Upload 5 files

app.py

@@ -0,0 +1,30 @@
+
+import gradio as gr
+from predictor import predict_risk
+
+def predict(policy_id, last_premium_paid_date, payment_mode, policy_term, policy_age):
+    input_data = {
+        "policy_id": policy_id,
+        "last_premium_paid_date": last_premium_paid_date,
+        "payment_mode": payment_mode,
+        "policy_term": int(policy_term),
+        "policy_age": int(policy_age)
+    }
+    risk = predict_risk(input_data)
+    return {"Lapse Risk Score (0–1)": risk}
+
+iface = gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.Textbox(label="Policy ID"),
+        gr.Textbox(label="Last Premium Paid Date (YYYY-MM-DD)"),
+        gr.Dropdown(["Annual", "Semi-Annual", "Quarterly", "Monthly"], label="Payment Mode"),
+        gr.Number(label="Policy Term (Years)"),
+        gr.Number(label="Policy Age (Years)")
+    ],
+    outputs="json",
+    title="Lapse Risk Predictor",
+    description="Enter policy details to predict the risk of lapse using an XGBoost model"
+)
+
+iface.launch()

predictor.py

@@ -0,0 +1,11 @@
+
+import xgboost as xgb
+from preprocessing import preprocess_input
+
+model = xgb.XGBClassifier()
+model.load_model("model/xgb_model.json")
+
+def predict_risk(input_dict):
+    df = preprocess_input(input_dict)
+    score = model.predict_proba(df)[0][1]
+    return round(score, 2)

preprocessing.py

@@ -0,0 +1,28 @@
+
+import pandas as pd
+from datetime import datetime
+
+def encode_payment_mode(mode):
+    return {"Annual": 0, "Semi-Annual": 1, "Quarterly": 2, "Monthly": 3}.get(mode, -1)
+
+def calculate_months_since(date_str):
+    try:
+        delta = datetime.now() - datetime.strptime(date_str, "%Y-%m-%d")
+        return delta.days // 30
+    except:
+        return 0
+
+def preprocess_input(data):
+    return pd.DataFrame([{
+        "months_since_last_payment": calculate_months_since(data["last_premium_paid_date"]),
+        "payment_mode_encoded": encode_payment_mode(data["payment_mode"]),
+        "policy_term": data["policy_term"],
+        "policy_age": data["policy_age"]
+    }])
+
+def preprocess_dataframe(df):
+    df["months_since_last_payment"] = df["last_premium_paid_date"].apply(calculate_months_since)
+    df["payment_mode_encoded"] = df["payment_mode"].apply(encode_payment_mode)
+    X = df[["months_since_last_payment", "payment_mode_encoded", "policy_term", "policy_age"]]
+    y = df["risk"]
+    return X, y

requirements.txt

@@ -0,0 +1,5 @@
+
+gradio==4.24.0
+xgboost==2.0.3
+pandas==2.2.2
+scikit-learn==1.5.0

train_model.py

@@ -0,0 +1,18 @@
+
+import xgboost as xgb
+import pandas as pd
+import os
+from preprocessing import preprocess_dataframe
+
+# Sample training data
+data = pd.DataFrame([
+    {"last_premium_paid_date": "2023-06-15", "payment_mode": "Annual", "policy_term": 15, "policy_age": 3, "risk": 1},
+    {"last_premium_paid_date": "2024-03-10", "payment_mode": "Monthly", "policy_term": 20, "policy_age": 2, "risk": 0},
+])
+
+X, y = preprocess_dataframe(data)
+model = xgb.XGBClassifier()
+model.fit(X, y)
+
+os.makedirs("model", exist_ok=True)
+model.save_model("model/xgb_model.json")