python十折交叉验证_（数据挖掘-入门-6）十折交叉验证和K近邻

# #K Nearest Neighbor Classifier for Pima dataset#

importheapqimportrandomclassClassifier:def __init__(self, bucketPrefix, testBucketNumber, dataFormat, k):"""a classifier will be built from files with the bucketPrefix

excluding the file with textBucketNumber. dataFormat is a string that

describes how to interpret each line of the data files. For example,

for the mpg data the format is:

"class num num num num num comment""""self.medianAndDeviation=[]

self.k=k#reading the data in from the file

self.format= dataFormat.strip().split('\t')

self.data=[]#for each of the buckets numbered 1 through 10:

for i in range(1, 11):#if it is not the bucket we should ignore, read in the data

if i !=testBucketNumber:

filename= "%s-%02i" %(bucketPrefix, i)

f=open(filename)

lines=f.readlines()

f.close()for line in lines[1:]:

fields= line.strip().split('\t')

ignore=[]

vector=[]for i inrange(len(fields)):if self.format[i] == 'num':

vector.append(float(fields[i]))elif self.format[i] == 'comment':

ignore.append(fields[i])elif self.format[i] == 'class':

classification=fields[i]

self.data.append((classification, vector, ignore