# -*- coding: utf-8 -*-
from __future__ import print_function
from sklearn import datasets
from sklearn.cross_validation import train_test_split
from sklearn.neighbors import KNeighborsClassifier
data_x=[]
data_y=[]
with open('data.txt') as txt:
arrayContext = txt.readlines()
for context in arrayContext:
context = context.split()
for num in range(len(context)):
context[num] = context[num].replace('A' + str(num + 1), '')
data_x.append(context[1:19])
data_y.append(context[-1])
x_train,x_test,y_train,y_test=train_test_split(data_x,data_y,test_size=0.3)
knn = KNeighborsClassifier()
knn.fit(x_train, y_train)
print(knn.predict(x_test))
print(y_test)
运行结果:
runfile('C:/Users/钟琅/Desktop/t/untitled.py', wdir='C:/Users/钟琅/Desktop/t')
['2' '1' '1' '1' '2' '1' '1' '2' '1' '1' '1' '1' '2' '1' '1' '2' '1' '1'
'1' '1' '1' '2' '1' '1' '1' '1' '1' '1' '1' '2' '1' '1' '1' '1' '1' '1'
'2' '1' '2' '1' '1' '2' '1' '1' '1' '1' '1' '2' '1' '1' '1' '1' '1' '1'
'1' '1' '1' '1' '1' '1' '1' '1' '1' '2' '1' '1' '1' '1' '1' '1' '1' '1'
'2' '1' '1' '1' '1' '1' '1' '1' '1' '1' '1' '1' '1' '1' '1' '1'