Update app.py

app.py

@@ -1,52 +1,68 @@
-from flask import Flask, request, jsonify
-from flask_cors import CORS
+import gradio as gr
 import pickle
 
-app = Flask(__name__)
-CORS(app)  # Enable CORS for all routes
-
-# Load your model
+# Load the CatBoost model
 model = pickle.load(open("best_model_catboost.pkl", "rb"))
 
-@app.route('/predict', methods=['POST'])
-def predict():
-    try:
-        # Get data from the request
-        data = request.json
+def predict_loan_default(
+    person_age, person_income, person_emp_length, loan_amnt, loan_percent_income,
+    cb_person_default_on_file, person_home_ownership, loan_intent, loan_grade
+):
+    # Map categorical inputs to one-hot encoded features
+    home_ownership_map = {
+        "OTHER": [1, 0, 0],
+        "OWN": [0, 1, 0],
+        "RENT": [0, 0, 1]
+    }
+    intent_map = {
+        "DEBTCONSOLIDATION": [1, 0, 0, 0, 0, 0],
+        "EDUCATION": [0, 1, 0, 0, 0, 0],
+        "HOMEIMPROVEMENT": [0, 0, 1, 0, 0, 0],
+        "MEDICAL": [0, 0, 0, 1, 0, 0],
+        "PERSONAL": [0, 0, 0, 0, 1, 0],
+        "VENTURE": [0, 0, 0, 0, 0, 1]
+    }
+    grade_map = {
+        "A": [1, 0, 0, 0, 0, 0, 0],
+        "B": [0, 1, 0, 0, 0, 0, 0],
+        "C": [0, 0, 1, 0, 0, 0, 0],
+        "D": [0, 0, 0, 1, 0, 0, 0],
+        "E": [0, 0, 0, 0, 1, 0, 0],
+        "F": [0, 0, 0, 0, 0, 1, 0],
+        "G": [0, 0, 0, 0, 0, 0, 1]
+    }
+
+    # Prepare features for prediction
+    features = [
+        person_age,
+        person_income,
+        person_emp_length,
+        loan_amnt,
+        loan_percent_income,
+        int(cb_person_default_on_file == "Yes"),
+        *home_ownership_map[person_home_ownership],
+        *intent_map[loan_intent],
+        *grade_map[loan_grade]
+    ]
 
-        # Prepare features for prediction
-        features = [
-            data['person_age'],
-            data['person_income'],
-            data['person_emp_length'],
-            data['loan_amnt'],
-            data['loan_percent_income'],
-            data['cb_person_default_on_file'],
-            data['person_home_ownership_OTHER'],
-            data['person_home_ownership_OWN'],
-            data['person_home_ownership_RENT'],
-            data['loan_intent_DEBTCONSOLIDATION'],
-            data['loan_intent_EDUCATION'],
-            data['loan_intent_HOMEIMPROVEMENT'],
-            data['loan_intent_MEDICAL'],
-            data['loan_intent_PERSONAL'],
-            data['loan_intent_VENTURE'],
-            data['loan_grade_A'],
-            data['loan_grade_B'],
-            data['loan_grade_C'],
-            data['loan_grade_D'],
-            data['loan_grade_E'],
-            data['loan_grade_F'],
-            data['loan_grade_G']
-        ]
+    # Make prediction
+    prediction = model.predict([features])
+    return "Default" if prediction[0] == 1 else "No Default"
 
-        # Make prediction
-        prediction = model.predict([features])
+# Define Gradio interface
+inputs = [
+    gr.Number(label="Person Age"),
+    gr.Number(label="Person Income"),
+    gr.Number(label="Person Employment Length"),
+    gr.Number(label="Loan Amount"),
+    gr.Number(label="Loan Percent Income"),
+    gr.Radio(["Yes", "No"], label="Default on File"),
+    gr.Radio(["OTHER", "OWN", "RENT"], label="Home Ownership"),
+    gr.Radio(["DEBTCONSOLIDATION", "EDUCATION", "HOMEIMPROVEMENT", "MEDICAL", "PERSONAL", "VENTURE"], label="Loan Intent"),
+    gr.Radio(["A", "B", "C", "D", "E", "F", "G"], label="Loan Grade")
+]
 
-        # Return prediction as JSON
-        return jsonify({"prediction": prediction.tolist()})
-    except Exception as e:
-        return jsonify({"error": str(e)}), 500
+outputs = gr.Textbox(label="Prediction")
 
-if __name__ == "__main__":
-    app.run(debug=True)
+# Launch Gradio app
+gr.Interface(fn=predict_loan_default, inputs=inputs, outputs=outputs, title="Credit Risk Prediction").launch()