implement tests to check duplicate cols

Author: kunalgosar

pandas/tests/frame/test_dtypes.py

@@ -287,6 +287,21 @@ def test_select_dtypes_include_exclude_mixed_scalars_lists(self):
         ei = df[['b', 'c', 'f', 'k']]
         assert_frame_equal(ri, ei)
 
+    def test_select_dtypes_duplicate_columns(self):
+        df = DataFrame({'a': list('abc'),
+                        'b': list(range(1, 4)),
+                        'c': np.arange(3, 6).astype('u1'),
+                        'd': np.arange(4.0, 7.0, dtype='float64'),
+                        'e': [True, False, True],
+                        'f': pd.date_range('now', periods=3).values})
+        df.columns = ['a', 'a', 'b', 'b', 'b', 'c']
+
+        e = DataFrame({'a': list(range(1, 4)),
+                       'b': np.arange(3, 6).astype('u1')})
+
+        r = df.select_dtypes(include=[np.number], exclude=['floating'])
+        assert_frame_equal(r, e)
+
     def test_select_dtypes_not_an_attr_but_still_valid_dtype(self):
         df = DataFrame({'a': list('abc'),
                         'b': list(range(1, 4)),

pandas/tests/reshape/test_reshape.py

@@ -465,6 +465,20 @@ def test_get_dummies_dont_sparsify_all_columns(self, sparse):
 
         tm.assert_frame_equal(df[['GDP']], df2)
 
+    def test_get_dummies_duplicate_columns(self, df):
+        df.columns = ["A", "A", "A"]
+        result = get_dummies(df).sort_index(axis=1)
+
+        expected = DataFrame([[1, 1, 0, 1, 0],
+                              [2, 0, 1, 1, 0],
+                              [3, 1, 0, 0, 1]],
+                             columns=['A', 'A_a', 'A_b', 'A_b', 'A_c'],
+                             dtype=np.uint8).sort_index(axis=1)
+
+        expected = expected.astype({"A": np.int64})
+
+        tm.assert_frame_equal(result, expected)
+
 
 class TestCategoricalReshape(object):