文本分类-NLP

数据集及任务分析

项目主题：新闻的主题分类，10分类任务
一般对于NLP项目来说的话需要进行数据预处理的，但是由于本项目的数据是经过处理过的，所以就不需要进行数据预处理了，但是数据预处理对NLP项目是重中之重的。
THUCNews文件夹
train.txt（训练集）

dev.txt(验证集)
test.txt（测试集）
class.txt

文本任务的数据处理的基本流程分析

step1：分词或分字
step2：ID替换

语料表（vocab.pkl已知的）
step3 向量的映射
Embedding（将一个词映射成一个向量embedding_SougouNews.npz
embedding_Tencent.npz）

总体的流程

命令行参数与debug

#--model TextRNN
parser = argparse.ArgumentParser(description='Chinese Text Classification')
parser.add_argument('--model', type=str, required=True, help='choose a model: TextCNN, TextRNN, FastText, TextRCNN, TextRNN_Att, DPCNN, Transformer')
parser.add_argument('--embedding', default='pre_trained', type=str, help='random or pre_trained')
parser.add_argument('--word', default=False, type=bool, help='True for word, False for char')
args = parser.parse_args()

上面的命令行参数代码的解析
parser = argparse.ArgumentParser(description=‘Chinese Text Classification’)：创建一个参数解析器对象，用于解析命令行参数。

parser.add_argument(‘–model’, type=str, required=True, help=‘choose a model: TextCNN, TextRNN, FastText, TextRCNN, TextRNN_Att, DPCNN, Transformer’)：添加一个名为 --model 的命令行参数，用于指定要使用的文本分类模型，它需要提供一个字符串类型的值，是以下模型之一：TextCNN、TextRNN、FastText、TextRCNN、TextRNN_Att、DPCNN、Transformer。

parser.add_argument(‘–embedding’, default=‘pre_trained’, type=str, help=‘random or pre_trained’)：添加一个名为 --embedding 的命令行参数，用于指定词嵌入的类型，它可以是 ‘random’（随机初始化的词向量）或 ‘pre_trained’（预训练的词向量）。

parser.add_argument(‘–word’, default=False, type=bool, help=‘True for word, False for char’)：添加一个名为 --word 的命令行参数，用于指定是基于词（True）进行分类还是基于字符（False）进行分类。

args = parser.parse_args()：解析命令行参数，并将结果存储在 args 对象中，你可以通过 args.model、args.embedding 和 args.word 来访问用户在命令行中指定的值。

这段代码的作用是让用户可以从命令行选择不同的模型、词嵌入类型以及基于词还是字符进行文本分类。用户在运行脚本时需要提供相应的参数，例如：python script.py --model TextCNN --embedding pre_trained --word True。

run.py

import time
import torch
import numpy as np
from train_eval import train, init_network
from importlib import import_module
import argparse
from tensorboardX import SummaryWriter

#--model TextRNN
parser = argparse.ArgumentParser(description='Chinese Text Classification')
parser.add_argument('--model', type=str, required=True, help='choose a model: TextCNN, TextRNN, FastText, TextRCNN, TextRNN_Att, DPCNN, Transformer')
parser.add_argument('--embedding', default='pre_trained', type=str, help='random or pre_trained')
parser.add_argument('--word', default=False, type=bool, help='True for word, False for char')
args = parser.parse_args()


if __name__ == '__main__':
    dataset = 'THUCNews'  # 数据集

    # 搜狗新闻:embedding_SougouNews.npz, 腾讯:embedding_Tencent.npz, 随机初始化:random
    embedding = 'embedding_SougouNews.npz'
    if args.embedding == 'random':
        embedding = 'random'
    model_name = args.model  #TextCNN, TextRNN,
    if model_name == 'FastText':
        from utils_fasttext import build_dataset, build_iterator, get_time_dif
        embedding = 'random'
    else:
        from utils import build_dataset, build_iterator, get_time_dif

    x = import_module('models.'   model_name)
    config = x.Config(dataset, embedding)
    np.random.seed(1)
    torch.manual_seed(1)
    torch.cuda.manual_seed_all(1)
    torch.backends.cudnn.deterministic = True  # 保证每次结果一样
    start_time = time.time()
    print("Loading data...")
    vocab, train_data, dev_data, test_data = build_dataset(config, args.word)
    train_iter = build_iterator(train_data, config)
    dev_iter = build_iterator(dev_data, config)
    test_iter = build_iterator(test_data, config)
    time_dif = get_time_dif(start_time)
    print("Time usage:", time_dif)

