better food mapping, init stuff

.gitignore

@@ -0,0 +1,62 @@
+# Data files
+*.csv
+*.xlsx
+*.json
+*.parquet
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# Virtual environments
+venv/
+env/
+ENV/
+env.bak/
+venv.bak/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# Gradio cache
+gradio_cached_examples/
+flagged/
+
+# Logs
+*.log
+logs/
+/uv.lock
+/.claude/

.python-version

@@ -0,0 +1 @@
+3.10

app.py

@@ -7,6 +7,7 @@ from functools import lru_cache
 from collections import Counter
 import requests
 import os
+import time
 
 # --- Constants and Mappings (Unchanged) ---
 BODY_ORDER = ['Very light-bodied', 'Light-bodied', 'Medium-bodied', 'Full-bodied', 'Very full-bodied']
@@ -22,10 +23,49 @@ COUNTRY_FLAGS = {
     'Romania': '🇷🇴', 'Georgia': '🇬🇪', 'Moldova': '🇲🇩', 'Switzerland': '🇨🇭', 'England': '🏴'
 }
 FOOD_EMOJIS = {
-    'Beef': '🥩', 'Pork': '🍖', 'Lamb': '🍖', 'Poultry': '🍗', 'Seafood': '🐟', 'Rich Fish': '🐠',
-    'Shellfish': '🦐', 'Cheese': '🧀', 'Pasta': '🍝', 'Pizza': '🍕', 'Vegetables': '🥬', 'Vegetarian': '🥬',
-    'Veal': '🥩', 'Game Meat': '🦌', 'Barbecue': '🍖', 'Codfish': '🐟', 'Sweet Dessert': '🍰', 'Dessert': '🍰',
-    'Appetizers': '🍾', 'Fruit': '🍇', 'Nuts': '🥜', 'Chocolate': '🍫'
+    # Meat - Specific Animals
+    'Beef': '🐄', 'Pork': '🐷', 'Lamb': '🐑', 'Veal': '🐄', 'Ham': '🐷',
+    'Poultry': '🐔', 'Chicken': '🐔', 'Duck': '🦆',
+    'Game Meat': '🦌', 'Meat': '🥩',
+    
+    # Cured/Processed Meats
+    'Cured Meat': '🥓', 'Cold Cuts': '🥪', 'Barbecue': '🔥', 'Grilled': '🔥', 'Roast': '🍖',
+    
+    # Fish & Seafood - Specific Types
+    'Rich Fish': '🐟', 'Lean Fish': '🐟', 'Fish': '🐟', 'Codfish': '🐟',
+    'Shellfish': '🦐', 'Seafood': '🦞', 'Sushi': '🍣', 'Sashimi': '🍣',
+    
+    # Cheese - Different Types
+    'Cheese': '🧀', 'Soft Cheese': '🧀', 'Hard Cheese': '🧀', 'Blue Cheese': '🧀',
+    'Goat Cheese': '🐐', 'Maturated Cheese': '🧀', 'Mild Cheese': '🧀', 'Medium-cured Cheese': '🧀',
+    
+    # Pasta & Italian
+    'Pasta': '🍝', 'Tagliatelle': '🍝', 'Lasagna': '🍝', 'Risotto': '🍚',
+    'Pizza': '🍕', 'Eggplant Parmigiana': '🍆',
+    
+    # Asian Food
+    'Asian Food': '🥢', 'Curry Chicken': '🍛', 'Yakissoba': '🍜', 'Paella': '🥘',
+    
+    # Vegetables & Vegetarian
+    'Vegetarian': '🥬', 'Salad': '🥗', 'Mushrooms': '🍄', 'Beans': '🫘',
+    'Baked Potato': '🥔', 'French Fries': '🍟',
+    
+    # Desserts & Sweets
+    'Sweet Dessert': '🍰', 'Dessert': '🍰', 'Fruit Dessert': '🍓',
+    'Cake': '🍰', 'Cookies': '🍪', 'Chocolate': '🍫', 'Cream': '🍨',
+    'Citric Dessert': '🍋', 'Spiced Fruit Cake': '🍰',
+    
+    # Fruits & Nuts
+    'Fruit': '🍇', 'Dried Fruits': '🍇', 'Chestnut': '🌰',
+    
+    # Appetizers & Snacks
+    'Appetizer': '🍤', 'Snack': '🥨', 'Aperitif': '🥂',
+    
+    # Soups & Stews
+    'Light Stews': '🍲', 'Soufflé': '🥄',
+    
+    # Dishes & Preparations
+    'Spicy Food': '🌶️', 'Tomato Dishes': '🍅'
 }
 
