pushed changes app.py

app.py

@@ -536,7 +536,47 @@ columns = list(initial_df.columns)
 
 # --- Gradio App ---
 with gr.Blocks() as demo:
-    gr.Markdown("## Dataset Insight Portal")
+    gr.Markdown("""
+    # Dataset Insight Portal
+    Welcome! This portal helps you explore and manage datasets from our Hugging Face organization.
+    ## What is this space for?
+    This space provides a table of datasets along with metadata. You can:
+    - Browse datasets with pagination.
+    - Search datasets by various fields.
+    - Assign responsibility for reviewing datasets (`assigned_to`).
+    - Track progress using `status`.
+    ## Why the table?
+    The table gives a structured view of all datasets, making it easy to sort, filter, and update information for each dataset. It consists of all datasets until 20-09-2025. 
+    ## What does the table contain?
+    Each row represents a dataset. Columns include:
+    - **dataset_id**: Unique identifier of the dataset.
+    - **dataset_url**: Link to the dataset page on Hugging Face.
+    - **downloads**: Number of downloads.
+    - **author**: Dataset author.
+    - **license**: License type.
+    - **tags**: Tags describing the dataset. Obtained from the dataset card.
+    - **task_categories**: Categories of tasks the dataset is useful for. Obtained from the dataset card.
+    - **last_modified**: Date of last update.
+    - **field, keyword**: Metadata columns describing dataset purpose based on heuristics. Use the `field` and `keyword` to filter for science based datasets.
+    - **category**: Category of the dataset (`rich` means it is good dataset card. `minimal` means it needs improvement for the reasons below).
+    - **reason**: Reason why the dataset is classified as `minimal`. Options: `Failed to load card`, `No metadata and no description`, `No metadata and has description`, `Short description`.
+    - **usedStorage**: Storage used by the dataset (bytes).
+    - **assigned_to**: Person responsible for the dataset (editable).
+    - **status**: Progress status (editable). Options: `todo`, `inprogress`, `PR submitted`, `PR merged`.
+    ## How to use search
+    - Select a **column** from the dropdown.
+    - If the column is textual, type your query in the text box.
+    - If the column is a dropdown (like `assigned_to` or `status`), select the value from the dropdown.
+    - Click **Search** to filter the table.
+    ## How to add or update `assigned_to` and `status`
+    1. Search for the **dataset_id** initially.
+    2. Then, select the **dataset_id** from the dropdown below the table.
+    3. Choose the person responsible in **Assigned To**. If you are a member of the organization, your username should appear in the list. Else refresh and try again.
+    4. Select the current status in **Status**.
+    5. Click **Save Changes** to update the table and persist the changes.
+    6. Use **Refresh All** to reload the table and the latest members list.
+    This portal makes it easy to keep track of dataset reviews, assignments, and progress all in one place.
+    """)
 
     # Pagination
     with gr.Row():
@@ -652,7 +692,7 @@ with gr.Blocks() as demo:
     )
 
 # --- Auto-push ---
-def auto_push_loop(interval=300):
+def auto_push_loop(interval=3600):
     while True:
         try:
             hf_token = os.environ.get("HF_TOKEN")
@@ -674,5 +714,5 @@ def auto_push_loop(interval=300):
             print("⚠️ Push failed:", e)
         time.sleep(interval)
 
-threading.Thread(target=auto_push_loop, args=(300,), daemon=True).start()
+threading.Thread(target=auto_push_loop, args=(3600,), daemon=True).start()
 demo.launch()

datasetcards_new.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc6f8cbcec66be439c4824865f51129d42c538c2554cad2e87ccd6b7c489c8ba
-size 27585820
+oid sha256:b0d3770a3024eaf459d5c12d2c4a9d0d5a5043660d0a15c062a387595602eacf
+size 38347730