Update app.py

app.py

@@ -184,28 +184,25 @@ with tab1:
         st.write("""
         ##### 🧠 PCA (Principal Component Analysis) is like looking at a messy room from the best angle to see the most mess. It helps us see our data more clearly!
         """)
-        
         # Apply PCA for dimensionality reduction
         pca = PCA(n_components=2)
         X_transformed = pca.fit_transform(X)
         user_features_transformed = pca.transform([user_features])[0]
-        st.write("Using PCA for visualization.")  # Debugging print statement
     else:
         X_transformed = X[:, :2]  # Just use the first two features for visualization
         user_features_transformed = user_features[:2]
-        st.write("Using the first two features for visualization.")  # Debugging print statement
+    
+    # Create a DataFrame for easier plotting with plotly
+    df_transformed = pd.DataFrame(X_transformed, columns=['Feature1', 'Feature2'])
     
     # K-Means Algorithm
     kmeans = KMeans(n_clusters=n_clusters_advanced)
     y_kmeans = kmeans.fit_predict(X_transformed)
+    df_transformed['cluster'] = y_kmeans
     
     # Predict the cluster for the user input in the transformed space
     predicted_cluster = kmeans.predict([user_features_transformed])
     
-    # Create a DataFrame for easier plotting with plotly
-    df_transformed = pd.DataFrame(X_transformed, columns=['Feature1', 'Feature2'])
-    df_transformed['cluster'] = y_kmeans
-    
     # For tab1
     fig = go.Figure()
     
@@ -218,8 +215,11 @@ with tab1:
             hull = ConvexHull(cluster_data[['Feature1', 'Feature2']])
             fig.add_trace(go.Scatter(x=x_data[hull.vertices], y=y_data[hull.vertices], fill='toself', fillcolor=px.colors.qualitative.Set1[cluster], opacity=0.5, line=dict(width=0), showlegend=False))
     
-    # Add scatter plot
-    fig.add_trace(go.Scatter(x=df_transformed['Feature1'], y=df_transformed['Feature2'], mode='markers', marker=dict(color=y_kmeans, colorscale=px.colors.qualitative.Set1), showlegend=False))
+    # Add scatter plot based on PCA toggle
+    if use_pca:
+        fig.add_trace(go.Scatter(x=df_transformed['Feature1'], y=df_transformed['Feature2'], mode='markers', marker=dict(color=y_kmeans, colorscale=px.colors.qualitative.Set1), showlegend=False))
+    else:
+        fig.add_trace(go.Scatter(x=df_transformed['Feature1'], y=df_transformed['Feature2'], mode='markers', marker=dict(color=y_kmeans, colorscale=px.colors.qualitative.Set1, symbol='square'), showlegend=False))
     
     # Add user input as a star marker
     fig.add_trace(go.Scatter(x=[user_features_transformed[0]], y=[user_features_transformed[1]], mode='markers', marker=dict(symbol='star', size=30, color='white')))
@@ -236,7 +236,7 @@ with tab1:
     
     # Update layout
     fig.update_layout(width=1200, height=500)
-    
+        
     st.write("""
     ### Visualizing Groups
     ##### Here are the groups from our tidying method. Each color has a number at its center, representing its group.