Update app.py

app.py

@@ -1,23 +1,19 @@
 # --- START OF FILE app.py ---
 
-import json
 import gradio as gr
 import pandas as pd
 import plotly.express as px
-import os
-import numpy as np
-import duckdb
-from tqdm.auto import tqdm # Standard tqdm for console, gr.Progress will track it
 import time
-import ast # For safely evaluating string representations of lists/dicts
+from datasets import load_dataset # Import the datasets library
 
 # --- Constants ---
 MODEL_SIZE_RANGES = {
     "Small (<1GB)": (0, 1), "Medium (1-5GB)": (1, 5), "Large (5-20GB)": (5, 20),
     "X-Large (20-50GB)": (20, 50), "XX-Large (>50GB)": (50, float('inf'))
 }
-PROCESSED_PARQUET_FILE_PATH = "models_processed.parquet"
-HF_PARQUET_URL = 'https://huggingface.co/datasets/cfahlgren1/hub-stats/resolve/main/models.parquet' # Added for completeness within app.py context
+
+# The Hugging Face dataset ID to load.
+HF_DATASET_ID = "evijit/orgstats_daily_data"
 
 TAG_FILTER_CHOICES = [
     "Audio & Speech", "Time series", "Robotics", "Music", "Video", "Images",
@@ -38,139 +34,16 @@ PIPELINE_TAGS = [
  'table-question-answering',
 ]
 
-def extract_model_size(safetensors_data):
-    try:
-        if pd.isna(safetensors_data): return 0.0
-        data_to_parse = safetensors_data
-        if isinstance(safetensors_data, str):
-            try:
-                if (safetensors_data.startswith('{') and safetensors_data.endswith('}')) or \
-                   (safetensors_data.startswith('[') and safetensors_data.endswith(']')):
-                    data_to_parse = ast.literal_eval(safetensors_data)
-                else: data_to_parse = json.loads(safetensors_data)
-            except: return 0.0
-        if isinstance(data_to_parse, dict) and 'total' in data_to_parse:
-            try:
-                total_bytes_val = data_to_parse['total']
-                size_bytes = float(total_bytes_val)
-                return size_bytes / (1024 * 1024 * 1024)
-            except (ValueError, TypeError): pass
-        return 0.0
-    except: return 0.0
-
-def extract_org_from_id(model_id):
-    if pd.isna(model_id): return "unaffiliated"
-    model_id_str = str(model_id)
-    return model_id_str.split("/")[0] if "/" in model_id_str else "unaffiliated"
-
-def process_tags_for_series(series_of_tags_values):
-    processed_tags_accumulator = []
-
-    for i, tags_value_from_series in enumerate(tqdm(series_of_tags_values, desc="Standardizing Tags", leave=False, unit="row")):
-        temp_processed_list_for_row = []
-        current_value_for_error_msg = str(tags_value_from_series)[:200] # Truncate for long error messages
 
