add dataset selection

app.py

@@ -0,0 +1,66 @@
+import gradio as gr
+import requests
+from huggingface_hub import HfApi
+
+session = requests.Session()
+
+css = """
+@media (prefers-color-scheme: dark) {
+    .transparent-dropdown, .transparent-dropdown .container .wrap  {
+        background: var(--bg-dark);
+    }
+}
+@media (prefers-color-scheme: light) {
+    .transparent-dropdown, .transparent-dropdown .container .wrap  {
+        background: var(--bg);
+    }
+}
+"""
+
+with gr.Blocks(css=css) as demo:
+    with gr.Row():
+        with gr.Column(scale=4):
+            with gr.Group():
+                dataset_dropdown = gr.Dropdown(label="Dataset", allow_custom_value=True, interactive=True)
+                with gr.Row():
+                    subset_dropdown = gr.Dropdown(info="Subset", show_label=False, visible=False, elem_classes="transparent-dropdown")
+                    split_dropdown = gr.Dropdown(info="Split", show_label=False, visible=False, elem_classes="transparent-dropdown")
+        gr.LoginButton()
+    loading_codes_json = gr.JSON(visible=False)
+    dataset_subset_split_textbox = gr.Textbox(visible=False)
+    dataframe = gr.DataFrame()
+
+    @demo.load(outputs=dataset_dropdown)
+    def fetch_datasets(request: gr.Request, oauth_token: gr.OAuthToken | None):
+        api = HfApi(token=oauth_token.token if oauth_token else None)
+        datasets = list(api.list_datasets(limit=3, sort="trendingScore", direction=-1, filter=["format:parquet"]))
+        if oauth_token and (user := api.whoami().get("user")):
+            datasets += list(api.list_datasets(limit=3, sort="trendingScore", direction=-1, filter=["format:parquet"], author=user))
+        dataset = request.query_params.get("dataset") or datasets[0].id
+        return {dataset_dropdown: gr.Dropdown(choices=[dataset.id for dataset in datasets], value=dataset)}
+
+    @dataset_dropdown.change(inputs=dataset_dropdown, outputs=loading_codes_json)
+    def fetch_read_parquet_loading(dataset: str):
+        if "/" not in dataset.strip().strip("/"):
+            return []
+        resp = session.get(f"https://datasets-server.huggingface.co/compatible-libraries?dataset={dataset}", timeout=3).json()
+        return ([lib["loading_codes"] for lib in resp.get("libraries", []) if lib["function"] == "dd.read_parquet"] or [[]])[0] or []
+
+    @loading_codes_json.change(inputs=loading_codes_json, outputs=[subset_dropdown, split_dropdown])
+    def show_subset_dropdown(loading_codes: list[dict]):
+        subsets = [loading_code["config_name"] for loading_code in loading_codes]
+        subset = (subsets or [""])[0]
+        splits = ([list(loading_code["arguments"]["splits"]) for loading_code in loading_codes if loading_code["config_name"] == subset] or [[]])[0]
+        split = (splits or [""])[0]
+        return gr.Dropdown(subsets, value=subset, visible=len(subsets) > 1), gr.Dropdown(splits, value=split, visible=len(splits) > 1)
+
+    @subset_dropdown.change(inputs=[loading_codes_json, subset_dropdown], outputs=split_dropdown)
+    def show_split_dropdown(loading_codes: list[dict], subset: str):
+        splits = ([list(loading_code["arguments"]["splits"]) for loading_code in loading_codes if loading_code["config_name"] == subset] or [[]])[0]
+        split = (splits or [""])[0]
+        return gr.Dropdown(splits, value=split, visible=len(splits) > 1)
+        
+
+
+if __name__ == "__main__":
+    demo.launch()