文本预处理
读入文本
import collections
import re
def read_time_machine():
with open('/home/kesci/input/timemachine7163/timemachine.txt', 'r') as f:
# strip():移除字符串头尾的空字符
# 将非小写英文字符构成的非空字符串用空格
lines = [re.sub('[^a-z]+', ' ', line.strip().lower()) for line in f]
# 返回的lines是文件的每一行处理后得到的列表
return lines
lines = read_time_machine()
print('# sentences %d' % len(lines))
分词
我们对每个句子进行分词，也就是将一个句子划分成若干个词（token），转换为一个词的序列。
def tokenize(sentences, token='word'):
"""Split sentences into word or char tokens"""
if token == 'word': # 单词级别的分词
# str.split(' '): 字符串以' '空格字符为分隔符构成list
return [sentence.split(' ') for sentence in sentences]
elif token == 'char': # 字符级别的分词
# list(str): 将字符串以每个字符为分隔符构成list
return [list(sentence) for sentence in sentences]
else:
print('ERROR: unkown token type '+token)
tokens = tokenize(lines)
tokens[0:2]
建立字典
class Vocab(object):
def __init__(self, tokens, min_freq=0, use_special_tokens=False):
"""
tokens: 整个预料库上所有的词
min_freq: 词出现最小的次数
"""
# 统计词频
counter = count_corpus(tokens) # <key, value>: <词， 词频>
self.token_freqs = list(counter.items())
# 记录字典所需维护的token
self.idx_to_token = []
if use_special_tokens:
# padding, begin of sentence, end of sentence, unknown
self.pad, self.bos, self.eos, self.unk = (0, 1, 2, 3)
self.idx_to_token += ['', '', '', '']
else:
self.unk = 0
self.idx_to_token += ['']
self.idx_to_token += [token for token, freq in self.token_freqs
if freq >= min_freq and token not in self.idx_to_token]
self.token_to_idx = dict()
for idx, token in enumerate(self.idx_to_token):
self.token_to_idx[token] = idx
# 字典的长度
def __len__(self):
return len(self.idx_to_token)
# 词到索引的映射
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]
# 统计词频
def count_corpus(sentences):
tokens = [tk for st in sentences for tk in st]
return collections.Counter(tokens) # 返回一个字典，记录每个词的出现次数
将词转化为索引
for i in range(8, 10):
print('words:', tokens[i])
print('indices:', vocab[tokens[i]])
语言模型
读取数据集
with open('/home/kesci/input/jaychou_lyrics4703/jaychou_lyrics.txt') as f:
corpus_chars = f.read()
print(len(corpus_chars))
print(corpus_chars[: 40])
corpus_chars = corpus_chars.replace('\n', ' ').replace('\r', ' ')
corpus_chars = corpus_chars[: 10000]
建立字符索引
idx_to_char = list(set(corpus_chars)) # 去重，得到索引到字符的映射
char_to_idx = {char: i for i, char in enumerate(idx_to_char)} # 字符到索引的映射
vocab_size = len(char_to_idx)
print(vocab_size)
corpus_indices = [char_to_idx[char] for char in corpus_chars] # 将每个字符转化为索引，得到一个索引的序列
sample = corpus_indices[: 20]
print('chars:', ''.join([idx_to_char[idx] for idx in sample]))
print('indices:', sample)
def load_data_jay_lyrics():
with open('/home/kesci/input/jaychou_lyrics4703/jaychou_lyrics.txt') as f:
corpus_chars = f.read()
corpus_chars = corpus_chars.replace('\n', ' ').replace('\r', ' ')
corpus_chars = corpus_chars[0:10000]
idx_to_char = list(set(corpus_chars))
char_to_idx = dict([(char, i) for i, char in enumerate(idx_to_char)])
vocab_size = len(char_to_idx)
corpus_indices = [char_to_idx[char] for char in corpus_chars]
return corpus_indices, char_to_idx, idx_to_char, vocab_size
时序数据的采样
随机采样
每次从数据里随机采样一个小批量。其中批量大小batch_size是每个小批量的样本数，num_steps是每个样本所包含的时间步数。 在随机采样中，每个样本是原始序列上任意截取的一段序列，相邻的两个随机小批量在原始序列上的位置不一定相毗邻。
import torch
import random
def data_iter_random(corpus_indices, batch_size, num_steps, device=None):
# 减1是因为对于长度为n的序列，X最多只有包含其中的前n - 1个字符
num_examples = (len(corpus_indices) - 1) // num_steps # 下取整，得到不重叠情况下的样本个数
example_indices = [i * num_steps for i in range(num_examples)] # 每个样本的第一个字符在corpus_indices中的下标
random.shuffle(example_indices)
def _data(i):
