聚類--K均值算法：自主實現與sklearn.cluster.KMeans調用

1.用python實現K均值算法
import numpy as np
x=np.random.randint(1,100,[20,1])  
y=np.zeros(20) 
k=3

def initcenter(x,k):
    return x[:k]
kc=initcenter(x,k)
kc

def nearest(kc,i):
    d=(abs(kc-i))
    w=np.where(d==np.min(d))
    return w[0][0]

kc=initcenter(x,k)
nearest(kc,93)

for i in range(x.shape[0]):
    y[i]=nearest(kc,x[i])
print(y)

def nearest(kc,i):
    d=(abs(kc-i))
    w=np.where(d==np.min(d))
    return w[0][0]

def initcenter(x,k):
    return x[:k]

def nearest(kc,i):
    d=(abs(kc - i))
    w=np.where(d==np.min(d))
    return w[0][0]

def xclassify(x,y,kc):
    for i in range(x.shape[0]):
        y[i]=nearest(kc,x[i])
    return y
kc=initcenter(x,k)
y=xclassify(x,y,kc)
print(kc,y)

m=np.where(y==0)
m

np.mean(x[m])

kc[0]=66
flag=True

def kcmean (x,y,kc,k):  #計算各聚類新均值
    l=list(kc)
    flag=False
    for c in range(k):
        m=np.where(y==c)
        n=np.mean(x[m])
        if l[c] !=n:
                l[c]=n
                flag=True  #聚類中心發生變化
    return (np.array(l),flag)             

def xclassify(x,y,kc):
    for i in range (x.shape[0]):  #對數組的每個值分類
        y[i]=nearest(kc,x[i])
    return y

flag = True
print(x,y,kc,flag)
while flag:
    y = xclassify(x,y,kc)
    kc,flag = kcmean(x,y,kc,k)
print(y,kc,type(kc))

import matplotlib.pyplot as plt
plt.scatter(x,x,s=50,cmap="rainbow");
plt.show()

 

 

 

2. 鳶尾花花瓣長度數據做聚類並用散點圖顯示。
import numpy as np
from sklearn.datasets import load_iris

iris = load_iris()
x = iris.data[:, 1]
y = np.zeros(150)


def initcent(x, k):  # 初始聚類中心數組
    return x[0:k].reshape(k)


def nearest(kc, i):  # 數組中的值，與聚類中心最小距離所在類別的索引號
    d = (abs(kc - i))
    w = np.where(d == np.min(d))
    return w[0][0]





def kcmean(x, y, kc, k):  # 計算各聚類新均值
    l = list(kc)
    flag = False
    for c in range(k):
        m = np.where(y == c)
        n = np.mean(x[m])
        if l[c] != n:
            l[c] = n
            flag = True  # 聚類中心發生變化
    return (np.array(l), flag)





def xclassify(x, y, kc):
    for i in range(x.shape[0]):  # 對數組的每個值分類
        y[i] = nearest(kc, x[i])
    return y


k = 3
kc = initcent(x, k)
flag = True
print(x, y, kc, flag)
while flag:
    y = xclassify(x, y, kc)
    kc, flag = kcmean(x, y, kc, k)
print(y, kc, type(kc))

import matplotlib.pyplot as plt
plt.scatter(x,x,c=y,s=50,cmap='rainbow',marker='p',alpha=0.5);
plt.show()

 

 

 

 

3. 用sklearn.cluster.KMeans，鳶尾花花瓣長度數據做聚類並用散點圖顯示.
import matplotlib.pyplot as plt
import numpy as np
from sklearn.datasets import load_iris

iris=load_iris()
X=iris.data
print(X)

from sklearn.cluster import KMeans

est=KMeans(n_clusters=3)
est.fit(X)
kc=est.cluster_centers_
y_kmeans=est.predict(X)

print(y_kmeans,kc)
print(kc.shape,y_kmeans.shape,X.shape)
plt.scatter(X[:,0],X[:,1],c=y_kmeans,s=50,cmap='rainbow');
plt.show()

 

 

 

 

 

4. 鳶尾花完整數據做聚類並用散點圖顯示.
from sklearn.cluster import KMeans
import numpy as np
from sklearn.datasets import load_iris
import matplotlib.pyplot as plt
data = load_iris()
iris = data.data
petal_len = iris
print(petal_len)
k_means = KMeans(n_clusters=3) #三個聚類中心
result = k_means.fit(petal_len) #Kmeans自動分類
kc = result.cluster_centers_ #自動分類后的聚類中心
y_means = k_means.predict(petal_len) #預測Y值
plt.scatter(petal_len[:,0],petal_len[:,2],c=y_means, marker='*', label='see')
plt.show()