import streamlit as st
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix

# Load Dataset
df = pd.read_csv("bank_loan.csv")

# Data Preprocessing
df['CCAvg'] = df['CCAvg'].astype(float)
df[df['Experience'] < 0] = df[df['Experience'] < 0].abs()
df.drop(['ID', 'ZIP Code'], axis=1, inplace=True)
df['Income'] = round(df['Income']/12, 2)

# Define Features and Target Variable
X = df.drop('Personal Loan', axis=1)
y = df['Personal Loan']

# Standardize Features
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# Split Data into Train, Validation, and Test Sets
X_train, X_temp, y_train, y_temp = train_test_split(X_scaled, y, test_size=0.3, stratify=y, random_state=42)
X_val, X_test, y_val, y_test = train_test_split(X_temp, y_temp, test_size=0.5, stratify=y_temp, random_state=42)

# Train Model
svm_model = SVC(kernel='rbf', C=10, gamma=0.1, probability=True)
svm_model.fit(X_train, y_train)

def predict_loan_acceptance(sample):
    sample_scaled = scaler.transform(sample)
    prediction = svm_model.predict(sample_scaled)[0]
    probability = svm_model.predict_proba(sample_scaled)[0][1]
    return prediction, probability

# Streamlit UI
st.title("Personal Loan Eligibility Checker")
st.write("Answer the following questions to check if you're eligible for a personal loan.")

age = st.number_input("Enter your age:", min_value=18, max_value=100, step=1)
experience = st.number_input("Enter your years of experience:", min_value=0, max_value=80, step=1)
income = st.number_input("Enter your monthly income (in thousands):", min_value=0.0, step=0.1)
family = st.selectbox("Select number of family members:", [1, 2, 3, 4])
ccavg = st.number_input("Enter your average monthly credit card spending:", min_value=0.0, step=0.1)
education = st.selectbox("Select your education level:", [1, 2, 3], format_func=lambda x: ["Undergraduate", "Graduate", "Advanced/Professional"][x-1])
mortgage = st.number_input("Enter your mortgage amount (Enter 0 if none):", min_value=0.0, step=0.1)
securities_account = st.radio("Do you have a securities account?", [0, 1], format_func=lambda x: "Yes" if x else "No")
cd_account = st.radio("Do you have a certificate of deposit (CD) account?", [0, 1], format_func=lambda x: "Yes" if x else "No")
online = st.radio("Do you use online banking?", [0, 1], format_func=lambda x: "Yes" if x else "No")
credit_card = st.radio("Do you have a credit card with the bank?", [0, 1], format_func=lambda x: "Yes" if x else "No")

if st.button("Check Eligibility"):
    sample = pd.DataFrame({
        'Age': [age],
        'Experience': [experience],
        'Income': [income],
        'Family': [family],
        'CCAvg': [ccavg],
        'Education': [education],
        'Mortgage': [mortgage],
        'Securities Account': [securities_account],
        'CD Account': [cd_account],
        'Online': [online],
        'CreditCard': [credit_card]
    })
    prediction, probability = predict_loan_acceptance(sample)
    
    st.subheader("Prediction Result")
    if prediction == 1:
        st.success(f"Loan Accepted ✅\nProbability of Acceptance: {probability:.4f}")
    else:
        st.error(f"Loan Not Accepted ❌\nProbability of Acceptance: {probability:.4f}")