Python实战演练之python实现神经网络模型算法

python实现神经网络模型算法

今天，厾罗和大家分享用Python实现神经网络模型算法，仅用于技术学习交流。

实现技巧

1.导入依赖库

主要是安装相关的依赖库。本文实现的环境为：python 3.7。

from __future__ import division    
import math      
import random    
import pandas as pd  

2.构建BP神经网络类

主要是构建三层反向传播神经网络类。

""" 三层反向传播神经网络 """
class NN:
    def __init__(self, ni, nh, no):
        self.ni = ni + 1                            # 输入层节点
        self.nh = nh + 1                    # 隐藏层节点
        self.no = no                      # 输出层种类
        self.ai = [1.0] * self.ni    
        self.ah = [1.0] * self.nh    
        self.ao = [1.0] * self.no    
        self.wi = self.makeMatrix(self.ni, self.nh)  # 输出层到隐藏层的映射矩阵
        self.wo = self.makeMatrix(self.nh, self.no)  # 隐藏层到输出层的映射矩阵
        for i in range(self.ni):          
            for j in range(self.nh):    
                self.wi[i][j] = self.rand(-0.2, 0.2)  
        for j in range(self.nh):
            for k in range(self.no):
                self.wo[j][k] = self.rand(-2, 2)  
 
    #前向传播，激活神经网络的所有节点
    def update(self, inputs):
        if len(inputs) != self.ni - 1:
            print(len(inputs),self.ni - 1)
            raise ValueError('与输入层节点数不符！')    
        for i in range(self.ni - 1):    
            self.ai[i] = inputs[i]    
        for j in range(self.nh):                  # self.nh表示隐藏层的节点数
            sum = 0.0                            # 激活项a = g(z)  z = Θ^T x ;sum相当于z，每次循环归零
            for i in range(self.ni):                  #通过循环z = Θ^T x ，因为Θ、x均为向量
                sum = sum + self.ai[i] * self.wi[i][j]  #〖 Z〗^((2))=Θ^((1)) a^((1))
            self.ah[j] = self.sigmoid(sum)    # a^((2))=g(z^((2)))，这里使用sigmoid()函数作为激活函数
        for k in range(self.no):
            sum = 0.0
            for j in range(self.nh):
                sum = sum + self.ah[j] * self.wo[j][k]  #〖 Z〗^((3))=Θ^((2)) a^((2))
            self.ao[k] = self.sigmoid(sum)    # a^((3))=g(z^((3)))
        return self.ao[:]
    
    #反向传播,计算节点激活项的误差
    def backPropagate(self, targets, lr):               # targets为某样本实际种类分类，lr为梯度下降算法的学习率
        output_deltas = [0.0] * self.no
        for k in range(self.no):
            error = targets[k] - np.round_(self.ao[k])
            output_deltas[k] = self.dsigmoid(self.ao[k]) * error
        # 计算隐藏层的误差
        hidden_deltas = [0.0] * self.nh    
        for j in range(self.nh):
            error = 0.0
            for k in range(self.no):
                error = error + output_deltas[k] * self.wo[j][k]    
            hidden_deltas[j] = self.dsigmoid(self.ah[j]) * error
 
        # 更新输出层权重
        for j in range(self.nh):            # 反向传播算法，求出每个节点的误差后，反向更新权重
            for k in range(self.no):
                change = output_deltas[k] * self.ah[j]    
                self.wo[j][k] = self.wo[j][k] + lr * change   
        # 更新输入层权重
        for i in range(self.ni):                    
            for j in range(self.nh):
                change = hidden_deltas[j] * self.ai[i]
                self.wi[i][j] = self.wi[i][j] + lr * change
        # 计算误差
        error = 0.0
        for k in range(self.no):                                    
            error += 0.5 * (targets[k] - np.round_(self.ao[k])) ** 2  
        return error                                          
 
    #用测试集输出准确率
    def test(self, patterns):                            
        count = 0
        num=0
        for p in patterns:
            target = p[1]
            result = self.update(p[0])                    
            print(p[0], ':', target, '->', np.round_(result))
            num=0
            for k in range(self.no):
                if (target[k] == np.round_(result[k])):
                    num +=1
            print(num)
            if num==3:
                count +=1
            print("******************",(target) == (np.round_(result)),"******************")
            accuracy = int(float(count / len(patterns))*100)
        print('accuracy: %-.9f' % accuracy,"%")      
 
