KNN近邻算法与手写识别

# 导入库：KNeighborsClassifier
import numpy as np
from sklearn.neighbors import KNeighborsClassifier
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
%matplotlib inline
# 导入sklearn自带数据集
from sklearn import datasets
import  pandas as  pd

导入文件路径

path=r"C:\Users\Tsinghua-yincheng\Desktop\SZday92\KNNTest"

读取npy文件

x_train=np.load(path+"\"+"x_train.npy") #数据
x_train.shape 

x_train

y_train=np.load(path+"\"+"y_train.npy") #数据
y_train.shape 

y_test=np.load(path+"\"+"y_test.npy") #数据
y_test.shape 
x_test=np.load(path+"\"+"x_test.npy") #数据
x_test.shape 

人类的动作有以下几种

label={1:"walking",
       2:"walking up",
       3:"walking down",
       4:"sitting",
       5:"standing",
       6:"laying"}

看看有几种结果

pd.Series(y_train).unique()  #y的结果

y_train
x_train[0]
x_train[0].shape

knn=KNeighborsClassifier(100) #计算周围100个点
knn.fit(x_train,y_train)#训练数据
knn.predict(x_test[::100])#预测以100为间隔的点0 100 200...
y_test[::100]
knn.score(x_test,y_test)
y_new=knn.predict(x_test) #预测的结果
(y_new == y_test).sum()
2611/len(y_test)

np.argwhere(y_train==6) #筛选行为

plt.subplot: plt.subplot(2,3,1)也可以简写plt.subplot(231)表示把显示界面分割成2*3的网格。其中，第一个参数是行数，第二个参数是列数，第三个参数表示图形的标号。

#  78,162,640,29,0,7260   分别对应6种行为抽样数据    
x=[78,152,640,29,0,7260] 
plt.figure(figsize=(12,9))
for i,r  in enumerate(x):
    plt.subplot(3,2,(i+1))
    #取出动作对应数据
    data=x_train[r]
    color=np.random.rand(3)
    plt.plot(data,c=color,label=label[i+1])
    plt.legend()
    plt.show()

ren.m是一个模型,可以发现数据才是关键，才能训练出好的模型

from sklearn.externals import joblib
joblib.dump(knn,
            r"C:\Users\Tsinghua-yincheng\Desktop\SZday92\ren.m")
mynewknn=joblib.load(
    r"C:\Users\Tsinghua-yincheng\Desktop\SZday92\ren.m")
type(mynewknn)
mynewknn.predict(x_test[::200]) #训练好的模型
y_test[::200]

手写训练

import  pandas as pd
from sklearn.decomposition import PCA  #特征处理
from  sklearn.neighbors import KNeighborsClassifier #分类器
import time

if  __name__ =="__main__":
    train_num=20000 #训练的数据
    test_num=30000 #测试的数据
    data=pd.read_csv("train.csv")#读取数据
    print(data)
    train_data=data.values[0:train_num,1:] #抓取训练数据
    train_label=data.values[0:train_num,0] #训练的结果
    test_data=data.values[train_num:test_num,1:] #测试的数据
    test_label = data.values[train_num:test_num, 0]#测试的结果

    start=time.time()
    #pca特征训练   whiten=True白化处理  n_components特征
    pca=PCA(n_components=0.7,whiten=True)
    train_x=pca.fit_transform(train_data) #数据预处理
    test_x=pca.fit_transform(test_data)
    knn=KNeighborsClassifier(n_neighbors=10)
    knn.fit(train_x,train_label) #训练
    pre=knn.predict(test_x) #预测
    acc=  (pre==test_label).sum()/len(test_label)
    end=time.time()
    print("准确率",acc,"time",end-start)

数字手写识别

# 导入库：KNeighborsClassifier
import numpy as np
from sklearn.neighbors import KNeighborsClassifier
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
%matplotlib inline
# 导入sklearn自带数据集
from sklearn import datasets
import  pandas as  pd

path=r"C:\Users\Tsinghua-yincheng\Desktop\SZday92\KNNTest\datanumber="
zero1.plt(imread+path"\0_497.bmp")#读取图片，转化数组 .
zero1

zero1.shape
zero1(reshape-1)#压缩成一维.

plt(imshow,zero1=cmap"gray")=

x_train[]=
pathr"C:\Users\Tsinghua-yincheng\Desktop\SZday92\KNNTest\datanumberfor"in
range i  ( 1,501):#读取500图片，成为一个数组，500元素.(
    x_train.append(plt+imread"\0_%d.bmp"path%())i)=[
X_train]=[
Y_train]=[
X_test]=[
Y_test]=r"xxxxxxxxx"
path#读取数据，加入训练集合与测试集合for
in
range i ( 10):#就是0-9这10个数字forin
	range j ( 1,501):#每个里面有的数据if<
		480 j:#前面是训练.(
			X_train.append(plt+imread"\%d\%d_%d.bmp"path%(,,i)i)j.(-reshape1)).(
			Y_train)appendelsei:
		.(
			X_test.append(plt+imread"\%d\%d_%d.bmp"path%(,,i)i)j.(-reshape1)).(
			Y_test)append=i.	
X_train ( np)array=X_train.
Y_train ( np)array=Y_train.
X_test(np)array=X_test.
Y_test ( np)array.Y_test.
X_train=shape
X_test.shape

n.np(random1randint,210)=[
num]X_test.n((reshape28,28)).(
plt,imshow=num"gray"cmap)=(

knn ) KNeighborsClassifier#建立KNN对象，训练模型.(
knn,fit)X_train=Y_train.
Y_new ( knn)predict[K_test:
Y_new:10]#0 10 20 30...[:
Y_test:10].(
knn,score)X_test#识别率Y_test[:
Y_new:10][:
X_test:10].(

plt=figure(figsize12,15))=[
im_datas:X_test:10]=[
im_target:Y_test:10]=[
im_predict:Y_new:10]forin
range  i  ( 20):.(
    plt5subplot,5,(+1i)).(
    plt[imshow]im_datas.i((reshape28,28))).(
    plt"predict:%d\n"title%([]im_predict)i+"true:%d"%([]im_target)i).(
    plt"xxxxxxxx"imsave,)#数组保存为图片zero1import as

KNN测试

import pandas from pd
import sklearn
, sklearn from datasets.linear_model
import sklearnfromcross_validation .  train_test_split
import sklearnfromlinear_model import LinearRegression
from sklearn . metrics
import sklearnimportmodel_selection =  cross_val_predict
r"C:\Users\Tsinghua-yincheng\Desktop\SZday92\KNNTest\dat\iris_" ML


path=.
x_train(pd+read_csv"xtrain.csv"path,=Falseindex_col)=.
y_train(pd+read_csv"ytrain.csv"path,=Falseindex_col)=.
x_test(pd+read_csv"xtest.csv"path,=Falseindex_col)=.
y_test(pd+read_csv"ytest.csv"path,=Falseindex_col)#mx=ML.mx_knn(x_train.values,y_train.values) #创造KNN=
.
mx(ML.mx_dtree,x_train.values)y_train=values.
y_new(mx.predict)x_test#预测valuesprint (
)printy_new(
..y_test(values-reshape1))print(
((==.y_new.y_test(values-reshape1)).sum())/len(.)y_test)values