import pandas as pd
import gradio as gr
import csv
import json
import os
import shutil
from huggingface_hub import Repository

HF_TOKEN = os.environ.get("HUGGINGFACE_TOKEN")

MODEL_INFO = [
    "Model",
    "Avg",
    "Visual Quality",
    "Temporal Consistency",
    "Dynamic Degree",
    "Text-to-Video Alignment",
    ]

DATA_TITILE_TYPE = ['markdown', 'number', 'number', 'number', 'number', 'number',]

SUBMISSION_NAME = "VideoScore-Leaderboard"
SUBMISSION_URL = os.path.join("https://huggingface.co/datasets/hexuan21/", SUBMISSION_NAME)
CSV_DIR = "./VideoScore-Leaderboard/results.csv"

COLUMN_NAMES = MODEL_INFO

LEADERBORAD_INTRODUCTION = """# VideoScore Leaderboard
    
    """

TABLE_INTRODUCTION = """
    """

LEADERBORAD_INFO = """
We list the information of the used datasets as follows:<br>

"""

CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""@inproceedings{hendrycks2021measuring,
  title={Measuring Mathematical Problem Solving With the MATH Dataset},
  author={Hendrycks, Dan and Burns, Collin and Kadavath, Saurav and Arora, Akul and Basart, Steven and Tang, Eric and Song, Dawn and Steinhardt, Jacob},
  booktitle={Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)},
  year={2021}
}
}"""

SUBMIT_INTRODUCTION = """# Submit on Science Leaderboard Introduction

## ⚠ Please note that you need to submit the json file with following format:

```json
{
    "Model": "[NAME]",
    "Repo": "https://huggingface.co/[MODEL_NAME]"
    "TheoremQA": 50,
    "MATH": 50,
    "GSM": 50,
    "GPQA": 50,
    "MMLU-STEM": 50
}
```
After submitting, you can click the "Refresh" button to see the updated leaderboard(it may takes few seconds).

"""

def get_df():
    repo = Repository(local_dir=SUBMISSION_NAME, clone_from=SUBMISSION_URL, use_auth_token=HF_TOKEN)
    repo.git_pull()
    df = pd.read_csv(CSV_DIR)
    df['Model'] = df['Model'].apply(lambda x: f"[{x.split(']')[0][1:]}]({x.split('(')[1][:-1]})")
    df['Avg'] = df[["Visual Quality",
    "Temporal Consistency",
    "Dynamic Degree",
    "Text-to-Video Alignment",]].mean(axis=1).round(2)
    df = df.sort_values(by=['Avg'], ascending=False)
    return df[COLUMN_NAMES]


def refresh_data():
    return get_df()