LSTM 预测时间序列（Pytorch）

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/baidu_36669549/article/details/85595807

得到的数据是10年的飞机月流量，大致的变化趋势是这样的

简单的将前几年的数据作为训练集后几年的数据作为测试集

将数据归一化到0~1之间，70%作为训练集，其余作为测试集

训练过程

import numpy as np 
import pandas as pd 
import matplotlib.pyplot as plt 
import torch 
from torch import nn
from torch.autograd import Variable



data_csv = pd.read_csv('F:/tracker_programe/lstm_test/data.csv',usecols=[1])

# plt.plot(data_csv)
# plt.show()
#数据预处理
data_csv = data_csv.dropna() #去掉na数据
dataset = data_csv.values
dataset = dataset.astype('float32')
max_value = np.max(dataset)
min_value = np.min(dataset)
scalar = max_value-min_value
dataset = list(map(lambda x: x/scalar, dataset)) #将数据标准化到0~1之间

def create_dataset(dataset,look_back=2):
    dataX, dataY=[], []
    for i in range(len(dataset)-look_back):
        a=dataset[i:(i+look_back)]
        dataX.append(a)
        dataY.append(dataset[i+look_back])
    return np.array(dataX), np.array(dataY)

data_X, data_Y = create_dataset(dataset)

#划分训练集和测试集，70%作为训练集
train_size = int(len(data_X) * 0.7)
test_size = len(data_X)-train_size

train_X = data_X[:train_size]
train_Y = data_Y[:train_size]

test_X = data_X[train_size:]
test_Y = data_Y[train_size:]

train_X = train_X.reshape(-1,1,2)
train_Y = train_Y.reshape(-1,1,1)

test_X = test_X.reshape(-1,1,2)


train_x = torch.from_numpy(train_X)
train_y = torch.from_numpy(train_Y)
test_x = torch.from_numpy(test_X)

class lstm_reg(nn.Module):
    def __init__(self,input_size,hidden_size, output_size=1,num_layers=2):
        super(lstm_reg,self).__init__()

        self.rnn = nn.LSTM(input_size,hidden_size,num_layers)
        self.reg = nn.Linear(hidden_size,output_size)

    def forward(self,x):
        x, _ = self.rnn(x)
        s,b,h = x.shape
        x = x.view(s*b, h)
        x = self.reg(x)
        x = x.view(s,b,-1)
        return x


net = lstm_reg(2,4)

criterion = nn.MSELoss()
optimizer = torch.optim.Adam(net.parameters(),lr=1e-2)

for e in range(10000):
    var_x = Variable(train_x)
    var_y = Variable(train_y)

    out = net(var_x)
    loss = criterion(out, var_y)

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    if (e+1)%100 == 0:
        print('Epoch: {}, Loss:{:.5f}'.format(e+1, loss.data[0]))
        
torch.save(net.state_dict(), 'net_params.pkl')

测试过程

import numpy as np 
import pandas as pd 
import matplotlib.pyplot as plt 
import torch 
from torch import nn
from torch.autograd import Variable



data_csv = pd.read_csv('F:/tracker_programe/lstm_test/data.csv',usecols=[1])

# plt.plot(data_csv)
# plt.show()
#数据预处理
data_csv = data_csv.dropna() #去掉na数据
dataset = data_csv.values
dataset = dataset.astype('float32')
max_value = np.max(dataset)
min_value = np.min(dataset)
scalar = max_value-min_value
dataset = list(map(lambda x: x/scalar, dataset)) #将数据标准化到0~1之间

def create_dataset(dataset,look_back=2):
    dataX, dataY=[], []
    for i in range(len(dataset)-look_back):
        a=dataset[i:(i+look_back)]
        dataX.append(a)
        dataY.append(dataset[i+look_back])
    return np.array(dataX), np.array(dataY)

data_X, data_Y = create_dataset(dataset)

#划分训练集和测试集，70%作为训练集
train_size = int(len(data_X) * 0.7)
test_size = len(data_X)-train_size

train_X = data_X[:train_size]
train_Y = data_Y[:train_size]

test_X = data_X[train_size:]
test_Y = data_Y[train_size:]

train_X = train_X.reshape(-1,1,2)
train_Y = train_Y.reshape(-1,1,1)

test_X = test_X.reshape(-1,1,2)


train_x = torch.from_numpy(train_X)
train_y = torch.from_numpy(train_Y)
test_x = torch.from_numpy(test_X)

class lstm_reg(nn.Module):
    def __init__(self,input_size,hidden_size, output_size=1,num_layers=2):
        super(lstm_reg,self).__init__()

        self.rnn = nn.LSTM(input_size,hidden_size,num_layers)
        self.reg = nn.Linear(hidden_size,output_size)

    def forward(self,x):
        x, _ = self.rnn(x)
        s,b,h = x.shape
        x = x.view(s*b, h)
        x = self.reg(x)
        x = x.view(s,b,-1)
        return x


net = lstm_reg(2,4)

net.load_state_dict(torch.load('net_params.pkl')) 

data_X = data_X.reshape(-1, 1, 2)
data_X = torch.from_numpy(data_X)
var_data = Variable(data_X)
pred_test = net(var_data) # 测试集的预测结果
pred_test = pred_test.view(-1).data.numpy()

plt.plot(pred_test, 'r', label='prediction')
plt.plot(dataset, 'b', label='real')
plt.legend(loc='best')
plt.show()

参考：

链接