数据准备

使用IMDB影评数据集，包含Positive和Negative两类。

数据下载

import os
import shutil
import requests
import tempfile
from tqdm import tqdm
from typing import IO
from pathlib import Path

# 指定保存路径为 `home_path/.mindspore_examples`
cache_dir = Path.home() / '.mindspore_examples'

def http_get(url: str, temp_file: IO):
    """使用requests库下载数据，并使用tqdm库进行流程可视化"""
    req = requests.get(url, stream=True)
    content_length = req.headers.get('Content-Length')
    total = int(content_length) if content_length is not None else None
    progress = tqdm(unit='B', total=total)
    for chunk in req.iter_content(chunk_size=1024):
        if chunk:
            progress.update(len(chunk))
            temp_file.write(chunk)
    progress.close()

def download(file_name: str, url: str):
    """下载数据并存为指定名称"""
    if not os.path.exists(cache_dir):
        os.makedirs(cache_dir)
    cache_path = os.path.join(cache_dir, file_name)
    cache_exist = os.path.exists(cache_path)
    if not cache_exist:
        with tempfile.NamedTemporaryFile() as temp_file:
            http_get(url, temp_file)
            temp_file.flush()
            temp_file.seek(0)
            with open(cache_path, 'wb') as cache_file:
                shutil.copyfileobj(temp_file, cache_file)
    return cache_path

imdb_path = download('aclImdb_v1.tar.gz', 'https://mindspore-website.obs.myhuaweicloud.com/notebook/datasets/aclImdb_v1.tar.gz')
imdb_path

加载IMDB数据集

import re
import six
import string
import tarfile

class IMDBData():
    """IMDB数据集加载器

    加载IMDB数据集并处理为一个Python迭代对象。

    """
    label_map = {
        "pos": 1,
        "neg": 0
    }
    def __init__(self, path, mode="train"):
        self.mode = mode
        self.path = path
        self.docs, self.labels = [], []

        self._load("pos")
        self._load("neg")

    def _load(self, label):
        pattern = re.compile(r"aclImdb/{}/{}/.*\.txt$".format(self.mode, label))
        # 将数据加载至内存
        with tarfile.open(self.path) as tarf:
            tf = tarf.next()
            while tf is not None:
                if bool(pattern.match(tf.name)):
                    # 对文本进行分词、去除标点和特殊字符、小写处理
                    self.docs.append(str(tarf.extractfile(tf).read().rstrip(six.b("\n\r"))
                                         .translate(None, six.b(string.punctuation)).lower()).split())
                    self.labels.append([self.label_map[label]])
                tf = tarf.next()

    def __getitem__(self, idx):
        return self.docs[idx], self.labels[idx]

    def __len__(self):
        return len(self.docs)

imdb_train = IMDBData(imdb_path, 'train')
len(imdb_train)

将IMDB数据集加载至内存并构造为迭代对象，并加载为train和test

import mindspore.dataset as ds

def load_imdb(imdb_path):
    imdb_train = ds.GeneratorDataset(IMDBData(imdb_path, "train"), column_names=["text", "label"], shuffle=True, num_samples=10000)
    imdb_test = ds.GeneratorDataset(IMDBData(imdb_path, "test"), column_names=["text", "label"], shuffle=False)
    return imdb_train, imdb_test

imdb_train, imdb_test = load_imdb(imdb_path)
imdb_train

加载预训练词向量

预训练词向量是对输入单词的数值化表示，采用查表的方式，输入单词对应词表中的index，获得对应的表达向量。 因此进行模型构造前，需要将Embedding层所需的词向量和词表进行构造。使用Glove(Global Vectors for Word Representation)这种经典的预训练词向量， 其数据格式如下：

Word	Vector
the	0.418 0.24968 -0.41242 0.1217 0.34527 -0.044457 -0.49688 -0.17862 -0.00066023 ...
,	0.013441 0.23682 -0.16899 0.40951 0.63812 0.47709 -0.42852 -0.55641 -0.364 ...

