utils.py

import json
import os
from datetime import datetime

import pandas as pd
from huggingface_hub import HfApi

API = HfApi()

SUBMISSIONS_REPO = "isic-archive/ISIC2024_submissions"  # private
RESULTS_REPO = "isic-archive/ISIC2024_results"           # public or private

# Use your HF token (set as a Space secret)
HF_TOKEN = os.environ.get("ISIC2024_ACCESS_TOKEN")


def submit_prediction(model_name: str, predictions_file) -> str:
    """Upload a submission to the submissions dataset."""
    timestamp = datetime.now().isoformat()
    submission_id = f"{model_name}_{timestamp}".replace(" ", "_")

    # Upload the predictions file
    API.upload_file(
        path_or_fileobj=predictions_file.name,
        path_in_repo=f"predictions/{submission_id}.jsonl",
        repo_id=SUBMISSIONS_REPO,
        repo_type="dataset",
        token=HF_TOKEN,
    )

    # Upload a metadata record
    metadata = {
        "model_name": model_name,
        "submitted_by": "user",  # could use HF OAuth here
        "submission_time": timestamp,
        "predictions_file": f"predictions/{submission_id}.jsonl",
    }
    metadata_bytes = json.dumps(metadata).encode()
    API.upload_file(
        path_or_fileobj=metadata_bytes,
        path_in_repo=f"metadata/{submission_id}.json",
        repo_id=SUBMISSIONS_REPO,
        repo_type="dataset",
        token=HF_TOKEN,
    )

    return f"Submitted! Your submission ID is `{submission_id}`. Results will appear on the leaderboard once evaluation is complete."


def load_results() -> pd.DataFrame:
    """Load the latest results from the results dataset."""
    try:
        from datasets import load_dataset
        ds = load_dataset(RESULTS_REPO, token=HF_TOKEN)
        df = ds["train"].to_pandas()
        # Sort by score descending
        df = df.sort_values("overall_score", ascending=False).reset_index(drop=True)
        return df
    except Exception:
        return pd.DataFrame(columns=["model_name", "overall_score"])