 
@@ -60,13 +100,18 @@ def download_data():
 @lru_cache(maxsize=1)
 def load_and_preprocess_data():
     """Loads and performs expensive one-time preprocessing on the dataset."""
+    start_time = time.time()
+    print("[TIMING] Starting data loading and preprocessing...")
+    
     csv_filename = download_data()
+    print(f"[TIMING] File check/download completed in {time.time() - start_time:.2f}s")
     
     try:
-        print("Loading CSV data...")
+        csv_start = time.time()
+        print("[TIMING] Loading CSV data...")
         # Use efficient data types and only load needed columns if possible
         df = pd.read_csv(csv_filename, low_memory=False)
-        print(f"Loaded {len(df):,} wine records")
+        print(f"[TIMING] CSV loaded in {time.time() - csv_start:.2f}s - {len(df):,} wine records")
     except FileNotFoundError:
         raise FileNotFoundError(f"CSV file '{csv_filename}' not found.")
 
@@ -83,11 +128,24 @@ def load_and_preprocess_data():
             return []
 
     # Vectorized string processing for better performance
+    parse_start = time.time()
+    print("[TIMING] Starting string parsing...")
+    
     df['grapes_list'] = df['Grapes'].fillna('[]').apply(parse_list_string)
+    print(f"[TIMING] Grapes parsing completed in {time.time() - parse_start:.2f}s")
+    
+    harmonize_start = time.time()
     df['harmonize_list'] = df['Harmonize'].fillna('[]').apply(parse_list_string)
+    print(f"[TIMING] Harmonize parsing completed in {time.time() - harmonize_start:.2f}s")
+    
+    derived_start = time.time()
     df['main_grape'] = df['grapes_list'].apply(lambda x: x[0] if x else 'Unknown')
     df['num_grapes'] = df['grapes_list'].apply(len)
     df['body_numeric'] = df['Body'].map(BODY_MAPPING)
+    print(f"[TIMING] Derived columns completed in {time.time() - derived_start:.2f}s")
+    
+    total_time = time.time() - start_time
+    print(f"[TIMING] Total preprocessing completed in {total_time:.2f}s")
     return df
 
 
@@ -111,6 +169,9 @@ def get_top_food_pairings(harmonize_list, top_n=3):
 
 def aggregate_wine_data(df, wine_types, max_grape_count, min_samples_choice, regional_grouping):
     """Filters and aggregates wine data using efficient, vectorized pandas operations."""
+    agg_start = time.time()
+    print(f"[TIMING] Starting aggregation with {len(df):,} records...")
+    
     filtered_df = df.copy()
 
     if wine_types and 'All' not in wine_types:
@@ -122,6 +183,7 @@ def aggregate_wine_data(df, wine_types, max_grape_count, min_samples_choice, reg
     if regional_grouping:
         group_by_cols.append('Country')
 
+    groupby_start = time.time()
     agg_df = filtered_df.groupby(group_by_cols).agg(
         count=('ABV', 'size'),
         avg_fullness=('body_numeric', 'mean'),
@@ -132,6 +194,7 @@ def aggregate_wine_data(df, wine_types, max_grape_count, min_samples_choice, reg
         region_count=('RegionName', 'nunique'),
         winery_count=('WineryName', 'nunique')
     ).reset_index()
+    print(f"[TIMING] GroupBy aggregation completed in {time.time() - groupby_start:.2f}s")
 
     min_samples = SAMPLE_THRESHOLDS[min_samples_choice]
     agg_df = agg_df[agg_df['count'] >= min_samples].copy()
@@ -147,27 +210,39 @@ def aggregate_wine_data(df, wine_types, max_grape_count, min_samples_choice, reg
         counts = pd.Series(values_list).value_counts(normalize=True) * 100
         return {cat: counts.get(cat, 0.0) for cat in categories}
     
