src/populate.py

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)
    for subset_name, subset_data in subsets.items():
        subset_df = subset_data.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