def run_kmeans(X, initial_centroids, max_iters, plot):
if plot:
plt.figure()
# Initialize values
(m, n) = X.shape
K = initial_centroids.shape[0]
centroids = initial_centroids
previous_centroids = centroids
idx = np.zeros(m)
# Run K-Means
for i in range(max_iters):
# Output progress
print('K-Means iteration {}/{}'.format((i + 1), max_iters))
# For each example in X, assign it to the closest centroid
idx = fc.find_closest_centroids(X, centroids)
# Optionally plot progress
if plot:
plot_progress(X, centroids, previous_centroids, idx, K, i)
previous_centroids = centroids
input('Press ENTER to continue')
# Given the memberships, compute new centroids
centroids = cc.compute_centroids(X, idx, K)
return centroids, idx
def run_k_means(x, initial_centroids, max_iters, plot_progress=False):
if plot_progress:
plt.ion()
plt.figure()
centroids = initial_centroids
previous_centroids = centroids
k = initial_centroids.shape[0]
idx = 0
for i in range(max_iters):
# Output progress
print('K-Means iteration {}/{}...\n'.format(i + 1, max_iters),
flush=True)
# For each example in X, assign it to the closest centroid
idx = find_closest_centroids(x, centroids)
# Optionally, plot progress here
if plot_progress:
plot_progressk_means(x, centroids, previous_centroids, idx, k, i)
previous_centroids = centroids
# Given the memberships, compute new centroids
centroids = compute_centroids(x, idx, k)
if plot_progress:
plt.close()
return centroids, idx
def run_kmeans(X, initial_centroids, max_iters, plot_progress=False):
"""[centroids, idx] = RUNKMEANS(X, initial_centroids, max_iters, ...
plot_progress) runs the K-Means algorithm on data matrix X, where each
row of X is a single example.
It uses initial_centroids used as the
initial centroids. max_iters specifies the total number of interactions
of K-Means to execute. plot_progress is a true/false flag that
indicates if the function should also plot its progress as the
learning happens. This is set to false by default. runkMeans returns
centroids, a Kxn matrix of the computed centroids and idx, a m x 1
vector of centroid assignments (i.e. each entry in range [1..K])
"""
# Initialize values
m, n = X.shape
K = initial_centroids.shape[0]
centroids = initial_centroids
previous_centroids = centroids
idx = np.zeros((m, 1))
# Run K-Means
for i in range(max_iters):
# Output progress
print('K-Means iteration {}/{}...'.format(i + 1, max_iters))
# For each example in X, assign it to the closest centroid
idx = find_closest_centroids(X, centroids)
# Optionally, plot progress here
if plot_progress:
plot_progress_kmeans(X, centroids, previous_centroids, idx, K, i)
previous_centroids = centroids
print('Press enter to continue.\n')
pause()
# Given the memberships, compute new centroids
centroids = compute_centroids(X, idx, K)
return centroids, idx
def run_kmeans(X, initial_centroids, max_iters, plot): #plot设置是否进行可视化
if plot:
plt.figure()
(m, n) = X.shape #m样本数 n样本特征数
K = initial_centroids.shape[0] #聚类中心数量
centroids = initial_centroids
previous_centroids = centroids
idx = np.zeros(m) #存放每个样本所属的聚类中心序号
# 运行k-means
for i in range(max_iters): #外循环
print('K-Means iteration {}/{}'.format((i + 1), max_iters))
idx = fc.find_closest_centroids(X, centroids) #第一个内循环 为每个样本找到最近的聚类中心
if plot:
plot_progress(X, centroids, previous_centroids, idx, K, i) #画出此时簇分配的状态
previous_centroids = centroids
input('Press ENTER to continue')
centroids = cc.compute_centroids(X, idx, K) #第2个内循环 更新聚类中心
return centroids, idx #返回最终聚类中心的位置 和每个样本所属的聚类中心序号
print('Closest centroids for the first 3 examples: ')
print('{}'.format(idx[0:3]))
print('(the closest centroids should be 0, 2, 1 respectively)')
input('Program paused. Press ENTER to continue')
# ===================== Part 2: Compute Means =====================
# After implementing the closest centroids function, you should now
# complete the compute_centroids function.
#
print('Computing centroids means.')