    # train
    config.n_vocab = len(vocab)
    model = x.Model(config).to(config.device)
    writer = SummaryWriter(log_dir=config.log_path   '/'   time.strftime('%m-%d_%H.%M', time.localtime()))
    if model_name != 'Transformer':
        init_network(model)
    print(model.parameters)
    train(config, model, train_iter, dev_iter, test_iter,writer)

train_eval.py

# coding: UTF-8
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
from sklearn import metrics
import time
from utils import get_time_dif
from tensorboardX import SummaryWriter


# 权重初始化，默认xavier
def init_network(model, method='xavier', exclude='embedding', seed=123):
    for name, w in model.named_parameters():
        if exclude not in name:
            if 'weight' in name:
                if method == 'xavier':
                    nn.init.xavier_normal_(w)
                elif method == 'kaiming':
                    nn.init.kaiming_normal_(w)
                else:
                    nn.init.normal_(w)
            elif 'bias' in name:
                nn.init.constant_(w, 0)
            else:
                pass


def train(config, model, train_iter, dev_iter, test_iter,writer):
    start_time = time.time()
    model.train()
    optimizer = torch.optim.Adam(model.parameters(), lr=config.learning_rate)

    # 学习率指数衰减，每次epoch：学习率 = gamma * 学习率
    # scheduler = torch.optim.lr_scheduler.ExponentialLR(optimizer, gamma=0.9)
    total_batch = 0  # 记录进行到多少batch
    dev_best_loss = float('inf')
    last_improve = 0  # 记录上次验证集loss下降的batch数
    flag = False  # 记录是否很久没有效果提升
    #writer = SummaryWriter(log_dir=config.log_path   '/'   time.strftime('%m-%d_%H.%M', time.localtime()))
    for epoch in range(config.num_epochs):
        print('Epoch [{}/{}]'.format(epoch   1, config.num_epochs))
        # scheduler.step() # 学习率衰减
        for i, (trains, labels) in enumerate(train_iter):
            #print (trains[0].shape)
            outputs = model(trains)
            model.zero_grad()
            loss = F.cross_entropy(outputs, labels)
            loss.backward()
            optimizer.step()
            if total_batch % 100 == 0:
                # 每多少轮输出在训练集和验证集上的效果
                true = labels.data.cpu()
                predic = torch.max(outputs.data, 1)[1].cpu()
                train_acc = metrics.accuracy_score(true, predic)
                dev_acc, dev_loss = evaluate(config, model, dev_iter)
                if dev_loss < dev_best_loss:
                    dev_best_loss = dev_loss
                    torch.save(model.state_dict(), config.save_path)
                    improve = '*'
                    last_improve = total_batch
                else:
                    improve = ''
                time_dif = get_time_dif(start_time)
                msg = 'Iter: {0:>6},  Train Loss: {1:>5.2},  Train Acc: {2:>6.2%},  Val Loss: {3:>5.2},  Val Acc: {4:>6.2%},  Time: {5} {6}'
                print(msg.format(total_batch, loss.item(), train_acc, dev_loss, dev_acc, time_dif, improve))
                writer.add_scalar("loss/train", loss.item(), total_batch)
                writer.add_scalar("loss/dev", dev_loss, total_batch)
                writer.add_scalar("acc/train", train_acc, total_batch)
                writer.add_scalar("acc/dev", dev_acc, total_batch)
                model.train()
            total_batch  = 1
            if total_batch - last_improve > config.require_improvement:
                # 验证集loss超过1000batch没下降，结束训练
                print("No optimization for a long time, auto-stopping...")
                flag = True
                break
        if flag:
            break
    writer.close()
    test(config, model, test_iter)


def test(config, model, test_iter):
    # test
    model.load_state_dict(torch.load(config.save_path))
    model.eval()
    start_time = time.time()
    test_acc, test_loss, test_report, test_confusion = evaluate(config, model, test_iter, test=True)
    msg = 'Test Loss: {0:>5.2},  Test Acc: {1:>6.2%}'
    print(msg.format(test_loss, test_acc))
    print("Precision, Recall and F1-Score...")
    print(test_report)
    print("Confusion Matrix...")
    print(test_confusion)
    time_dif = get_time_dif(start_time)
    print("Time usage:", time_dif)


