# -*- coding: utf-8 -*-
import numpy as np
def tanh(x):
return np.tanh(x)
def tanh_deriv(x):
return 1.0-np.tanh(x)*np.tanh(x)
def logistic(x):
return 1/(1+np.exp(-x))
def logistic_derivate(x):
return logistic(x)*(1-logistic(x))
class NeuralNetwork:
def __init__(self, layers,activation='tanh'):
#默认tanh
#实例化一个对象,首先调用构造函数。self:指引类本身的指针,layer:包含神经网络有几层,每层有多少个神经元:10,2,2
if activation == 'logistic':
self.activation = logistic
self.activation_deriv = logistic_derivative
elif activation == 'tanh':
self.activation = tanh
self.activation_deriv = tanh_deriv
self.weights=[]
for i in range(1, len(layers)-1):
#layer:10 10 3
self.weights.append(2*np.random.random((layers[i-1]+1, layers[i]-1)*0.25)
self.weights.append(2*np.random.random((layers[i]+1),layers[i+1]-1)*0.25)
def fit(self, X, y, learning_rate=0.2, epochs=10000):#X 每一行对应一个实例,y 函数的分类标记
#抽样的方法对神经网络进行更新,每抽取一次成为一个epochs循环
#权重低于某个阈值;预测的错误率低于某个阈值;达到一定的循环次数。可以停止
X = np.atleast_2d(X)
temp = np.ones([X.shape[0],X.shape[1]+1]) #初始化矩阵都是1
temp[:, 0:-1] #对bias偏置赋值,除了最后一列
X= temp
y = np.array(y)
for k in range(epochs):
i = np.random.randint(X.shape[0])#从0到n随机抽取一行
a = [X[i]]
for l in range(len(self.weights)):
a.append(self.activation(np.dot(a[l], self.weights[l]))) #计算node 内积 完成正向所有更新
error = y[i] - a[-1] #真实y a最后一层 差值
deltas = [error * self.activation_deriv(a[-1])]
for l in range(len(a)-2,0,-1): #往回循环
deltas.append(deltas[-1].dot(self.weights[l].T)*self.activation_derive)
deltas.reverse() #层数顺序颠倒
for i in range(len(self.weights)):
layer = np.atleast_2d(a[i])
delta = np.atleast_2d(deltas[i])
self.weights[i] += learning_rate *layer.T.dot(delta)
def predit(self, x):
x = np.array(x)
temp = np.ones(x.shape[0]+1)
temp[0:-1] = x
a = temp
for l in range(0, len(self.weights)):
a = self.activation(np.dot(a,self.weights[l]))
return a