Update app.py

app.py

@@ -1,70 +1,97 @@
-import gradio as gr
+import streamlit as st
 import joblib
 import pandas as pd
 from PIL import Image
 
-best_model = joblib.load("best_model.pkl")
-roc_img = Image.open("roc_curve_rf_tuned.png")
+# Load the model and image
+@st.cache_resource
+def load_model():
+    return joblib.load("best_model.pkl")
 
-def churn_prediction(age, gender, tenure, usage_frequency, support_calls,
-                     payment_delay, last_interaction, total_spend,
-                     subscription_type, contract_length):
-    try:
-
-        input_data = {
-            "Age": age,
-            "Gender_Male": 1 if gender == "Male" else 0,
-            "Gender_Female": 1 if gender == "Female" else 0,
-            "Usage Frequency": usage_frequency,
-            "Support Calls": support_calls,
-            "Contract Length_Monthly": 1 if contract_length == "Monthly" else 0,
-            "Contract Length_Quarterly": 1 if contract_length == "Quarterly" else 0,
-            "Contract Length_Annual": 1 if contract_length == "Annual" else 0,
-            "Payment Delay": payment_delay,
-            "Last Interaction": last_interaction,
-            "Total Spend": total_spend,
-            "Tenure": tenure,
-            "Subscription Type_Basic": 1 if subscription_type == "Basic" else 0,
-            "Subscription Type_Premium": 1 if subscription_type == "Premium" else 0,
-            "Subscription Type_Standard": 1 if subscription_type == "Standard" else 0,
-        }
-
-        input_df = pd.DataFrame([input_data])
+@st.cache_data
+def load_roc_image():
+    return Image.open("roc_curve_rf_tuned.png")
 
-        # Predict churn and probability
-        prediction = best_model.predict(input_df)
-        prediction_proba = best_model.predict_proba(input_df)[:, 1]
+try:
+    best_model = load_model()
+    roc_img = load_roc_image()
+except Exception as e:
+    st.error(f"Error loading model or image: {str(e)}")
+    st.stop()
 
-        churn_result = "Yes" if prediction[0] == 1 else "No"
-        churn_probability = f"{prediction_proba[0]:.2f}"
+# App title and description
+st.title("Customer Churn Prediction")
+st.write("Enter customer information to predict likelihood of churn")
 
-        return churn_result, churn_probability, roc_img
+# Create two columns for inputs
+col1, col2 = st.columns(2)
 
-    except Exception as e:
-        return f"Error: {str(e)}", "N/A", None
+with col1:
+    age = st.slider("Age", min_value=18, max_value=100, value=40)
+    gender = st.selectbox("Gender", options=["Male", "Female"])
+    tenure = st.slider("Tenure (months)", min_value=1, max_value=60, value=30)
+    usage_frequency = st.slider("Usage Frequency", min_value=1, max_value=30, value=15)
+    support_calls = st.slider("Support Calls", min_value=0, max_value=10, value=4)
 
-inputs = [
-    gr.Slider(18, 100, value=40, label="Age"),
-    gr.Dropdown(["Female", "Male"], value="Male", label="Gender"),
-    gr.Slider(1, 60, value=30, label="Tenure (months)"),
-    gr.Slider(1, 30, value=15, label="Usage Frequency"),
-    gr.Slider(0, 10, value=4, label="Support Calls"),
-    gr.Slider(0, 30, value=15, label="Payment Delay"),
-    gr.Slider(1, 30, value=15, label="Last Interaction (days ago)"),
-    gr.Slider(100, 1000, value=620, label="Total Spend"),
-    gr.Dropdown(["Premium", "Standard", "Basic"], value="Standard", label="Subscription Type"),
-    gr.Dropdown(["Monthly", "Quarterly", "Annual"], value="Annual", label="Contract Length")
-]
+with col2:
+    payment_delay = st.slider("Payment Delay", min_value=0, max_value=30, value=15)
+    last_interaction = st.slider("Last Interaction (days ago)", min_value=1, max_value=30, value=15)
+    total_spend = st.slider("Total Spend", min_value=100, max_value=1000, value=620)
+    subscription_type = st.selectbox("Subscription Type", options=["Premium", "Standard", "Basic"])
+    contract_length = st.selectbox("Contract Length", options=["Monthly", "Quarterly", "Annual"])
 
-outputs = [
-    gr.Textbox(label="Churn Prediction"),
-    gr.Textbox(label="Churn Probability"),
-    gr.Image(label="ROC Curve")
-]
+# Prediction function
+def make_prediction():
+    input_data = {
+        "Age": age,
+        "Gender_Male": 1 if gender == "Male" else 0,
+        "Gender_Female": 1 if gender == "Female" else 0,
+        "Usage Frequency": usage_frequency,
+        "Support Calls": support_calls,
+        "Contract Length_Monthly": 1 if contract_length == "Monthly" else 0,
+        "Contract Length_Quarterly": 1 if contract_length == "Quarterly" else 0,
+        "Contract Length_Annual": 1 if contract_length == "Annual" else 0,
+        "Payment Delay": payment_delay,
+        "Last Interaction": last_interaction,
+        "Total Spend": total_spend,
+        "Tenure": tenure,
+        "Subscription Type_Basic": 1 if subscription_type == "Basic" else 0,
+        "Subscription Type_Premium": 1 if subscription_type == "Premium" else 0,
+        "Subscription Type_Standard": 1 if subscription_type == "Standard" else 0,
+    }
+    
+    input_df = pd.DataFrame([input_data])
+    
+    # Predict churn and probability
+    prediction = best_model.predict(input_df)
+    prediction_proba = best_model.predict_proba(input_df)[:, 1]
+    
+    return prediction[0], prediction_proba[0]
 
-gr.Interface(
-    fn=churn_prediction,
-    inputs=inputs,
-    outputs=outputs,
-    title="Customer Churn Prediction"
-).launch()
+# Make prediction when button is clicked
+if st.button("Predict Churn"):
+    try:
+        prediction, probability = make_prediction()
+        
+        # Display results
+        st.header("Prediction Results")
+        
+        # Create three columns for results
+        col1, col2, col3 = st.columns(3)
+        
+        with col1:
+            st.metric("Churn Prediction", "Yes" if prediction == 1 else "No")
+            
+        with col2:
+            st.metric("Churn Probability", f"{probability:.2f}")
+            
+        with col3:
+            risk_level = "High" if probability > 0.7 else ("Medium" if probability > 0.4 else "Low")
+            st.metric("Risk Level", risk_level)
+        
+        # Display ROC curve
+        st.subheader("Model ROC Curve")
+        st.image(roc_img, caption="ROC Curve for Random Forest Model")
+        
+    except Exception as e:
+        st.error(f"Error making prediction: {str(e)}")