人工神经网络逼近股票价格

代码：

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

#日期15天
data = np.linspace(0,14,15) #生成1到15个数
#收盘
endPrice = np.array([2511.90,2538.26,2510.68,2591.66,2732.98,2701.69,2701.29,2678.67,2726.50,2681.50,2739.17,2715.07,2823.58,2864.90,2919.08])
#开盘
beginPrice = np.array([2438.71,2535.88,2534.95,2512.52,2594.04,2743.26,2697.47,2695.24,2678.23,2722.13,2674.93,2744.13,2717.46,2832.73,2877.40])

#plt.figure()
for i in range(0,15):
    dataOne = np.zeros([2])
    dataOne[0] = i
    dataOne[1] = i

    priceOne = np.zeros([2])           #纵坐标 开盘与收盘的平均范围
    priceOne[0] = beginPrice[i]        #开盘价
    priceOne[1] = endPrice[i]          #收盘价

    if endPrice[i] > beginPrice[i]:
        plt.plot(dataOne,priceOne,'r',lw = 8) #参数12是np数组
    else:
        plt.plot(dataOne,priceOne, 'g',lw = 8)




              #模型预测
#plt.show()
#A:输入层     B:隐藏层        C:输出层
#A(15*1) * w1(1*10) + b1(1*10) = B(15*10) 隐藏层
#B(15*10) * w2(10*1) + b2(15*1) = C(15*1) 输出层

dataNormal = np.zeros([15,1])  #15行1列    天数
priceNormal = np.zeros([15,1]) #           营收

#天数与盈收归一化处理
for i in range(0,15):
    dataNormal[i,0] = i/14.0
    priceNormal[i,0] = endPrice[i] / 3000.0

#输入层A
#n行1列
x = tf.placeholder(tf.float32,[None,1])
y = tf.placeholder(tf.float32,[None,1])

#隐藏层B
w1 = tf.Variable(tf.random_uniform([1,10],0,1)) #权值  随机生成1行10列，范围在[0,1]
b1 = tf.Variable(tf.zeros([1,10]))      #偏移量 1行10列
wb1 = tf.matmul(x,w1)+b1
layer1 = tf.nn.relu(wb1) #激励函数
'''
激励函数
如果wb1的值大于0值不变，如果wb1小于0值变为0
'''
#输出层C
w2 = tf.Variable(tf.random_uniform([10,1],0,1)) #权值  随机生成10行1列，范围在[0,1]
b2 = tf.Variable(tf.zeros([15,1]))      #偏移量 15行1列
wb2 = tf.matmul(layer1,w2)+b2
layer2 = tf.nn.relu(wb2) #激励函数

#求平均值
loss = tf.reduce_mean(tf.square(y - layer2))
#梯度下降  每次下降0.1
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)


with tf.Session() as sess:
    sess.run(tf.global_variables_initializer()) #初始化变量

    #训练10000次
    for i in range(0,10000):
        sess.run(train_step,feed_dict = {x:dataNormal, y:priceNormal})

    #获得准确w1 w2 b1 b2
    #获得预测的价格
    pred = sess.run(layer2,feed_dict = {x:dataNormal})
    predPrice = np.zeros([15,1])
    for i in range(0,15):
        predPrice[i,0] = (pred * 3000)[i,0]
    plt.plot(data,predPrice,'b',lw = 1)
plt.show()`在这里插入代码片`