代码实现：

import zipfile
import numpy as np

def load_glove(glove_path):
    glove_100d_path = os.path.join(cache_dir, 'glove.6B.100d.txt')
    if not os.path.exists(glove_100d_path):
        glove_zip = zipfile.ZipFile(glove_path)
        glove_zip.extractall(cache_dir)

    embeddings = []
    tokens = []
    with open(glove_100d_path, encoding='utf-8') as gf:
        for glove in gf:
            word, embedding = glove.split(maxsplit=1)
            tokens.append(word)
            embeddings.append(np.fromstring(embedding, dtype=np.float32, sep=' '))
    # 添加 <unk>, <pad> 两个特殊占位符对应的embedding
    embeddings.append(np.random.rand(100))
    embeddings.append(np.zeros((100,), np.float32))

    vocab = ds.text.Vocab.from_list(tokens, special_tokens=["<unk>", "<pad>"], special_first=False)
    embeddings = np.array(embeddings).astype(np.float32)
    return vocab, embeddings

下载Glove词向量，并加载生成词表和词向量权重矩阵。

glove_path = download('glove.6B.zip', 'https://mindspore-website.obs.myhuaweicloud.com/notebook/datasets/glove.6B.zip')
vocab, embeddings = load_glove(glove_path)
len(vocab.vocab())

使用词表将 the 转换为index id，并查询词向量矩阵对应的词向量：

idx = vocab.tokens_to_ids('the')
embedding = embeddings[idx]
idx, embedding

数据集预处理

包含的预处理如下

1. 通过Vocab将所有的Token处理为index id

2. 将文本序列同意长度，不足的使用 <pad> 补齐，超出的进行截断

代码实现：

import mindspore as ms

lookup_op = ds.text.Lookup(vocab, unknown_token='<unk>')
pad_op = ds.transforms.PadEnd([500], pad_value=vocab.tokens_to_ids('<pad>'))
type_cast_op = ds.transforms.TypeCast(ms.float32)

imdb_train = imdb_train.map(operations=[lookup_op, pad_op], input_columns=['text'])
imdb_train = imdb_train.map(operations=[type_cast_op], input_columns=['label'])

imdb_test = imdb_test.map(operations=[lookup_op, pad_op], input_columns=['text'])
imdb_test = imdb_test.map(operations=[type_cast_op], input_columns=['label'])

imdb_train, imdb_valid = imdb_train.split([0.7, 0.3])

imdb_train = imdb_train.batch(64, drop_remainder=True)
imdb_valid = imdb_valid.batch(64, drop_remainder=True)

模型构建

Embedding

Embedding层又可称为EmbeddingLookup层，其作用是使用index id对权重矩阵对应id的向量进行查找，当输入为一个由index id组成的序列时，则查找并返回一个相同长度的矩阵。

RNN

循环神经网络（Recurrent Neural Network, RNN）是一类以序列（sequence）数据为输入，在序列的演进方向进行递归（recursion）且所有节点（循环单元）按链式连接的神经网络。

由于RNN的循环特性，和自然语言文本的序列特性(句子是由单词组成的序列)十分匹配，因此被大量应用于自然语言处理研究中。

RNN单个Cell的结构简单，因此也造成了梯度消失(Gradient Vanishing)问题，具体表现为RNN网络在序列较长时，在序列尾部已经基本丢失了序列首部的信息。为了克服这一问题，LSTM(Long short-term memory)被提出，通过门控机制(Gating Mechanism)来控制信息流在每个循环步中的留存和丢弃。

LSTM对应的公式：

Dense

在经过LSTM编码获取句子特征后，将其送入一个全连接层，将特征维度变换为二分类所需的维度1，经过Dense层后的输出即为模型预测结果。

import math
import mindspore as ms
import mindspore.nn as nn
import mindspore.ops as ops
from mindspore.common.initializer import Uniform, HeUniform

class RNN(nn.Cell):
    def __init__(self, embeddings, hidden_dim, output_dim, n_layers,
                 bidirectional, pad_idx):
        super().__init__()
        vocab_size, embedding_dim = embeddings.shape
        self.embedding = nn.Embedding(vocab_size, embedding_dim, embedding_table=ms.Tensor(embeddings), padding_idx=pad_idx)
        self.rnn = nn.LSTM(embedding_dim,
                           hidden_dim,
                           num_layers=n_layers,
                           bidirectional=bidirectional,
                           batch_first=True)
        weight_init = HeUniform(math.sqrt(5))
        bias_init = Uniform(1 / math.sqrt(hidden_dim * 2))
        self.fc = nn.Dense(hidden_dim * 2, output_dim, weight_init=weight_init, bias_init=bias_init)

    def construct(self, inputs):
        embedded = self.embedding(inputs)
        _, (hidden, _) = self.rnn(embedded)
        hidden = ops.concat((hidden[-2, :, :], hidden[-1, :, :]), axis=1)
        output = self.fc(hidden)
        return output

