【机器学习】python实现KNN模型识别手写题数字

机器学习是AI人工智能的重要组成部分。机器学习不仅包含了KNN、SVM、决策树等模型与方法，更有近年来越来越潮流的DP（深度学习）。这回讲一讲如何利用python构建KNN模型源码并实现识别手写体数字。

目录

1.导入第三方函数库

2.读取训练数据

3.读取测试数据

4.建立模型

5.绘制超参数N与模型准确率的关系曲线

---

1.导入第三方函数库

import numpy as np
import pandas as pd
import matplotlib.pylab as plt
%matplotlib inline
import os

2.读取训练数据

# 获取数据文件
fileList = os.listdir('C:/Users/15405/Desktop/digits/digits/trainingDigits/')
# 定义数据标签列表
trainingIndex = []
# 添加数据标签
for filename in fileList:
    trainingIndex.append(int(filename.split('_')[0]))
# 定义矩阵数据格式
trainingData = np.zeros((len(trainingIndex),32*32))

# 获取矩阵数据
index = 0
for filename in fileList:
    with open('C:/Users/15405/Desktop/digits/digits/trainingDigits/%s'%filename, 'rb') as f:
        # 定义一个空矩阵
        vect = np.zeros((1,1024))
        # 循环32行
        for i in range(32):
            # 读取每一行数据
            line = f.readline()
            # 遍历每行数据索引  line[j] 即为数据
            for j in range(32):
                vect[0,32*i+j] = int(line[j])
        
        trainingData[index,:] = vect
        index+=1

3.读取测试数据

fileList2 = os.listdir('C:/Users/15405/Desktop/digits/digits/testDigits/')
# 定义数据标签列表
testIndex = []# 获取数据标签
for filename2 in fileList2:
    testIndex.append(int(filename2.split('_')[0]))
# 定义矩阵数据格式
testData = np.zeros((len(testIndex),1024))
# 获取矩阵数据
index = 0
for filename2 in fileList2:
    with open('C:/Users/15405/Desktop/digits/digits/testDigits/%s'%filename2, 'rb') as f:   
        # 定义一个空矩阵
        vect = np.zeros((1,1024))
        # 循环32行
        for i in range(32):
            # 读取每一行数据
            line = f.readline()
            # 遍历每行数据索引  line[j] 即为数据
            for j in range(32):
                vect[0,32*i+j] = int(line[j])
        testData[index,:] = vect
        index+=1

4.建立模型

def KNN(n_neighbors):
    from sklearn.neighbors import KNeighborsClassifier
    knn = KNeighborsClassifier(n_neighbors=n_neighbors)#超参数N
    #利用训练数据拟合模型
    knn.fit(trainingData,trainingIndex)
    # 预测数据 
    predict_data = knn.predict(testData)
    print("超参数n="+str(n_neighbors)+"时，模型的准确率："+str(knn.score(testData,testIndex)))
    return knn.score(testData,testIndex)

5.绘制超参数N与模型准确率的关系曲线

correct=[]
for i in range(1,10):
    correct.append(KNN(i))
#绘制平滑曲线
import matplotlib.pyplot as plt
from scipy.interpolate import make_interp_spline
xnew = np.linspace(1,10,300) #将自变量划分为300段
power_smooth = make_interp_spline(range(1,10),correct)(xnew)
plt.plot(xnew,power_smooth)
plt.show()