binary_classification.py

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder, StandardScaler, MinMaxScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import SVC
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, f1_score

file_id = '19IfOP0QmCHccMu8A6B2fCUpFqZwCxuzO'

download_url = f'https://drive.google.com/uc?id={file_id}'

data = pd.read_csv(download_url)
data.head()

print("\nInformasi Dataset")
data.info()

print("\nMissing values per fitur:")
print(data.isnull().sum())

data = data.drop(columns=['RowNumber', 'CustomerId', 'Surname'])
data.head()

num_features = data.select_dtypes(include=[np.number])
plt.figure(figsize=(14, 10))
for i, column in enumerate(num_features.columns, 1):
    plt.subplot(3, 4, i)
    sns.histplot(data[column], bins=30, kde=True, color='red')
    plt.title(f'Distirbusi {column}')
plt.tight_layout()
plt.show()

cat_features = data.select_dtypes(include=[object])
plt.figure(figsize=(14, 8))
for i, column in enumerate(cat_features.columns, 1):
    plt.subplot(2, 4, i)
    sns.countplot(y=data[column], palette='viridis', legend=False)
    plt.title(f'Distribusi {column}')
plt.tight_layout
plt.show()

plt.figure(figsize=(12, 10))
correlation_matrix = num_features.corr()
sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt='.2f', linewidths=0.5)
plt.title('Heatmap Korelasi')
plt.show()

sns.pairplot(num_features)
plt.show()

plt.figure(figsize=(8, 4))
sns.countplot(x='Exited', data=data, palette='viridis', legend=False)
plt.title('Distribusi Variabel Target (Exited)')
plt.show()

label_encoder = LabelEncoder()
categorical_columns = ['Geography', 'Gender']

for column in categorical_columns:
    data[column] = label_encoder.fit_transform(data[column])
data.head()

scaler = MinMaxScaler()

numeric_columns = data.select_dtypes(include=['int64', 'float64']).columns
data[numeric_columns] = scaler.fit_transform(data[numeric_columns])

X = data.drop(columns=['Exited'])
y = data['Exited']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

print(f'Training set shape: X_train={X_train.shape}, y_train={y_train.shape}')
print(f'Test set shape: X_test={X_test.shape}, y_test={y_test.shape}')

knn = KNeighborsClassifier().fit(X_train, y_train)
dt = DecisionTreeClassifier().fit(X_train, y_train)
rf = RandomForestClassifier().fit(X_train, y_train)
svm = SVC().fit(X_train, y_train)
nb = GaussianNB().fit(X_train, y_train)

print("Model training selesai")

def evaluate_model(model, X_test, y_test):
    y_pred = model.predict(X_test)
    cm = confusion_matrix(y_test, y_pred)
    tn, fp, fn, tp = cm.ravel()
    results = {
        'Confusion Matrix': cm,
        'Trues Positive (TP)': tp,
        'False Positive (FN)': fp,
        'False Negative (FN)': fn,
        'True Negative (TN)': tn,
        '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)
    }
    return results

results = {
    'K-Nearest Neighbors (KNN)': evaluate_model(knn, X_test, y_test),
    'Decision Tree (DT)': evaluate_model(dt, X_test, y_test),
    'Random Forest (RF)': evaluate_model(rf, X_test, y_test),
    'Support Vector Machine (SVM)': evaluate_model(rf, X_test, y_test),
    'Naive Bayes (NB)': evaluate_model(nb, X_test, y_test)
}

summary_df = pd.DataFrame(columns=['Model', 'Accuracy', 'Precision', 'Recall', 'F1_Score'])

rows = []
for model_name, metrics in results.items():
    rows.append({
        'Model': model_name,
        'Accuracy': metrics['Accuracy'],
        'Precision': metrics['Precision'],
        'Recall': metrics['Recall'],
        'F1-Score': metrics['F1-Score']
    })

summary_df = pd.DataFrame(rows)
print(summary_df)