lklearn之knn算法分类实例

knn算法：在训练集中取前n个距离目标最近的点，统计这些点的类别，哪个类别出现的次数最多，则数据属于哪一类

代码：

from __future__ import print_function
from numpy import *
import operator
import csv
from sklearn import datasets
from sklearn.cross_validation import train_test_split
from sklearn.neighbors import KNeighborsClassifier
def file2matrix(filename):
    Mat = zeros((1000,20))
    label = []
    index = 0
    t = 0
    with open(filename,"r",encoding="utf-8") as csvfile:
        read = csv.reader(csvfile)
        for i in read:
            if t ==0 :
                t=t+1
                continue
            else:
                Mat[index,:] = i[0:20]
                label.append(i[20])
                index = index + 1
    return Mat,label
normMat,datingLabels = file2matrix("1.csv")
errorcount = 0;
X_train, X_test, y_train, y_test = train_test_split(normMat,datingLabels, test_size=0.3)
knn = KNeighborsClassifier()
knn.fit(X_train,y_train)
for i in range(300):
    if(knn.predict(X_test)[i]!=y_test[i]):
        errorcount=errorcount+1
print(errorcount/300)