Update app.py

app.py

@@ -29,6 +29,11 @@ def load_models_data():
         else:
             # If 'params' column doesn't exist, assume all are unknown
             df['params'] = -1
+        
+        # NEW: Ensure createdAt is in datetime format, coercing errors
+        if 'createdAt' in df.columns:
+            df['createdAt'] = pd.to_datetime(df['createdAt'], errors='coerce')
+
         msg = f"Successfully loaded dataset in {time.time() - overall_start_time:.2f}s."
         print(msg)
         return df, True, msg
@@ -43,7 +48,7 @@ def get_param_range_values(param_range_labels):
     max_val = float('inf') if '>' in max_label else float(max_label.replace('B', ''))
     return min_val, max_val
 
-def make_treemap_data(df, count_by, top_k=25, tag_filter=None, pipeline_filter=None, param_range=None, skip_orgs=None, include_unknown_param_size=True):
+def make_treemap_data(df, count_by, top_k=25, tag_filter=None, pipeline_filter=None, param_range=None, skip_orgs=None, include_unknown_param_size=True, created_after_date=None): # ADDED created_after_date
     if df is None or df.empty: return pd.DataFrame()
     filtered_df = df.copy()
 
@@ -66,6 +71,12 @@ def make_treemap_data(df, count_by, top_k=25, tag_filter=None, pipeline_filter=N
             if min_params is not None: filtered_df = filtered_df[filtered_df['params'] >= min_params]
             if max_params is not None and max_params != float('inf'): filtered_df = filtered_df[filtered_df['params'] < max_params]
 
+    # NEW: Filter by creation date
+    if created_after_date is not None and 'createdAt' in filtered_df.columns:
+        # The 'createdAt' column should already be datetime from the loading function
+        # We also convert the input date to ensure timezone consistency (or lack thereof)
+        filtered_df = filtered_df[filtered_df['createdAt'] > pd.to_datetime(created_after_date)]
+
     if skip_orgs and len(skip_orgs) > 0 and "organization" in filtered_df.columns:
         filtered_df = filtered_df[~filtered_df["organization"].isin(skip_orgs)]
     if filtered_df.empty: return pd.DataFrame()
@@ -144,6 +155,9 @@ with gr.Blocks(title="🤗 ModelVerse Explorer", fill_width=True, css=custom_css
                 include_unknown_params_checkbox = gr.Checkbox(label="Include models with unknown parameter size", value=True)
             
             # This section remains un-grouped
+            # NEW: Date picker for filtering by creation date
+            created_after_datepicker = gr.DatePicker(label="Created After", value=None)
+            
             top_k_dropdown = gr.Dropdown(label="Number of Top Organizations", choices=TOP_K_CHOICES, value=25)
             skip_orgs_textbox = gr.Textbox(label="Organizations to Skip (comma-separated)", value="TheBloke,MaziyarPanahi,unsloth,modularai,Gensyn,bartowski")
             
@@ -222,20 +236,24 @@ with gr.Blocks(title="🤗 ModelVerse Explorer", fill_width=True, css=custom_css
         default_param_indices = PARAM_CHOICES_DEFAULT_INDICES
         default_k = 25
         default_skip_orgs = "TheBloke,MaziyarPanahi,unsloth,modularai,Gensyn,bartowski"
-        # New default: include unknown params initially (matches checkbox default)
-        default_include_unknown_params = True 
+        default_include_unknown_params = True
+        default_created_after_date = None # NEW: Default for date picker is no filter
 
         # Reuse the existing controller function for plotting
         initial_plot, initial_status = ui_generate_plot_controller(
             default_metric, default_filter_type, default_tag, default_pipeline, 
-            default_param_indices, default_k, default_skip_orgs, default_include_unknown_params, current_df, progress
+            default_param_indices, default_k, default_skip_orgs, default_include_unknown_params,
+            default_created_after_date, # Pass new default date
+            current_df, progress
         )
         
         # Return all the necessary updates for the UI
         return current_df, load_success_flag, data_info_text, initial_status, initial_plot
 
     def ui_generate_plot_controller(metric_choice, filter_type, tag_choice, pipeline_choice, 
-                                   param_range_indices, k_orgs, skip_orgs_input, include_unknown_param_size_flag, df_current_models, progress=gr.Progress()):
+                                   param_range_indices, k_orgs, skip_orgs_input, include_unknown_param_size_flag,
+                                   created_after_date, # ADDED created_after_date
+                                   df_current_models, progress=gr.Progress()):
         if df_current_models is None or df_current_models.empty:
             return create_treemap(pd.DataFrame(), metric_choice, "Error: Model Data Not Loaded"), "Model data is not loaded. Cannot generate plot."
         
@@ -256,7 +274,8 @@ with gr.Blocks(title="🤗 ModelVerse Explorer", fill_width=True, css=custom_css
             pipeline_to_use, 
             param_labels_for_filtering, 
             orgs_to_skip, 
-            include_unknown_param_size_flag # Pass the new flag
+            include_unknown_param_size_flag,
+            created_after_date # Pass the new date filter value
         )
         
         progress(0.7, desc="Generating plot...")
@@ -281,8 +300,12 @@ with gr.Blocks(title="🤗 ModelVerse Explorer", fill_width=True, css=custom_css
 
     generate_plot_button.click(
         fn=ui_generate_plot_controller,
-        inputs=[count_by_dropdown, filter_choice_radio, tag_filter_dropdown, pipeline_filter_dropdown,
-                param_range_slider, top_k_dropdown, skip_orgs_textbox, include_unknown_params_checkbox, models_data_state], # Add checkbox to inputs
+        inputs=[
+            count_by_dropdown, filter_choice_radio, tag_filter_dropdown, pipeline_filter_dropdown,
+            param_range_slider, top_k_dropdown, skip_orgs_textbox, include_unknown_params_checkbox,
+            created_after_datepicker, # ADDED date picker to inputs
+            models_data_state
+        ],
         outputs=[plot_output, status_message_md]
     )