# Compute means based on the closest centroids found in the previous part.
centroids = cc.compute_centroids(X, idx, k)
print('Centroids computed after initial finding of closest centroids: \n{}'.
format(centroids))
print('the centroids should be')
print('[[ 2.428301 3.157924 ]')
print(' [ 5.813503 2.633656 ]')
print(' [ 7.119387 3.616684 ]]')
input('Program paused. Press ENTER to continue')
# ===================== Part 3: K-Means Clustering =====================
# After you have completed the two functions compute_centroids and
# find_closest_centroids, you will have all the necessary pieces to run the
# kMeans algorithm. In this part, you will run the K-Means algorithm on
# the example dataset we have provided.
K = 3 # 3 Centroids
initial_centroids = [[3, 3], [6, 2], [8, 5]]
initial_centroids = np.array(initial_centroids)
# Find the closest centroids for the examples using the initial_centroids
idx = find_closest_centroids(X, initial_centroids)
print('Closest centroids for the first 3 examples: \n {}'.format(idx[0:3]))
print('\n(the closest centroids should be 1, 3, 2 respectively)\n')
print('Program paused. Press enter to continue.\n')
# pause_func()
# ===================== Part 2: Compute Means =========================
# After implementing the closest centroids function, you should now
# complete the computeCentroids function.
print('\nComputing centroids means.\n\n')
# Compute means based on the closest centroids found in the previous part.
centroids = compute_centroids(X, idx, K)
print('Centroids computed after initial finding of closest centroids: \n')
print(' %s \n' % centroids)
print('\n(the centroids should be\n')
print(' [ 2.428301 3.157924 ]\n')
print(' [ 5.813503 2.633656 ]\n')
print(' [ 7.119387 3.616684 ]\n\n')
print('Program paused. Press enter to continue.\n')
# pause_func()
# =================== Part 3: K-Means Clustering ======================
# After you have completed the two functions computeCentroids and
# findClosestCentroids, you have all the necessary pieces to run the
# kMeans algorithm. In this part, you will run the K-Means algorithm on
# the example dataset we have provided.
k = 3 # 随机初始化3个聚类中心
initial_centroids = np.array([[3, 3], [6, 2], [8, 5]])
#找到离每个样本最近的初始聚类中心序号
idx = fc.find_closest_centroids(X, initial_centroids)
print('Closest centroids for the first 3 examples: ')
print('{}'.format(idx[0:3]))
print('(the closest centroids should be 0, 2, 1 respectively)')
input('Program paused. Press ENTER to continue')
'''第2部分 更新聚类中心'''
print('Computing centroids means.')
centroids = cc.compute_centroids(X, idx, k) #在簇分配结束后 对每个簇的样本点重新计算聚类中心
print('Centroids computed after initial finding of closest centroids: \n{}'.
format(centroids))
print('the centroids should be')
print('[[ 2.428301 3.157924 ]')
print(' [ 5.813503 2.633656 ]')
print(' [ 7.119387 3.616684 ]]')
input('Program paused. Press ENTER to continue')
'''第3部分 运行k-means聚类算法'''
print('Running K-Means Clustering on example dataset.')
#加载数据集
data = scio.loadmat('ex7data2.mat')
X = data['X']
print('Closest centroids for the first 3 examples: \n')
print(idx[0:3])
print('\n(the closest centroids should be 0, 2, 1 respectively)\n')
print('Program paused. Press enter to continue.\n')
pause()
"""
## Part 2: Compute Means
After implementing the closest centroids function, we compute centroids.
"""
print('\nComputing centroids means.\n\n')
# Compute means based on the closest centroids found in the previous part.
centroids = compute_centroids(X, idx, K)
print('Centroids computed after initial finding of closest centroids: \n')
print(centroids)
print("centroids shape", centroids.shape)
print('\n(the centroids should be\n')
print(' [ 2.428301 3.157924 ]\n')
print(' [ 5.813503 2.633656 ]\n')
print(' [ 7.119387 3.616684 ]\n\n')
print('Program paused. Press enter to continue.\n')
pause()
"""