Update train_model.py

train_model.py

@@ -1,17 +1,36 @@
-
 import xgboost as xgb
 import pandas as pd
+from datetime import datetime, timedelta
 import os
-from preprocessing import preprocess_dataframe
 
-# Sample training data
+# Extended dummy dataset
 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},
+    {"last_premium_paid_date": (datetime.now() - timedelta(days=60)).strftime('%Y-%m-%d'), "payment_mode": "Annual", "policy_term": 15, "policy_age": 3, "risk": 1},
+    {"last_premium_paid_date": (datetime.now() - timedelta(days=10)).strftime('%Y-%m-%d'), "payment_mode": "Monthly", "policy_term": 20, "policy_age": 2, "risk": 0},
+    {"last_premium_paid_date": (datetime.now() - timedelta(days=400)).strftime('%Y-%m-%d'), "payment_mode": "Quarterly", "policy_term": 25, "policy_age": 5, "risk": 1},
+    {"last_premium_paid_date": (datetime.now() - timedelta(days=700)).strftime('%Y-%m-%d'), "payment_mode": "Semi-Annual", "policy_term": 10, "policy_age": 8, "risk": 1},
+    {"last_premium_paid_date": (datetime.now() - timedelta(days=90)).strftime('%Y-%m-%d'), "payment_mode": "Annual", "policy_term": 12, "policy_age": 4, "risk": 0},
+    {"last_premium_paid_date": (datetime.now() - timedelta(days=30)).strftime('%Y-%m-%d'), "payment_mode": "Monthly", "policy_term": 20, "policy_age": 1, "risk": 0},
+    {"last_premium_paid_date": (datetime.now() - timedelta(days=300)).strftime('%Y-%m-%d'), "payment_mode": "Annual", "policy_term": 15, "policy_age": 3, "risk": 1},
+    {"last_premium_paid_date": (datetime.now() - timedelta(days=180)).strftime('%Y-%m-%d'), "payment_mode": "Quarterly", "policy_term": 18, "policy_age": 6, "risk": 0},
 ])
 
-X, y = preprocess_dataframe(data)
-model = xgb.XGBClassifier()
+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
+
+data["months_since_last_payment"] = data["last_premium_paid_date"].apply(calculate_months_since)
+data["payment_mode_encoded"] = data["payment_mode"].apply(encode_payment_mode)
+X = data[["months_since_last_payment", "payment_mode_encoded", "policy_term", "policy_age"]]
+y = data["risk"]
+
+model = xgb.XGBClassifier(use_label_encoder=False, eval_metric="logloss")
 model.fit(X, y)
 
 os.makedirs("model", exist_ok=True)