Skip to content

add quoting=csv.QUOTE_NONE #250

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

Merged
Eleven1Liu merged 2 commits into from
Feb 9, 2023
Merged

add quoting=csv.QUOTE_NONE #250

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
108caa9
add quoting=csv.QUOTE_NONE
Feb 8, 2023
6b46df1
sort import
ChengYehLi Feb 9, 2023
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
3 changes: 2 additions & 1 deletion libmultilabel/linear/preprocessor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
from __future__ import annotations

import csv
import logging
import re
from array import array
Expand Down Expand Up @@ -141,7 +142,7 @@ def _generate_label_mapping(self, labels, classes=None):
def read_libmultilabel_format(path: str) -> 'dict[str,list[str]]':
data = pd.read_csv(path, sep='\t', header=None,
dtype=str,
on_bad_lines='skip').fillna('')
on_bad_lines='skip', quoting=csv.QUOTE_NONE).fillna('')
if data.shape[1] == 2:
data.columns = ['label', 'text']
data = data.reset_index()
Expand Down
3 changes: 2 additions & 1 deletion libmultilabel/nn/data_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
import csv
import gc
import logging
import warnings
Expand Down Expand Up @@ -136,7 +137,7 @@ def _load_raw_data(path, is_test=False, tokenize_text=True, remove_no_label_data
"""
logging.info(f'Load data from {path}.')
data = pd.read_csv(path, sep='\t', header=None,
error_bad_lines=False, warn_bad_lines=True).fillna('')
error_bad_lines=False, warn_bad_lines=True, quoting=csv.QUOTE_NONE).fillna('')
if data.shape[1] == 2:
data.columns = ['label', 'text']
data = data.reset_index()
Expand Down