Update app.py

app.py

@@ -88,37 +88,43 @@ with col_a:
 with col_b:
     words_per_theme = st.slider("Words to Output per Theme", 3, 10, 5)
 
+# --- THE VERTICAL CONFIGURATION WIZARD ---
 st.header("⚙️ Model Configuration")
 
-col1, col2 = st.columns(2)
-with col1:
-    with st.expander("1️⃣ Semantic Layer (Embeddings)", expanded=True):
-        ui_embedding = st.selectbox("Embedding Model", list(EMBEDDING_MAP.keys()))
-        ui_pooling = st.selectbox("Pooling Strategy", list(POOLING_MAP.keys()))
-
-with col2:
-    with st.expander("2️⃣ Geometry Layer (Dimensionality Reduction)", expanded=True):
-        ui_algo = st.selectbox("Algorithm", ["UMAP (Complex geometry)", "PCA (Fast/Deterministic)"])
-        ui_metric = st.selectbox("Distance Metric", ["cosine", "euclidean", "manhattan"]) if "UMAP" in ui_algo else "euclidean"
-
-col3, col4 = st.columns(2)
-with col3:
-    with st.expander("3️⃣ Clustering Layer (Grouping)", expanded=True):
-        st.markdown("""
-        *Clustering mathematically draws boundaries around similar sentences.*
-        * **Primary (HDBSCAN):** $\ge$ 15 sentences. Filters outliers. *(Defaults: min_cluster_size=10)*
-        * **Fallback (K-Means):** $<$ 15 sentences. Forces buckets to prevent math crashes on tiny text.
-        """)
-
-with col4:
-    with st.expander("4️⃣ Vocabulary Layer (Vectorization)", expanded=True):
-        ngram_range = st.slider("N-Gram Range", 1, 3, (1, 2))
-        auto_noise = st.checkbox("Auto-Remove Redundant Noise", value=True, help="Mathematically deletes words appearing in >85% of documents.")
+with st.expander("1️⃣ Semantic Layer (Embeddings & Pooling)", expanded=True):
+    st.markdown("*💡 **BERTopic Default:** Uses `all-MiniLM-L6-v2` with `Mean` pooling.*")
+    ui_embedding = st.selectbox("Embedding Model (Override Default):", list(EMBEDDING_MAP.keys()))
+    ui_pooling = st.selectbox("Pooling Strategy (Override Default):", list(POOLING_MAP.keys()))
+
+with st.expander("2️⃣ Geometry Layer (Dimensionality Reduction)", expanded=True):
+    st.markdown("*💡 **BERTopic Default:** Uses `UMAP` with `Cosine` distance to reduce 384D to 5D space.*")
+    ui_algo = st.selectbox("Algorithm", ["UMAP (Complex geometry)", "PCA (Fast/Deterministic)"])
+    if "UMAP" in ui_algo:
+        ui_metric = st.selectbox("Distance Metric", ["cosine", "euclidean", "manhattan"])
+    else:
+        ui_metric = "euclidean"
+        st.info("PCA inherently uses Variance (Euclidean math), so distance metrics are bypassed.")
+
+with st.expander("3️⃣ Clustering Layer (Grouping)", expanded=True):
+    st.markdown("*💡 **BERTopic Default:** Uses `HDBSCAN` exclusively (which crashes on tiny datasets).*")
+    st.markdown("""
+    *Our Engine mathematically draws boundaries around similar sentences using a smart-routing system:*
+    * **Primary Engine (HDBSCAN):** Runs on datasets $\ge$ 15 sentences. Automatically filters outliers and finds dense semantic clouds. *(Defaults: min_cluster_size=10)*
+    * **Fallback Engine (K-Means):** Runs on datasets $<$ 15 sentences. Forces all sentences into buckets to prevent math crashes on tiny text samples.
+    """)
+
+with st.expander("4️⃣ Vocabulary Layer (Vectorization)", expanded=True):
+    st.markdown("*💡 **BERTopic Default:** Uses `Unigrams` (1 word) and does **not** filter redundant dataset noise.*")
+    ngram_range = st.slider("N-Gram Range", 1, 3, (1, 2), help="1=Unigrams, 2=Bigrams (e.g., 'machine learning')")
+    auto_noise = st.checkbox("Auto-Remove Redundant Noise (max_df)", value=True, help="Mathematically deletes words appearing in >85% of documents.")
 
 with st.expander("5️⃣ Extraction Layer (Representation)", expanded=True):
-    st.markdown("*BERTopic ALWAYS extracts baseline words using **c-TF-IDF**. Do you want to apply an advanced mathematical filter on top of it?*")
-    ui_extraction = st.selectbox("Apply Advanced Filter:", ["None (Base c-TF-IDF only)", "KeyBERTInspired (Semantic alignment)", "MMR (Reduce redundancy)"])
-    mmr_diversity = st.slider("MMR Diversity Penalty", 0.0, 1.0, 0.3) if "MMR" in ui_extraction else None
+    st.markdown("*💡 **BERTopic Default:** ALWAYS extracts baseline words using **c-TF-IDF** (Word Frequency).*")
+    ui_extraction = st.selectbox("Apply Advanced Filter on top of c-TF-IDF:", ["None (Base c-TF-IDF only)", "KeyBERTInspired (Semantic cosine)", "MMR (Reduce redundancy)"])
+    if "MMR" in ui_extraction:
+        mmr_diversity = st.slider("MMR Diversity Penalty", 0.0, 1.0, 0.3)
+    else:
+        mmr_diversity = None
 
 st.header("📊 Evaluation Metrics")
 eval_metrics = st.multiselect(