K-Means Clustering: Panduan Lengkap

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler

# === BUAT DATASET PELANGGAN ===
np.random.seed(42)
n = 200

data_pelanggan = pd.DataFrame({
    'customer_id': range(1, n + 1),
    'annual_income': np.concatenate([
        np.random.normal(25, 5, 50),   # Income rendah
        np.random.normal(55, 8, 60),   # Income menengah
        np.random.normal(85, 10, 50),  # Income tinggi
        np.random.normal(45, 6, 40),   # Income menengah-rendah
    ]).round(1),
    'spending_score': np.concatenate([
        np.random.normal(20, 8, 50),   # Spending rendah
        np.random.normal(50, 10, 60),  # Spending menengah
        np.random.normal(75, 8, 50),   # Spending tinggi
        np.random.normal(35, 7, 40),   # Spending rendah-menengah
    ]).clip(1, 100).round(1),
    'age': np.random.randint(18, 65, n),
})

print("Dataset Pelanggan:")
print(data_pelanggan.describe())
print(f"\nSample data:")
print(data_pelanggan.head(10))

# === PREPROCESSING ===
# Pilih fitur untuk clustering
fitur = ['annual_income', 'spending_score']
X_pelanggan = data_pelanggan[fitur].values

# Normalisasi (PENTING untuk K-Means!)
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X_pelanggan)

print(f"\nData sebelum scaling:")
print(f"  Mean: {X_pelanggan.mean(axis=0)}")
print(f"  Std:  {X_pelanggan.std(axis=0)}")
print(f"\nData setelah scaling:")
print(f"  Mean: {X_scaled.mean(axis=0).round(4)}")
print(f"  Std:  {X_scaled.std(axis=0).round(4)}")

# === ELBOW METHOD ===
K_range = range(1, 11)
inertias = []
sil_scores = []

for k in K_range:
    km = KMeans(n_clusters=k, init='k-means++', n_init=10, random_state=42)
    km.fit(X_scaled)
    inertias.append(km.inertia_)
    if k >= 2:
        from sklearn.metrics import silhouette_score
        sil = silhouette_score(X_scaled, km.labels_)
        sil_scores.append(sil)
        print(f"K={k}: Inertia={km.inertia_:.1f}, Silhouette={sil:.3f}")
    else:
        print(f"K={k}: Inertia={km.inertia_:.1f}")

# Plot Elbow & Silhouette berdampingan
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(14, 5))

ax1.plot(K_range, inertias, 'bo-', linewidth=2)
ax1.set_xlabel('K')
ax1.set_ylabel('Inertia')
ax1.set_title('Elbow Method')
ax1.grid(True, alpha=0.3)

ax2.plot(range(2, 11), sil_scores, 'go-', linewidth=2)
ax2.set_xlabel('K')
ax2.set_ylabel('Silhouette Score')
ax2.set_title('Silhouette Analysis')
ax2.grid(True, alpha=0.3)

plt.tight_layout()
plt.show()

# === CLUSTERING DENGAN K OPTIMAL ===
K_OPTIMAL = 5  # Berdasarkan elbow + silhouette
kmeans_final = KMeans(n_clusters=K_OPTIMAL, init='k-means++',
                       n_init=10, random_state=42)
data_pelanggan['cluster'] = kmeans_final.fit_predict(X_scaled)

# Profil setiap cluster
print(f"\n{'='*60}")
print(f"PROFIL CLUSTER (K={K_OPTIMAL})")
print(f"{'='*60}")
for i in range(K_OPTIMAL):
    cluster_data = data_pelanggan[data_pelanggan['cluster'] == i]
    print(f"\n--- Cluster {i} ({len(cluster_data)} pelanggan) ---")
    print(f"  Income rata-rata:  ${cluster_data['annual_income'].mean():.1f}k")
    print(f"  Spending rata-rata: {cluster_data['spending_score'].mean():.1f}")
    print(f"  Usia rata-rata:    {cluster_data['age'].mean():.0f} tahun")

# Visualisasi scatter plot berwarna cluster
plt.figure(figsize=(10, 8))
colors = ['#FF6B6B', '#4ECDC4', '#45B7D1', '#96CEB4', '#FFEAA7']
cluster_names = [
    'Budget Conscious', 'Average Spenders', 'Premium Customers',
    'High Income Low Spend', 'Young Big Spenders'
]

for i in range(K_OPTIMAL):
    mask = data_pelanggan['cluster'] == i
    plt.scatter(data_pelanggan[mask]['annual_income'],
                data_pelanggan[mask]['spending_score'],
                s=60, alpha=0.7, c=colors[i],
                label=f'Cluster {i}: {cluster_names[i]}',
                edgecolors='white', linewidth=0.5)

# Plot centroid
centroids_orig = scaler.inverse_transform(kmeans_final.cluster_centers_)
plt.scatter(centroids_orig[:, 0], centroids_orig[:, 1],
            s=250, c='black', marker='★', edgecolors='white',
            linewidth=2, label='Centroid', zorder=5)

plt.xlabel('Annual Income ($k)', fontsize=12)
plt.ylabel('Spending Score (1-100)', fontsize=12)
plt.title('Segmentasi Pelanggan — K-Means Clustering', fontsize=14)
plt.legend(fontsize=9)
plt.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()