Update app.py

app.py

@@ -11,12 +11,49 @@ st.title("📽️ Horror Reference Library")
 st.markdown("### Search 11,500+ Cinematic AI-Tagged Comic Panels")
 
 # ==========================================
-# 2. DATA LOADING
+# 2. DATA BUCKETING & CLEANING
 # ==========================================
+# This groups the messy AI tags into clean, professional cinematic categories
+def categorize_camera(text):
+    text = str(text).lower()
+    if 'dutch' in text: return 'Dutch Angle'
+    elif 'extreme close' in text or 'ecu' in text: return 'Extreme Close Up'
+    elif 'close' in text or 'cu' in text: return 'Close Up'
+    elif 'wide' in text or 'long' in text or 'establishing' in text: return 'Wide Shot'
+    elif 'mid' in text or 'medium' in text: return 'Mid Shot'
+    elif 'low angle' in text or 'looking up' in text: return 'Low Angle'
+    elif 'high angle' in text or 'looking down' in text: return 'High Angle'
+    elif 'pov' in text or 'point of view' in text: return 'Point of View'
+    else: return 'Other / Mixed'
+
+def categorize_mood(text):
+    text = str(text).lower()
+    if 'tense' in text or 'suspense' in text or 'anxiety' in text: return 'Tense & Suspenseful'
+    elif 'action' in text or 'chaos' in text or 'dynamic' in text: return 'Action & Chaos'
+    elif 'creepy' in text or 'eerie' in text or 'ominous' in text: return 'Creepy & Eerie'
+    elif 'gore' in text or 'violent' in text or 'blood' in text: return 'Gore & Violence'
+    elif 'sad' in text or 'melancholy' in text or 'somber' in text: return 'Somber & Melancholic'
+    else: return 'Neutral / Standard'
+
+def categorize_lighting(text):
+    text = str(text).lower()
+    if 'silhouette' in text: return 'Silhouetted'
+    elif 'high contrast' in text or 'chiaroscuro' in text: return 'High Contrast'
+    elif 'low key' in text or 'shadow' in text or 'dark' in text: return 'Low Key (Shadowy)'
+    elif 'harsh' in text or 'bright' in text: return 'Harsh & Bright'
+    elif 'flat' in text or 'even' in text: return 'Flat Lighting'
+    else: return 'Standard Lighting'
+
 @st.cache_data
 def load_data():
-    # This loads the CSV "Map" you uploaded to the Space
     df = pd.read_csv("horror_shot_database.csv")
+    
+    # Create new "Clean" columns for the UI
+    df['broad_camera'] = df['camera_angle'].apply(categorize_camera)
+    df['broad_mood'] = df['mood'].apply(categorize_mood)
+    # We search both mood and description to figure out the lighting
+    df['broad_lighting'] = (df['mood'].fillna('') + " " + df['description'].fillna('')).apply(categorize_lighting)
+    
     return df
 
 try:
@@ -30,54 +67,62 @@ except Exception as e:
 # ==========================================
 st.sidebar.header("🔍 Search Library")
 
-# 1. The Global Text Search Bar
-search_query = st.sidebar.text_input("Keyword Search", placeholder="e.g., monster, shadow, running...")
+# The Global Text Search Bar
+search_query = st.sidebar.text_input("Keyword Search", placeholder="e.g., monster, running, eyes...")
 st.sidebar.write("---")
 
 st.sidebar.header("📂 Filter Categories")
 
-# 2. Expandable Category: Camera
-with st.sidebar.expander("🎥 Camera & Framing"):
-    all_angles = ["Any"] + sorted(df['camera_angle'].dropna().unique().tolist())
-    selected_angle = st.selectbox("Camera Angle", all_angles)
+# Expandable Category: Camera
+with st.sidebar.expander("🎥 Camera & Framing", expanded=True):
+    all_angles = ["Any"] + sorted(df['broad_camera'].unique().tolist())
+    selected_angle = st.selectbox("Shot Type", all_angles)
 
-# 3. Expandable Category: Mood & Emotion
-with st.sidebar.expander("🎭 Mood & Character"):
-    all_moods = ["Any"] + sorted(df['mood'].dropna().unique().tolist())
-    selected_mood = st.selectbox("Lighting/Mood", all_moods)
-    
-    all_emotions = ["Any"] + sorted(df['emotion'].dropna().unique().tolist())
-    selected_emotion = st.selectbox("Character Emotion", all_emotions)
+# Expandable Category: Lighting
+with st.sidebar.expander("💡 Lighting Style"):
+    all_lighting = ["Any"] + sorted(df['broad_lighting'].unique().tolist())
+    selected_lighting = st.selectbox("Lighting Category", all_lighting)
 
-# Add more expanders here later if you add things like "Time of Day" or "Location"!
+# Expandable Category: Mood
+with st.sidebar.expander("🎭 Scene Mood"):
+    all_moods = ["Any"] + sorted(df['broad_mood'].unique().tolist())
+    selected_mood = st.selectbox("Atmosphere", all_moods)
 
 # ==========================================
-# 4. FILTERING LOGIC (Connecting to Dataset)
+# 4. FILTERING LOGIC
 # ==========================================
 results = df.copy()
 
-# Apply the text search (searches the AI description column)
+# Apply the text search
 if search_query:
     results = results[results['description'].str.contains(search_query, case=False, na=False)]
 
-# Apply the dropdown filters
+# Apply the clean dropdown filters
 if selected_angle != "Any":
-    results = results[results['camera_angle'] == selected_angle]
+    results = results[results['broad_camera'] == selected_angle]
+if selected_lighting != "Any":
+    results = results[results['broad_lighting'] == selected_lighting]
 if selected_mood != "Any":
-    results = results[results['mood'] == selected_mood]
-if selected_emotion != "Any":
-    results = results[results['emotion'] == selected_emotion]
+    results = results[results['broad_mood'] == selected_mood]
 
-# --- KEEP YOUR EXISTING URL CONSTRUCTOR BELOW THIS ---
 base_url = "https://huggingface.co/datasets/Roshanurs/Horror-Reference-Data/resolve/main/Panels_Out"
 
-# ... (The rest of your code stays exactly the same!)
+valid_images = []
+for idx, row in results.iterrows():
+    img_url = f"{base_url}/{row['filename']}"
+    valid_images.append({
+        "url": img_url,
+        "filename": row['filename'],
+        "desc": row['description']
+    })
+
+st.markdown(f"**Found {len(valid_images)} matching shots**")
+st.write("---") 
 
 # ==========================================
 # 5. THE MASONRY GALLERY 
 # ==========================================
 if len(valid_images) > 0:
-    # We show the first 100 results to keep the page fast
     display_limit = 100
     display_list = valid_images[:display_limit]
     
@@ -85,10 +130,8 @@ if len(valid_images) > 0:
     
     for index, img_data in enumerate(display_list):
         with cols[index % 4]:
-            # Streamlit fetches the image directly from the Dataset URL
             st.image(img_data["url"], use_container_width=True)
             
-            # Download button that opens the raw image in a new tab
             st.markdown(
                 f'<a href="{img_data["url"]}" target="_blank">'
                 f'<button style="width:100%; padding:8px; border-radius:4px; border:1px solid #444; background:#222; color:white; cursor:pointer;">'