Update app.py

app.py

@@ -1,15 +1,18 @@
-# --- START OF FULLY CORRECTED AND IMPROVED FILE app.py ---
+# --- START OF FINAL POLISHED FILE app.py ---
 
 import gradio as gr
 import pandas as pd
 import plotly.express as px
 import time
-from datasets import load_dataset # Import the datasets library
+from datasets import load_dataset
 
 # --- Constants ---
 PARAM_CHOICES = ['< 1B', '1B', '5B', '12B', '32B', '64B', '128B', '256B', '> 500B']
 PARAM_CHOICES_DEFAULT_INDICES = [0, len(PARAM_CHOICES) - 1]
 
+# --- NEW: Define choices for the Top-K dropdown ---
+TOP_K_CHOICES = list(range(5, 51, 5))
+
 HF_DATASET_ID = "evijit/orgstats_daily_data"
 TAG_FILTER_CHOICES = [ "Audio & Speech", "Time series", "Robotics", "Music", "Video", "Images", "Text", "Biomedical", "Sciences" ]
 PIPELINE_TAGS = [ 'text-generation', 'text-to-image', 'text-classification', 'text2text-generation', 'audio-to-audio', 'feature-extraction', 'image-classification', 'translation', 'reinforcement-learning', 'fill-mask', 'text-to-speech', 'automatic-speech-recognition', 'image-text-to-text', 'token-classification', 'sentence-similarity', 'question-answering', 'image-feature-extraction', 'summarization', 'zero-shot-image-classification', 'object-detection', 'image-segmentation', 'image-to-image', 'image-to-text', 'audio-classification', 'visual-question-answering', 'text-to-video', 'zero-shot-classification', 'depth-estimation', 'text-ranking', 'image-to-video', 'multiple-choice', 'unconditional-image-generation', 'video-classification', 'text-to-audio', 'time-series-forecasting', 'any-to-any', 'video-text-to-text', 'table-question-answering' ]
@@ -17,18 +20,12 @@ PIPELINE_TAGS = [ 'text-generation', 'text-to-image', 'text-classification', 'te
 def load_models_data():
     overall_start_time = time.time()
     print(f"Attempting to load dataset from Hugging Face Hub: {HF_DATASET_ID}")
-    expected_cols = [ 'id', 'downloads', 'downloadsAllTime', 'likes', 'pipeline_tag', 'tags', 'params', 'organization', 'has_audio', 'has_speech', 'has_music', 'has_robot', 'has_bio', 'has_med', 'has_series', 'has_video', 'has_image', 'has_text', 'has_science', 'is_audio_speech', 'is_biomed', 'data_download_timestamp' ]
     try:
         dataset_dict = load_dataset(HF_DATASET_ID)
         if not dataset_dict: raise ValueError(f"Dataset '{HF_DATASET_ID}' loaded but appears empty.")
         split_name = list(dataset_dict.keys())[0]
-        print(f"Using dataset split: '{split_name}'. Converting to Pandas.")
         df = dataset_dict[split_name].to_pandas()
         elapsed = time.time() - overall_start_time
-        missing_cols = [col for col in expected_cols if col not in df.columns]
-        if missing_cols:
-            if 'params' in missing_cols: raise ValueError(f"FATAL: Loaded dataset is missing the crucial 'params' column.")
-            print(f"Warning: Loaded dataset is missing some expected columns: {missing_cols}.")
         if 'params' in df.columns:
             df['params'] = pd.to_numeric(df['params'], errors='coerce').fillna(0)
         else:
@@ -53,33 +50,25 @@ def make_treemap_data(df, count_by, top_k=25, tag_filter=None, pipeline_filter=N
     if df is None or df.empty: return pd.DataFrame()
     filtered_df = df.copy()
     col_map = { "Audio & Speech": "is_audio_speech", "Music": "has_music", "Robotics": "has_robot", "Biomedical": "is_biomed", "Time series": "has_series", "Sciences": "has_science", "Video": "has_video", "Images": "has_image", "Text": "has_text" }
-    if tag_filter and tag_filter in col_map:
-        target_col = col_map[tag_filter]
-        if target_col in filtered_df.columns: filtered_df = filtered_df[filtered_df[target_col]]
-        else: print(f"Warning: Tag filter column '{col_map[tag_filter]}' not found in DataFrame.")
-    if pipeline_filter:
-        if "pipeline_tag" in filtered_df.columns: filtered_df = filtered_df[filtered_df["pipeline_tag"].astype(str) == pipeline_filter]
-        else: print(f"Warning: 'pipeline_tag' column not found for filtering.")
+    if tag_filter and tag_filter in col_map and col_map[tag_filter] in filtered_df.columns:
+        filtered_df = filtered_df[filtered_df[col_map[tag_filter]]]
+    if pipeline_filter and "pipeline_tag" in filtered_df.columns:
+        filtered_df = filtered_df[filtered_df["pipeline_tag"].astype(str) == pipeline_filter]
     if param_range:
         min_params, max_params = get_param_range_values(param_range)
         is_default_range = (param_range[0] == PARAM_CHOICES[0] and param_range[1] == PARAM_CHOICES[-1])
         if not is_default_range and 'params' in filtered_df.columns:
             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]
-        elif 'params' not in filtered_df.columns: print("Warning: 'params' column not found for filtering.")
-    if skip_orgs and len(skip_orgs) > 0:
-        if "organization" in filtered_df.columns: filtered_df = filtered_df[~filtered_df["organization"].isin(skip_orgs)]
-        else: print("Warning: 'organization' column not found for filtering.")
+    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()
-    if count_by not in filtered_df.columns:
-        print(f"Warning: Metric column '{count_by}' not found. Using 0.")
-        filtered_df[count_by] = 0.0
+    if count_by not in filtered_df.columns: filtered_df[count_by] = 0.0
     filtered_df[count_by] = pd.to_numeric(filtered_df[count_by], errors="coerce").fillna(0.0)
     org_totals = filtered_df.groupby("organization")[count_by].sum().nlargest(top_k, keep='first')
     top_orgs_list = org_totals.index.tolist()
     treemap_data = filtered_df[filtered_df["organization"].isin(top_orgs_list)][["id", "organization", count_by]].copy()
     treemap_data["root"] = "models"
-    treemap_data[count_by] = pd.to_numeric(treemap_data[count_by], errors="coerce").fillna(0.0)
     return treemap_data
 
