index.py

# Credit Scoring Model
# Objective: Predict if an individual is creditworthy (Good or Bad Credit)

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import (
    accuracy_score,
    precision_score,
    recall_score,
    f1_score,
    roc_auc_score,
    classification_report
)

# -----------------------------
# 1️⃣ Simulated Dataset
# -----------------------------
np.random.seed(42)

data = pd.DataFrame({
    "income": np.random.randint(2000, 10000, 500),
    "debt": np.random.randint(0, 8000, 500),
    "payment_history": np.random.randint(0, 10, 500),  # higher = better
    "loan_amount": np.random.randint(500, 5000, 500),
    "age": np.random.randint(18, 65, 500)
})

# Target variable: creditworthy (1 = Good, 0 = Bad)
data["creditworthy"] = np.where(
    (data["income"] > 4000)
    & (data["debt"] < 5000)
    & (data["payment_history"] > 4),
    1, 0
)

# -----------------------------
# 2️⃣ Feature Engineering
# -----------------------------
data["debt_to_income_ratio"] = data["debt"] / (data["income"] + 1)
data["income_log"] = np.log1p(data["income"])

# Features & Target
X = data.drop("creditworthy", axis=1)
y = data["creditworthy"]

# -----------------------------
# 3️⃣ Train-Test Split
# -----------------------------
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=42)

# -----------------------------
# 4️⃣ Feature Scaling
# -----------------------------
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# -----------------------------
# 5️⃣ Model Training
# -----------------------------
models = {
    "Logistic Regression": LogisticRegression(),
    "Decision Tree": DecisionTreeClassifier(random_state=42),
    "Random Forest": RandomForestClassifier(random_state=42)
}

results = {}

for name, model in models.items():
    model.fit(X_train_scaled, y_train)
    y_pred = model.predict(X_test_scaled)

    results[name] = {
        "Accuracy": accuracy_score(y_test, y_pred),
        "Precision": precision_score(y_test, y_pred),
        "Recall": recall_score(y_test, y_pred),
        "F1 Score": f1_score(y_test, y_pred),
        "ROC-AUC": roc_auc_score(y_test, y_pred)
    }

# -----------------------------
# 6️⃣ Model Evaluation
# -----------------------------
results_df = pd.DataFrame(results).T
print("📊 Model Performance Comparison:\n")
print(results_df.round(3))

# Detailed classification report for best model
best_model_name = results_df["F1 Score"].idxmax()
print(f"\n🏆 Best Model: {best_model_name}\n")
print(classification_report(
    y_test, models[best_model_name].predict(X_test_scaled)))