Update app.py

app.py

@@ -26,7 +26,17 @@ warnings.filterwarnings("ignore")
 # ==========================================
 # 1. PAGE CONFIGURATION & MAPPINGS
 # ==========================================
-st.set_page_config(page_title="Topic Modeling Pipeline", layout="wide", initial_sidebar_state="collapsed")
+st.set_page_config(page_title="Topic Modeling Pipeline", layout="wide", initial_sidebar_state="expanded")
+
+# Add this right below set_page_config to stop the screen from jumping left/right
+st.markdown("""
+    <style>
+        /* Force the vertical scrollbar to always show so the page width never changes */
+        html { overflow-y: scroll; }
+        /* Prevent horizontal scrolling */
+        .block-container { max-width: 100%; overflow-x: hidden; }
+    </style>
+    """, unsafe_allow_html=True)
 
 EMBEDDING_MAP = {
     "MiniLM (Fast & Lightweight)": "sentence-transformers/all-MiniLM-L6-v2",
@@ -305,7 +315,11 @@ if st.button("🚀 Run Topic Modeling Pipeline", type="primary", use_container_w
     with st.spinner("Rendering Mathematical Dashboard..."):
         sns.set_theme(style="whitegrid")
         fig = plt.figure(figsize=(18, 16)) 
-        fig.suptitle(f"Topic Modeling Mathematical Pipeline\n(Pooling: {ui_pooling.split()[0]} | Rep: {ui_extraction.split()[0]})", fontsize=20, fontweight='bold', y=0.98)
+        
+        # Safe extraction for the title
+        pool_title = ui_pooling.split()[0]
+        rep_title = ui_extraction.split()[0]
+        fig.suptitle(f"Topic Modeling Mathematical Pipeline\n(Pooling: {pool_title} | Rep: {rep_title})", fontsize=20, fontweight='bold', y=0.98)
         
         # Style for the Math/Data boxes
         box_style = dict(boxstyle="round,pad=0.5", facecolor='#f8f9fa', edgecolor='#4b72b8', alpha=0.95, lw=2)
@@ -372,12 +386,16 @@ if st.button("🚀 Run Topic Modeling Pipeline", type="primary", use_container_w
         # 4. Representation
         # --------------------------------------------------
         ax4 = plt.subplot(3, 2, 4)
-        theme_1_data = topic_model.get_topic(0)
+        
+        # Safely grab the first valid topic found
+        valid_topics = [t for t in topic_model.get_topics().keys() if t != -1]
+        theme_1_data = topic_model.get_topic(valid_topics[0]) if valid_topics else None
+
         if theme_1_data:
             words = [x[0] for x in theme_1_data][::-1] 
             scores = [x[1] for x in theme_1_data][::-1]
             ax4.barh(words, scores, color='coral', edgecolor='black')
-            ax4.set_title(f"STEP 4: Topic Representation ({ui_extraction.split()[0]})", fontsize=13, fontweight='bold')
+            ax4.set_title(f"STEP 4: Topic Representation ({rep_title})", fontsize=13, fontweight='bold')
             
             # Live Data Extraction
             top_word_score = round(scores[-1], 4)
@@ -392,12 +410,12 @@ if st.button("🚀 Run Topic Modeling Pipeline", type="primary", use_container_w
         else:
             ax4.text(0.5, 0.5, "Theme not found", ha='center', transform=ax4.transAxes)
 
-# --------------------------------------------------
-        # 5. KPI Dashboard (Formulas & Live Calculations)
+        # --------------------------------------------------
+        # 5. KPI Dashboard
         # --------------------------------------------------
         ax5 = plt.subplot(3, 2, 5)
         ax5.axis('off') 
-        ax5.set_title("STEP 5: Post-Hoc Evaluation (Math & Live Data)", fontsize=13, fontweight='bold', y=0.9)
+        ax5.set_title("STEP 5: Post-Hoc Evaluation Formulas", fontsize=13, fontweight='bold', y=0.9)
         
         # Get the actual distance metric used for the label
         dist_used = ui_metric if algo_used == "UMAP" else "euclidean"
@@ -413,9 +431,9 @@ if st.button("🚀 Run Topic Modeling Pipeline", type="primary", use_container_w
             f"Live Calc: Score = {npmi_status} across {len(all_words)} valid themes"
         )
         
-        ax5.text(0.5, 0.4, kpi_math, fontsize=11, va='center', ha='center', 
+        ax5.text(0.5, 0.4, kpi_math, fontsize=12, va='center', ha='center', 
                  bbox=dict(boxstyle="square,pad=1.5", facecolor='#e6f2ff', edgecolor='#377eb8', lw=2))
-        
+
         # --------------------------------------------------
         # 6. Summary Matrix Transformations
         # --------------------------------------------------
@@ -427,7 +445,7 @@ if st.button("🚀 Run Topic Modeling Pipeline", type="primary", use_container_w
             f"2. {emb_shape} $\\rightarrow$ {red_shape} Matrix (Geometric Compression)\n"
             f"3. {red_shape} $\\rightarrow$ ({len(topics)},) Array (Discrete Bucketing)\n"
             f"4. ({len(topics)},) $\\rightarrow$ c-TF-IDF Matrix (Word Extraction)\n"
-            f"5. c-TF-IDF $\\rightarrow$ {CONFIG['words_per_theme']} Output Words (Per Theme)\n\n"
+            f"5. c-TF-IDF $\\rightarrow$ {words_per_theme} Output Words (Per Theme)\n\n"  # THE BUG FIX!
             "This proves Topic Modeling is a sequence of \ndimensionality reductions and matrix multiplications."
         )
         ax6.text(0.1, 0.5, summary_text, fontsize=12, va='center', ha='left', 
@@ -435,5 +453,3 @@ if st.button("🚀 Run Topic Modeling Pipeline", type="primary", use_container_w
 
         plt.subplots_adjust(hspace=0.7, wspace=0.3)
         st.pyplot(fig, use_container_width=True)
-
-