损失函数与优化器

采用二分类交叉熵损失函数

hidden_size = 256
output_size = 1
num_layers = 2
bidirectional = True
lr = 0.001
pad_idx = vocab.tokens_to_ids('<pad>')

model = RNN(embeddings, hidden_size, output_size, num_layers, bidirectional, pad_idx)
loss_fn = nn.BCEWithLogitsLoss(reduction='mean')
optimizer = nn.Adam(model.trainable_params(), learning_rate=lr)

训练逻辑

1. 读取一个Batch的数据

2. 送入网络，进行正向计算和反向传播，更新权重

3. 返回loss

代码实现：

def forward_fn(data, label):
    logits = model(data)
    loss = loss_fn(logits, label)
    return loss

grad_fn = ms.value_and_grad(forward_fn, None, optimizer.parameters)

def train_step(data, label):
    loss, grads = grad_fn(data, label)
    optimizer(grads)
    return loss

def train_one_epoch(model, train_dataset, epoch=0):
    model.set_train()
    total = train_dataset.get_dataset_size()
    loss_total = 0
    step_total = 0
    with tqdm(total=total) as t:
        t.set_description('Epoch %i' % epoch)
        for i in train_dataset.create_tuple_iterator():
            loss = train_step(*i)
            loss_total += loss.asnumpy()
            step_total += 1
            t.set_postfix(loss=loss_total/step_total)
            t.update(1)

评估指标和逻辑

训练逻辑完成后，需要对模型进行评估。即使用模型的预测结果和测试集的正确标签进行对比，求出预测的准确率。由于IMDB的情感分类为二分类问题，对预测值直接进行四舍五入即可获得分类标签(0或1)，然后判断是否与正确标签相等即可。

def binary_accuracy(preds, y):
    """
    计算每个batch的准确率
    """

    # 对预测值进行四舍五入
    rounded_preds = np.around(ops.sigmoid(preds).asnumpy())
    correct = (rounded_preds == y).astype(np.float32)
    acc = correct.sum() / len(correct)
    return acc

有了准确率计算函数后，类似于训练逻辑，对评估逻辑进行设计, 分别为以下步骤：

1. 读取一个Batch的数据

2. 送入网络，进行正向计算，获得预测结果

3. 计算准确率

def evaluate(model, test_dataset, criterion, epoch=0):
    total = test_dataset.get_dataset_size()
    epoch_loss = 0
    epoch_acc = 0
    step_total = 0
    model.set_train(False)

    with tqdm(total=total) as t:
        t.set_description('Epoch %i' % epoch)
        for i in test_dataset.create_tuple_iterator():
            predictions = model(i[0])
            loss = criterion(predictions, i[1])
            epoch_loss += loss.asnumpy()

            acc = binary_accuracy(predictions, i[1])
            epoch_acc += acc

            step_total += 1
            t.set_postfix(loss=epoch_loss/step_total, acc=epoch_acc/step_total)
            t.update(1)

    return epoch_loss / total

模型训练与保存

num_epochs = 2
best_valid_loss = float('inf')
ckpt_file_name = os.path.join(cache_dir, 'sentiment-analysis.ckpt')

for epoch in range(num_epochs):
    train_one_epoch(model, imdb_train, epoch)
    valid_loss = evaluate(model, imdb_valid, loss_fn, epoch)

    if valid_loss < best_valid_loss:
        best_valid_loss = valid_loss
        ms.save_checkpoint(model, ckpt_file_name)

可见每轮Loss逐步下降，再验证集上的准确率逐步提升。

模型加载与测试

param_dict = ms.load_checkpoint(ckpt_file_name)
ms.load_param_into_net(model, param_dict)

imdb_test = imdb_test.batch(64)
evaluate(model, imdb_test, loss_fn)

自定义输入测试

score_map = {
    1: "Positive",
    0: "Negative"
}

def predict_sentiment(model, vocab, sentence):
    model.set_train(False)
    tokenized = sentence.lower().split()
    indexed = vocab.tokens_to_ids(tokenized)
    tensor = ms.Tensor(indexed, ms.int32)
    tensor = tensor.expand_dims(0)
    prediction = model(tensor)
    return score_map[int(np.round(ops.sigmoid(prediction).asnumpy()))]

predict_sentiment(model, vocab, "This film is terrible")

'Positive'

predict_sentiment(model, vocab, "This film is great")

'Positive'

可见由于迭代次数太少，结果与实际依然有偏差。

总结

LSTM作为RNN的一种升级，在自然语言处理情感分类任务中有着重要作用。