Adding draft

app.py

@@ -0,0 +1,63 @@
+import gradio as gr
+from gradio_huggingfacehub_search import HuggingfaceHubSearch
+import nbformat as nbf
+from huggingface_hub import HfApi
+
+api = HfApi()
+
+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 generate_notebook(dataset_id):
+    commands = [
+        f"from datasets import load_dataset",
+        f"dataset = load_dataset('{dataset_id}')",
+        f"dataset",
+    ]
+    notebook_name = f"{dataset_id.replace('/', '-')}.ipynb"
+    create_notebook_file(commands, notebook_name=notebook_name)
+    api.upload_file(
+        path_or_fileobj=notebook_name,
+        path_in_repo="dataset_analysis.ipynb",
+        repo_id="asoria/en-text",
+        repo_type="dataset",
+    )
+    print("Notebook uploaded to Huggingface Hub.")
+    link = f"https://huggingface.co/datasets/{dataset_id}/blob/main/dataset_analyst.ipynb"
+    return f'<a target="_blank" href="{link}"  style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">See notebook</a>'
+
+
+
+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="",
+        )
+
+    @gr.render(inputs=dataset_name)
+    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="600px"
+        ></iframe>
+            """
+        return gr.HTML(value=html_code)
+
+    generate_btn = gr.Button("Generate notebook")
+    output_lbl = gr.HTML(value="")
+    generate_btn.click(generate_notebook, inputs=[dataset_name], outputs=[output_lbl])
+demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio_huggingfacehub_search==0.0.7
+huggingface_hub
+nbformat