通过学习文本预处理、语言模型以及循环神经网络，仿照教材的代码编写了《三国演义》的文本预测。
import collections
import re
import torch
import random
import torch
import torch.nn as nn
import time
import math
import sys
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
'''第一步：读取文本，用集合剔除所有重复的字，给剩下来的字标序'''
def load_data_3kingdoms():
with open('三国演义utf-8.txt', 'r', encoding='UTF-8') as f:
corpus_chars = f.read()
corpus_chars = corpus_chars.replace('\n', ' ').replace('\r', ' ')
corpus_chars = corpus_chars[1000:11000]
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
(corpus_indices, char_to_idx, idx_to_char, vocab_size) = load_data_3kingdoms()
'''第二步： 根据序号，将文本里所有的字都改成one-hot向量'''
def one_hot(x, n_class, dtype=torch.float32):
result = torch.zeros(x.shape[0], n_class, dtype=dtype, device=x.device)
result.scatter_(1, x.long().view(-1, 1), 1)
return result
def to_onehot(X, n_class):
return [one_hot(X[:, i], n_class) for i in range(X.shape[1])]
'''第三步：随机采样和相邻采样'''
def data_iter_random(corpus_indices, batch_size, num_steps, device=None): # 随机采样
# 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)
def data_iter_consecutive(corpus_indices, batch_size, num_steps, device=None): #相邻采样
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
'''第四步：初始化循环神经网络的参数，超参数为隐藏层单元个数，并假定输入和输出的维度相同'''
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)
'''第五步：根据循环神经网络的核心公式写出代码'''
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,)
def init_rnn_state(batch_size, num_hiddens, device): # 函数init_rnn_state初始化隐藏变量，这里的返回值是一个元组。
return (torch.zeros((batch_size, num_hiddens), device=device),)
'''第六步：为防止梯度爆炸，对梯度进行剪裁'''
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)
'''第七步：定义预测函数'''
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])
'''第八步：定义模型训练函数'''
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 = data_iter_random
else:
data_iter_fn = data_iter_consecutive
params = get_params()
loss = nn.CrossEntropyLoss()
def sgd(params, lr, batch_size): # 定义梯度下降函数
for param in params:
param.data -= lr * param.grad / batch_size
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
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)