-        try:
-            # Order of checks is important!
-            # 1. Handle explicit Python lists first
-            if isinstance(tags_value_from_series, list):
-                current_tags_in_list = []
-                for idx_tag, tag_item in enumerate(tags_value_from_series):
-                    try:
-                        # Ensure item is not NaN before string conversion if it might be a float NaN in a list
-                        if pd.isna(tag_item): continue 
-                        str_tag = str(tag_item)
-                        stripped_tag = str_tag.strip()
-                        if stripped_tag:
-                            current_tags_in_list.append(stripped_tag)
-                    except Exception as e_inner_list_proc:
-                        print(f"ERROR processing item '{tag_item}' (type: {type(tag_item)}) within a list for row {i}. Error: {e_inner_list_proc}. Original list: {current_value_for_error_msg}")
-                temp_processed_list_for_row = current_tags_in_list
-
-            # 2. Handle NumPy arrays
-            elif isinstance(tags_value_from_series, np.ndarray):
-                # Convert to list, then process elements, handling potential NaNs within the array
-                current_tags_in_list = []
-                for idx_tag, tag_item in enumerate(tags_value_from_series.tolist()): # .tolist() is crucial
-                    try:
-                        if pd.isna(tag_item): continue # Check for NaN after converting to Python type
-                        str_tag = str(tag_item)
-                        stripped_tag = str_tag.strip()
-                        if stripped_tag:
-                            current_tags_in_list.append(stripped_tag)
-                    except Exception as e_inner_array_proc:
-                        print(f"ERROR processing item '{tag_item}' (type: {type(tag_item)}) within a NumPy array for row {i}. Error: {e_inner_array_proc}. Original array: {current_value_for_error_msg}")
-                temp_processed_list_for_row = current_tags_in_list
-            
-            # 3. Handle simple None or pd.NA after lists and arrays (which might contain pd.NA elements handled above)
-            elif tags_value_from_series is None or pd.isna(tags_value_from_series): # Now pd.isna is safe for scalars
-                temp_processed_list_for_row = []
-
-            # 4. Handle strings (could be JSON-like, list-like, or comma-separated)
-            elif isinstance(tags_value_from_series, str):
-                processed_str_tags = []
-                # Attempt ast.literal_eval for strings that look like lists/tuples
-                if (tags_value_from_series.startswith('[') and tags_value_from_series.endswith(']')) or \
-                   (tags_value_from_series.startswith('(') and tags_value_from_series.endswith(')')):
-                    try:
-                        evaluated_tags = ast.literal_eval(tags_value_from_series)
-                        if isinstance(evaluated_tags, (list, tuple)): # Check if eval result is a list/tuple
-                            # Recursively process this evaluated list/tuple, as its elements could be complex
-                            # For simplicity here, assume elements are simple strings after eval
-                            current_eval_list = []
-                            for tag_item in evaluated_tags:
-                                if pd.isna(tag_item): continue
-                                str_tag = str(tag_item).strip()
-                                if str_tag: current_eval_list.append(str_tag)
-                            processed_str_tags = current_eval_list
-                    except (ValueError, SyntaxError):
-                        pass # If ast.literal_eval fails, let it fall to JSON or comma split
-
-                # If ast.literal_eval didn't populate, try JSON
-                if not processed_str_tags:
-                    try:
-                        json_tags = json.loads(tags_value_from_series)
-                        if isinstance(json_tags, list):
-                            # Similar to above, assume elements are simple strings after JSON parsing
-                            current_json_list = []
-                            for tag_item in json_tags:
-                                if pd.isna(tag_item): continue
-                                str_tag = str(tag_item).strip()
-                                if str_tag: current_json_list.append(str_tag)
-                            processed_str_tags = current_json_list
-                    except json.JSONDecodeError:
-                        # If not a valid JSON list, fall back to comma splitting as the final string strategy
-                        processed_str_tags = [tag.strip() for tag in tags_value_from_series.split(',') if tag.strip()]
-                    except Exception as e_json_other:
-                        print(f"ERROR during JSON processing for string '{current_value_for_error_msg}' for row {i}. Error: {e_json_other}")
-                        processed_str_tags = [tag.strip() for tag in tags_value_from_series.split(',') if tag.strip()] # Fallback
-
-                temp_processed_list_for_row = processed_str_tags
-            
-            # 5. Fallback for other scalar types (e.g., int, float that are not NaN)
-            else:
-                # This path is for non-list, non-ndarray, non-None/NaN, non-string types.
-                # Or for NaNs that slipped through if they are not None or pd.NA (e.g. float('nan'))
-                if pd.isna(tags_value_from_series): # Catch any remaining NaNs like float('nan')
-                     temp_processed_list_for_row = []
-                else:
-                    str_val = str(tags_value_from_series).strip()
-                    temp_processed_list_for_row = [str_val] if str_val else []
-            
-            processed_tags_accumulator.append(temp_processed_list_for_row)
-
-        except Exception as e_outer_tag_proc:
-            print(f"CRITICAL UNHANDLED ERROR processing row {i}: value '{current_value_for_error_msg}' (type: {type(tags_value_from_series)}). Error: {e_outer_tag_proc}. Appending [].")
-            processed_tags_accumulator.append([])
-            
-    return processed_tags_accumulator
-
-def load_models_data(force_refresh=False, tqdm_cls=None):
-    if tqdm_cls is None: tqdm_cls = tqdm
+def load_models_data():
+    """
+    Loads the pre-processed models data using the HF datasets library.
+    """
     overall_start_time = time.time()
-    print(f"Gradio load_models_data called with force_refresh={force_refresh}")
+    print(f"Attempting to load dataset from Hugging Face Hub: {HF_DATASET_ID}")
 
