Skip to content

Fix Encoding Error When Reading TSV Files in load_custom_dataset_from_folder #132

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
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Fix Encoding Error When Reading TSV Files in load_custom_dataset_from_folder #132

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
60b9c22
fix encoding in load_custom_dataset_from_folder
Seanium Mar 30, 2025
92f63e8
Merge pull request #1 from Seanium/Seanium-patch-1
Seanium Mar 30, 2025
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: 8 additions & 8 deletions octis/dataset/dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,7 +119,7 @@ def _save_metadata(self, file_name):
else:
raise Exception("error in saving metadata")

def _load_metadata(self, file_name):
def _load_metadata(self, file_name, encoding='utf-8'):
"""
Loads metadata from json serialized format
Parameters
Expand All @@ -128,7 +128,7 @@ def _load_metadata(self, file_name):
"""
file = Path(file_name)
if file.is_file():
with open(file_name, 'r') as metadata_file:
with open(file_name, 'r', encoding=encoding) as metadata_file:
metadata = json.load(metadata_file)
self.__metadata = metadata

Expand Down Expand Up @@ -234,7 +234,7 @@ def _save_document_indexes(self, file_name):
for i in self.__original_indexes:
outfile.write(str(i) + "\n")

def _load_vocabulary(self, file_name):
def _load_vocabulary(self, file_name, encoding='utf-8'):
"""
Loads vocabulary from a file
Parameters
Expand All @@ -244,7 +244,7 @@ def _load_vocabulary(self, file_name):
vocabulary = []
file = Path(file_name)
if file.is_file():
with open(file_name, 'r') as vocabulary_file:
with open(file_name, 'r', encoding=encoding) as vocabulary_file:
for line in vocabulary_file:
vocabulary.append(line.strip())
self.__vocabulary = vocabulary
Expand Down Expand Up @@ -311,7 +311,7 @@ def save(self, path, multilabel=False):
except:
raise Exception("error in saving the dataset")

def load_custom_dataset_from_folder(self, path, multilabel=False):
def load_custom_dataset_from_folder(self, path, multilabel=False, encoding='utf-8'):
"""
Loads all the dataset from a folder
Parameters
Expand All @@ -321,11 +321,11 @@ def load_custom_dataset_from_folder(self, path, multilabel=False):
self.dataset_path = path
try:
if exists(self.dataset_path + "/metadata.json"):
self._load_metadata(self.dataset_path + "/metadata.json")
self._load_metadata(self.dataset_path + "/metadata.json", encoding=encoding)
else:
self.__metadata = dict()
df = pd.read_csv(
self.dataset_path + "/corpus.tsv", sep='\t', header=None)
self.dataset_path + "/corpus.tsv", sep='\t', header=None, encoding=encoding)
if len(df.keys()) > 1:
# just make sure docs are sorted in the right way (train - val - test)
final_df = pd.concat(
Expand All @@ -351,7 +351,7 @@ def load_custom_dataset_from_folder(self, path, multilabel=False):
self.__metadata['last-training-doc'] = len(df[0])

if exists(self.dataset_path + "/vocabulary.txt"):
self._load_vocabulary(self.dataset_path + "/vocabulary.txt")
self._load_vocabulary(self.dataset_path + "/vocabulary.txt", encoding=encoding)
else:
vocab = set()
for d in self.__corpus:
Expand Down