基于Python中theano库的线性回归（随机梯度下降）

基于Python中theano库的线性回归

theano库是做deep learning重要的一部分，其最吸引人的地方之一是你给出符号化的公式之后，能自动生成导数。本文使用梯度下降的方法，进行数据拟合，现在把代码贴在下方

代码块

import numpy as np  
import theano.tensor as T  
import theano  
import time  

class Linear_Reg(object):  
    def __init__(self,x):  
        self.a = theano.shared(value = np.zeros((1,), dtype=theano.config.floatX),name = 'a')  
        self.b = theano.shared(value = np.zeros((1,),  
dtype=theano.config.floatX),name = 'b')  
        self.result = self.a * x + self.b  
        self.params = [self.a,self.b]  
    def msl(self,y):  
        return T.mean((y - self.result)**2)  

def regrun(rate,data,labels):  

    X = theano.shared(np.asarray(data,  
                                 dtype=theano.config.floatX),borrow = True)  
    Y = theano.shared(np.asarray(labels,  
                                 dtype=theano.config.floatX),borrow = True)  

    index = T.lscalar()  #定义符号化的公式
    x = T.dscalar('x')   #定义符号化的公式
    y = T.dscalar('y')   #定义符号化的公式

    reg = Linear_Reg(x = x)  
    cost = reg.msl(y)  


    a_g = T.grad(cost = cost,wrt = reg.a)  #计算梯度 
    b_g = T.grad(cost = cost, wrt = reg.b)  #计算梯度

    updates=[(reg.a,reg.a - rate * a_g),(reg.b,reg.b - rate * b_g)]  #更新参数
    train_model = theano.function(inputs=[index],  outputs = reg.msl(y),updates = updates,givens = {x:X[index], y:Y[index]})  

    done = True  
    err = 0.0  
    count = 0  
    last = 0.0  
    start_time = time.clock()  
    while done:  
        #err_s = [train_model(i) for i in xrange(data.shape[0])]  
        for i in xxx:
            err_s = [train_model(i) ]
            err = np.mean(err_s)    

        #print err  
        count = count + 1  
        if count > 10000 or err <0.1:  
            done = False  
        last = err  
    end_time = time.clock()  
    print 'Total time is ：',end_time -start_time,' s' # 5.12s  
    print 'last error :',err  
    print 'a value : ',reg.a.get_value() #  [ 2.92394467]   
    print 'b value : ',reg.b.get_value() # [ 1.81334458]  

if __name__ == '__main__':   
    rate = 0.01  
    data = np.linspace(1,10,10)  
    labels = data * 3 + np.ones(data.shape[0],dtype=np.float64) +np.random.rand(data.shape[0])
    regrun(rate,data,labels)  

其基本思想是随机梯度下降