    #输出训练过后神经网络的权重矩阵
    def weights(self):
        print('输入层权重:')
        for i in range(self.ni):
            print(self.wi[i])
        print()
        print('输出层权重:')
        for j in range(self.nh):
            print(self.wo[j])
            
    #用训练集训练神经网络
    def train(self, patterns, iterations=1000, lr=0.1):  
        for i in range(iterations):
            error = 0.0                    
            for p in patterns:            
                inputs = p[0]            
                targets = p[1]            
                self.update(inputs)          
                error = error + self.backPropagate(targets, lr)  
            if i % 100 == 0:
                print("percent：",int(i/iterations*100),"%",'   error: %-.9f' % error)

    #生成区间[a, b)内的随机数
    def rand(self, a, b):    
        return (b - a) * random.random() + a    
    
    # 生成大小 I*J 的矩阵，默认零矩阵
    def makeMatrix(self, I, J, fill=0.0):    
        m = []    
        for i in range(I):    
            m.append([fill] * J)    
        return m   

    # 函数 sigmoid，bp神经网络前向传播的激活函数
    def sigmoid(self, x):
        return 1.0 / (1.0 + math.exp(-x))       
     
    # 函数 sigmoid 的导数，反向传播时使用
    def dsigmoid(self, x):
        return x * (1 - x)

3.读取数据并进行预处理

主要是读取构建分类模型的数据，并进行预处理。

  data = []                            
    raw = pd.read_csv('iris.csv')    
    raw_data = raw.values            
    raw_feature = raw_data[1:, 1:5]    
    for i in range(len(raw_feature)):          
        ele = []                    
        ele.append(list(raw_feature[i]))  
        if raw_data[i][5] == 0:   
            ele.append([0, 0,1])    
        elif raw_data[i][5] == 1:
            ele.append([0,1, 0])
        elif raw_data[i][5] == 2:
            ele.append([1, 1,1])
        else:
            ele.append([0, 0,0])
        data.append(ele)

4.利用构建的BP神经网络预测类，创建神经网络模型

主要是用BP神经网络预测类创建神经网络类模型。

  nn = NN(4, 10, 3)  

5.BP分类模型训练及预测

主要是划分训练集和测试集，并进行BP分类模型训练和预测。

   training = data[1:100]            
    test = data[101:]            
    nn.train(training, iterations=1000)  
    nn.test(test) 

完整源代码

from __future__ import division    
import math      
import random    
import pandas as pd    
import numpy as np
 
""" 三层反向传播神经网络 """
class NN:
    def __init__(self, ni, nh, no):
        self.ni = ni + 1                            # 输入层节点
        self.nh = nh + 1                    # 隐藏层节点
        self.no = no                      # 输出层种类
        self.ai = [1.0] * self.ni    
        self.ah = [1.0] * self.nh    
        self.ao = [1.0] * self.no    
        self.wi = self.makeMatrix(self.ni, self.nh)  # 输出层到隐藏层的映射矩阵
        self.wo = self.makeMatrix(self.nh, self.no)  # 隐藏层到输出层的映射矩阵
        for i in range(self.ni):          
            for j in range(self.nh):    
                self.wi[i][j] = self.rand(-0.2, 0.2)  
        for j in range(self.nh):
            for k in range(self.no):
                self.wo[j][k] = self.rand(-2, 2)  
 
    #前向传播，激活神经网络的所有节点
    def update(self, inputs):
        if len(inputs) != self.ni - 1:
            print(len(inputs),self.ni - 1)
            raise ValueError('与输入层节点数不符！')    
        for i in range(self.ni - 1):    
            self.ai[i] = inputs[i]    
        for j in range(self.nh):                  # self.nh表示隐藏层的节点数
            sum = 0.0                            # 激活项a = g(z)  z = Θ^T x ;sum相当于z，每次循环归零
            for i in range(self.ni):                  #通过循环z = Θ^T x ，因为Θ、x均为向量
                sum = sum + self.ai[i] * self.wi[i][j]  #〖 Z〗^((2))=Θ^((1)) a^((1))
            self.ah[j] = self.sigmoid(sum)    # a^((2))=g(z^((2)))，这里使用sigmoid()函数作为激活函数
        for k in range(self.no):
            sum = 0.0
            for j in range(self.nh):
                sum = sum + self.ah[j] * self.wo[j][k]  #〖 Z〗^((3))=Θ^((2)) a^((2))
            self.ao[k] = self.sigmoid(sum)    # a^((3))=g(z^((3)))
        return self.ao[:]
    
