Text preprocessing

Common four steps:

1. Read in text
2. participle
3. Build a dictionary to map each word to a unique index
4. Convert the text from the sequence of words to the sequence of indexes to facilitate the input of models

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))

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]

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)  # Returns a dictionary that records the number of occurrences of each word

Language model

The n-element model is mainly considered:

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]

# Build character index
idx_to_char = list(set(corpus_chars)) # De duplicate to get index to character mapping
char_to_idx = {char: i for i, char in enumerate(idx_to_char)} # Character to index mapping
vocab_size = len(char_to_idx)
print(vocab_size)

corpus_indices = [char_to_idx[char] for char in corpus_chars]  # Turn each character into an index to get a sequence of indexes
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


import torch
import random
def data_iter_random(corpus_indices, batch_size, num_steps, device=None):
    # Minus 1 is because for a sequence of length N, X contains at most the first n - 1 characters
    num_examples = (len(corpus_indices) - 1) // Get the number of samples without overlapping by rounding under num steps
    example_indices = [i * num_steps for i in range(num_examples)]  # The subscript of the first character of each sample in corpus  indexes
    random.shuffle(example_indices)

    def _data(i):
        # Returns a sequence of num steps from i
        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):
        # Each time, select batch_size random samples
        batch_indices = example_indices[i: i + batch_size]  # Subscript of the first character of each sample of the current batch
        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')

Cyclic neural network:

The next step is to realize the cyclic neural network from zero

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')

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)


num_inputs, num_hiddens, num_outputs = vocab_size, 256, vocab_size
# num_inputs: d
# Num? Hidden: H, the number of hidden cells is a super parameter
# 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)

    # Hide layer parameters
    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))
    # Output layer parameters
    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)


def rnn(inputs, state, params):
    # Input and output are both num steps and matrix with shape (batch size, vocab size)
    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)


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 record prefix plus predicted num ﹐ chars characters
    for t in range(num_chars + len(prefix) - 1):
        # Take the output of the previous time step as the input of the current time step
        X = to_onehot(torch.tensor([[output[-1]]], device=device), vocab_size)
        # Calculate output and update hidden state
        (Y, state) = rnn(X, state, params)
        # The next time step is to input the characters in the prefix or the current best prediction character
        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])