DOC: Error msg using Python keyword in numexpr query pandas-dev#18221 (pandas-dev#18248)

Author: WillAyd

doc/source/whatsnew/v0.22.0.txt

@@ -161,6 +161,6 @@ Categorical
 Other
 ^^^^^
 
--
+- Improved error message when attempting to use a Python keyword as an identifier in a numexpr query (:issue:`18221`)
 -
 -

pandas/core/computation/expr.py

@@ -307,7 +307,14 @@ def __init__(self, env, engine, parser, preparser=_preparse):
     def visit(self, node, **kwargs):
         if isinstance(node, string_types):
             clean = self.preparser(node)
-            node = ast.fix_missing_locations(ast.parse(clean))
+            try:
+                node = ast.fix_missing_locations(ast.parse(clean))
+            except SyntaxError as e:
+                from keyword import iskeyword
+                if any(iskeyword(x) for x in clean.split()):
+                    e.msg = ("Python keyword not valid identifier"
+                             " in numexpr query")
+                raise e
 
         method = 'visit_' + node.__class__.__name__
         visitor = getattr(self, method)

pandas/core/frame.py

@@ -2267,7 +2267,8 @@ def query(self, expr, inplace=False, **kwargs):
         by default, which allows you to treat both the index and columns of the
         frame as a column in the frame.
         The identifier ``index`` is used for the frame index; you can also
-        use the name of the index to identify it in a query.
+        use the name of the index to identify it in a query. Please note that
+        Python keywords may not be used as identifiers.
 
         For further details and examples see the ``query`` documentation in
         :ref:`indexing <indexing.query>`.

pandas/tests/computation/test_eval.py

@@ -718,6 +718,18 @@ def test_float_truncation(self):
         expected = df.loc[[1], :]
         tm.assert_frame_equal(expected, result)
 
+    def test_disallow_python_keywords(self):
+        # GH 18221
+        df = pd.DataFrame([[0, 0, 0]], columns=['foo', 'bar', 'class'])
+        msg = "Python keyword not valid identifier in numexpr query"
+        with tm.assert_raises_regex(SyntaxError, msg):
+            df.query('class == 0')
+
+        df = pd.DataFrame()
+        df.index.name = 'lambda'
+        with tm.assert_raises_regex(SyntaxError, msg):
+            df.query('lambda == 0')
+
 
 class TestEvalNumexprPython(TestEvalNumexprPandas):