
+    assert_array_equal(['1', 'x0', 'x1', 'x2', 'x0^2', 'x0 x1',
+                        'x0 x2', 'x1^2', 'x1 x2', 'x2^2'],
+                       feature_names)
+
+    poly = PolynomialFeatures(degree=3, include_bias=False).fit(X)
+    feature_names = poly.get_feature_names(["a", "b", "c"])
+    assert_array_equal(['a', 'b', 'c', 'a^2', 'a b', 'a c', 'b^2',
+                        'b c', 'c^2', 'a^3', 'a^2 b', 'a^2 c',
+                        'a b^2', 'a b c', 'a c^2', 'b^3', 'b^2 c',
+                        'b c^2', 'c^3'], feature_names)
+    # test some unicode
+    poly = PolynomialFeatures(degree=1, include_bias=True).fit(X)
+    feature_names = poly.get_feature_names([u"\u0001F40D", u"\u262E", u"\u05D0"])
+    assert_array_equal([u"1", u"\u0001F40D", u"\u262E", u"\u05D0"],
+                       feature_names)
+
 
 def test_standard_scaler_1d():
     # Test scaling of dataset along single axis