-    expected_cols_in_processed_parquet = [
+    # These are the columns expected to be in the pre-processed dataset.
+    expected_cols = [
         'id', 'downloads', 'downloadsAllTime', 'likes', 'pipeline_tag', 'tags', 'params',
         'size_category', 'organization', 'has_audio', 'has_speech', 'has_music',
         'has_robot', 'has_bio', 'has_med', 'has_series', 'has_video', 'has_image',
@@ -178,139 +51,44 @@ def load_models_data(force_refresh=False, tqdm_cls=None):
         'data_download_timestamp'
     ]
 
-    if not force_refresh and os.path.exists(PROCESSED_PARQUET_FILE_PATH):
-        print(f"Attempting to load pre-processed data from: {PROCESSED_PARQUET_FILE_PATH}")
-        try:
-            df = pd.read_parquet(PROCESSED_PARQUET_FILE_PATH)
-            elapsed = time.time() - overall_start_time
-            missing_cols = [col for col in expected_cols_in_processed_parquet if col not in df.columns]
-            if missing_cols:
-                raise ValueError(f"Pre-processed Parquet is missing columns: {missing_cols}. Please run preprocessor or refresh data in app.")
-            
-            # --- Diagnostic for 'has_robot' after loading parquet ---
-            if 'has_robot' in df.columns:
-                robot_count_parquet = df['has_robot'].sum()
-                print(f"DIAGNOSTIC (App - Parquet Load): 'has_robot' column found. Number of True values: {robot_count_parquet}")
-                if 0 < robot_count_parquet < 10:
-                     print(f"Sample 'has_robot' models (from parquet): {df[df['has_robot']]['id'].head().tolist()}")
-            else:
-                print("DIAGNOSTIC (App - Parquet Load): 'has_robot' column NOT FOUND.")
-            # --- End Diagnostic ---
-
-            msg = f"Successfully loaded pre-processed data in {elapsed:.2f}s. Shape: {df.shape}"
-            print(msg)
-            return df, True, msg
-        except Exception as e:
-            print(f"Could not load pre-processed Parquet: {e}. ")
-            if force_refresh: print("Proceeding to fetch fresh data as force_refresh=True.")
-            else:
-                 err_msg = (f"Pre-processed data could not be loaded: {e}. "
-                           "Please use 'Refresh Data from Hugging Face' button.")
-                 return pd.DataFrame(), False, err_msg
-
-    df_raw = None
-    raw_data_source_msg = ""
-    if force_refresh:
-        print("force_refresh=True (Gradio). Fetching fresh data...")
-        fetch_start = time.time()
-        try:
-            query = f"SELECT * FROM read_parquet('{HF_PARQUET_URL}')" # Ensure HF_PARQUET_URL is defined
-            df_raw = duckdb.sql(query).df()
-            if df_raw is None or df_raw.empty: raise ValueError("Fetched data is empty or None.")
-            raw_data_source_msg = f"Fetched by Gradio in {time.time() - fetch_start:.2f}s. Rows: {len(df_raw)}"
-            print(raw_data_source_msg)
-        except Exception as e_hf:
-            return pd.DataFrame(), False, f"Fatal error fetching from Hugging Face (Gradio): {e_hf}"
-    else: 
-        err_msg = (f"Pre-processed data '{PROCESSED_PARQUET_FILE_PATH}' not found/invalid. "
-                   "Run preprocessor or use 'Refresh Data' button.")
-        return pd.DataFrame(), False, err_msg
+    try:
+        # Load the dataset using the datasets library
+        # It will be cached locally after the first run.
+        dataset_dict = load_dataset(HF_DATASET_ID)
+        
+        if not dataset_dict:
+             raise ValueError(f"Dataset '{HF_DATASET_ID}' loaded but appears empty.")
 
