文本預處理
文本預處理的參考文本爲：http://www.gutenberg.org/ebooks/35
文本預處理的實現代碼爲：
##讀入文本
import collections
import re
def read_time_machine():
with open('/home/kesci/input/timemachine7163/timemachine.txt', 'r') as f:
lines = [re.sub('[^a-z]+', ' ', line.strip().lower()) for line in f]
return lines
lines = read_time_machine()
print('# sentences %d' % len(lines))
##分詞
def tokenize(sentences, token='word'):
"""Split sentences into word or char tokens"""
if token == 'word':
return [sentence.split(' ') for sentence in sentences]
elif token == 'char':
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):
counter = count_corpus(tokens) # :
self.token_freqs = list(counter.items())
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
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]
def count_corpus(sentences):
tokens = [tk for st in sentences for tk in st]
return collections.Counter(tokens) # 返回一個字典，記錄每個詞的出現次數
vocab = Vocab(tokens)
print(list(vocab.token_to_idx.items())[0:10])
##將詞語轉化爲索引
for i in range(8, 10):
print('words:', tokens[i])
print('indices:', vocab[tokens[i]])
語言模型
##讀取數據集
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] # 將每個字符轉化爲索引，得到一個索引的序列
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
##建立隨機採樣
import torch
import random
def data_iter_random(corpus_indices, batch_size, num_steps, device=None):
# 減1是因爲對於長度爲n的序列，X最多隻有包含其中的前n - 1個字符
num_examples = (len(corpus_indices) - 1) // num_steps # 下取整，得到不重疊情況下的樣本個數
example_indices = [i * num_steps for i in range(num_examples)] # 每個樣本的第一個字符在corpus_indices中的下標
random.shuffle(example_indices)
def _data(i):
# 返回從i開始的長爲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):
# 每次選出batch_size個隨機樣本
batch_indices = example_indices[i: i + batch_size] # 當前batch的各個樣本的首字符的下標
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)
my_seq = list(range(30))
for X, Y in data_iter_random(my_seq, batch_size=2, num_steps=6):
print('X: ', X, '\nY:', Y, '\n')
##建立相鄰採樣
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 # 保留下來的序列的長度
corpus_indices = corpus_indices[: corpus_len] # 僅保留前corpus_len個字符
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
for X, Y in data_iter_consecutive(my_seq, batch_size=2, num_steps=6):
print('X: ', X, '\nY:', Y, '\n')
CNN循環神經網絡
##one-hot向量構造
def one_hot(x, n_class, dtype=torch.float32):
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))
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)
##初始化模型參數
num_inputs, num_hiddens, num_outputs = vocab_size, 256, vocab_size
# num_inputs: d
# num_hiddens: h, 隱藏單元的個數是超參數
# 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)
# 隱藏層參數
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))
# 輸出層參數
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)
##定義模型
def rnn(inputs, state, params):
# inputs和outputs皆爲num_steps個形狀爲(batch_size, vocab_size)的矩陣
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):
return (torch.zeros((batch_size, num_hiddens), device=device), )
print(X.shape)
print(num_hiddens)
print(vocab_size)
state = init_rnn_state(X.shape[0], num_hiddens, device)
inputs = to_onehot(X.to(device), vocab_size)
params = get_params()
outputs, state_new = rnn(inputs, state, params)
print(len(inputs), inputs[0].shape)
print(len(outputs), outputs[0].shape)
print(len(state), state[0].shape)
print(len(state_new), state_new[0].shape)
##裁剪梯度
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)
##定義預測函數
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記錄prefix加上預測的num_chars個字符
for t in range(num_chars + len(prefix) - 1):
# 將上一時間步的輸出作爲當前時間步的輸入
X = to_onehot(torch.tensor([[output[-1]]], device=device), vocab_size)
# 計算輸出和更新隱藏狀態
(Y, state) = rnn(X, state, params)
# 下一個時間步的輸入是prefix裏的字符或者當前的最佳預測字符
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])
predict_rnn('分開', 10, rnn, params, init_rnn_state, num_hiddens, vocab_size,
device, idx_to_char, char_to_idx)
##定義模型訓練函數
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: # 如使用相鄰採樣，在epoch開始時初始化隱藏狀態
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: # 如使用隨機採樣，在每個小批量更新前初始化隱藏狀態
state = init_rnn_state(batch_size, num_hiddens, device)
else: # 否則需要使用detach函數從計算圖分離隱藏狀態
for s in state:
s.detach_()
# inputs是num_steps個形狀爲(batch_size, vocab_size)的矩陣
inputs = to_onehot(X, vocab_size)
# outputs有num_steps個形狀爲(batch_size, vocab_size)的矩陣
(outputs, state) = rnn(inputs, state, params)
# 拼接之後形狀爲(num_steps * batch_size, vocab_size)
outputs = torch.cat(outputs, dim=0)
# Y的形狀是(batch_size, num_steps)，轉置後再變成形狀爲
# (num_steps * batch_size,)的向量，這樣跟輸出的行一一對應
y = torch.flatten(Y.T)
# 使用交叉熵損失計算平均分類誤差
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) # 因爲誤差已經取過均值，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))
##訓練模型並創作歌詞
num_epochs, num_steps, batch_size, lr, clipping_theta = 250, 35, 32, 1e2, 1e-2
pred_period, pred_len, prefixes = 50, 50, ['分開', '不分開']
##下面採用隨機採樣訓練模型並創作歌詞。
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)
##接下來採用相鄰採樣訓練模型並創作歌詞。
train_and_predict_rnn(rnn, get_params, init_rnn_state, num_hiddens,
vocab_size, device, corpus_indices, idx_to_char,
char_to_idx, False, num_epochs, num_steps, lr,
clipping_theta, batch_size, pred_period, pred_len,
prefixes)