Skip to content

Support a list of column positions for read_csv index_col #24004

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

Open
lukiod wants to merge 2 commits into
base: main
Choose a base branch
from
+38 −5
Open

Support a list of column positions for read_csv index_col #24004

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
df553db
Support a list of column positions for read_csv index_col
lukiod Sep 6, 2026
4c9d298
Fix index_col name resolution for an explicit header= argument
lukiod Sep 8, 2026
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
16 changes: 15 additions & 1 deletion python/cudf/cudf/io/csv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
import csv
import itertools
import os
from collections.abc import Collection, Mapping
from collections.abc import Collection, Mapping, Sequence
from io import BytesIO, StringIO, TextIOBase
from typing import TYPE_CHECKING, cast

Expand Down Expand Up @@ -366,6 +366,20 @@ def read_csv(
df.index.name = None
elif names is None:
df.index.name = index_col
elif isinstance(index_col, Sequence) and all(
isinstance(col, int) for col in index_col
Comment on lines +366 to +367

@mroeschke mroeschke Sep 8, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can index_col be a str here? I don't think this is the correct behavior in that case

):
index_col_labels = list(df._data.get_labels_by_index(index_col))
df = df.set_index(index_col_labels)
if names is None:
df.index.names = [
(None if label.startswith("Unnamed:") else label)
if isinstance(label, str) and orig_header == "infer"
Comment thread
coderabbitai[bot] marked this conversation as resolved.
Outdated
else position
for label, position in zip(
index_col_labels, index_col, strict=True
)
]
else:
df = df.set_index(index_col)

Expand Down
10 changes: 10 additions & 0 deletions python/cudf/cudf/tests/input_output/test_csv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1263,6 +1263,16 @@ def test_csv_reader_index_col():
pd_df = pd.read_csv(StringIO(buffer), header=None, index_col=False)
assert_eq(cu_df.index, pd_df.index)

# using a single column index wrapped in a list
cu_df = read_csv(StringIO(buffer), header=None, index_col=[0])
pd_df = pd.read_csv(StringIO(buffer), header=None, index_col=[0])
assert_eq(cu_df.index, pd_df.index)

# using multiple column indices
cu_df = read_csv(StringIO(buffer), header=None, index_col=[0, 1])
pd_df = pd.read_csv(StringIO(buffer), header=None, index_col=[0, 1])
assert_eq(cu_df.index, pd_df.index)


@pytest.mark.parametrize("index_name", [None, "custom name", 124])
@pytest.mark.parametrize("index_col", [None, 0, "a"])
Expand Down
Loading