时间序列
预测方式有自回归模型（与过去所有时间有关）、马尔可夫模型（只与x个过去数据有关）、潜变量模型（h+x->新的h，再循环）。
多层感知机实现马尔可夫模型：
%matplotlib inline
import torch
from torch import nn
from d2l import torch as d2l
T = 1000 # 总共产生1000个点
time = torch.arange(1, T + 1, dtype=torch.float32)
x = torch.sin(0.01 * time) + torch.normal(0, 0.2, (T,))
d2l.plot(time, [x], 'time', 'x', xlim=[1, 1000], figsize=(6, 3))
tau = 4
features = torch.zeros((T - tau, tau))
for i in range(tau):
features[:, i] = x[i: T - tau + i]
labels = x[tau:].reshape((-1, 1))
batch_size, n_train = 16, 600
# 只有前n_train个样本用于训练
train_iter = d2l.load_array((features[:n_train], labels[:n_train]),
batch_size, is_train=True)
# 初始化网络权重的函数
def init_weights(m):
if type(m) == nn.Linear:
nn.init.xavier_uniform_(m.weight)
# 一个简单的多层感知机
def get_net():
net = nn.Sequential(nn.Linear(4, 10),
nn.ReLU(),
nn.Linear(10, 1))
net.apply(init_weights)
return net
# 平方损失。注意：MSELoss计算平方误差时不带系数1/2
loss = nn.MSELoss(reduction='none')
def train(net, train_iter, loss, epochs, lr):
trainer = torch.optim.Adam(net.parameters(), lr)
for epoch in range(epochs):
for X, y in train_iter:
trainer.zero_grad()
l = loss(net(X), y)
l.sum().backward()
trainer.step()
print(f'epoch {epoch + 1}, '
f'loss: {d2l.evaluate_loss(net, train_iter, loss):f}')
net = get_net()
train(net, train_iter, loss, 5, 0.01)
max_steps = 64
features = torch.zeros((T - tau - max_steps + 1, tau + max_steps))
# 列i（i=tau）是来自（i-tau+1）步的预测，其时间步从（i+1）到（i+T-tau-max_steps+1）
for i in range(tau, tau + max_steps):
features[:, i] = net(features[:, i - tau:i]).reshape(-1)
steps = (1, 4, 16, 64)
d2l.plot([time[tau + i - 1: T - max_steps + i] for i in steps],
[features[:, (tau + i - 1)].detach().numpy() for i in steps], 'time', 'x',
legend=[f'{i}-step preds' for i in steps], xlim=[5, 1000],
figsize=(6, 3))
单步预测：例如用已知的x1、x2、x3、x4来预测x5，再用已知的x2、x3、x4、x5来预测x6，由此由已知的x1到x996得到预测的x5到x1000。
多步预测：例如步长为4，用已知的x1、x2、x3、x4来预测x5，再用已知的x2、x3、x4和预测的x5来预测x6。（这里还有一些疑问，看看后面能否解决。）“虽然4步预测看起来仍然不错，但超过这个跨度的任何预测几乎都是无用的。”
import collections
import re
from d2l import torch as d2l
d2l.DATA_HUB['time_machine'] = (d2l.DATA_URL + 'timemachine.txt',
'090b5e7e70c295757f55df93cb0a180b9691891a')
def read_time_machine():
"""将时间机器数据集加载到文本行的列表中"""
with open(d2l.download('time_machine'), 'r') as f:
lines = f.readlines()
return [re.sub('[^A-Za-z]+', ' ', line).strip().lower() for line in lines]
lines = read_time_machine()
def tokenize(lines, token='word'):
"""将文本行拆分为单词或字符词元"""
if token == 'word':
return [line.split() for line in lines]
elif token == 'char':
return [list(line) for line in lines]
else:
print('错误：未知词元类型：' + token)
tokens = tokenize(lines)
class Vocab:
"""文本词表"""
def __init__(self, tokens=None, min_freq=0, reserved_tokens=None):
if tokens is None:
tokens = []
if reserved_tokens is None:
reserved_tokens = []
# 按出现频率排序
counter = count_corpus(tokens)
self._token_freqs = sorted(counter.items(), key=lambda x: x[1],
reverse=True)
# 未知词元的索引为0
self.idx_to_token = [''] + reserved_tokens
self.token_to_idx = {token: idx
for idx, token in enumerate(self.idx_to_token)}
for token, freq in self._token_freqs:
if freq < min_freq:
break
if token not in self.token_to_idx:
self.idx_to_token.append(token)
self.token_to_idx[token] = len(self.idx_to_token) - 1
def __len__(self):
return len(self.idx_to_token)
def __getitem__(self, tokens):
if not isinstance(tokens, (list, tuple)):
return self.token_to_idx.get(tokens, self.unk)
return [self.__getitem__(token) for token in tokens]
def to_tokens(self, indices):
if not isinstance(indices, (list, tuple)):
return self.idx_to_token[indices]
return [self.idx_to_token[index] for index in indices]
@property
def unk(self): # 未知词元的索引为0
return 0
@property
def token_freqs(self):
return self._token_freqs
def count_corpus(tokens):
"""统计词元的频率"""
# 这里的tokens是1D列表或2D列表
if len(tokens) == 0 or isinstance(tokens[0], list):
# 将词元列表展平成一个列表
tokens = [token for line in tokens for token in line]
return collections.Counter(tokens)
vocab = Vocab(tokens)
# for i in [0, 10]:
# print('文本:', tokens[i])
# print('索引:', vocab[tokens[i]])
def load_corpus_time_machine(max_tokens=-1):
"""返回时光机器数据集的词元索引列表和词表"""
lines = read_time_machine()
tokens = tokenize(lines, 'char')
vocab = Vocab(tokens)
# 因为时光机器数据集中的每个文本行不一定是一个句子或一个段落，
# 所以将所有文本行展平到一个列表中
corpus = [vocab[token] for line in tokens for token in line]
if max_tokens > 0:
corpus = corpus[:max_tokens]
return corpus, vocab
corpus, vocab = load_corpus_time_machine()
len(corpus), len(vocab)
print(corpus)
