non-existent columns in DataFrame.dropna subset argument now raises KeyError

Author: mcjcode

doc/source/v0.15.0.txt

@@ -971,4 +971,4 @@ Bug Fixes
 - Bug in DataFrame terminal display: Setting max_column/max_rows to zero did not trigger auto-resizing of dfs to fit terminal width/height (:issue:`7180`).
 - Bug in OLS where running with "cluster" and "nw_lags" parameters did not work correctly, but also did not throw an error
   (:issue:`5884').
-
+- Bug in ``DataFrame.dropna`` that interpreted non-existent columns in the subset argument as the 'last column' (:issue:`8303`)

pandas/core/frame.py

@@ -2552,7 +2552,11 @@ def dropna(self, axis=0, how='any', thresh=None, subset=None,
             agg_obj = self
             if subset is not None:
                 ax = self._get_axis(agg_axis)
-                agg_obj = self.take(ax.get_indexer_for(subset),axis=agg_axis)
+                indices = ax.get_indexer_for(subset)
+                check = indices == -1
+                if check.any():
+                    raise KeyError(list(np.compress(check,subset)))
+                agg_obj = self.take(indices,axis=agg_axis)
 
             count = agg_obj.count(axis=agg_axis)
 

pandas/tests/test_frame.py

@@ -7200,6 +7200,8 @@ def test_dropna_corner(self):
         # bad input
         self.assertRaises(ValueError, self.frame.dropna, how='foo')
         self.assertRaises(TypeError, self.frame.dropna, how=None)
+        # non-existent column - 8303
+        self.assertRaises(KeyError, self.frame.dropna, subset=['A','X'])
 
     def test_dropna_multiple_axes(self):
         df = DataFrame([[1, np.nan, 2, 3],