def evaluate(config, model, data_iter, test=False):
    model.eval()
    loss_total = 0
    predict_all = np.array([], dtype=int)
    labels_all = np.array([], dtype=int)
    with torch.no_grad():
        for texts, labels in data_iter:
            outputs = model(texts)
            loss = F.cross_entropy(outputs, labels)
            loss_total  = loss
            labels = labels.data.cpu().numpy()
            predic = torch.max(outputs.data, 1)[1].cpu().numpy()
            labels_all = np.append(labels_all, labels)
            predict_all = np.append(predict_all, predic)

    acc = metrics.accuracy_score(labels_all, predict_all)
    if test:
        report = metrics.classification_report(labels_all, predict_all, target_names=config.class_list, digits=4)
        confusion = metrics.confusion_matrix(labels_all, predict_all)
        return acc, loss_total / len(data_iter), report, confusion
    return acc, loss_total / len(data_iter)

utils.py

# coding: UTF-8
import os
import torch
import numpy as np
import pickle as pkl
from tqdm import tqdm
import time
from datetime import timedelta


MAX_VOCAB_SIZE = 10000  # 词表长度限制
UNK, PAD = '<UNK>', '<PAD>'  # 未知字，padding符号


def build_vocab(file_path, tokenizer, max_size, min_freq):
    vocab_dic = {}
    with open(file_path, 'r', encoding='UTF-8') as f:
        for line in tqdm(f):
            lin = line.strip()
            if not lin:
                continue
            content = lin.split('\t')[0]
            for word in tokenizer(content):
                vocab_dic[word] = vocab_dic.get(word, 0)   1
        vocab_list = sorted([_ for _ in vocab_dic.items() if _[1] >= min_freq], key=lambda x: x[1], reverse=True)[:max_size]
        vocab_dic = {word_count[0]: idx for idx, word_count in enumerate(vocab_list)}
        vocab_dic.update({UNK: len(vocab_dic), PAD: len(vocab_dic)   1})
    return vocab_dic


def build_dataset(config, ues_word):
    if ues_word:
        tokenizer = lambda x: x.split(' ')  # 以空格隔开，word-level
    else:
        tokenizer = lambda x: [y for y in x]  # char-level
    if os.path.exists(config.vocab_path):
        vocab = pkl.load(open(config.vocab_path, 'rb'))
    else:
        vocab = build_vocab(config.train_path, tokenizer=tokenizer, max_size=MAX_VOCAB_SIZE, min_freq=1)
        pkl.dump(vocab, open(config.vocab_path, 'wb'))
    print(f"Vocab size: {len(vocab)}")

    def load_dataset(path, pad_size=32):
        contents = []
        with open(path, 'r', encoding='UTF-8') as f:
            for line in tqdm(f):
                lin = line.strip()
                if not lin:
                    continue
                content, label = lin.split('\t')
                words_line = []
                token = tokenizer(content)
                seq_len = len(token)
                if pad_size:
                    if len(token) < pad_size:
                        token.extend([vocab.get(PAD)] * (pad_size - len(token)))
                    else:
                        token = token[:pad_size]
                        seq_len = pad_size
                # word to id
                for word in token:
                    words_line.append(vocab.get(word, vocab.get(UNK)))
                contents.append((words_line, int(label), seq_len))
        return contents  # [([...], 0), ([...], 1), ...]
    train = load_dataset(config.train_path, config.pad_size)
    dev = load_dataset(config.dev_path, config.pad_size)
    test = load_dataset(config.test_path, config.pad_size)
    return vocab, train, dev, test


class DatasetIterater(object):
    def __init__(self, batches, batch_size, device):
        self.batch_size = batch_size
        self.batches = batches
        self.n_batches = len(batches) // batch_size
        self.residue = False  # 记录batch数量是否为整数
        if len(batches) % self.n_batches != 0:
            self.residue = True
        self.index = 0
        self.device = device

    def _to_tensor(self, datas):
        x = torch.LongTensor([_[0] for _ in datas]).to(self.device)
        y = torch.LongTensor([_[1] for _ in datas]).to(self.device)

