Update app.py

app.py

@@ -1,13 +1,12 @@
-# app.py
-
 import pandas as pd
 import gradio as gr
+import plotly.graph_objects as go
 from sklearn.pipeline import Pipeline
 from sklearn.preprocessing import StandardScaler
 from sklearn.decomposition import PCA
 from sklearn.ensemble import RandomForestClassifier
 
-# Simulated Morningstar-like data
+# Sample data
 data = {
     'Expense_Ratio': [0.7, 0.5, 1.2, 0.9, 0.6, 1.5, 0.3, 0.8, 1.0, 0.4],
     'AUM': [1000, 1500, 800, 1200, 1100, 500, 1600, 1400, 700, 1800],
@@ -20,7 +19,7 @@ df = pd.DataFrame(data)
 X = df.drop("Label", axis=1)
 y = df["Label"]
 
-# Build ML pipeline
+# ML pipeline
 pipeline = Pipeline([
     ('scaler', StandardScaler()),
     ('pca', PCA(n_components=2)),
@@ -28,8 +27,30 @@ pipeline = Pipeline([
 ])
 pipeline.fit(X, y)
 
-# Gradio prediction function
-def predict(expense_ratio, aum, risk_score, return_3y, return_5y):
+# Radar chart function
+def create_radar_chart(input_data):
+    categories = list(input_data.columns)
+    values = input_data.iloc[0].tolist()
+    
+    fig = go.Figure(data=go.Scatterpolar(
+        r=values + [values[0]],
+        theta=categories + [categories[0]],
+        fill='toself',
+        name='Fund Metrics'
+    ))
+    
+    fig.update_layout(
+        polar=dict(
+            radialaxis=dict(visible=True)
+        ),
+        showlegend=False,
+        margin=dict(t=10, b=10)
+    )
+    
+    return fig
+
+# Main Gradio function
+def predict_and_visualize(expense_ratio, aum, risk_score, return_3y, return_5y):
     input_df = pd.DataFrame([{
         "Expense_Ratio": expense_ratio,
         "AUM": aum,
@@ -37,12 +58,16 @@ def predict(expense_ratio, aum, risk_score, return_3y, return_5y):
         "3_Year_Return": return_3y,
         "5_Year_Return": return_5y
     }])
+    
     prediction = pipeline.predict(input_df)[0]
-    return "High-performing Fund" if prediction == 1 else "Low-performing Fund"
+    label = "High-performing Fund ✅" if prediction == 1 else "Low-performing Fund ❌"
+    chart = create_radar_chart(input_df)
+    
+    return label, chart
 
-# Interface
+# Gradio interface
 gr.Interface(
-    fn=predict,
+    fn=predict_and_visualize,
     inputs=[
         gr.Number(label="Expense Ratio"),
         gr.Number(label="AUM (in crores)"),
@@ -50,7 +75,10 @@ gr.Interface(
         gr.Number(label="3-Year Return (%)"),
         gr.Number(label="5-Year Return (%)"),
     ],
-    outputs="text",
-    title="Morningstar Fund Classifier",
-    description="Predict if a fund is high or low performing based on its metrics."
+    outputs=[
+        gr.Textbox(label="Prediction"),
+        gr.Plot(label="Fund Score Radar Chart")
+    ],
+    title="Morningstar Fund Classifier with Score Chart",
+    description="Predict and visualize if a fund is high or low performing based on its key metrics."
 ).launch()