Tensorflow实现酸奶销量预测分析

# coding:utf-8# 酸奶成本为1元，利润为9元# 预测少了相应的损失较大，故不要预测少# 导入相应的模块import tensorflow as tfimport numpy as npimport matplotlib.pyplot as plt BATCH_SIZE=8SEED=23455COST=3PROFIT=4 rdm=np.random.RandomState(SEED)X=rdm.randn(100,2)Y_=[[x1+x2+(rdm.rand()/10.0-0.05)] for (x1,x2) in X] # 定义神经网络的输入、参数和输出，定义向前传播过程x=tf.placeholder(tf.float32,shape=(None,2))y_=tf.placeholder(tf.float32,shape=(None,1))w1=tf.Variable(tf.random_normal([2,1],stddev=1,seed=1))y=tf.matmul(x,w1) # 定义损失函数和反向传播过程loss=tf.reduce_sum(tf.where(tf.greater(y,y_),(y-y_)*COST,(y_-y)*PROFIT)) #损失函数要根据不同的模型进行变换train_step=tf.train.GradientDescentOptimizer(0.001).minimize(loss) # sess=tf.Session()# STEPS=20000# init_op=tf.global_variables_initializer()# sess.run(init_op)# for i in range(STEPS):#  start=(i*BATCH_SIZE)%32#  end=start+BATCH_SIZE#  sess.run(train_step,feed_dict={x:X[start:end],y_:Y[start:end]})#  if i%500==0:##   print("After %d steps,w1 is %f",(i,sess.run(w1))) sess=tf.Session()init_op=tf.global_variables_initializer()sess.run(init_op)STEPS=20000for i in range(STEPS): start=(i*BATCH_SIZE)%100 end=start+BATCH_SIZE sess.run(train_step,feed_dict={x:X[start:end],y_:Y_[start:end]}) if i%500==0:  print("After %d steps"%(i))  # print(sess.run(loss_mse))  # print("Loss is:%f",sess.run(loss_mse,feed_dict={y_:Y_,y:Y_}))  print("w1 is:",sess.run(w1)) print("Final is :",sess.run(w1)) xx,yy=np.mgrid[-3:3:.01,-3:3:.01]grid=np.c_[xx.ravel(),yy.ravel()]probs=sess.run(y,feed_dict={x:grid})probs=probs.reshape(xx.shape) plt.scatter(X[:,0],X[:,1],c=np.squeeze(Y_))plt.contour(xx,yy,probs,[.9])plt.show()