Skip to content

BUG: IndexError on read_csv/read_table when using usecols/names parameters and omitting last column #5767

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

BUG: IndexError on read_csv/read_table when using usecols/names parameters and omitting last column #5767

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 4 additions & 5 deletions pandas/io/tests/test_parsers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2037,16 +2037,16 @@ def test_usecols(self):
4,5,6
7,8,9
10,11,12"""
result = self.read_csv(StringIO(data), names=['b', 'c'],
header=None, usecols=[1, 2])
result = self.read_csv(StringIO(data), names=['a', 'b'],
header=None, usecols=[0, 1])

expected = self.read_csv(StringIO(data), names=['a', 'b', 'c'],
header=None)
expected = expected[['b', 'c']]
expected = expected[['a', 'b']]
tm.assert_frame_equal(result, expected)

result2 = self.read_csv(StringIO(data), names=['a', 'b', 'c'],
header=None, usecols=['b', 'c'])
header=None, usecols=['a', 'b'])
tm.assert_frame_equal(result2, result)

# length conflict, passed names and usecols disagree
Expand All @@ -2072,7 +2072,6 @@ def test_catch_too_many_names(self):
10,11,12\n"""
tm.assertRaises(Exception, read_csv, StringIO(data), header=0, names=['a', 'b', 'c', 'd'])


class TestPythonParser(ParserTests, tm.TestCase):
def test_negative_skipfooter_raises(self):
text = """#foo,a,b,c
Expand Down
5 changes: 4 additions & 1 deletion pandas/parser.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1135,8 +1135,11 @@ cdef class TextReader:

cdef _get_column_name(self, Py_ssize_t i, Py_ssize_t nused):
if self.has_usecols and self.names is not None:
if len(self.names) == len(self.usecols):
if len(self.names) == len(self.usecols) and nused < len(self.names):
return self.names[nused]
# addresses Issue #5766
elif nused >= len(self.names):
return None
else:
return self.names[i - self.leading_cols]
else:
Expand Down