第二部分__建模应用篇__第八章__聚类

Python实现的KMeans聚类

import numpy as np 
from sklearn import datasets
import matplotlib.pyplot as plt 
from mpl_toolkits.mplot3d import Axes3D

#正则化数据集
def normalize(X,axis=-1,p=2):
    lp_norm=np.atleast_1d(np.linalg.norm(X,p,axis))
    lp_norm[lp_norm==0]=1
    return X/np.expand_dims(lp_norm,axis)
#计算一个样本与所有样本的欧氏距离的平方
def euclidean_distance(one_sample,X):
    one_sample=one_sample.reshape(1,-1)
    X=X.reshape(X.shape[0],-1)
    dis=np.power(np.tile(one_sample,(X.shape[0],1))-X,2).sum(axis=1)
    return dis
class Kmeans():
    def __init__(self,k=2,max_iteration=500,varepsilon=0.0001):
        self.k=k
        self.max_iteration=max_iteration
        self.varepsilon=varepsilon
    #从样本点随机选择聚类中心
    def init_random_center(self,X):
        n_samples,n_features=np.shape(X)
        centers=np.zeros((self.k,n_features))
        for i in range(self.k):
            center=X[np.random.choice(range(n_samples))]
            centers[i]=center
        return  centers
    #返回距离该样本最近的一个中心索引[0,self.k]
    def _cloest_center(self,sample,centers):
        dis=euclidean_distance(sample,centers)
        closest_i=np.argmin(dis)
        return  closest_i
    #将所有样本进行归类
    def create_clusters(self,centers,X):
        n_samples=np.shape(X)[0]
        clusters=[[] for _ in  range(self.k)]
        for sample_i,sample in enumerate(X):
            center_i=self._cloest_center(sample,centers)
            clusters[center_i].append(sample_i)
        return  clusters
    #对中心进行更新
    def update_centers(self,clusters,X):
        n_features=np.shape(X)[1]
        centers=np.zeros((self.k,n_features))
        for i,cluster in enumerate(clusters):
            center=np.mean(X[cluster],axis=0)
            centers[i]=center
        return centers
    def get_cluster_labels(self,clusters,X):
        y_pred=np.zeros(X.shape[0])
        for cluster_i,cluster in enumerate(clusters):
            for sample_i in cluster:
                y_pred[sample_i]=cluster_i
        return y_pred
    def predict(self,X):
        centers=self.init_random_center(X)
        for _ in range(self.max_iteration):
            clusters=self.create_clusters(centers,X)
            former_centers=centers
            centers = self.update_centers(clusters,X)
            diff=centers-former_centers
            if diff.any()<self.varepsilon:
                break
        return self.get_cluster_labels(clusters,X)
def main():
    X, y = datasets.make_blobs(n_samples=10000,
                               n_features=3,
                               centers=[[3, 3, 3], [0, 0, 0], [1, 1, 1], [2, 2, 2]],
                               cluster_std=[0.2, 0.1, 0.2, 0.2],
                               random_state=9)

    # 用Kmeans算法进行聚类
    clf = Kmeans(k=4)
    y_pred = clf.predict(X)
    # 可视化聚类效果
    fig = plt.figure(figsize=(12, 8))
    ax = Axes3D(fig, rect=[0, 0, 1, 1], elev=30, azim=20)
    plt.scatter(X[y == 0][:, 0], X[y == 0][:, 1], X[y == 0][:, 2])
    plt.scatter(X[y == 1][:, 0], X[y == 1][:, 1], X[y == 1][:, 2])
    plt.scatter(X[y == 2][:, 0], X[y == 2][:, 1], X[y == 2][:, 2])
    plt.scatter(X[y == 3][:, 0], X[y == 3][:, 1], X[y == 3][:, 2])
    plt.show()
if __name__=="__main__":
    main()