+    dist_start = time.time()
     agg_df['body_dist'] = agg_df['body_list'].apply(
         lambda x: calc_distribution(x, BODY_ORDER))
     agg_df['acid_dist'] = agg_df['acidity_list'].apply(
         lambda x: calc_distribution(x, ACIDITY_ORDER))
+    print(f"[TIMING] Distribution calculations completed in {time.time() - dist_start:.2f}s")
 
     # Pre-compute food pairings more efficiently
+    pairing_start = time.time()
     pairing_data = []
     for harmonize_list in agg_df['harmonize_list']:
         pairing_data.append(get_top_food_pairings(harmonize_list))
     agg_df['pairing_data'] = pairing_data
     agg_df['pairing_emoji'] = agg_df['pairing_data'].apply(lambda x: x['emojis'])
     agg_df['pairing_names'] = agg_df['pairing_data'].apply(lambda x: x['names'])
+    print(f"[TIMING] Food pairing calculations completed in {time.time() - pairing_start:.2f}s")
+    
+    final_start = time.time()
     agg_df['wine_type_order'] = agg_df['Type'].map(WINE_TYPE_ORDER)
     agg_df = agg_df.sort_values(by=['wine_type_order', 'avg_fullness'], ascending=[False, True])
-
+    print(f"[TIMING] Final sorting completed in {time.time() - final_start:.2f}s")
+    
+    total_agg_time = time.time() - agg_start
+    print(f"[TIMING] Total aggregation completed in {total_agg_time:.2f}s - {len(agg_df)} combinations")
     return agg_df
 
 
 # --- OPTIMIZATION 3: Efficient & Clean Chart Creation ---
 def create_wine_chart(chart_data, regional_grouping):
     """Creates the Plotly figure with optimized traces and layout."""
+    chart_start = time.time()
+    print(f"[TIMING] Starting chart creation with {len(chart_data)} rows...")
+    
     if chart_data.empty:
         fig = go.Figure()
         fig.add_annotation(text="No data available with current filters.", xref="paper", yref="paper", x=0.5, y=0.5,
@@ -176,15 +251,19 @@ def create_wine_chart(chart_data, regional_grouping):
 
     num_rows = len(chart_data)
 
-    # Add wine type emoji based on type
+    # Pre-compute labels more efficiently
+    prep_start = time.time()
     wine_type_emojis = {'Red': '🍷', 'White': '🥂', 'Rosé': '🌸', 'Sparkling': '🍾'}
+    chart_data = chart_data.copy()  # Avoid SettingWithCopyWarning
     chart_data['wine_emoji'] = chart_data['Type'].map(wine_type_emojis).fillna('🍷')
     
     if regional_grouping:
         chart_data['flag'] = chart_data['Country'].map(COUNTRY_FLAGS).fillna('🌍')
-        chart_data['grape_label'] = chart_data.apply(lambda row: f"{row['wine_emoji']} {row['main_grape']} {row['flag']}", axis=1)
+        # Vectorized string concatenation instead of apply
+        chart_data['grape_label'] = chart_data['wine_emoji'] + ' ' + chart_data['main_grape'] + ' ' + chart_data['flag']
     else:
-        chart_data['grape_label'] = chart_data.apply(lambda row: f"{row['wine_emoji']} {row['main_grape']}", axis=1)
+        chart_data['grape_label'] = chart_data['wine_emoji'] + ' ' + chart_data['main_grape']
+    print(f"[TIMING] Label preparation completed in {time.time() - prep_start:.2f}s")
 
     y_labels = chart_data['grape_label'].tolist()
 
@@ -196,14 +275,16 @@ def create_wine_chart(chart_data, regional_grouping):
         shared_yaxes=True
     )
 
