add card data

app.py

@@ -4,6 +4,7 @@ import gradio as gr
 import pandas as pd
 from datasets import ClassLabel, Dataset, Image
 from httpx import Client
+from huggingface_hub import DatasetCard
 
 client = Client()
 USER_DATA = {}
@@ -42,6 +43,31 @@ def check_user_data():
 #     return pd.read_csv(StringIO(resp.text)).columns.tolist()
 
 
+def convert_value(value: int) -> str:
+    if value < 1_000:
+        return "n<1K"
+    elif value < 10_000:
+        return "1K<n<10K"
+    elif value < 100_000:
+        return "10K<n<100K"
+    elif value < 1_000_000:
+        return "100K<n<1M"
+    elif value < 10_000_000:
+        return "1M<n<10M"
+    elif value < 100_000_000:
+        return "10M<n<100M"
+    elif value < 1_000_000_000:
+        return "100M<n<1B"
+    elif value < 10_000_000_000:
+        return "1B<n<10B"
+    elif value < 100_000_000_000:
+        return "10B<n<100B"
+    elif value < 1_000_000_000_000:
+        return "100B<n<1T"
+    else:
+        return "n>1T"
+
+
 def push_annotations_to_hub(project_id, input_column, input_column_type, label_column):
     headers = {"Authorization": f'Token {USER_DATA["api_key"]}'}
     resp = client.get(
@@ -56,6 +82,10 @@ def push_annotations_to_hub(project_id, input_column, input_column_type, label_c
     if input_column_type == "image":
         ds = ds.cast_column(input_column, Image())
     ds.push_to_hub(USER_DATA["hub_dataset_id"], token=USER_DATA["hub_api_key"])
+    card = DatasetCard.load(USER_DATA["hub_dataset_id"])
+    card.data.tags = ["label-studio-exported"]
+    card.data.size_categories = [convert_value(len(ds))]
+    card.push_to_hub(USER_DATA["hub_dataset_id"], repo_type="dataset")
     return ds.to_pandas().head(5)