Spaces:
Runtime error
Runtime error
| 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 src.leaderboard.read_evals import get_raw_eval_results | |
| def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchmark_cols: list) -> pd.DataFrame: | |
| """Creates a dataframe from all the individual experiment results""" | |
| raw_data = get_raw_eval_results(results_path, requests_path) | |
| all_data_json = [v.to_dict() for v in raw_data] | |
| df = pd.DataFrame.from_records(all_data_json) | |
| present_benchmark_cols = [col for col in benchmark_cols if col in df.columns] | |
| if df.empty: | |
| return pd.DataFrame(columns=cols) | |
| # Ensure all expected columns exist so downstream operations never fail | |
| for column in cols: | |
| if column not in df.columns: | |
| df[column] = pd.NA | |
| average_col = AutoEvalColumn.average.name | |
| rank_col = AutoEvalColumn.rank.name | |
| if average_col not in df.columns: | |
| df[average_col] = pd.NA | |
| df[average_col] = pd.to_numeric(df[average_col], errors="coerce") | |
| if df[average_col].notna().any(): | |
| df = df.sort_values(by=[average_col], ascending=False, na_position="last") | |
| # Add ranking based on average score | |
| df[rank_col] = range(1, len(df) + 1) | |
| df = df[cols].round(decimals=2) | |
| # filter out if any of the benchmarks have not been produced | |
| if present_benchmark_cols: | |
| df = df[has_no_nan_values(df, present_benchmark_cols)] | |
| if df.empty: | |
| placeholder_df = pd.DataFrame(columns=cols) | |
| placeholder_df.loc[0] = {column: pd.NA for column in cols} | |
| placeholder_df.loc[0, rank_col] = "-" | |
| placeholder_df.loc[0, AutoEvalColumn.model.name] = "No completed evaluations yet" | |
| placeholder_df.loc[0, average_col] = pd.NA | |
| return placeholder_df | |
| return df.reset_index(drop=True) | |
| def get_evaluation_queue_df(save_path: str, cols: list) -> list[pd.DataFrame]: | |
| """Creates the different dataframes for the evaluation queues requestes""" | |
| entries = [entry for entry in os.listdir(save_path) if not entry.startswith(".")] | |
| all_evals = [] | |
| for entry in entries: | |
| if ".json" in entry: | |
| file_path = os.path.join(save_path, entry) | |
| with open(file_path) as fp: | |
| data = json.load(fp) | |
| data[EvalQueueColumn.model.name] = make_clickable_model(data["model"]) | |
| data[EvalQueueColumn.revision.name] = data.get("revision", "main") | |
| all_evals.append(data) | |
| elif ".md" not in entry: | |
| # this is a folder | |
| sub_entries = [e for e in os.listdir(f"{save_path}/{entry}") if os.path.isfile(e) and not e.startswith(".")] | |
| for sub_entry in sub_entries: | |
| file_path = os.path.join(save_path, entry, sub_entry) | |
| with open(file_path) as fp: | |
| data = json.load(fp) | |
| data[EvalQueueColumn.model.name] = make_clickable_model(data["model"]) | |
| data[EvalQueueColumn.revision.name] = data.get("revision", "main") | |
| all_evals.append(data) | |
| pending_list = [e for e in all_evals if e["status"] in ["PENDING", "RERUN"]] | |
| running_list = [e for e in all_evals if e["status"] == "RUNNING"] | |
| finished_list = [e for e in all_evals if e["status"].startswith("FINISHED") or e["status"] == "PENDING_NEW_EVAL"] | |
| df_pending = pd.DataFrame.from_records(pending_list, columns=cols) | |
| df_running = pd.DataFrame.from_records(running_list, columns=cols) | |
| df_finished = pd.DataFrame.from_records(finished_list, columns=cols) | |
| return df_finished[cols], df_running[cols], df_pending[cols] | |