# 返回从i开始的长为num_steps的序列
return corpus_indices[i: i + num_steps]
if device is None:
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
for i in range(0, num_examples, batch_size):
# 每次选出batch_size个随机样本
batch_indices = example_indices[i: i + batch_size] # 当前batch的各个样本的首字符的下标
X = [_data(j) for j in batch_indices]
Y = [_data(j + 1) for j in batch_indices]
yield torch.tensor(X, device=device), torch.tensor(Y, device=device)
相邻采样
在相邻采样中，相邻的两个随机小批量在原始序列上的位置相毗邻。
def data_iter_consecutive(corpus_indices, batch_size, num_steps, device=None):
if device is None:
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
corpus_len = len(corpus_indices) // batch_size * batch_size # 保留下来的序列的长度
corpus_indices = corpus_indices[: corpus_len] # 仅保留前corpus_len个字符
indices = torch.tensor(corpus_indices, device=device)
indices = indices.view(batch_size, -1) # resize成(batch_size, )
batch_num = (indices.shape[1] - 1) // num_steps
for i in range(batch_num):
i = i * num_steps
X = indices[:, i: i + num_steps]
Y = indices[:, i + 1: i + num_steps + 1]
yield X, Y
RNN
H
t
H_t
Ht的计算的基于当前的输入
X
t
X_t
Xt和前一时刻的状态
H
t
−
1
H_{t-1}
Ht−1,
H
t
H_t
Ht记录了当前字符为止的序列信息， 利用
H
t
H_t
Ht对序列的下一个字符进行预测。
H
t
=
ϕ
(
X
t
W
x
h
+
H
t
−
1
W
h
h
+
b
h
)
O
t
=
H
t
W
h
q
+
b
q
H_t = \phi(X_tW_{xh}+H_{t-1}W_{hh}+b_h)\\ O_t = H_tW_{hq} + b_q
Ht=ϕ(XtWxh+Ht−1Whh+bh)Ot=HtWhq+bq
从零实现RNN
import torch
import torch.nn as nn
import time
import math
import sys
sys.path.append("/home/kesci/input")
import d2l_jay9460 as d2l
(corpus_indices, char_to_idx, idx_to_char, vocab_size) = d2l.load_data_jay_lyrics()
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
one-hot 向量
假设词典大小是N，每次字符对应一个从0到N-1的唯一的索引，则该字符的向量是一个长度为N的向量，若字符的索引是i，则该向量的第i个位置为1，其他位置为0。
def one_hot(x, n_class, dtype=torch.float32):
# n_class:字典的大小
result = torch.zeros(x.shape[0], n_class, dtype=dtype, device=x.device) # shape: (n, n_class)
result.scatter_(1, x.long().view(-1, 1), 1) # result[i, x[i, 0]] = 1
return result
x = torch.tensor([0, 2])
x_one_hot = one_hot(x, vocab_size)
print(x_one_hot)
print(x_one_hot.shape)
print(x_one_hot.sum(axis=1))
我们每次采样的小批量的形状是（批量大小, 时间步数）。下面的函数将这样的小批量变换成数个形状为（批量大小, 词典大小）的矩阵，矩阵个数等于时间步数。
def to_onehot(X, n_class):
return [one_hot(X[:, i], n_class) for i in range(X.shape[1])]
X = torch.arange(10).view(2, 5)
inputs = to_onehot(X, vocab_size)
print(len(inputs), inputs[0].shape)
初始化模型参数
num_inputs, num_hiddens, num_outputs = vocab_size, 256, vocab_size
# num_inputs: d
# num_hiddens: h, 隐藏单元的个数是超参数
# num_outputs: q
def get_params():
def _one(shape):
param = torch.zeros(shape, device=device, dtype=torch.float32)
nn.init.normal_(param, 0, 0.01)
return torch.nn.Parameter(param)
# 隐藏层参数
W_xh = _one((num_inputs, num_hiddens))
W_hh = _one((num_hiddens, num_hiddens))
b_h = torch.nn.Parameter(torch.zeros(num_hiddens, device=device))
# 输出层参数
W_hq = _one((num_hiddens, num_outputs))
b_q = torch.nn.Parameter(torch.zeros(num_outputs, device=device))
return (W_xh, W_hh, b_h, W_hq, b_q)
定义模型
def rnn(inputs, state, params):
# inputs和outputs皆为num_steps个形状为(batch_size, vocab_size)的矩阵
W_xh, W_hh, b_h, W_hq, b_q = params
H, = state
outputs = []
for X in inputs:
H = torch.tanh(torch.matmul(X, W_xh) + torch.matmul(H, W_hh) + b_h)
Y = torch.matmul(H, W_hq) + b_q
outputs.append(Y)
return outputs, (H,)
函数init_rnn_state是初始化隐藏变量， 返回值是一个元组
def init_rnn_state(batch_size, num_hiddens, device):
return (torch.zeros((batch_size, num_hiddens), device=device), )
裁剪梯度
循环神经网络容易出现梯度衰减或梯度爆炸， 应该权重参数对时间序列会产生长期依赖。针对梯度爆炸，使用裁剪梯度， 将模型参数的梯度拼接成一个向量
g
g
g, 并设裁剪的阈值为
θ
\theta
θ.