 def create_treemap(treemap_data, count_by, title=None):
@@ -108,14 +97,19 @@ with gr.Blocks(title="ModelVerse Explorer", fill_width=True) as demo:
                 with gr.Row():
                     param_label_display = gr.Markdown("<div style='font-weight: 500;'>Parameters</div>")
                     reset_params_button = gr.Button("🔄 Reset", visible=False, size="sm", min_width=80)
-                
                 param_slider = gr.Slider(
                     minimum=0, maximum=len(PARAM_CHOICES) - 1, step=1,
                     value=PARAM_CHOICES_DEFAULT_INDICES,
-                    label="Parameter Range", show_label=False # Use a hidden label for accessibility
+                    label="Parameter Range", show_label=False
                 )
+            
+            # --- MODIFIED: Replaced Slider with Dropdown for Top-K selection ---
+            top_k_dropdown = gr.Dropdown(
+                label="Number of Top Organizations", 
+                choices=TOP_K_CHOICES, 
+                value=25
+            )
 
-            top_k_slider = gr.Slider(label="Number of Top Organizations", minimum=5, maximum=50, value=25, step=5)
             skip_orgs_textbox = gr.Textbox(label="Organizations to Skip (comma-separated)", value="TheBloke,MaziyarPanahi,unsloth,modularai,Gensyn,bartowski")
             generate_plot_button = gr.Button(value="Generate Plot", variant="primary", interactive=False)
 
@@ -124,31 +118,19 @@ with gr.Blocks(title="ModelVerse Explorer", fill_width=True) as demo:
             status_message_md = gr.Markdown("Initializing...")
             data_info_md = gr.Markdown("")
 