        # pad前的长度(超过pad_size的设为pad_size)
        seq_len = torch.LongTensor([_[2] for _ in datas]).to(self.device)
        return (x, seq_len), y

    def __next__(self):
        if self.residue and self.index == self.n_batches:
            batches = self.batches[self.index * self.batch_size: len(self.batches)]
            self.index  = 1
            batches = self._to_tensor(batches)
            return batches

        elif self.index > self.n_batches:
            self.index = 0
            raise StopIteration
        else:
            batches = self.batches[self.index * self.batch_size: (self.index   1) * self.batch_size]
            self.index  = 1
            batches = self._to_tensor(batches)
            return batches

    def __iter__(self):
        return self

    def __len__(self):
        if self.residue:
            return self.n_batches   1
        else:
            return self.n_batches


def build_iterator(dataset, config):
    iter = DatasetIterater(dataset, config.batch_size, config.device)
    return iter


def get_time_dif(start_time):
    """获取已使用时间"""
    end_time = time.time()
    time_dif = end_time - start_time
    return timedelta(seconds=int(round(time_dif)))


if __name__ == "__main__":
    '''提取预训练词向量'''
    # 下面的目录、文件名按需更改。
    train_dir = "./THUCNews/data/train.txt"
    vocab_dir = "./THUCNews/data/vocab.pkl"
    pretrain_dir = "./THUCNews/data/sgns.sogou.char"
    emb_dim = 300
    filename_trimmed_dir = "./THUCNews/data/embedding_SougouNews"
    if os.path.exists(vocab_dir):
        word_to_id = pkl.load(open(vocab_dir, 'rb'))
    else:
        # tokenizer = lambda x: x.split(' ')  # 以词为单位构建词表(数据集中词之间以空格隔开)
        tokenizer = lambda x: [y for y in x]  # 以字为单位构建词表
        word_to_id = build_vocab(train_dir, tokenizer=tokenizer, max_size=MAX_VOCAB_SIZE, min_freq=1)
        pkl.dump(word_to_id, open(vocab_dir, 'wb'))

    embeddings = np.random.rand(len(word_to_id), emb_dim)
    f = open(pretrain_dir, "r", encoding='UTF-8')
    for i, line in enumerate(f.readlines()):
        # if i == 0:  # 若第一行是标题，则跳过
        #     continue
        lin = line.strip().split(" ")
        if lin[0] in word_to_id:
            idx = word_to_id[lin[0]]
            emb = [float(x) for x in lin[1:301]]
            embeddings[idx] = np.asarray(emb, dtype='float32')
    f.close()
    np.savez_compressed(filename_trimmed_dir, embeddings=embeddings)

utils_fasttext.py

# coding: UTF-8
import os
import torch
import numpy as np
import pickle as pkl
from tqdm import tqdm
import time
from datetime import timedelta


MAX_VOCAB_SIZE = 10000
UNK, PAD = '<UNK>', '<PAD>'


def build_vocab(file_path, tokenizer, max_size, min_freq):
    vocab_dic = {}
    with open(file_path, 'r', encoding='UTF-8') as f:
        for line in tqdm(f):
            lin = line.strip()
            if not lin:
                continue
            content = lin.split('\t')[0]
            for word in tokenizer(content):
                vocab_dic[word] = vocab_dic.get(word, 0)   1
        vocab_list = sorted([_ for _ in vocab_dic.items() if _[1] >= min_freq], key=lambda x: x[1], reverse=True)[:max_size]
        vocab_dic = {word_count[0]: idx for idx, word_count in enumerate(vocab_list)}
        vocab_dic.update({UNK: len(vocab_dic), PAD: len(vocab_dic)   1})
    return vocab_dic


def build_dataset(config, ues_word):
    if ues_word:
        tokenizer = lambda x: x.split(' ')  # 以空格隔开，word-level
    else:
        tokenizer = lambda x: [y for y in x]  # char-level
    if os.path.exists(config.vocab_path):
        vocab = pkl.load(open(config.vocab_path, 'rb'))
    else:
        vocab = build_vocab(config.train_path, tokenizer=tokenizer, max_size=MAX_VOCAB_SIZE, min_freq=1)
        pkl.dump(vocab, open(config.vocab_path, 'wb'))
    print(f"Vocab size: {len(vocab)}")

    def biGramHash(sequence, t, buckets):
        t1 = sequence[t - 1] if t - 1 >= 0 else 0
        return (t1 * 14918087) % buckets

    def triGramHash(sequence, t, buckets):
        t1 = sequence[t - 1] if t - 1 >= 0 else 0
        t2 = sequence[t - 2] if t - 2 >= 0 else 0
        return (t2 * 14918087 * 18408749   t1 * 14918087) % buckets

