src/leaderboard/load_results.py

import pandas as pd

def load_data(data_path):
    df = pd.read_csv(data_path, skiprows=1, header=0).dropna()

    columns = ['Model', 'type', 'open?', 'shot', 'en', 'zh', 'id', 'th', 'vi', 'avg', 'avg_sea']
    
    # Splitting into three separate DataFrames based on the groups M3Exam and MMLU and average
    df_m3exam = df.iloc[:, :11]  # M3Exam columns
    df_mmlu = df.iloc[:, [0, 1, 2, 3, 11, 12, 13, 14, 15, 16, 17]]  # MMLU columns
    df_avg = df.iloc[:, [0, 1, 2, 3, 18, 19, 20, 21, 22, 23, 24]]  # Average columns
    df_mmlu.columns = columns
    df_avg.columns = columns

    # # multiply the values in the ['en', 'zh', 'id', 'th', 'vi', 'avg', 'avg_sea'] by 100 and display as 1 decimal
    for df_tmp in [df_m3exam, df_mmlu, df_avg]:
        df_tmp[['en', 'zh', 'id', 'th', 'vi', 'avg', 'avg_sea']] *= 100
        df_tmp[['en', 'zh', 'id', 'th', 'vi', 'avg', 'avg_sea']] = df_tmp[['en', 'zh', 'id', 'th', 'vi', 'avg', 'avg_sea']].round(2)
        df_tmp['rank'] = df_tmp['avg'].rank(ascending=False).astype(int)
        
    # change the order of the columns to ['Model', 'type', 'open?', 'shot', 'avg', 'avg_sea', 'en', 'zh', 'id', 'th', 'vi'] 
    # and sort the columns by 'avg' in descending order
    columns_sorted = ['rank','type', 'Model', 'open?', 'shot', 'avg', 'avg_sea', 'en', 'zh', 'id', 'th', 'vi']
    df_m3exam = df_m3exam[columns_sorted].sort_values(by='avg', ascending=False)
    df_mmlu = df_mmlu[columns_sorted].sort_values(by='avg', ascending=False)
    df_avg = df_avg[columns_sorted].sort_values(by='avg', ascending=False)

    # change the column name from 'avg' to 'avg⬆️'
    df_m3exam = df_m3exam.rename(columns={'avg': 'avg⬆️'})
    df_mmlu = df_mmlu.rename(columns={'avg': 'avg⬆️'})
    df_avg = df_avg.rename(columns={'avg': 'avg⬆️'})

    # map the values in the 'type' column to the following values: {'base': 'Base', 'chat': 'Chat'}
    df_m3exam['type'] = df_m3exam['type'].map({'base': '🟢', 'chat': '🔶'})
    df_mmlu['type'] = df_mmlu['type'].map({'base': '🟢', 'chat': '🔶'})
    df_avg['type'] = df_avg['type'].map({'base': '🟢', 'chat': '🔶'})
    
    return df_m3exam, df_mmlu, df_avg