[人工智能]使用RNN预测各个国家的人均GDP

参照肖智清老师的《神经网络与PyTorch实战》

import torch.nn
import torch
from pandas_datareader import wb
import torch.optim
import pandas as pd


countries = ['BR', 'CN', 'FR', 'DE', 'IN', 'JP', 'SA', 'GB', 'US']
dat = wb.download(indicator='NY.GDP.PCAP.KD', country=countries, start=1970, end=2016)
df = dat.unstack().T
df.index = df.index.droplevel(0)


class Net(torch.nn.Module):
    def __init__(self, input_size, hidden_size):
        super(Net, self).__init__()
        self.rnn = torch.nn.LSTM(input_size=input_size, hidden_size=hidden_size)
        self.fc = torch.nn.Linear(hidden_size, 1)

    def forward(self, x):
        x = x[:, :, None]
        x, _ = self.rnn(x)
        x = self.fc(x)
        x = x[:, :, 0]
        return x

net = Net(input_size=1, hidden_size=5)


df_scaled = df / df.std()
years = df.index
train_seq_len = sum((years >= '1971') & (years <= '2000'))
test_seq_len = sum(years > '2000')
print(f'Train length: {train_seq_len}, Test length: {test_seq_len}.')
inputs = torch.tensor(df_scaled.iloc[:-1].values, dtype=torch.float32)
labels = torch.tensor(df_scaled.iloc[1:].values, dtype=torch.float32)


criterion = torch.nn.MSELoss()
optimizer = torch.optim.Adam(net.parameters())
for step in range(10001):
    if step:
        optimizer.zero_grad()
        train_loss.backward()
        optimizer.step()

    preds = net(inputs)
    train_preds = preds[:train_seq_len]
    train_labels = labels[:train_seq_len]
    train_loss = criterion(train_preds, train_labels)

    test_preds = preds[-test_seq_len]
    test_labels = labels[-test_seq_len]
    test_loss = criterion(test_preds, test_labels)

    if step % 500 == 0:
        print(f'Step: {step}, Test loss: {test_loss:.001%}, Train loss: {train_loss:.001%}')

#
# df_lately_scaled = df / df.std()
# inputs_lately = torch.tensor(df_scaled.iloc[:-1].values, dtype=torch.float32)
# labels_lately = torch.tensor(df_scaled.iloc[1:].values, dtype=torch.float32)
# preds_lately = net(inputs_lately)
# Final_loss = criterion(preds_lately, labels_lately)
# print(f'The final loss is: {Final_loss}')

1. 原文中有两个国家（加拿大和以色列），数据有空缺，运行时，loss函数会一直出现nan
   为了避免这种情况，把这两个国家删掉
2. 这段程序的input是(46, 11)，46应该对应的是batch_size，但作者没有进行修正，直接导入了net，这导致，rnn中的第一项seq_len对应成了46， 第二项batch_size对应11，与输入的含义不符，相当于进行了一次batch_first = True，这样做不影响结果，只是含义不符。有点别扭。可以在37,38行插入下面两句话：

inputs = inputs.T
labels = labels.T

48， 49行修改为：

    train_preds = preds[:, :train_seq_len]
    train_labels = labels[:, :train_seq_len]

52，53行修改为：

    test_preds = preds[:, :-test_seq_len]
    test_labels = labels[:, :-test_seq_len]