聚类模型K均值介绍
#7.1.1 引入依赖
import numpy as np
import matplotlib.pyplot as plt
import sklearn.datasets.samples_generator import make_blobs
#7.1.2 数据加载
x,y = make_blobs(n_samples=100,centers=6, random_state=1234,cluster_std=0.6)
plt.figure(figsize=(6,6))
plt.scatter(x[:,0],x[:,1],c=y)
plt.show()
#7.1.3 算法实现
from scipy.spatial.distance import cdist
class K_Means(object):
def __init__(self,n_clusters=6,maxiter=300,centroids=[]):
self.n_clusters=n_clusters
self.max_iter= max_iter
self.centroids=np.array(centroids, dtype=np.float)
def fit(self,data):
if(self.centroids.shape == (0,)):
self.controids=data[np.random.randint(0,data.shape[0],self.n_clusters) ,:]
for i in range(self.max_iter):
distances=cdist(data,self.centroids)
c_ind=np.argmin(distances,axis=1)
for i in range(self.n_clusters):
if i in c_ind:
self.centroids[i]=np.mean(data[c_ind==i],axis=0)
def predict(self,samples):
distances=cdist(samples,self.centroids)
c_ind=np.argmin(distance,axis=1)
return c_ind