    #反向传播,计算节点激活项的误差
    def backPropagate(self, targets, lr):               # targets为某样本实际种类分类，lr为梯度下降算法的学习率
        output_deltas = [0.0] * self.no
        for k in range(self.no):
            error = targets[k] - np.round_(self.ao[k])
            output_deltas[k] = self.dsigmoid(self.ao[k]) * error
        # 计算隐藏层的误差
        hidden_deltas = [0.0] * self.nh    
        for j in range(self.nh):
            error = 0.0
            for k in range(self.no):
                error = error + output_deltas[k] * self.wo[j][k]    
            hidden_deltas[j] = self.dsigmoid(self.ah[j]) * error
 
        # 更新输出层权重
        for j in range(self.nh):            # 反向传播算法，求出每个节点的误差后，反向更新权重
            for k in range(self.no):
                change = output_deltas[k] * self.ah[j]    
                self.wo[j][k] = self.wo[j][k] + lr * change   
        # 更新输入层权重
        for i in range(self.ni):                    
            for j in range(self.nh):
                change = hidden_deltas[j] * self.ai[i]
                self.wi[i][j] = self.wi[i][j] + lr * change
        # 计算误差
        error = 0.0
        for k in range(self.no):                                    
            error += 0.5 * (targets[k] - np.round_(self.ao[k])) ** 2  
        return error                                          
 
    #用测试集输出准确率
    def test(self, patterns):                            
        count = 0
        num=0
        for p in patterns:
            target = p[1]
            result = self.update(p[0])                    
            print(p[0], ':', target, '->', np.round_(result))
            num=0
            for k in range(self.no):
                if (target[k] == np.round_(result[k])):
                    num +=1
            print(num)
            if num==3:
                count +=1
            print("******************",(target) == (np.round_(result)),"******************")
            accuracy = int(float(count / len(patterns))*100)
        print('accuracy: %-.9f' % accuracy,"%")      
 
    #输出训练过后神经网络的权重矩阵
    def weights(self):
        print('输入层权重:')
        for i in range(self.ni):
            print(self.wi[i])
        print()
        print('输出层权重:')
        for j in range(self.nh):
            print(self.wo[j])
 
    #用训练集训练神经网络
    def train(self, patterns, iterations=1000, lr=0.1):  
        for i in range(iterations):
            error = 0.0                    
            for p in patterns:            
                inputs = p[0]            
                targets = p[1]            
                self.update(inputs)          
                error = error + self.backPropagate(targets, lr)  
            if i % 100 == 0:
                print("percent：",int(i/iterations*100),"%",'   error: %-.9f' % error)

    #生成区间[a, b)内的随机数
    def rand(self, a, b):    
        return (b - a) * random.random() + a    
    
    # 生成大小 I*J 的矩阵，默认零矩阵
    def makeMatrix(self, I, J, fill=0.0):    
        m = []    
        for i in range(I):    
            m.append([fill] * J)    
        return m   

    # 函数 sigmoid，bp神经网络前向传播的激活函数
    def sigmoid(self, x):
        return 1.0 / (1.0 + math.exp(-x))       
     
    # 函数 sigmoid 的导数，反向传播时使用
    def dsigmoid(self, x):
        return x * (1 - x)

if __name__ == '__main__':
    data = []                            
    raw = pd.read_csv('iris.csv')    
    raw_data = raw.values            
    raw_feature = raw_data[1:, 1:5]    
    for i in range(len(raw_feature)):          
        ele = []                    
        ele.append(list(raw_feature[i]))  
        if raw_data[i][5] == 0:   
            ele.append([0, 0,1])    
        elif raw_data[i][5] == 1:
            ele.append([0,1, 0])
        elif raw_data[i][5] == 2:
            ele.append([1, 1,1])
        else:
            ele.append([0, 0,0])
        data.append(ele)
    nn = NN(4, 10, 3)  
    training = data[1:100]            
    test = data[101:]            
    nn.train(training, iterations=1000)  
    nn.test(test)