Skip to content

Fixes for tasks 211 and 215 #49

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.

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
merged 2 commits into from
Feb 23, 2025
Merged
Changes from all commits
Commits
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
91 changes: 91 additions & 0 deletions tools/fix_v023.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,91 @@
from datasets import load_dataset, Dataset, DatasetDict
from huggingface_hub import HfApi

import json
import copy

BIGCODEBENCH_HF = "bigcode/bigcodebench"
BIGCODEBENCH_HARD_HF = "bigcode/bigcodebench-hard"
BIGCODEBENCH_VERSION = "v0.1.3"
BIGCODEBENCH_UPDATE = "bigcode/bcb_update"
BIGCODEBENCH_NEW_VERSION = "v0.1.4"

def map_ds(sample):
if sample["task_id"] in ["BigCodeBench/211"]:
sample['test'] = sample['test'].replace(
"""
mock_response = MagicMock()
mock_response.content = MOCK_CONTENT
""",
"""
mock_response = MagicMock()
mock_response.content = MOCK_CONTENT
mock_response.status_code = 200
"""
)
if sample["task_id"] in ["BigCodeBench/215"]:
sample['test'] = sample['test'].replace(
"""
mock_response = Mock()
""",
"""
mock_response = Mock()
mock_response.status_code = 200
"""
)
sample['test'] = sample['test'].replace(
"""
mock_response.text =""",
"""
MOCK_TEXT ="""
)
sample['test'] = sample['test'].replace(
"""
mock_get.return_value = mock_response
""",
"""
mock_response.text = MOCK_TEXT
mock_response.json = lambda: json.loads(MOCK_TEXT)
mock_get.return_value = mock_response
"""
)
sample['complete_prompt'] = sample['complete_prompt'].replace("Thif function will raise", "This function will raise")
sample['instruct_prompt'] = sample['instruct_prompt'].replace("Thif function will raise", "This function will raise")
sample['doc_struct'] = sample['doc_struct'].replace("Thif function will raise", "This function will raise")
return sample

if __name__ == "__main__":
api = HfApi()
ds_dict = load_dataset(BIGCODEBENCH_HF)
hard_ds_dict = load_dataset(BIGCODEBENCH_HARD_HF)
ds = ds_dict[BIGCODEBENCH_VERSION]
hard_ds = hard_ds_dict[BIGCODEBENCH_VERSION]
function_id = [211, 215]

new_ds = ds.map(map_ds)
new_ds.to_json("BigCodeBench.jsonl")
ds_dict[BIGCODEBENCH_NEW_VERSION] = new_ds
ds_dict.push_to_hub(BIGCODEBENCH_HF)

new_hard_ds = hard_ds.map(map_ds)
new_hard_ds.to_json("BigCodeBench-Hard.jsonl")
hard_ds_dict[BIGCODEBENCH_NEW_VERSION] = new_hard_ds
hard_ds_dict.push_to_hub(BIGCODEBENCH_HARD_HF)

for i in function_id:
old_sample = ds.select([i])
new_sample = new_ds.select([i])
old_sample.to_json("old.jsonl")
new_sample.to_json("new.jsonl")
api.upload_file(
path_or_fileobj="old.jsonl",
path_in_repo=f"{i}/old.jsonl",
repo_id=BIGCODEBENCH_UPDATE,
# repo_type="dataset"
)
api.upload_file(
path_or_fileobj="new.jsonl",
path_in_repo=f"{i}/new.jsonl",
repo_id=BIGCODEBENCH_UPDATE,
# repo_type="dataset"
)