car evaluation dataset is a free dataset provided by hfh .
I now want to cluster this data set through kmeans by studying the book "Machine Learning practice". It is found that because the car data set is a classified data set, while the kmeans clustering algorithm can only cluster numerical data.
my idea is that because the data in car is classified but size-dependent, I use pandas to map

size_mapping = {
       "low": 1,
       "med": 2,
       "high": 3,
        "vhigh":4,
        "5more":5,
        "small":1,
        "big":3}

however, it is not clear how to convert all the original car data sets to numeric types and import them into kmeans. The kmeans program has been typed out according to the book.

-sharp encoding:utf-8
from numpy import *
import matplotlib.pyplot as plt

def loadDataSet(filename):
    dataMat = []  -sharp 
    fr = open(filename)
    for line in fr.readlines():
        curLine = line.strip().split("   ")
        fltLine = map(float, curLine)  -sharp mapcurLinefloat
        dataMat.append(fltLine)
    return dataMat


def distEclud(vecA, vecB):  -sharp 
    return sqrt(sum(power(vecA - vecB, 2)))


def randCent(dataSet, k):  -sharp k
    n = shape(dataSet)[1]  -sharp shapedataSet
    centroids = mat(zeros((k, n)))  -sharp matkncentroids
    for j in range(n):
        minJ = min(dataSet[:, j])  -sharp j
        rangeJ = float(max(dataSet[:, j]) - minJ)
        centroids[:, j] = minJ + rangeJ * random.rand(k, 1)  -sharp random.rand(k,1)shape(k,1)
    return centroids

def kMeans(dataSet, k, distMeas=distEclud, createCent=randCent):
    m = shape(dataSet)[0]  -sharp shapedataSet
    clusterAssment = mat(zeros((m, 2)))  -sharp m2
    centroids = createCent(dataSet, k)  -sharp kcreateCent()
    clusterChanged = True  -sharp true
    print ":"
    while clusterChanged:
        clusterChanged = False
        for i in range(m):
            minDist = inf  -sharp inf
            minIndex = -1  -sharp 
            for j in range(k):
                -sharp 
                distJI = distMeas(centroids[j, :], dataSet[i, :])  -sharp 
                if distJI < minDist:
                    minDist = distJI; minIndex = j
            if clusterAssment[i,0] != minIndex: clusterChanged = True
            clusterAssment[i,:] = minIndex,minDist**2
        print centroids
        for cent in range(k):
            ptsInClust = dataSet[nonzero(clusterAssment[:,0].A==cent)[0]]
            centroids[cent, :] = mean(ptsInClust, axis=0)  -sharp axis=0
    return centroids, clusterAssment  -sharp 


datMat = mat(loadDataSet("car.txt"))
myCentroids, clustAssing = kMeans(datMat, 4)
print ":\n", myCentroids
print ":\n", clustAssing