-    # --- MODIFIED: More robust event handlers for the slider ---
     def _update_slider_ui_elements(current_range_indices):
-        """Updates the labels above the slider and the reset button visibility."""
-        if not isinstance(current_range_indices, list) or len(current_range_indices) != 2:
-            # This is a defensive check to prevent crashes if the input is malformed.
-            return gr.update(), gr.update()
-            
+        if not isinstance(current_range_indices, list) or len(current_range_indices) != 2: return gr.update(), gr.update()
         min_idx, max_idx = int(current_range_indices[0]), int(current_range_indices[1])
         min_label, max_label = PARAM_CHOICES[min_idx], PARAM_CHOICES[max_idx]
-        
-        # Using HTML for bold is more reliable in gr.Markdown
         label_md = f"<div style='font-weight: 500;'>Parameters <span style='float: right; font-weight: normal; color: #555;'>{min_label} to {max_label}</span></div>"
-        
         is_default = (min_idx == 0 and max_idx == len(PARAM_CHOICES) - 1)
-        button_visibility = gr.update(visible=not is_default)
-        
-        return label_md, button_visibility
+        return label_md, gr.update(visible=not is_default)
 
     def _reset_param_slider_and_ui():
-        """Resets the slider to default and updates the UI elements accordingly."""
         default_label = "<div style='font-weight: 500;'>Parameters</div>"
         return gr.update(value=PARAM_CHOICES_DEFAULT_INDICES), default_label, gr.update(visible=False)
 
-    # Use .change() for better reliability
-    param_slider.change(fn=_update_slider_ui_elements, inputs=param_slider, outputs=[param_label_display, reset_params_button])
+    param_slider.release(fn=_update_slider_ui_elements, inputs=param_slider, outputs=[param_label_display, reset_params_button])
     reset_params_button.click(fn=_reset_param_slider_and_ui, outputs=[param_slider, param_label_display, reset_params_button])
     
     def _update_button_interactivity(is_loaded_flag): return gr.update(interactive=is_loaded_flag)
@@ -157,44 +139,37 @@ with gr.Blocks(title="ModelVerse Explorer", fill_width=True) as demo:
     def _toggle_filters_visibility(choice): return gr.update(visible=choice == "Tag Filter"), gr.update(visible=choice == "Pipeline Filter")
     filter_choice_radio.change(fn=_toggle_filters_visibility, inputs=filter_choice_radio, outputs=[tag_filter_dropdown, pipeline_filter_dropdown])
 
-    # --- MODIFIED: Fixed the timezone handling logic ---
     def ui_load_data_controller(progress=gr.Progress()):
-        progress(0, desc=f"Loading dataset '{HF_DATASET_ID}' from Hugging Face Hub...")
-        status_msg_ui, data_info_text, load_success_flag = "Loading data...", "", False
+        progress(0, desc=f"Loading dataset '{HF_DATASET_ID}'...")
         try:
             current_df, load_success_flag, status_msg_from_load = load_models_data()
             if load_success_flag:
-                progress(0.9, desc="Processing loaded data...")
+                progress(0.9, desc="Processing data...")
                 date_display = "Pre-processed (date unavailable)"
-                if 'data_download_timestamp' in current_df.columns and not current_df.empty and pd.notna(current_df['data_download_timestamp'].iloc[0]):
-                    timestamp = pd.to_datetime(current_df['data_download_timestamp'].iloc[0])
-                    # Check if tz-aware. If so, convert. If not, localize.
-                    if timestamp.tzinfo is None:
-                        ts = timestamp.tz_localize('UTC')
-                    else:
-                        ts = timestamp.tz_convert('UTC')
+                if 'data_download_timestamp' in current_df.columns and pd.notna(current_df['data_download_timestamp'].iloc[0]):
+                    ts = pd.to_datetime(current_df['data_download_timestamp'].iloc[0], utc=True)
                     date_display = ts.strftime('%B %d, %Y, %H:%M:%S %Z')
-
                 param_count = (current_df['params'] > 0).sum() if 'params' in current_df.columns else 0
                 data_info_text = f"### Data Information\n- Source: `{HF_DATASET_ID}`\n- Status: {status_msg_from_load}\n- Total models loaded: {len(current_df):,}\n- Models with parameter counts: {param_count:,}\n- Data as of: {date_display}\n"
-                status_msg_ui = "Data loaded successfully. Ready to generate plot."
+                status_msg_ui = "Data loaded. Ready to generate plot."
             else:
                 data_info_text = f"### Data Load Failed\n- {status_msg_from_load}"
                 status_msg_ui = status_msg_from_load
         except Exception as e:
-            status_msg_ui = f"An unexpected error occurred: {str(e)}"
+            status_msg_ui = f"An unexpected error occurred during data loading: {str(e)}"
             data_info_text = f"### Critical Error\n- {status_msg_ui}"
+            load_success_flag = False
             print(f"Critical error in ui_load_data_controller: {e}")
         return current_df, load_success_flag, data_info_text, status_msg_ui
 
