python聚类问题

Question

问题遇到的现象和发生背景

部分数据集
d=[[1994.0, 9.6], [1957.0, 9.5], [1997.0, 9.5], [1994.0, 9.4], [1993.0, 9.4], [2012.0, 9.4], [1993.0, 9.4], [1997.0, 9.4], [2013.0, 9.4], [1994.0, 9.4], [2003.0, 9.3], [2016.0, 9.3], [2009.0, 9.3], [2009.0, 9.3], [2008.0, 9.3], [2008.0, 9.3], [1957.0, 9.3], [2008.0, 9.3], [2001.0, 9.2], [2009.0, 9.2], [1931.0, 9.2], [1961.0, 9.2], [2010.0, 9.2], [2004.0, 9.2], [1998.0, 9.2]]

import random
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

# 计算欧拉距离
def calcDis(dataSet, centroids, k):
    clalist=[]
    for data in dataSet:
        diff = np.tile(data, (k, 1)) - centroids  #相减   (np.tile(a,(2,1))就是把a先沿x轴复制1倍，即没有复制，仍然是 [0,1,2]。 再把结果沿y方向复制2倍得到array([[0,1,2],[0,1,2]]))
        squaredDiff = diff ** 2     #平方
        squaredDist = np.sum(squaredDiff, axis=1)   #和  (axis=1表示行)
        distance = squaredDist ** 0.5  #开根号
        clalist.append(distance) 
    clalist = np.array(clalist)  #返回一个每个点到质点的距离len(dateSet)*k的数组
    return clalist

# 计算质心
def classify(dataSet, centroids, k):
    # 计算样本到质心的距离
    clalist = calcDis(dataSet, centroids, k)
    # 分组并计算新的质心
    minDistIndices = np.argmin(clalist, axis=1)    #axis=1 表示求出每行的最小值的下标
    newCentroids = pd.DataFrame(dataSet).groupby(minDistIndices).mean() #DataFramte(dataSet)对DataSet分组，groupby(min)按照min进行统计分类，mean()对分类结果求均值
    newCentroids = newCentroids.values
 
    # 计算变化量
    changed = newCentroids - centroids
 
    return changed, newCentroids

# 使用k-means分类
def kmeans(dataSet, k):
    # 随机取质心
    centroids = random.sample(dataSet, k)
    
    # 更新质心 直到变化量全为0
    changed, newCentroids = classify(dataSet, centroids, k)
    while np.any(changed != 0):
        changed, newCentroids = classify(dataSet, newCentroids, k)
 
    centroids = sorted(newCentroids.tolist())   #tolist()将矩阵转换成列表 sorted()排序
 
    # 根据质心计算每个集群
    cluster = []
    clalist = calcDis(dataSet, centroids, k) #调用欧拉距离
    minDistIndices = np.argmin(clalist, axis=1)  
    for i in range(k):
        cluster.append([])
    for i, j in enumerate(minDistIndices):   #enymerate()可同时遍历索引和遍历元素
        cluster[j].append(dataSet[i])
        
    return centroids, cluster
 
# 创建数据集
def createDataSet():
   
    return d
    
if __name__=='__main__': 
    dataset = createDataSet()
    
    centroids, cluster = kmeans(dataset, 3)
    print('质心为：%s' % centroids)
    print('集群为：%s' % cluster)
    for i in range(len(dataset)):
        label_pred = estimator.labels_  # 获取聚类标签
        # 绘制k-means结果
        x0 = X[label_pred == 0]
        x1 = X[label_pred == 1]
        x2 = X[label_pred == 2]
        plt.scatter(x0[:, 0], x0[:, 1], c="deeppink", marker='o', label='label0')
        plt.scatter(x1[:, 0], x1[:, 1], c="green", marker='*', label='label1')
        plt.scatter(x2[:, 0], x2[:, 1], c="blue", marker='+', label='label2')
      
        for j in range(len(centroids)):
            plt.scatter(centroids[j][0],centroids[j][1],marker='x',color='red',s=70,label='质心')
        
    plt.show()

运行结果及详细报错内容

想知道错在哪里，怎么修改

Answer 1

你的数据中有非数值型的字符串型数据，你检查一下新使用的数据