LiveBench / src /populate.py
pufanyi's picture
chore: Refactor get_leaderboard_df to handle multiple subsets in populate.py
88477a4
raw
history blame
750 Bytes
import json
import os
import pandas as pd
from src.display.formatting import has_no_nan_values, make_clickable_model
from src.display.utils import AutoEvalColumn, EvalQueueColumn
from datasets import load_dataset
def get_leaderboard_df(results_repo, results_path):
subsets = load_dataset(results_repo, split='all', cache_dir=results_path)
subset_dfs = {}
print("Subsets:", subsets.keys())
for subset_name in subsets.keys():
subset_df = subsets[subset_name].to_pandas()
subset_df = subset_df.sort_values(by="Total", ascending=False)
subset_df = subset_df.round(2) # Round all numeric columns to two decimal places
print(subset_df)
subset_dfs[subset_name] = subset_df
return subset_dfs