Update app.py

app.py

@@ -12,13 +12,19 @@ import pandas as pd
 import numpy as np
 import time
 
-
 # ==========================================
-# 1. PAGE CONFIG & UI SETUP
+# 1. PAGE CONFIG & UI SETUP (WITH ANTI-GLITCH CSS)
 # ==========================================
 st.set_page_config(page_title="Neural VAE Architecture", layout="wide")
 
-# (Make sure these two lines only appear ONCE in your entire file!)
+# FIX: CSS injection to permanently lock the scrollbar and prevent horizontal jumping!
+st.markdown("""
+    <style>
+        html { overflow-y: scroll; }
+        .block-container { overflow-x: hidden; }
+    </style>
+    """, unsafe_allow_html=True)
+
 st.title("🧠 Variational Autoencoder (VAE): Inside the Black Box")
 st.markdown("Watch the mathematics of a Neural Network transform text into topics in real-time.")
 
@@ -35,7 +41,6 @@ st.divider()
 def load_bert():
     return SentenceTransformer("all-MiniLM-L6-v2")
 
-
 # --- SIDEBAR CONTROLS ---
 st.sidebar.header("1. Input & Text Prep")
 n_topics = st.sidebar.slider("Number of Topics (Latent Dimensions)", 2, 10, 3)
@@ -69,7 +74,6 @@ class ContextualVAE(nn.Module):
         super().__init__()
         act_fn = nn.ReLU() if activation == "ReLU" else nn.Softplus() if activation == "Softplus" else nn.GELU()
 
-        # 1. ENCODER
         self.encoder = nn.Sequential(
             nn.Linear(input_dim, hidden_dim), 
             act_fn, 
@@ -78,8 +82,6 @@ class ContextualVAE(nn.Module):
         )
         self.fc_mu = nn.Linear(hidden_dim, latent_dim)
         self.fc_logvar = nn.Linear(hidden_dim, latent_dim)
-        
-        # 2. DECODER
         self.decoder = nn.Linear(latent_dim, vocab_size, bias=False)
 
     def encode(self, x):
@@ -150,7 +152,6 @@ if st.sidebar.button("🚀 Start Backpropagation", type="primary", use_container
     
     sentences = [s.strip() for s in raw_data.split('.') if len(s.strip()) > 10]
     
-    # Data Prep
     stop_w = list(CountVectorizer(stop_words='english').get_stop_words()) + ['students', 'course']
     vectorizer = CountVectorizer(stop_words=stop_w)
     bow_matrix = vectorizer.fit_transform(sentences).toarray()
@@ -167,11 +168,7 @@ if st.sidebar.button("🚀 Start Backpropagation", type="primary", use_container
     optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
     
     recon_hist, kl_hist = [], []
-    
-    # Trackers for the expanding history tables
-    history_encoder = []
-    history_latent = []
-    history_decoder = []
+    history_encoder, history_latent, history_decoder = [], [], []
     
 # --- PYTORCH TRAINING LOOP ---
     for epoch in range(1, epochs + 1):
@@ -189,20 +186,15 @@ if st.sidebar.button("🚀 Start Backpropagation", type="primary", use_container
         total_loss.backward()
         optimizer.step()
         
-        # ==========================================
-        # 1. RECORD DATA EVERY SINGLE EPOCH
-        # ==========================================
         # Grab math for Sentence 1
         s1_mu = np.round(mu[0].detach().numpy(), 3).tolist()
         s1_var = np.round(torch.exp(0.5 * logvar[0]).detach().numpy(), 3).tolist()
         s1_z = np.round(z[0].detach().numpy(), 3).tolist()
         s1_soft = np.round(F.softmax(z[0], dim=-1).detach().numpy(), 3).tolist()
         
-        # Save to Encoder & Latent History
         history_encoder.append({"Epoch": epoch, "Mean (μ)": str(s1_mu), "Variance (σ)": str(s1_var)})
         history_latent.append({"Epoch": epoch, "Sampled Vector (Z)": str(s1_z), "Topic Probs": str(s1_soft)})
         
-        # Dynamically create separate columns for EACH topic in the Decoder history!
         weights = model.decoder.weight.T
         dec_dict = {"Epoch": epoch}
         dec_text = ""
@@ -210,10 +202,7 @@ if st.sidebar.button("🚀 Start Backpropagation", type="primary", use_container
         for i in range(n_topics):
             top_idx = torch.argsort(weights[i], descending=True)[:words_per_theme]
             theme_words = [vocab[j] for j in top_idx]
-            
-            # Format for the UI Box
             dec_text += f"**T{i+1}:** {', '.join(theme_words)}\n\n"
-            # Format for the DataFrame (Separate column for Topic 1, Topic 2, etc.)
             dec_dict[f"Topic {i+1}"] = ", ".join(theme_words)
             
         history_decoder.append(dec_dict)
@@ -222,34 +211,28 @@ if st.sidebar.button("🚀 Start Backpropagation", type="primary", use_container
         kl_hist.append((current_beta * kl_loss).item())
         
         # ==========================================
-        # 2. SAFE UI RENDER (Draws the accumulated data every 20 epochs)
+        # 2. SAFE UI RENDER (Every 20 epochs)
         # ==========================================
         if epoch % 20 == 0 or epoch == epochs:
             
-            # Update Live Values
             ui_mu.info(f"**Mean (μ) for Sentence 1:**\n`{s1_mu}`")
             ui_var.warning(f"**Variance (σ) for Sentence 1:**\n`{s1_var}`")
             ui_z.success(f"**Sampled 'Z' for Sentence 1:**\n`{s1_z}`")
             ui_softmax.error(f"**Topic Probabilities:**\n`{s1_soft}`")
             ui_decoder.info(dec_text)
             
-            # Update Tables (These now contain ALL epochs up to this point!)
-            ui_encoder_table.dataframe(pd.DataFrame(history_encoder), hide_index=True, use_container_width=True)
-            ui_latent_table.dataframe(pd.DataFrame(history_latent), hide_index=True, use_container_width=True)
-            ui_decoder_table.dataframe(pd.DataFrame(history_decoder), hide_index=True, use_container_width=True)
+            # FIX: Added `height=200` to prevent the dataframe from stretching the webpage!
+            ui_encoder_table.dataframe(pd.DataFrame(history_encoder), hide_index=True, use_container_width=True, height=200)
+            ui_latent_table.dataframe(pd.DataFrame(history_latent), hide_index=True, use_container_width=True, height=200)
+            ui_decoder_table.dataframe(pd.DataFrame(history_decoder), hide_index=True, use_container_width=True, height=200)
             
-            # Update Optimization Metrics
             ui_beta.metric("Current Beta (Annealing)", f"{current_beta:.4f}")
             ui_recon_loss.metric("Reconstruction Loss", f"{recon_loss.item():.4f}")
             ui_kl_loss.metric("KL Penalty", f"{(current_beta * kl_loss).item():.4f}")
             
-            # Update Graph
-            chart_df = pd.DataFrame({
-                "Recon Loss": recon_hist, 
-                "KL Penalty": kl_hist
-            })
+            chart_df = pd.DataFrame({"Recon Loss": recon_hist, "KL Penalty": kl_hist})
             loss_chart_placeholder.line_chart(chart_df)
             
-            time.sleep(0.05)
+            time.sleep(0.01) # Slightly faster sleep to prevent HF WebSocket timeouts
 
     st.success("Neural Network Training Complete!")