TF之NN之回归预测：利用NN算法(RelU)实现根据三个自变量预测一个因变量的回归问题

TF之NN之回归预测：利用NN算法(RelU)实现根据三个自变量预测一个因变量的回归问题

目录

实验数据

设计思路

输出结果

实现代码

实验数据

TF之NN之回归预测：利用NN算法(RelU)实现基于30行样本(每个样本含有18列参数包括label)预测一个新样本值

说明：利用前四年的数据建立回归模型，并对第五年进行预测。

设计思路

输出结果

loss is: 913.6623
loss is: 781206160000.0
loss is: 9006693000.0
loss is: 103840136.0
loss is: 1197209.2
loss is: 13816.644
loss is: 173.0564
loss is: 15.756571
loss is: 13.9430275
loss is: 13.922119
loss is: 13.921878
loss is: 13.921875
loss is: 13.921875
loss is: 13.921875
loss is: 13.921875
input is:[120, 5, 85]
output is:15.375002

-selector-tag">y_list -selector-tag">is [[65.0], [64.0], [64.0], [61.0], [59.0], [61.0], [62.0], [60.0], [61.0], [61.0], [59.0], [61.0], [61.0], [60.0], [60.0], [60.0], [59.0], [61.0], [60.0], [59.0], [60.0], [60.0], [59.0], [60.0], [60.0], [60.0], [64.0], [61.0], [59.0], [59.0]]
-selector-tag">x_pred -selector-tag">is [[6.0, 30.0, 0.5, 3.12, 3.13, 364.0, 452.0, 473.0, 1858.0, 1996.0, 2036.0, 0.23, 0.47, 0.5, 0.0, 146.0, 149.0]]
 
-selector-tag">loss -selector-tag">is: 747890.9
-selector-tag">loss -selector-tag">is: 6.603946-selector-tag">e+26
-selector-tag">loss -selector-tag">is: 7.613832-selector-tag">e+24
-selector-tag">loss -selector-tag">is: 8.778148-selector-tag">e+22
-selector-tag">loss -selector-tag">is: 1.0120521-selector-tag">e+21
-selector-tag">loss -selector-tag">is: 1.1668169-selector-tag">e+19
-selector-tag">loss -selector-tag">is: 1.3452473-selector-tag">e+17
-selector-tag">loss -selector-tag">is: 1550963400000000.0
-selector-tag">loss -selector-tag">is: 17881387000000.0
-selector-tag">loss -selector-tag">is: 206158180000.0
-selector-tag">loss -selector-tag">is: 2376841700.0
-selector-tag">loss -selector-tag">is: 27403098.0
-selector-tag">loss -selector-tag">is: 315938.72
-selector-tag">loss -selector-tag">is: 3645.1162
-selector-tag">loss -selector-tag">is: 44.61735
-selector-tag">loss -selector-tag">is: 3.1063914
-selector-tag">loss -selector-tag">is: 2.627804
-selector-tag">loss -selector-tag">is: 2.6222868
-selector-tag">loss -selector-tag">is: 2.622223
-selector-tag">loss -selector-tag">is: 2.6222224
-selector-tag">input -selector-tag">is:[6.0, 30.0, 0.5, 3.12, 3.13, 364.0, 452.0, 473.0, 1858.0, 1996.0, 2036.0, 0.23, 0.47, 0.5, 0.0, 146.0, 149.0]
-selector-tag">output -selector-tag">is:60.66666

实现代码

import numpy as np
import tensorflow as tf
 
x = [[80,3,50],[90,8,70],[180,20,120],[140,16,90]]
y = [[11],[12.5],[20],[18]]
 y = [11,12.5,20,18]
x_pred = [[120,5,85]]
 
 dataset = np.loadtxt("data/20181127test04.csv", delimiter=",")
  split into input (X) and output (Y) variables
 x = dataset[0:7,0:17]
 print(x)
 y = dataset[0:7,17]
 print(y)
 x_pred = dataset[7,0:17]
 print(x_pred)
 
tf_x = tf.placeholder(tf.float32, [None,3])      input x
tf_y = tf.placeholder(tf.float32, [None,1])      input y
 
print(tf_x)
 
 neural network layers
l1 = tf.layers.dense(tf_x, 100, tf.nn.relu)           hidden layer  18*8
output = tf.layers.dense(l1, 1)                       output layer
 
loss = tf.losses.mean_squared_error(tf_y, output)    compute cost
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.1)
train_op = optimizer.minimize(loss)
 
sess = tf.Session()                                  control training and others
sess.run(tf.global_variables_initializer())          initialize var in graph
 
 
for step in range(150):
     train and net output
    _, l, pred = sess.run([train_op, loss, output], {tf_x: x, tf_y: y})
    if step % 10 == 0:
        print('loss is: ' + str(l))
         print('prediction is:' + str(pred))
 
output_pred = sess.run(output,{tf_x:x_pred})
print('input is:' + str(x_pred[0][:]))
print('output is:' + str(output_pred[0][0]))