【Pytorch深度学习实战】（13）时序预测

 🔎大家好，我是Sonhhxg_柒，希望你看完之后，能对你有所帮助，不足请指正！共同学习交流🔎

📝个人主页－Sonhhxg_柒的博客_CSDN博客 📃

🎁欢迎各位→点赞👍 + 收藏⭐️ + 留言📝​

📣系列专栏 - 机器学习【ML】 自然语言处理【NLP】  深度学习【DL】

​

 🖍foreword

✔说明⇢本人讲解主要包括Python、机器学习（ML）、深度学习（DL）、自然语言处理（NLP）等内容。

如果你对这个系列感兴趣的话，可以关注订阅哟👋

时序预测

这是初学者开始的玩具示例。它有助于学习 PyTorch 和时间序列预测。本例中使用了两个 LSTMCell 单元来学习一些从不同相位开始的正弦波信号。在学习了正弦波之后，网络尝试预测未来的信号值。结果如下图所示。

结果

初始信号和预测结果显示在图像中。我们首先给出一些初始信号（实线）。该网络随后将给出一些预测结果（虚线）。可以得出结论，网络可以产生新的正弦波。 

时序预测Pytorch的实现 

generate_sine_ware.py 

import numpy as np
import torch

np.random.seed(2)

T = 20
L = 1000
N = 100

x = np.empty((N, L), 'int64')
x[:] = np.array(range(L)) + np.random.randint(-4 * T, 4 * T, N).reshape(N, 1)
data = np.sin(x / 1.0 / T).astype('float64')
torch.save(data, open('traindata.pt', 'wb'))

 train.py

from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.optim as optim
import numpy as np
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt

class Sequence(nn.Module):
    def __init__(self):
        super(Sequence, self).__init__()
        self.lstm1 = nn.LSTMCell(1, 51)
        self.lstm2 = nn.LSTMCell(51, 51)
        self.linear = nn.Linear(51, 1)

    def forward(self, input, future = 0):
        outputs = []
        h_t = torch.zeros(input.size(0), 51, dtype=torch.double)
        c_t = torch.zeros(input.size(0), 51, dtype=torch.double)
        h_t2 = torch.zeros(input.size(0), 51, dtype=torch.double)
        c_t2 = torch.zeros(input.size(0), 51, dtype=torch.double)

        for input_t in input.split(1, dim=1):
            h_t, c_t = self.lstm1(input_t, (h_t, c_t))
            h_t2, c_t2 = self.lstm2(h_t, (h_t2, c_t2))
            output = self.linear(h_t2)
            outputs += [output]
        for i in range(future):# if we should predict the future
            h_t, c_t = self.lstm1(output, (h_t, c_t))
            h_t2, c_t2 = self.lstm2(h_t, (h_t2, c_t2))
            output = self.linear(h_t2)
            outputs += [output]
        outputs = torch.cat(outputs, dim=1)
        return outputs


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--steps', type=int, default=15, help='steps to run')
    opt = parser.parse_args()
    # 将随机种子设置为 0
    np.random.seed(0)
    torch.manual_seed(0)
    # 加载数据并制作训练集
    data = torch.load('traindata.pt')
    input = torch.from_numpy(data[3:, :-1])
    target = torch.from_numpy(data[3:, 1:])
    test_input = torch.from_numpy(data[:3, :-1])
    test_target = torch.from_numpy(data[:3, 1:])
    # 建立模型
    seq = Sequence()
    seq.double()
    criterion = nn.MSELoss()
    # 使用 LBFGS 作为优化器，因为我们可以加载整个数据进行训练
    optimizer = optim.LBFGS(seq.parameters(), lr=0.8)
    # 开始训练
    for i in range(opt.steps):
        print('STEP: ', i)
        def closure():
            optimizer.zero_grad()
            out = seq(input)
            loss = criterion(out, target)
            print('loss:', loss.item())
            loss.backward()
            return loss
        optimizer.step(closure)
        # 开始预测，这里不需要跟踪梯度
        with torch.no_grad():
            future = 1000
            pred = seq(test_input, future=future)
            loss = criterion(pred[:, :-future], test_target)
            print('test loss:', loss.item())
            y = pred.detach().numpy()
        # 绘制结果
        plt.figure(figsize=(30,10))
        plt.title('Predict future values for time sequences\n(Dashlines are predicted values)', fontsize=30)
        plt.xlabel('x', fontsize=20)
        plt.ylabel('y', fontsize=20)
        plt.xticks(fontsize=20)
        plt.yticks(fontsize=20)
        def draw(yi, color):
            plt.plot(np.arange(input.size(1)), yi[:input.size(1)], color, linewidth = 2.0)
            plt.plot(np.arange(input.size(1), input.size(1) + future), yi[input.size(1):], color + ':', linewidth = 2.0)
        draw(y[0], 'r')
        draw(y[1], 'g')
        draw(y[2], 'b')
        plt.savefig('predict%d.pdf'%i)
        plt.close()