creditCard.py

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, accuracy_score
from xgboost import XGBClassifier
import matplotlib.pyplot as plt
from xgboost import plot_importance

# Load dataset
data = pd.read_csv('data.csv')


# Features and label
X = data.drop(columns=["ID", "default payment next month"])
y = data["default payment next month"]

# Train-test split
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42)

# Calculate class imbalance ratio
ratio = sum(y_train == 0) / sum(y_train == 1)

# Train XGBoost with imbalance handling
model = XGBClassifier(
    scale_pos_weight=ratio,  # boosts minority class
    eval_metric='logloss',
    random_state=42
)
model.fit(X_train, y_train)

# Predictions
y_pred = model.predict(X_test)

# Evaluation
print("Accuracy:", accuracy_score(y_test, y_pred))
print(classification_report(y_test, y_pred))