-    print(f"Initiating processing for data newly fetched by Gradio. {raw_data_source_msg}")
-    df = pd.DataFrame()
-    proc_start = time.time()
-    
-    core_cols = {'id': str, 'downloads': float, 'downloadsAllTime': float, 'likes': float,
-                 'pipeline_tag': str, 'tags': object, 'safetensors': object}
-    for col, dtype in core_cols.items():
-        if col in df_raw.columns:
-            df[col] = df_raw[col]
-            if dtype == float: df[col] = pd.to_numeric(df[col], errors='coerce').fillna(0.0)
-            elif dtype == str: df[col] = df[col].astype(str).fillna('')
+        # Get the name of the first split (e.g., 'train')
+        split_name = list(dataset_dict.keys())[0]
+        print(f"Using dataset split: '{split_name}'. Converting to Pandas.")
+
+        # Convert the dataset object to a Pandas DataFrame
+        df = dataset_dict[split_name].to_pandas()
+
+        elapsed = time.time() - overall_start_time
+        
+        # Validate that the loaded data has the columns we expect.
+        missing_cols = [col for col in expected_cols if col not in df.columns]
+        if missing_cols:
+            raise ValueError(f"Loaded dataset is missing expected columns: {missing_cols}.")
+
+        # --- Diagnostic for 'has_robot' after loading ---
+        if 'has_robot' in df.columns:
+            robot_count = df['has_robot'].sum()
+            print(f"DIAGNOSTIC (Dataset Load): 'has_robot' column found. Number of True values: {robot_count}")
         else:
-            if col in ['downloads', 'downloadsAllTime', 'likes']: df[col] = 0.0
-            elif col == 'pipeline_tag': df[col] = ''
-            elif col == 'tags': df[col] = pd.Series([[] for _ in range(len(df_raw))])
-            elif col == 'safetensors': df[col] = None 
-            elif col == 'id': return pd.DataFrame(), False, "Critical: 'id' column missing."
-    
-    output_filesize_col_name = 'params'
-    if output_filesize_col_name in df_raw.columns and pd.api.types.is_numeric_dtype(df_raw[output_filesize_col_name]):
-        df[output_filesize_col_name] = pd.to_numeric(df_raw[output_filesize_col_name], errors='coerce').fillna(0.0)
-    elif 'safetensors' in df.columns:
-        safetensors_iter = df['safetensors']
-        if tqdm_cls != tqdm :
-             safetensors_iter = tqdm_cls(df['safetensors'], desc="Extracting model sizes (GB)")
-        df[output_filesize_col_name] = [extract_model_size(s) for s in safetensors_iter]
-        df[output_filesize_col_name] = pd.to_numeric(df[output_filesize_col_name], errors='coerce').fillna(0.0)
-    else:
-        df[output_filesize_col_name] = 0.0
-
-    def get_size_category_gradio(size_gb_val):
-        try: numeric_size_gb = float(size_gb_val)
-        except (ValueError, TypeError): numeric_size_gb = 0.0
-        if pd.isna(numeric_size_gb): numeric_size_gb = 0.0
-        if 0 <= numeric_size_gb < 1: return "Small (<1GB)"
-        elif 1 <= numeric_size_gb < 5: return "Medium (1-5GB)"
-        elif 5 <= numeric_size_gb < 20: return "Large (5-20GB)"
-        elif 20 <= numeric_size_gb < 50: return "X-Large (20-50GB)"
-        elif numeric_size_gb >= 50: return "XX-Large (>50GB)"
-        else: return "Small (<1GB)"
-    df['size_category'] = df[output_filesize_col_name].apply(get_size_category_gradio)
-
-    df['tags'] = process_tags_for_series(df['tags'])
-    df['temp_tags_joined'] = df['tags'].apply(
-        lambda tl: '~~~'.join(str(t).lower() for t in tl if pd.notna(t) and str(t).strip()) if isinstance(tl, list) else ''
-    )
-    tag_map = {
-        'has_audio': ['audio'], 'has_speech': ['speech'], 'has_music': ['music'],
-        'has_robot': ['robot', 'robotics'],
-        'has_bio': ['bio'], 'has_med': ['medic', 'medical'],
-        'has_series': ['series', 'time-series', 'timeseries'],
-        'has_video': ['video'], 'has_image': ['image', 'vision'],
-        'has_text': ['text', 'nlp', 'llm']
-    }
-    for col, kws in tag_map.items():
-        pattern = '|'.join(kws)
-        df[col] = df['temp_tags_joined'].str.contains(pattern, na=False, case=False, regex=True)
-    df['has_science'] = (
-        df['temp_tags_joined'].str.contains('science', na=False, case=False, regex=True) &
-        ~df['temp_tags_joined'].str.contains('bigscience', na=False, case=False, regex=True)
-    )
-    del df['temp_tags_joined']
-    df['is_audio_speech'] = (df['has_audio'] | df['has_speech'] |
-                            df['pipeline_tag'].str.contains('audio|speech', case=False, na=False, regex=True))
-    df['is_biomed'] = df['has_bio'] | df['has_med']
-    df['organization'] = df['id'].apply(extract_org_from_id)
-
-    if 'safetensors' in df.columns and \
-       not (output_filesize_col_name in df_raw.columns and pd.api.types.is_numeric_dtype(df_raw[output_filesize_col_name])):
-        df = df.drop(columns=['safetensors'], errors='ignore')
-    
-    # --- Diagnostic for 'has_robot' after app-side processing (force_refresh path) ---
-    if force_refresh and 'has_robot' in df.columns:
-        robot_count_app_proc = df['has_robot'].sum()
-        print(f"DIAGNOSTIC (App - Force Refresh Processing): 'has_robot' column processed. Number of True values: {robot_count_app_proc}")
-        if 0 < robot_count_app_proc < 10:
-            print(f"Sample 'has_robot' models (App processed): {df[df['has_robot']]['id'].head().tolist()}")
-    # --- End Diagnostic ---
-
-    print(f"Data processing by Gradio completed in {time.time() - proc_start:.2f}s.")
-    
-    total_elapsed = time.time() - overall_start_time
-    final_msg = f"{raw_data_source_msg}. Processing by Gradio took {time.time() - proc_start:.2f}s. Total: {total_elapsed:.2f}s. Shape: {df.shape}"
-    print(final_msg)
-    return df, True, final_msg
+            print("DIAGNOSTIC (Dataset Load): 'has_robot' column NOT FOUND.")
+        # --- End Diagnostic ---
+
+        msg = f"Successfully loaded dataset '{HF_DATASET_ID}' (split: {split_name}) from HF Hub in {elapsed:.2f}s. Shape: {df.shape}"
+        print(msg)
+        return df, True, msg
+        
+    except Exception as e:
+        err_msg = f"Failed to load dataset '{HF_DATASET_ID}' from Hugging Face Hub. Error: {e}"
+        print(err_msg)
+        return pd.DataFrame(), False, err_msg
 
