python实现学生成绩聚类分析_聚类分析的python实现

K-Means算法import numpy as np

import pandas as pd

from sklearn.cluster import KMeans

data = pd.read_csv('multi_vol.csv')

data1 = data.T #使待分类样本格式正确

estimator = KMeans(n_clusters=4) #构造聚类器

estimator.fit(data1)

label_pred = estimator.labels_  #最终聚类类别

centroids = estimator.cluster_centers_ #最终聚类中心

inertia = estimator.inertia_

学习向量量化LVQ#迭代轮数

for i in range(loops):

#随机产生样本

index = np.random.randint(0,30)

min_dist = sum((q[0] - x[index])**2)

q_index = 0

#搜索里样本最近原型向量

for j in range(1,len(q)):

dist = sum((q[j] - x[index])**2)

if dist < min_dist:

min_dist = dist

q_index = j

if q_label[q_index] == y[index]:

#样本标记和原型向量标记相同，该原型向量向样本方向移动

#eta为学习率

q[q_index] += eta*(x[index]-q[q_index])

else:

#样本标记和原型向