    def load_dataset(path, pad_size=32):
        contents = []
        with open(path, 'r', encoding='UTF-8') as f:
            for line in tqdm(f):
                lin = line.strip()
                if not lin:
                    continue
                content, label = lin.split('\t')
                words_line = []
                token = tokenizer(content)
                seq_len = len(token)
                if pad_size:
                    if len(token) < pad_size:
                        token.extend([vocab.get(PAD)] * (pad_size - len(token)))
                    else:
                        token = token[:pad_size]
                        seq_len = pad_size
                # word to id
                for word in token:
                    words_line.append(vocab.get(word, vocab.get(UNK)))

                # fasttext ngram
                buckets = config.n_gram_vocab
                bigram = []
                trigram = []
                # ------ngram------
                for i in range(pad_size):
                    bigram.append(biGramHash(words_line, i, buckets))
                    trigram.append(triGramHash(words_line, i, buckets))
                # -----------------
                contents.append((words_line, int(label), seq_len, bigram, trigram))
        return contents  # [([...], 0), ([...], 1), ...]
    train = load_dataset(config.train_path, config.pad_size)
    dev = load_dataset(config.dev_path, config.pad_size)
    test = load_dataset(config.test_path, config.pad_size)
    return vocab, train, dev, test


class DatasetIterater(object):
    def __init__(self, batches, batch_size, device):
        self.batch_size = batch_size
        self.batches = batches
        self.n_batches = len(batches) // batch_size
        self.residue = False  # 记录batch数量是否为整数 
        if len(batches) % self.n_batches != 0:
            self.residue = True
        self.index = 0
        self.device = device

    def _to_tensor(self, datas):
        # xx = [xxx[2] for xxx in datas]
        # indexx = np.argsort(xx)[::-1]
        # datas = np.array(datas)[indexx]
        x = torch.LongTensor([_[0] for _ in datas]).to(self.device)
        y = torch.LongTensor([_[1] for _ in datas]).to(self.device)
        bigram = torch.LongTensor([_[3] for _ in datas]).to(self.device)
        trigram = torch.LongTensor([_[4] for _ in datas]).to(self.device)

        # pad前的长度(超过pad_size的设为pad_size)
        seq_len = torch.LongTensor([_[2] for _ in datas]).to(self.device)
        return (x, seq_len, bigram, trigram), y

    def __next__(self):
        if self.residue and self.index == self.n_batches:
            batches = self.batches[self.index * self.batch_size: len(self.batches)]
            self.index  = 1
            batches = self._to_tensor(batches)
            return batches

        elif self.index > self.n_batches:
            self.index = 0
            raise StopIteration
        else:
            batches = self.batches[self.index * self.batch_size: (self.index   1) * self.batch_size]
            self.index  = 1
            batches = self._to_tensor(batches)
            return batches

    def __iter__(self):
        return self

    def __len__(self):
        if self.residue:
            return self.n_batches   1
        else:
            return self.n_batches


def build_iterator(dataset, config):
    iter = DatasetIterater(dataset, config.batch_size, config.device)
    return iter


def get_time_dif(start_time):
    """获取已使用时间"""
    end_time = time.time()
    time_dif = end_time - start_time
    return timedelta(seconds=int(round(time_dif)))

if __name__ == "__main__":
    '''提取预训练词向量'''
    vocab_dir = "./THUCNews/data/vocab.pkl"
    pretrain_dir = "./THUCNews/data/sgns.sogou.char"
    emb_dim = 300
    filename_trimmed_dir = "./THUCNews/data/vocab.embedding.sougou"
    word_to_id = pkl.load(open(vocab_dir, 'rb'))
    embeddings = np.random.rand(len(word_to_id), emb_dim)
    f = open(pretrain_dir, "r", encoding='UTF-8')
    for i, line in enumerate(f.readlines()):
        # if i == 0:  # 若第一行是标题，则跳过
        #     continue
        lin = line.strip().split(" ")
        if lin[0] in word_to_id:
            idx = word_to_id[lin[0]]
            emb = [float(x) for x in lin[1:301]]
            embeddings[idx] = np.asarray(emb, dtype='float32')
    f.close()
    np.savez_compressed(filename_trimmed_dir, embeddings=embeddings)

这篇好文章是转载于：学新通技术网