# -*- coding: utf-8 -*-
import sklearn
from sklearn import neighbors
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn import datasets
import pandas as pd
import numpy


def getData_1():

    iris = datasets.load_iris()
    X = iris.data   #樣本特徵矩陣，150*4矩陣，每行一個樣本，每個樣本維度是4
 
    y = iris.target #樣本類別矩陣，150維行向量，每個元素代表一個樣本的類別


    df1=pd.DataFrame(X, columns =['SepalLengthCm','SepalWidthCm','PetalLengthCm','PetalWidthCm'])
    df1['target']=y

    return df1

df=getData_1()


X_train, X_test, y_train, y_test = train_test_split(df.iloc[:,0:3],df['target'], test_size=0.3, random_state
 
=42)
print X_train, X_test, y_train, y_test

model = neighbors.KNeighborsClassifier(n_neighbors=5, n_jobs=1)  # knn
"""引數
---
    n_neighbors： 使用鄰居的數目
    n_jobs：並行任務數
"""
model.fit(X_train,y_train)
predict=model.predict(X_test)
print predict
print y_test.values

print 'knn分類:{:.3f}'.format(model.score(X_test, y_test))

結果：

預測值：[2 0 2 1 1 0 1 1 1 1 2 0 0 0 0 1 2 1 1 2 0 2 0 2 2 2 2 2 0 0 0 0 1 0 0 2 1  0 0 0 2 1 1 0 0] 真實值：[1 0 2 1 1 0 1 2 1 1 2 0 0 0 0 1 2 1 1 2 0 2 0 2 2 2 2 2 0 0 0 0 1 0 0 2 1  0 0 0 2 1 1 0 0] knn分類準確度:0.956