import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# 資料預處理
dataset = pd.read_csv("Mall_Customers.csv")
X = dataset.iloc[:, 3:5].values # 無監督學習，無需應變數

# 獲取 K，得到結果 K = 5
from sklearn.cluster import KMeans
# wcss = []
#
# for i in range(1, 11):
#     kmeans = KMeans(n_clusters=i, max_iter=300, n_init=10, init='k-means++', random_state=0)
#     kmeans.fit(X)
#     wcss.append(kmeans.inertia_)
#
# plt.plot(range(1, 11), wcss)
# plt.title('The Elbow Method')
# plt.xlabel('Number of clusters')
# plt.ylabel('WCSS')
# plt.show()

# 開始分析
kmeans = KMeans(n_clusters=5, max_iter=300, n_init=10, init='k-means++', random_state=0)

Y_kmeans = kmeans.fit_predict(X)

print(Y_kmeans)

# 視覺化
plt.scatter(X[Y_kmeans == 0, 0], X[Y_kmeans == 0, 1], s = 100, c = 'red', label = 'Cluster 1')

plt.scatter(X[Y_kmeans == 1, 0], X[Y_kmeans == 1, 1], s = 100, c = 'blue', label = 'Cluster 2')

plt.scatter(X[Y_kmeans == 2, 0], X[Y_kmeans == 2, 1], s = 100, c = 'green', label = 'Cluster 3')

plt.scatter(X[Y_kmeans == 3, 0], X[Y_kmeans == 3, 1], s = 100, c = 'cyan', label = 'Cluster 4')

plt.scatter(X[Y_kmeans == 4, 0], X[Y_kmeans == 4, 1], s = 100, c = 'magenta', label = 'Cluster 5')

plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s = 300, c = 'yellow', label = 'Centroids')

plt.title('Clusters of customers')

plt.xlabel('Annual Income (k$)')

plt.ylabel('Spending Score (1-100)')

plt.legend()

plt.show()