core_leaderboard / scratch.py
benediktstroebl's picture
vis update
e24146f
raw
history blame
1.61 kB
import json
import os
from pathlib import Path
def process_json_files(directory, suffix="_updated"):
# Iterate through all JSON files in the directory
for filename in os.listdir(directory):
if filename.endswith(".json") and "USACO" in filename:
file_path = os.path.join(directory, filename)
# Read the JSON file
with open(file_path, 'r') as f:
data = json.load(f)
# Extract sdict from raw_eval_results
sdict = data['raw_eval_results']['sdict']
# Calculate successful_tasks and failed_tasks
successful_tasks = [key for key in sdict if float(sdict[key][0]['result']['fraction_passed']) == 1]
failed_tasks = [key for key in sdict if float(sdict[key][0]['result']['fraction_passed']) < 1]
# Add new key-value pairs to the results
data['results']['successful_tasks'] = successful_tasks
data['results']['failed_tasks'] = failed_tasks
# Create new filename with suffix
new_filename = f"{Path(filename).stem}{suffix}{Path(filename).suffix}"
new_file_path = os.path.join(directory, new_filename)
# Write updated data to new file
with open(new_file_path, 'w') as f:
json.dump(data, f, indent=4)
print(f"Processed {filename} and saved as {new_filename}")
# Usage
directory_path = "/Users/benediktstroebl/Documents/GitHub/leaderboard/evals_live"
process_json_files(directory_path)