PyTorch NLP From Scratch: 使用char-RNN对姓氏进行分类

在自然语言处理（NLP）领域，字符级循环神经网络（char-RNN）是一种强大的工具，可以用于对文本数据进行建模和分类。本教程教你如何从头开始构建和训练一个字符级 RNN 模型，用于对姓氏进行分类。

一、准备数据

我们将使用包含来自 18 种不同语言的姓氏的数据集。这些数据存储在多个文本文件中，每个文件对应一种语言。我们需要将这些数据加载到内存中，并进行预处理。

1. 加载数据文件

from io import open
import glob
import os


def findFiles(path):
    return glob.glob(path)


print(findFiles('data/names/*.txt'))  # 查找所有数据文件

2. 将 Unicode 转换为 ASCII

import unicodedata
import string


all_letters = string.ascii_letters + " .,;'"
n_letters = len(all_letters)


def unicodeToAscii(s):
    return ''.join(
        c for c in unicodedata.normalize('NFD', s)
        if unicodedata.category(c) != 'Mn' and c in all_letters
    )


print(unicodeToAscii('Ślusàrski'))  # 测试转换功能

3. 构建类别行字典

category_lines = {}
all_categories = []


def readLines(filename):
    lines = open(filename, encoding='utf-8').read().strip().split('\n')
    return [unicodeToAscii(line) for line in lines]


for filename in findFiles('data/names/*.txt'):
    category = os.path.splitext(os.path.basename(filename))[0]
    all_categories.append(category)
    lines = readLines(filename)
    category_lines[category] = lines


n_categories = len(all_categories)
print(category_lines['Italian'][:5])  # 查看意大利姓氏的前 5 个示例

二、将名称转换为张量

为了将名称输入到神经网络中，我们需要将字符转换为张量。我们使用 one-hot 编码来表示每个字符。

import torch


def letterToIndex(letter):
    return all_letters.find(letter)


def letterToTensor(letter):
    tensor = torch.zeros(1, n_letters)
    tensor[0][letterToIndex(letter)] = 1
    return tensor


def lineToTensor(line):
    tensor = torch.zeros(len(line), 1, n_letters)
    for li, letter in enumerate(line):
        tensor[li][0][letterToIndex(letter)] = 1
    return tensor


print(letterToTensor('J'))  # 测试单个字符转换
print(lineToTensor('Jones').size())  # 测试整个名称转换

三、构建字符级 RNN 模型

我们将构建一个字符级 RNN 模型，用于根据姓氏的拼写预测其来源。

import torch.nn as nn


class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(RNN, self).__init__()
        self.hidden_size = hidden_size
        self.i2h = nn.Linear(input_size + hidden_size, hidden_size)
        self.i2o = nn.Linear(input_size + hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=1)


    def forward(self, input, hidden):
        combined = torch.cat((input, hidden), 1)
        hidden = self.i2h(combined)
        output = self.i2o(combined)
        output = self.softmax(output)
        return output, hidden


    def initHidden(self):
        return torch.zeros(1, self.hidden_size)


n_hidden = 128
rnn = RNN(n_letters, n_hidden, n_categories)

四、训练模型

1. 准备训练数据

import random


def randomChoice(l):
    return l[random.randint(0, len(l) - 1)]


def randomTrainingExample():
    category = randomChoice(all_categories)
    line = randomChoice(category_lines[category])
    category_tensor = torch.tensor([all_categories.index(category)], dtype=torch.long)
    line_tensor = lineToTensor(line)
    return category, line, category_tensor, line_tensor


for i in range(10):
    category, line, category_tensor, line_tensor = randomTrainingExample()
    print('category =', category, '/ line =', line)

2. 定义训练函数

criterion = nn.NLLLoss()
learning_rate = 0.005


def train(category_tensor, line_tensor):
    hidden = rnn.initHidden()
    rnn.zero_grad()
    for i in range(line_tensor.size()[0]):
        output, hidden = rnn(line_tensor[i], hidden)
    loss = criterion(output, category_tensor)
    loss.backward()
    for p in rnn.parameters():
        p.data.add_(-learning_rate, p.grad.data)
    return output, loss.item()

3. 进行训练

n_iters = 100000
print_every = 5000
plot_every = 1000


current_loss = 0
all_losses = []


def timeSince(since):
    now = time.time()
    s = now - since
    m = math.floor(s / 60)
    s -= m * 60
    return '%dm %ds' % (m, s)


start = time.time()


for iter in range(1, n_iters + 1):
    category, line, category_tensor, line_tensor = randomTrainingExample()
    output, loss = train(category_tensor, line_tensor)
    current_loss += loss
    if iter % print_every == 0:
        guess, guess_i = categoryFromOutput(output)
        correct = '✓' if guess == category else '✗ (%s)' % category
        print('%d %d%% (%s) %.4f %s / %s %s' % (iter, iter / n_iters * 100, timeSince(start), loss, line, guess, correct))
    if iter % plot_every == 0:
        all_losses.append(current_loss / plot_every)
        current_loss = 0

五、评估模型

1. 绘制训练损失曲线

import matplotlib.pyplot as plt


plt.figure()
plt.plot(all_losses)
plt.title("Training Loss Curve")
plt.xlabel("Iteration")
plt.ylabel("Loss")
plt.show()

2. 构建混淆矩阵

confusion = torch.zeros(n_categories, n_categories)
n_confusion = 10000


def evaluate(line_tensor):
    hidden = rnn.initHidden()
    for i in range(line_tensor.size()[0]):
        output, hidden = rnn(line_tensor[i], hidden)
    return output


for i in range(n_confusion):
    category, line, category_tensor, line_tensor = randomTrainingExample()
    output = evaluate(line_tensor)
    guess, guess_i = categoryFromOutput(output)
    category_i = all_categories.index(category)
    confusion[category_i][guess_i] += 1


for i in range(n_categories):
    confusion[i] = confusion[i] / confusion[i].sum()


fig = plt.figure()
ax = fig.add_subplot(111)
cax = ax.matshow(confusion.numpy())
fig.colorbar(cax)
ax.set_xticklabels([''] + all_categories, rotation=90)
ax.set_yticklabels([''] + all_categories)
ax.xaxis.set_major_locator(ticker.MultipleLocator(1))
ax.yaxis.set_major_locator(ticker.MultipleLocator(1))
plt.show()

六、实际应用

现在，我们可以使用训练好的模型对新的姓氏进行分类。

def predict(input_line, n_predictions=3):
    print('\n> %s' % input_line)
    with torch.no_grad():
        output = evaluate(lineToTensor(input_line))
        topv, topi = output.topk(n_predictions, 1, True)
        predictions = []
        for i in range(n_predictions):
            value = topv[0][i].item()
            category_index = topi[0][i].item()
            print('(%.2f) %s' % (value, all_categories[category_index]))
            predictions.append([value, all_categories[category_index]])


predict('Dovesky')
predict('Jackson')
predict('Satoshi')

通过本教程，你学会了如何使用 PyTorch 构建和训练字符级 RNN 模型，用于对姓氏进行分类。