m
i
n
(
θ
∥
g
∥
，
1
)
g
min(\frac\theta{\left\|g\right\|}，1)g
min(∥g∥θ，1)g
def grad_clipping(params, theta, device):
norm = torch.tensor([0.0], device=device)
for param in params:
norm += (param.grad.data ** 2).sum()
norm = norm.sqrt().item()
if norm > theta:
for param in params:
param.grad.data *= (theta / norm)
预测函数
def predict_rnn(prefix, num_chars, rnn, params, init_rnn_state,
num_hiddens, vocab_size, device, idx_to_char, char_to_idx):
state = init_rnn_state(1, num_hiddens, device)
output = [char_to_idx[prefix[0]]] # output记录prefix加上预测的num_chars个字符
for t in range(num_chars + len(prefix) - 1):
# 将上一时间步的输出作为当前时间步的输入
X = to_onehot(torch.tensor([[output[-1]]], device=device), vocab_size)
# 计算输出和更新隐藏状态
(Y, state) = rnn(X, state, params)
# 下一个时间步的输入是prefix里的字符或者当前的最佳预测字符
if t < len(prefix) - 1:
output.append(char_to_idx[prefix[t + 1]])
else:
output.append(Y[0].argmax(dim=1).item())
return ''.join([idx_to_char[i] for i in output])
困惑度
我们通常使用困惑度（perplexity）来评价语言模型的好坏。困惑度是对交叉熵损失函数做指数运算后得到的值。
- 最佳情况下，模型总是把标签类别的概率预测为1，此时困惑度为1；
- 最坏情况下，模型总是把标签类别的概率预测为0，此时困惑度为正无穷；
- 基线情况下，模型总是预测所有类别的概率都相同，此时困惑度为类别个数。
定义模型训练函数
- 使用困惑度评价模型。
- 在迭代模型参数前裁剪梯度。
- 对时序数据采用不同采样方法将导致隐藏状态初始化的不同
def train_and_predict_rnn(rnn, get_params, init_rnn_state, num_hiddens,
vocab_size, device, corpus_indices, idx_to_char,
char_to_idx, is_random_iter, num_epochs, num_steps,
lr, clipping_theta, batch_size, pred_period,
pred_len, prefixes):
if is_random_iter:
data_iter_fn = d2l.data_iter_random
else:
data_iter_fn = d2l.data_iter_consecutive
params = get_params()
loss = nn.CrossEntropyLoss()
for epoch in range(num_epochs):
if not is_random_iter: # 如使用相邻采样，在epoch开始时初始化隐藏状态
state = init_rnn_state(batch_size, num_hiddens, device)
l_sum, n, start = 0.0, 0, time.time()
data_iter = data_iter_fn(corpus_indices, batch_size, num_steps, device)
for X, Y in data_iter:
if is_random_iter: # 如使用随机采样，在每个小批量更新前初始化隐藏状态
state = init_rnn_state(batch_size, num_hiddens, device)
else: # 否则需要使用detach函数从计算图分离隐藏状态
for s in state:
s.detach_()
# inputs是num_steps个形状为(batch_size, vocab_size)的矩阵
inputs = to_onehot(X, vocab_size)
# outputs有num_steps个形状为(batch_size, vocab_size)的矩阵
(outputs, state) = rnn(inputs, state, params)
# 拼接之后形状为(num_steps * batch_size, vocab_size)
outputs = torch.cat(outputs, dim=0)
# Y的形状是(batch_size, num_steps)，转置后再变成形状为
# (num_steps * batch_size,)的向量，这样跟输出的行一一对应
y = torch.flatten(Y.T)
# 使用交叉熵损失计算平均分类误差
l = loss(outputs, y.long())
# 梯度清0
if params[0].grad is not None:
for param in params:
param.grad.data.zero_()
l.backward()
grad_clipping(params, clipping_theta, device) # 裁剪梯度
d2l.sgd(params, lr, 1) # 因为误差已经取过均值，梯度不用再做平均
l_sum += l.item() * y.shape[0]
n += y.shape[0]
if (epoch + 1) % pred_period == 0:
print('epoch %d, perplexity %f, time %.2f sec' % (
epoch + 1, math.exp(l_sum / n), time.time() - start))
for prefix in prefixes:
print(' -', predict_rnn(prefix, pred_len, rnn, params, init_rnn_state,
num_hiddens, vocab_size, device, idx_to_char, char_to_idx))
num_epochs, num_steps, batch_size, lr, clipping_theta = 250, 35, 32, 1e2, 1e-2
pred_period, pred_len, prefixes = 50, 50, ['分开', '不分开']
train_and_predict_rnn(rnn, get_params, init_rnn_state, num_hiddens,
vocab_size, device, corpus_indices, idx_to_char,