-    hover_texts = chart_data.apply(
-        lambda row: (
-            f"<b>{row['main_grape']} ({row.get('Country', 'Global') if regional_grouping else 'Global'})</b><br>"
-            f"Wineries: {row['winery_count']}<br>"
-            f"Regions: {row['region_count']}<br>"
-            f"Total Wines: {row['count']:,}"),
-        axis=1
-    )
+    # Pre-compute hover texts more efficiently
+    hover_start = time.time()
+    country_part = chart_data['Country'] if regional_grouping else 'Global'
+    hover_texts = (
+        '<b>' + chart_data['main_grape'] + ' (' + country_part.astype(str) + ')</b><br>' +
+        'Wineries: ' + chart_data['winery_count'].astype(str) + '<br>' +
+        'Regions: ' + chart_data['region_count'].astype(str) + '<br>' +
+        'Total Wines: ' + chart_data['count'].apply(lambda x: f"{x:,}")
+    ).tolist()
+    print(f"[TIMING] Hover text preparation completed in {time.time() - hover_start:.2f}s")
     fig.add_trace(go.Bar(
         y=y_labels, x=[1] * num_rows, orientation='h',
         marker_color='rgba(0,0,0,0)', showlegend=False,
@@ -216,28 +297,47 @@ def create_wine_chart(chart_data, regional_grouping):
         hoverinfo='none', showlegend=False
     ), row=1, col=1)
 
+    # Optimize body distribution traces
+    body_start = time.time()
     body_colors = {'Very light-bodied': '#FFB6C1', 'Light-bodied': '#CD5C5C', 'Medium-bodied': '#C13636',
                    'Full-bodied': '#8B0000', 'Very full-bodied': '#4B0000'}
+    
+    # Pre-extract all body values at once
+    body_data = {}
+    for body_type in BODY_ORDER:
+        body_data[body_type] = [d.get(body_type, 0) for d in chart_data['body_dist']]
+    
     for body_type in BODY_ORDER:
-        values = chart_data['body_dist'].apply(lambda d: d.get(body_type, 0))
         fig.add_trace(go.Bar(
-            y=y_labels, x=values, name=body_type, orientation='h',
+            y=y_labels, x=body_data[body_type], name=body_type, orientation='h',
             marker_color=body_colors.get(body_type), showlegend=False,
             hovertemplate=f"{body_type}: %{{x:.1f}}%<extra></extra>"
         ), row=1, col=2)
+    print(f"[TIMING] Body traces completed in {time.time() - body_start:.2f}s")
 
+    # Optimize acidity distribution traces
+    acid_start = time.time()
     acid_colors = {'Low': '#F5F5DC', 'Medium': '#DAA520', 'High': '#B8860B'}
+    
+    # Pre-extract all acidity values at once
+    acid_data = {}
+    for acid_type in ACIDITY_ORDER:
+        acid_data[acid_type] = [d.get(acid_type, 0) for d in chart_data['acid_dist']]
+    
     for acid_type in ACIDITY_ORDER:
-        values = chart_data['acid_dist'].apply(lambda d: d.get(acid_type, 0))
         fig.add_trace(go.Bar(
-            y=y_labels, x=values, name=acid_type, orientation='h',
+            y=y_labels, x=acid_data[acid_type], name=acid_type, orientation='h',
             marker_color=acid_colors.get(acid_type), showlegend=False,
             hovertemplate=f"{acid_type} acidity: %{{x:.1f}}%<extra></extra>"
         ), row=1, col=3)
+    print(f"[TIMING] Acidity traces completed in {time.time() - acid_start:.2f}s")
 
-    # Color box plots by wine type
+    # Optimize box plot creation
+    box_start = time.time()
     box_colors = {'Red': '#8B0000', 'White': '#DAA520', 'Rosé': '#CD5C5C', 'Sparkling': '#9370DB'}
-    for idx, (i, row) in enumerate(chart_data.iterrows()):
+    
+    # Create box plots more efficiently
+    for idx, (_, row) in enumerate(chart_data.iterrows()):
         abv_values = row['abv_list']
         color = box_colors.get(row['Type'], '#6A5ACD')
         fig.add_trace(go.Box(
@@ -245,6 +345,7 @@ def create_wine_chart(chart_data, regional_grouping):
             showlegend=False, marker_color=color, line_color=color,
             hovertemplate=f"ABV: %{{x:.1f}}%<extra></extra>"
         ), row=1, col=4)
+    print(f"[TIMING] Box plot traces completed in {time.time() - box_start:.2f}s")
 
