from datasets import Dataset
from huggingface_hub import HfApi, login
import json

# Initialize the dataset with a sample entry
initial_data = {
    "model_id": ["example/model"],
    "revision": ["main"],
    "precision": ["fp16"],
    "security_score": [0.5],
    "safetensors_compliant": [True]
}

# Create a Dataset object
dataset = Dataset.from_dict(initial_data)

# Login to Hugging Face (you'll need to set the HUGGINGFACE_TOKEN environment variable)
login()

# Push the dataset to the Hugging Face Hub
dataset.push_to_hub("stacklok/results")

# Create a dataset card
dataset_card = """
---
language:
- en
license:
- mit
---

# Dataset Card for stacklok/results

This dataset contains evaluation results for various models, focusing on security scores and other relevant metrics.

## Dataset Structure

The dataset contains the following fields:
- `model_id`: The identifier of the model
- `revision`: The revision or version of the model
- `precision`: The precision used for the model (e.g., fp16, fp32)
- `security_score`: A score representing the model's security evaluation
- `safetensors_compliant`: A boolean indicating whether the model is compliant with safetensors

## Usage

This dataset is used to populate the secure code leaderboard, providing insights into the security aspects of various models.
"""

# Write the dataset card
with open("README.md", "w") as f:
    f.write(dataset_card)

# Upload the dataset card
api = HfApi()
api.upload_file(
    path_or_fileobj="README.md",
    path_in_repo="README.md",
    repo_id="stacklok/results",
    repo_type="dataset"
)

print("Dataset initialized and card uploaded successfully!")