import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sb
from scipy.io import loadmat

def find_closest_centroids(X, centroids):
  m = X.shape[0]
  k = centroids.shape[0] #要聚類的類別個(gè)數(shù)
  idx = np.zeros(m) 
  
  for i in range(m):
    min_dist = 1000000 #迭代終止條件
    for j in range(k):
      dist = np.sum((X[i,:] - centroids[j,:]) ** 2) 
      if dist < min_dist:
        # 記錄當(dāng)前最短距離和其中心的索引值
        min_dist = dist
        idx[i] = j
  
  return idx
data = loadmat('D:\python\Python ml\ex7data2.mat')
X = data['X']
initial_centroids = np.array([[3, 3], [6, 2], [8, 5]])

idx = find_closest_centroids(X, initial_centroids)
idx[0:3]

def compute_centroids(X, idx, k):
  m, n = X.shape
  centroids = np.zeros((k, n))
  
  for i in range(k):
    indices = np.where(idx == i)
    centroids[i,:] = (np.sum(X[indices,:], axis=1) / len(indices[0])).ravel()
  #這里簡(jiǎn)單的將該類中心的所有數(shù)值求平均值作為新的類中心
return centroids
compute_centroids(X, idx, 3)

def run_k_means(X, initial_centroids, max_iters):
  m, n = X.shape
  k = initial_centroids.shape[0]
  idx = np.zeros(m)
  centroids = initial_centroids
  
  for i in range(max_iters):
    idx = find_closest_centroids(X, centroids)
    centroids = compute_centroids(X, idx, k)
  
  return idx, centroids
idx, centroids = run_k_means(X, initial_centroids, 10)
cluster1 = X[np.where(idx == 0)[0],:] #獲取X中屬于第一個(gè)類別的數(shù)據(jù)集合，即類別1的點(diǎn)
cluster2 = X[np.where(idx == 1)[0],:]
cluster3 = X[np.where(idx == 2)[0],:]

fig, ax = plt.subplots(figsize=(12,8))
ax.scatter(cluster1[:,0], cluster1[:,1], s=30, color='r', label='Cluster 1')
ax.scatter(cluster2[:,0], cluster2[:,1], s=30, color='g', label='Cluster 2')
ax.scatter(cluster3[:,0], cluster3[:,1], s=30, color='b', label='Cluster 3')
ax.legend()
plt.show()

def init_centroids(X, k):
  m, n = X.shape
  centroids = np.zeros((k, n)) #初始化零矩陣
  idx = np.random.randint(0, m, k) #返回0-m之間的整數(shù)值
  
  for i in range(k):
    centroids[i,:] = X[idx[i],:]
  
return centroids
init_centroids(X, 3)