Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from gradio_huggingfacehub_search import HuggingfaceHubSearch | |
| import nbformat as nbf | |
| from huggingface_hub import HfApi | |
| """ | |
| TODOs: | |
| - Handle erros | |
| - Add more commands to the notebook | |
| - Parametrize the commands | |
| - How to handle configs and splits? | |
| - Let user choose the framework | |
| - Improve logs | |
| """ | |
| def create_notebook_file(cell_commands, notebook_name="generated_notebook.ipynb"): | |
| nb = nbf.v4.new_notebook() | |
| nb["cells"] = [nbf.v4.new_code_cell(command) for command in cell_commands] | |
| with open(notebook_name, "w") as f: | |
| nbf.write(nb, f) | |
| print(f"Notebook '{notebook_name}' created successfully.") | |
| def push_notebook(file_path, dataset_id, token): | |
| notebook_name = "dataset_analysis.ipynb" | |
| api = HfApi(token=token) | |
| api.upload_file( | |
| path_or_fileobj=file_path, | |
| path_in_repo=notebook_name, | |
| repo_id=dataset_id, | |
| repo_type="dataset", | |
| ) | |
| print("Notebook uploaded to Huggingface Hub.") | |
| link = f"https://huggingface.co/datasets/{dataset_id}/blob/main/{notebook_name}" | |
| html = f'<a target="_blank" href="{link}" style="color: var(--link-text-color); text-decoration: underline; text-decoration-style: dotted;">See notebook</a>' | |
| return gr.HTML(value=html, visible=True) | |
| def generate_notebook(dataset_id): | |
| commands = [ | |
| "!pip install pandas", | |
| "import pandas as pd", | |
| f"df = pd.read_parquet('hf://datasets/{dataset_id}/data/train-00000-of-00001.parquet')", | |
| "df.head()", | |
| ] | |
| notebook_name = f"{dataset_id.replace('/', '-')}.ipynb" | |
| create_notebook_file(commands, notebook_name=notebook_name) | |
| return gr.File(value=notebook_name, visible=True), gr.Row.update(visible=True) | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# 🤖 Dataset auto analyst creator 🕵️") | |
| dataset_name = HuggingfaceHubSearch( | |
| label="Hub Dataset ID", | |
| placeholder="Search for dataset id on Huggingface", | |
| search_type="dataset", | |
| value="", | |
| ) | |
| def embed(name): | |
| if not name: | |
| return gr.Markdown("### No dataset provided") | |
| html_code = f""" | |
| <iframe | |
| src="https://huggingface.co/datasets/{name}/embed/viewer/default/train" | |
| frameborder="0" | |
| width="100%" | |
| height="350px" | |
| ></iframe> | |
| """ | |
| return gr.HTML(value=html_code) | |
| generate_btn = gr.Button("Generate notebook") | |
| download_link = gr.File(label="Download notebook", visible=False) | |
| with gr.Row(visible=False) as auth_page: | |
| with gr.Column(): | |
| auth_title = gr.Markdown( | |
| "Want to push to hub? Enter your token ([settings](https://huggingface.co/settings/tokens)):" | |
| ) | |
| token_box = gr.Textbox( | |
| "", label="token", placeholder="hf_xxx", type="password" | |
| ) | |
| auth_error = gr.Markdown("", visible=False) | |
| push_btn = gr.Button("Push notebook to hub", visible=False) | |
| output_lbl = gr.HTML(value="", visible=False) | |
| generate_btn.click( | |
| generate_notebook, | |
| inputs=[dataset_name], | |
| outputs=[download_link, auth_page], | |
| ) | |
| def auth(token): | |
| if not token: | |
| return { | |
| auth_error: gr.Markdown(value="", visible=False), | |
| push_btn: gr.Button(visible=False), | |
| } | |
| return { | |
| auth_error: gr.Markdown(value="", visible=False), | |
| push_btn: gr.Button("Push notebook to hub", visible=True), | |
| } | |
| token_box.change( | |
| auth, | |
| inputs=token_box, | |
| outputs=[auth_error, push_btn], | |
| ) | |
| push_btn.click( | |
| push_notebook, | |
| inputs=[download_link, dataset_name, token_box], | |
| outputs=output_lbl, | |
| ) | |
| demo.launch() | |