char_to_idx, True, num_epochs, num_steps, lr,
clipping_theta, batch_size, pred_period, pred_len,
prefixes)
** 简易实现**
rnn_layer = nn.RNN(input_size=vocab_size, hidden_size=num_hiddens)
num_steps, batch_size = 35, 2
X = torch.rand(num_steps, batch_size, vocab_size)
state = None
Y, state_new = rnn_layer(X, state)
print(Y.shape, state_new.shape)
class RNNModel(nn.Module):
def __init__(self, rnn_layer, vocab_size):
super(RNNModel, self).__init__()
self.rnn = rnn_layer
self.hidden_size = rnn_layer.hidden_size * (2 if rnn_layer.bidirectional else 1)
self.vocab_size = vocab_size
self.dense = nn.Linear(self.hidden_size, vocab_size)
def forward(self, inputs, state):
# inputs.shape: (batch_size, num_steps)
X = to_onehot(inputs, vocab_size)
X = torch.stack(X) # X.shape: (num_steps, batch_size, vocab_size)
hiddens, state = self.rnn(X, state)
hiddens = hiddens.view(-1, hiddens.shape[-1]) # hiddens.shape: (num_steps * batch_size, hidden_size)
output = self.dense(hiddens)
return output, state
def predict_rnn_pytorch(prefix, num_chars, model, vocab_size, device, idx_to_char,
char_to_idx):
state = None
output = [char_to_idx[prefix[0]]] # output记录prefix加上预测的num_chars个字符
for t in range(num_chars + len(prefix) - 1):
X = torch.tensor([output[-1]], device=device).view(1, 1)
(Y, state) = model(X, state) # 前向计算不需要传入模型参数
if t < len(prefix) - 1:
output.append(char_to_idx[prefix[t + 1]])
else:
output.append(Y.argmax(dim=1).item())
return ''.join([idx_to_char[i] for i in output])
model = RNNModel(rnn_layer, vocab_size).to(device)
predict_rnn_pytorch('分开', 10, model, vocab_size, device, idx_to_char, char_to_idx)
def train_and_predict_rnn_pytorch(model, num_hiddens, vocab_size, device,
corpus_indices, idx_to_char, char_to_idx,
num_epochs, num_steps, lr, clipping_theta,
batch_size, pred_period, pred_len, prefixes):
loss = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=lr)
model.to(device)
for epoch in range(num_epochs):
l_sum, n, start = 0.0, 0, time.time()
data_iter = d2l.data_iter_consecutive(corpus_indices, batch_size, num_steps, device) # 相邻采样
state = None
for X, Y in data_iter:
if state is not None:
# 使用detach函数从计算图分离隐藏状态
if isinstance (state, tuple): # LSTM, state:(h, c)
state[0].detach_()
state[1].detach_()
else:
state.detach_()
(output, state) = model(X, state) # output.shape: (num_steps * batch_size, vocab_size)
y = torch.flatten(Y.T)
l = loss(output, y.long())
optimizer.zero_grad()
l.backward()
grad_clipping(model.parameters(), clipping_theta, device)
optimizer.step()
l_sum += l.item() * y.shape[0]
n += y.shape[0]
if (epoch + 1) % pred_period == 0:
print('epoch %d, perplexity %f, time %.2f sec' % (
epoch + 1, math.exp(l_sum / n), time.time() - start))
for prefix in prefixes:
print(' -', predict_rnn_pytorch(
prefix, pred_len, model, vocab_size, device, idx_to_char,
char_to_idx))
num_epochs, batch_size, lr, clipping_theta = 250, 32, 1e-3, 1e-2
pred_period, pred_len, prefixes = 50, 50, ['分开', '不分开']
train_and_predict_rnn_pytorch(model, num_hiddens, vocab_size, device,
corpus_indices, idx_to_char, char_to_idx,
num_epochs, num_steps, lr, clipping_theta,
batch_size, pred_period, pred_len, prefixes)
扫一扫
216
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