 
 def make_treemap_data(df, count_by, top_k=25, tag_filter=None, pipeline_filter=None, size_filter=None, skip_orgs=None):
@@ -320,49 +98,48 @@ def make_treemap_data(df, count_by, top_k=25, tag_filter=None, pipeline_filter=N
                 "Biomedical": "is_biomed", "Time series": "has_series", "Sciences": "has_science",
                 "Video": "has_video", "Images": "has_image", "Text": "has_text"}
     
-    # --- Diagnostic within make_treemap_data ---
-    if 'has_robot' in filtered_df.columns:
-        initial_robot_count = filtered_df['has_robot'].sum()
-        print(f"DIAGNOSTIC (make_treemap_data entry): Input df has {initial_robot_count} 'has_robot' models.")
-    else:
-        print("DIAGNOSTIC (make_treemap_data entry): 'has_robot' column NOT in input df.")
-    # --- End Diagnostic ---
-
     if tag_filter and tag_filter in col_map:
         target_col = col_map[tag_filter]
         if target_col in filtered_df.columns:
-            # --- Diagnostic for specific 'Robotics' filter application ---
-            if tag_filter == "Robotics":
-                count_before_robot_filter = filtered_df[target_col].sum()
-                print(f"DIAGNOSTIC (make_treemap_data): Applying 'Robotics' filter. Models with '{target_col}'=True before this filter step: {count_before_robot_filter}")
-            # --- End Diagnostic ---
             filtered_df = filtered_df[filtered_df[target_col]]
-            if tag_filter == "Robotics":
-                 print(f"DIAGNOSTIC (make_treemap_data): After 'Robotics' filter ({target_col}), df rows: {len(filtered_df)}")
         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"] == pipeline_filter]
+            # Ensure the comparison works even if pipeline_tag has NaNs or mixed types
+            filtered_df = filtered_df[filtered_df["pipeline_tag"].astype(str) == pipeline_filter]
         else:
             print(f"Warning: 'pipeline_tag' column not found for filtering.")
+
     if size_filter and size_filter != "None" and size_filter in MODEL_SIZE_RANGES.keys():
         if 'size_category' in filtered_df.columns:
             filtered_df = filtered_df[filtered_df['size_category'] == size_filter]
         else:
             print("Warning: 'size_category' 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 filtered_df.empty: return pd.DataFrame()
-    if count_by not in filtered_df.columns or not pd.api.types.is_numeric_dtype(filtered_df[count_by]):
-        filtered_df[count_by] = pd.to_numeric(filtered_df.get(count_by), errors="coerce").fillna(0.0)
+
+    # Ensure the metric column is numeric and handle potential missing values
+    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
+    filtered_df[count_by] = pd.to_numeric(filtered_df[count_by], errors="coerce").fillna(0.0)
+    
+    # Group and get top organizations
     org_totals = filtered_df.groupby("organization")[count_by].sum().nlargest(top_k, keep='first')
     top_orgs_list = org_totals.index.tolist()
+    
+    # Prepare data for treemap
     treemap_data = filtered_df[filtered_df["organization"].isin(top_orgs_list)][["id", "organization", count_by]].copy()
     treemap_data["root"] = "models"
+    # Ensure numeric again for the final slice
     treemap_data[count_by] = pd.to_numeric(treemap_data[count_by], errors="coerce").fillna(0.0) 
     return treemap_data
 