     def ui_generate_plot_controller(metric_choice, filter_type, tag_choice, pipeline_choice, 
                                    param_range_indices, k_orgs, skip_orgs_input, 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 or is empty."
-        progress(0.1, desc="Preparing data for visualization...")
+            return create_treemap(pd.DataFrame(), metric_choice, "Error: Model Data Not Loaded"), "Model data is not loaded."
+        progress(0.1, desc="Preparing data...")
         tag_to_use = tag_choice if filter_type == "Tag Filter" else None
         pipeline_to_use = pipeline_choice if filter_type == "Pipeline Filter" else None
-        orgs_to_skip = [org.strip() for org in skip_orgs_input.split(',') if org.strip()] if skip_orgs_input else []
+        orgs_to_skip = [org.strip() for org in skip_orgs_input.split(',') if org.strip()]
         
         min_label = PARAM_CHOICES[int(param_range_indices[0])]
         max_label = PARAM_CHOICES[int(param_range_indices[1])]
@@ -202,25 +177,26 @@ with gr.Blocks(title="ModelVerse Explorer", fill_width=True) as demo:
         
         treemap_df = make_treemap_data(df_current_models, metric_choice, k_orgs, tag_to_use, pipeline_to_use, param_labels_for_filtering, orgs_to_skip)
         
-        progress(0.7, desc="Generating Plotly visualization...")
+        progress(0.7, desc="Generating plot...")
         title_labels = {"downloads": "Downloads (last 30 days)", "downloadsAllTime": "Downloads (All Time)", "likes": "Likes"}
         chart_title = f"HuggingFace Models - {title_labels.get(metric_choice, metric_choice)} by Organization"
         plotly_fig = create_treemap(treemap_df, metric_choice, chart_title)
         
         if treemap_df.empty:
-            plot_stats_md = "No data matches the selected filters. Try adjusting your filters."
+            plot_stats_md = "No data matches the selected filters. Please try different options."
         else:
             total_items_in_plot = len(treemap_df['id'].unique())
-            total_value_in_plot = treemap_df[metric_choice].sum()
+            total_value_in_plot = treemap_df[count_by].sum()
             plot_stats_md = f"## Plot Statistics\n- **Models shown**: {total_items_in_plot:,}\n- **Total {metric_choice}**: {int(total_value_in_plot):,}"
         return plotly_fig, plot_stats_md
 
     demo.load(fn=ui_load_data_controller, inputs=[], outputs=[models_data_state, loading_complete_state, data_info_md, status_message_md])
 
+    # --- MODIFIED: The inputs list now uses top_k_dropdown ---
     generate_plot_button.click(
         fn=ui_generate_plot_controller,
         inputs=[count_by_dropdown, filter_choice_radio, tag_filter_dropdown, pipeline_filter_dropdown,
-                param_slider, top_k_slider, skip_orgs_textbox, models_data_state],
+                param_slider, top_k_dropdown, skip_orgs_textbox, models_data_state],
         outputs=[plot_output, status_message_md]
     )
 
@@ -228,4 +204,4 @@ if __name__ == "__main__":
     print(f"Application starting. Data will be loaded from Hugging Face dataset: {HF_DATASET_ID}")
     demo.queue().launch()
 
-# --- END OF FULLY CORRECTED AND IMPROVED FILE app.py ---
+# --- END OF FINAL POLISHED FILE app.py ---