问题遇到的现象和发生背景
在程序中我已经实现了单因子输入进行预测，想进一步输入多因子以提高预测准确性
问题相关代码，请勿粘贴截图
#———————————————————定义神经网络变量—————————————————————
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import tensorflow as tf
import os
os.chdir(r'C:/dissertation')
#数据标准化
from sklearn import preprocessing
#配置matplotlib画图的符号
plt.rcParams['font.sans-serif'] = ['SimHei'] #显示中文
plt.rcParams['axes.unicode_minus']=False #用来正常显示坐标中的负号
def read_data(code):
try:
data = pd.read_csv('C:/dissertation/data/bar/' + code + '_bardata.csv')
data = np.array(data.iloc[10:,2:])#还没对数据进行清洗，所以手动去除了有空值的部分
print(code,'股票数据读取完成！')
return data
except Exception:
print(code,'股票数据读取失败！')
data = read_data('000001.SZ')
normalize_data = preprocessing.scale(data)#对每列分别进行数据标准化
#———————————————————形成训练集—————————————————————
#设置rnn网络的常量
time_step=20 #时间步 ，rnn每迭代20次，就向前推进一步
rnn_unit=10 # hidden layer units
batch_size=60 # 每一批训练多少个样例
input_size=1 # 输入层数维度
output_size=1 # 输出层数维度
lr=0.0006 # 学习率
train_x,train_y=[],[] #训练集
for i in range(len(normalize_data)-time_step-1):
x=normalize_data[i:i+time_step]
y=normalize_data[i+1:i+time_step+1]
y=y[:,4]
train_x.append(x.tolist())
train_y.append(y.tolist())
X=tf.placeholder(tf.float32, [None,time_step,input_size]) #每批次输入网络的tensor
Y=tf.placeholder(tf.float32, [None,time_step,output_size]) # 每批次tensor对应的标签
#输入层、输出层的权重和偏置
weights={
'in':tf.Variable(tf.random_normal([input_size,rnn_unit])),
'out':tf.Variable(tf.random_normal([rnn_unit,1]))
}
biases={
'in':tf.Variable(tf.constant(0.1,shape=[rnn_unit,])),
'out':tf.Variable(tf.constant(0.1,shape=[1,]))
}
#———————————————————定义lstm网络—————————————————————
def lstm(batch): #参数：输入网络批次数
pred = 0
for factor_number in range(len(x[0])):
w_in=weights['in']
b_in=biases['in']
########################问题句########################################################
input=tf.reshape(list(map(lambda x:[[y] for y in x.tolist()],np.array(X)[:,:,factor_number])),[-1,input_size])
#此处X由后面的语句传入train_x，train_x为三层嵌套的list，经过X传入变为tensor，所以提示numpy不能处理
#######################################################################################
input_rnn=tf.matmul(input,w_in)+b_in
input_rnn=tf.reshape(input_rnn,[-1,time_step,rnn_unit])
cell=tf.nn.rnn_cell.BasicLSTMCell(rnn_unit)
init_state=cell.zero_state(batch,dtype=tf.float32)
output_rnn,final_states=tf.nn.dynamic_rnn(cell, input_rnn,initial_state=init_state, dtype=tf.float32)
output=tf.reshape(output_rnn,[-1,rnn_unit])
w_out=weights['out']
b_out=biases['out']
pred+=tf.matmul(output,w_out)+b_out
pred = pred / len(x[0])
return pred,final_states
#———————————————————对模型进行训练—————————————————————
def train_lstm():
global batch_size
with tf.variable_scope("sec_lstm"):
pred,_=lstm(batch_size)
#定义损失函数
loss=tf.reduce_mean(tf.square(tf.reshape(pred,[-1])-tf.reshape(Y, [-1])))
train_op=tf.train.AdamOptimizer(lr).minimize(loss)
saver=tf.train.Saver(tf.global_variables())
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(100): #We can increase the number of iterations to gain better result.
step=0
start=0
end=start+batch_size
while(end<len(train_x)):
################################此处将train_x传入###########################################
_,loss_=sess.run([train_op,loss],feed_dict={X:train_x[start:end],Y:train_y[start:end]})
start+=batch_size
end=start+batch_size
#每训练10次保存一次参数
if step%10==0:
print("Number of iterations:",i," loss:",loss_) #输出训练次数，输出损失值
print("model_save",saver.save(sess,'C:/dissertation/model_save1/modle.ckpt'))
step+=1
print("The train has finished")
train_lstm()
由于我是初学者，所以我尝试在单因子能成功运行的基础上分别将不同因子输入，预测值求平均，希望程序可以运行。如果可以直接输入多因子那就更棒了，感谢！