@@ -395,7 +172,7 @@ with gr.Blocks(title="HuggingFace Model Explorer", fill_width=True) as demo:
             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)
-            refresh_data_button = gr.Button(value="Refresh Data from Hugging Face", variant="secondary")
+
         with gr.Column(scale=3):
             plot_output = gr.Plot()
             status_message_md = gr.Markdown("Initializing...")
@@ -409,28 +186,30 @@ with gr.Blocks(title="HuggingFace Model Explorer", fill_width=True) as demo:
         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])
 
-    def ui_load_data_controller(force_refresh_ui_trigger=False, progress=gr.Progress(track_tqdm=True)):
-        print(f"ui_load_data_controller called with force_refresh_ui_trigger={force_refresh_ui_trigger}")
+    def ui_load_data_controller(progress=gr.Progress()):
+        progress(0, desc=f"Loading dataset '{HF_DATASET_ID}' from Hugging Face Hub...")
+        print("ui_load_data_controller called.")
         status_msg_ui = "Loading data..."
         data_info_text = ""
         current_df = pd.DataFrame()
         load_success_flag = False
         data_as_of_date_display = "N/A"
         try:
-            current_df, load_success_flag, status_msg_from_load = load_models_data(
-                force_refresh=force_refresh_ui_trigger, tqdm_cls=progress.tqdm
-            )
+            # Call the load function that uses the datasets library.
+            current_df, load_success_flag, status_msg_from_load = load_models_data()
             if load_success_flag:
-                if force_refresh_ui_trigger: 
-                    data_as_of_date_display = pd.Timestamp.now(tz='UTC').strftime('%B %d, %Y, %H:%M:%S %Z')
-                elif 'data_download_timestamp' in current_df.columns and not current_df.empty and pd.notna(current_df['data_download_timestamp'].iloc[0]):
+                progress(0.9, desc="Processing loaded data...")
+                # Get the data timestamp from the loaded file
+                if 'data_download_timestamp' in current_df.columns and not current_df.empty and pd.notna(current_df['data_download_timestamp'].iloc[0]):
                     timestamp_from_parquet = pd.to_datetime(current_df['data_download_timestamp'].iloc[0])
+                    # Ensure the timestamp is timezone-aware for consistent formatting
                     if timestamp_from_parquet.tzinfo is None:
                         timestamp_from_parquet = timestamp_from_parquet.tz_localize('UTC')
                     data_as_of_date_display = timestamp_from_parquet.strftime('%B %d, %Y, %H:%M:%S %Z')
                 else:
                     data_as_of_date_display = "Pre-processed (date unavailable)"
                 
+                # Create summary text for the UI
                 size_dist_lines = []
                 if 'size_category' in current_df.columns:
                     for cat in MODEL_SIZE_RANGES.keys():
@@ -440,22 +219,12 @@ with gr.Blocks(title="HuggingFace Model Explorer", fill_width=True) as demo:
                 size_dist = "\n".join(size_dist_lines)
                 
                 data_info_text = (f"### Data Information\n"
+                                  f"- Source: `{HF_DATASET_ID}`\n"
                                   f"- Overall Status: {status_msg_from_load}\n" 
                                   f"- Total models loaded: {len(current_df):,}\n"
                                   f"- Data as of: {data_as_of_date_display}\n"
                                   f"- Size categories:\n{size_dist}")
                 
