Tensorflow實(shí)現(xiàn)酸奶銷(xiāo)量預(yù)測(cè)分析

# coding:utf-8
# 酸奶成本為1元，利潤(rùn)為9元
# 預(yù)測(cè)少了相應(yīng)的損失較大，故不要預(yù)測(cè)少
# 導(dǎo)入相應(yīng)的模塊
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
 
BATCH_SIZE=8
SEED=23455
COST=3
PROFIT=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]
 
# 定義神經(jīng)網(wǎng)絡(luò)的輸入、參數(shù)和輸出，定義向前傳播過(guò)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)
 
# 定義損失函數(shù)和反向傳播過(guò)程
loss=tf.reduce_sum(tf.where(tf.greater(y,y_),(y-y_)*COST,(y_-y)*PROFIT)) #損失函數(shù)要根據(jù)不同的模型進(jìn)行變換
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=20000
for 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()