Update app.py

app.py

@@ -5,7 +5,7 @@ import matplotlib.pyplot as plt
 from sklearn.svm import SVC
 from sklearn.preprocessing import StandardScaler
 
-# --- Sample data mimicking Morningstar style ---
+# --- Sample Morningstar-style data ---
 data = {
     "5Y_Return": [14.0, 7.5, 13.2, 6.0, 15.0, 8.0, 12.0, 6.5, 10.5, 7.2],
     "Volatility": [8.0, 6.5, 7.8, 9.0, 7.0, 6.2, 7.1, 8.5, 6.8, 7.9],
@@ -15,7 +15,7 @@ data = {
 df = pd.DataFrame(data)
 df["Label"] = df["Rating"].map({"Good": 1, "Bad": 0})
 
-# --- Train the 3-feature SVM model for prediction ---
+# --- Train full SVM model for prediction ---
 X = df[["5Y_Return", "Volatility", "Risk_Score"]]
 y = df["Label"]
 
@@ -25,19 +25,18 @@ X_scaled = scaler.fit_transform(X)
 model = SVC(kernel="linear", probability=True)
 model.fit(X_scaled, y)
 
-# --- Function to predict and plot ---
+# --- Function to classify and plot 2D SVM boundary ---
 def classify_and_plot(return_5y, volatility, risk_score):
-    # Prediction
+    # Predict
     input_data = [[return_5y, volatility, risk_score]]
     input_scaled = scaler.transform(input_data)
     prediction = model.predict(input_scaled)[0]
     confidence = model.predict_proba(input_scaled)[0][prediction]
     result = "Good Investment" if prediction == 1 else "Bad Investment"
 
-    # --- Use only 2 features for plotting ---
+    # For plotting, use only 2D
     X_2d = df[["5Y_Return", "Volatility"]].values
     y_2d = df["Label"].values
-
     scaler_2d = StandardScaler()
     X_2d_scaled = scaler_2d.fit_transform(X_2d)
 
@@ -47,10 +46,12 @@ def classify_and_plot(return_5y, volatility, risk_score):
     # Plot decision boundary
     fig, ax = plt.subplots(figsize=(6, 5))
     ax.scatter(X_2d_scaled[:, 0], X_2d_scaled[:, 1], c=y_2d, cmap="bwr", edgecolors="k", s=60)
+
+    # Support vectors
     ax.scatter(model_2d.support_vectors_[:, 0], model_2d.support_vectors_[:, 1],
                s=150, facecolors='none', edgecolors='k', linewidths=1.5, label="Support Vectors")
 
-    # Grid
+    # Decision boundary
     xlim = ax.get_xlim()
     ylim = ax.get_ylim()
     xx = np.linspace(xlim[0], xlim[1], 30)
@@ -58,17 +59,17 @@ def classify_and_plot(return_5y, volatility, risk_score):
     YY, XX = np.meshgrid(yy, xx)
     xy = np.vstack([XX.ravel(), YY.ravel()]).T
     Z = model_2d.decision_function(xy).reshape(XX.shape)
-
     ax.contour(XX, YY, Z, colors='k', levels=[-1, 0, 1],
                alpha=0.7, linestyles=['--', '-', '--'])
 
+    # Annotations
     ax.set_title("SVM Decision Boundary (2 Features)")
     ax.set_xlabel("5Y Return (scaled)")
     ax.set_ylabel("Volatility (scaled)")
     ax.legend()
     ax.grid(True)
 
-    # Save and return plot
+    # Save and return image
     plot_path = "/tmp/svm_plot.png"
     fig.savefig(plot_path)
     plt.close(fig)
@@ -78,12 +79,23 @@ def classify_and_plot(return_5y, volatility, risk_score):
 # --- Gradio UI ---
 with gr.Blocks() as demo:
     gr.Markdown("## 🧠 SVM Classifier: Mutual Fund Recommendation")
+
     with gr.Row():
         return_input = gr.Number(label="5-Year Return (%)", value=10.0)
         vol_input = gr.Number(label="Volatility (%)", value=7.0)
         risk_input = gr.Number(label="Risk Score (1=Low, 5=High)", value=3)
+
     classify_btn = gr.Button("Classify and Show Decision Boundary")
     output_label = gr.Textbox(label="Prediction")
+
+    gr.Markdown("""### 📊 Benchmark Guide  
+**🔴 Blue Dots = Good Investments**  
+**🔴 Red Dots = Bad Investments**  
+**⚫ Solid Black Line = Decision Boundary**  
+**⚫ Dashed Lines = Margins (distance to support vectors)**  
+**⭕ Large Hollow Dots = Support Vectors (key data points)**  
+""")
+
     output_plot = gr.Image(label="SVM Decision Boundary")
 
     classify_btn.click(
@@ -92,6 +104,5 @@ with gr.Blocks() as demo:
         outputs=[output_label, output_plot]
     )
 
-# Launch app
 if __name__ == "__main__":
     demo.launch()