-                # # --- MODIFICATION: Add 'has_robot' count to UI data_info_text ---
-                # if not current_df.empty and 'has_robot' in current_df.columns:
-                #     robot_true_count = current_df['has_robot'].sum()
-                #     data_info_text += f"\n- **Models flagged 'has_robot'**: {robot_true_count}"
-                #     if 0 < robot_true_count <= 10: # If a few are found, list some IDs
-                #         sample_robot_ids = current_df[current_df['has_robot']]['id'].head(5).tolist()
-                #         data_info_text += f"\n  - Sample 'has_robot' model IDs: `{', '.join(sample_robot_ids)}`"
-                # elif not current_df.empty:
-                #     data_info_text += "\n- **Models flagged 'has_robot'**: 'has_robot' column not found in loaded data."
-                # # --- END MODIFICATION ---
-
                 status_msg_ui = "Data loaded successfully. Ready to generate plot."
             else: 
                 data_info_text = f"### Data Load Failed\n- {status_msg_from_load}"
@@ -468,46 +237,45 @@ with gr.Blocks(title="HuggingFace Model Explorer", fill_width=True) as demo:
         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, 
-                                   size_choice, k_orgs, skip_orgs_input, df_current_models):
+                                   size_choice, k_orgs, skip_orgs_input, df_current_models, progress=gr.Progress()):
         if df_current_models is None or df_current_models.empty:
             empty_fig = create_treemap(pd.DataFrame(), metric_choice, "Error: Model Data Not Loaded")
-            error_msg = "Model data is not loaded or is empty. Please load or refresh data first."
+            error_msg = "Model data is not loaded or is empty. Please wait for data to load."
             gr.Warning(error_msg)
             return empty_fig, error_msg
+        
+        progress(0.1, desc="Preparing data for visualization...")
+        
         tag_to_use = tag_choice if filter_type == "Tag Filter" else None
         pipeline_to_use = pipeline_choice if filter_type == "Pipeline Filter" else None
         size_to_use = size_choice if size_choice != "None" else None
         orgs_to_skip = [org.strip() for org in skip_orgs_input.split(',') if org.strip()] if skip_orgs_input else []
         
-        # --- Diagnostic before calling make_treemap_data ---
-        if 'has_robot' in df_current_models.columns:
-            robot_count_before_treemap = df_current_models['has_robot'].sum()
-            print(f"DIAGNOSTIC (ui_generate_plot_controller): df_current_models entering make_treemap_data has {robot_count_before_treemap} 'has_robot' models.")
-        # --- End Diagnostic ---
 
         treemap_df = make_treemap_data(df_current_models, metric_choice, k_orgs, tag_to_use, pipeline_to_use, size_to_use, orgs_to_skip)
         
+        progress(0.7, desc="Generating Plotly visualization...")
+
         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."
         else:
             total_items_in_plot = len(treemap_df['id'].unique())
             total_value_in_plot = treemap_df[metric_choice].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
 
+    # On app load, call the controller to fetch data using the datasets library.
     demo.load(
-        fn=lambda progress=gr.Progress(track_tqdm=True): ui_load_data_controller(force_refresh_ui_trigger=False, progress=progress),
+        fn=ui_load_data_controller,
         inputs=[],
         outputs=[models_data_state, loading_complete_state, data_info_md, status_message_md]
     )
-    refresh_data_button.click(
-        fn=lambda progress=gr.Progress(track_tqdm=True): ui_load_data_controller(force_refresh_ui_trigger=True, progress=progress),
-        inputs=[], 
-        outputs=[models_data_state, loading_complete_state, data_info_md, status_message_md]
-    )
+
     generate_plot_button.click(
         fn=ui_generate_plot_controller,
         inputs=[count_by_dropdown, filter_choice_radio, tag_filter_dropdown, pipeline_filter_dropdown,
@@ -516,11 +284,8 @@ with gr.Blocks(title="HuggingFace Model Explorer", fill_width=True) as demo:
     )
 
 if __name__ == "__main__":
-    if not os.path.exists(PROCESSED_PARQUET_FILE_PATH):
-        print(f"WARNING: Pre-processed data file '{PROCESSED_PARQUET_FILE_PATH}' not found.")
-        print("It is highly recommended to run the preprocessing script (e.g., preprocess.py) first.") # Corrected script name
-    else:
-        print(f"Found pre-processed data file: '{PROCESSED_PARQUET_FILE_PATH}'.")
-    demo.launch()
+    print(f"Application starting. Data will be loaded from Hugging Face dataset: {HF_DATASET_ID}")
+    # Increase the queue size for potentially busy traffic if hosted
+    demo.queue().launch()
 
 # --- END OF FILE app.py ---