ENH: Improve error message for read_csv header argument containing non int types. GH16338.

Adds error "header must be integer or list of integers" when the header argument is a list, tuple or numpy array containing non-integers. Initially intended to read_csv, but applies to other functions with similar header arguments. GH16338 refers to a case in which the user mixes up the "names" and "header" arguments. Revising PR16351 based on feedback Revising PR16351 lint issues

Author: mjlove12

pandas/io/parsers.py

@@ -1164,6 +1164,8 @@ def __init__(self, kwds):
  # validate header options for mi
  self.header = kwds.get('header')
  if isinstance(self.header, (list, tuple, np.ndarray)):
+ if not all(map(is_integer, self.header)):
+ raise ValueError("header must be integer or list of integers")
  if kwds.get('as_recarray'):
  raise ValueError("cannot specify as_recarray when "
  "specifying a multi-index header")
@@ -1184,6 +1186,10 @@ def __init__(self, kwds):
  raise ValueError("index_col must only contain row numbers "
  "when specifying a multi-index header")
 
+ # GH 16338
+ elif self.header is not None and not is_integer(self.header):
+ raise ValueError("header must be integer or list of integers")
+
  self._name_processed = False
 
  self._first_chunk = True

pandas/tests/io/parser/header.py

@@ -277,3 +277,12 @@ def test_no_header(self):
  tm.assert_index_equal(df.columns, Index(lrange(5)))
 
  tm.assert_index_equal(df2.columns, Index(names))
+
+ def test_non_int_header(self):
+ # GH 16338
+ msg = 'header must be integer or list of integers'
+ data = """1,2\n3,4"""
+ with tm.assert_raises_regex(ValueError, msg):
+ self.read_csv(StringIO(data), sep=',', header=['a', 'b'])
+ with tm.assert_raises_regex(ValueError, msg):
+ self.read_csv(StringIO(data), sep=',', header='string_header')