     fig.add_trace(go.Scatter(
         y=y_labels, x=[0.5] * num_rows, mode='text',
@@ -265,6 +366,8 @@ def create_wine_chart(chart_data, regional_grouping):
     )
 
     column_titles = ["Wine / Hover for Info", "Body Profile (%)", "Acidity Profile (%)", "Alcohol (ABV %)", "Food Pairing"]
+    # Add column titles
+    title_start = time.time()
     for i, title in enumerate(column_titles, 1):
         domain = fig.layout[f'xaxis{i if i > 1 else ""}'].domain
         fig.add_annotation(
@@ -272,18 +375,32 @@ def create_wine_chart(chart_data, regional_grouping):
             xref="paper", yref="paper", text=f"<b>{title}</b>",
             xanchor='center', showarrow=False, font={'size': 14, 'color': '#2F2F2F'}
         )
+    print(f"[TIMING] Column titles completed in {time.time() - title_start:.2f}s")
 
+    # Update axes formatting
+    axes_start = time.time()
     for i in range(1, 6):
         fig.update_yaxes(showticklabels=False, showgrid=False, zeroline=False, row=1, col=i)
         fig.update_xaxes(showticklabels=False, showgrid=False, zeroline=False, title_text="", row=1, col=i)
+    print(f"[TIMING] Axes formatting completed in {time.time() - axes_start:.2f}s")
 
+    # Final axis configuration
+    final_axes_start = time.time()
     fig.update_yaxes(categoryorder="array", categoryarray=y_labels, autorange=False, range=[-0.5, num_rows - 0.5],
                      row=1, col=1)
-
-    for i in range(num_rows):
-        if i % 2 == 1:
-            fig.add_hrect(y0=i - 0.5, y1=i + 0.5, fillcolor="#F0F0F0", layer="below", line_width=0, row=1, col="all")
-
+    print(f"[TIMING] Final axis configuration completed in {time.time() - final_axes_start:.2f}s")
+
+    # Skip alternating row backgrounds for better performance
+    # The rectangles were causing major slowdown (3+ seconds)
+    # bg_start = time.time()
+    # for i in range(num_rows):
+    #     if i % 2 == 1:
+    #         fig.add_hrect(y0=i - 0.5, y1=i + 0.5, fillcolor="#F0F0F0", layer="below", line_width=0, row=1, col="all")
+    # print(f"[TIMING] Background rectangles completed in {time.time() - bg_start:.2f}s")
+    print("[TIMING] Skipped background rectangles for performance")
+
+    chart_time = time.time() - chart_start
+    print(f"[TIMING] Chart creation completed in {chart_time:.2f}s")
     return fig
 
 
@@ -291,6 +408,9 @@ def create_wine_chart(chart_data, regional_grouping):
 def update_dashboard(wine_types, max_grape_count, min_samples_choice, regional_grouping,
                      progress=gr.Progress(track_tqdm=True)):
     """Main function to update dashboard."""
+    dashboard_start = time.time()
+    print(f"[TIMING] Starting dashboard update...")
+    
     progress(0, desc="Loading and processing data...")
     df = load_and_preprocess_data()
 
@@ -306,6 +426,8 @@ def update_dashboard(wine_types, max_grape_count, min_samples_choice, regional_g
     grouping_type = "grape+region" if regional_grouping else "grape+type"
     summary = f"📊 Showing **{total_combinations}** {grouping_type} combinations from **{total_wines:,}** wines (min {min_samples} samples each)"
 
+    total_dashboard_time = time.time() - dashboard_start
+    print(f"[TIMING] Total dashboard update completed in {total_dashboard_time:.2f}s")
     return fig, summary
 
 

pyproject.toml

@@ -0,0 +1,14 @@
+[project]
+name = "wine-analysis"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "pandas",
+    "plotly", 
+    "gradio",
+    "numpy",
+    "scipy",
+    "requests"
+]