文本情感分类
`bert.py`
# coding: UTF-8 import torch import torch.nn as nn # from pytorch_pretrained_bert import BertModel, BertTokenizer from pytorch_pretrained import BertModel, BertTokenizer class Config(object): """配置参数""" def __init__(self, dataset): self.model_name = 'bert' self.train_path = dataset + '/data/train.txt' # 训练集 self.dev_path = dataset + '/data/dev.txt' # 验证集 self.test_path = dataset + '/data/test.txt' # 测试集 self.class_list = [x.strip() for x in open( dataset + '/data/class.txt').readlines()] # 类别名单 self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt' # 模型训练结果 self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # 设备 self.require_improvement = 1000 # 若超过1000batch效果还没提升，则提前结束训练 self.num_classes = len(self.class_list) # 类别数 self.num_epochs = 3 # epoch数 self.batch_size = 32 # mini-batch大小 self.pad_size = 32 # 每句话处理成的长度(短填长切) self.learning_rate = 5e-5 # 学习率 self.bert_path = './bert_pretrain' self.tokenizer = BertTokenizer.from_pretrained(self.bert_path) self.hidden_size = 768 class Model(nn.Module): def __init__(self, config): super(Model, self).__init__() self.bert = BertModel.from_pretrained(config.bert_path) for param in self.bert.parameters(): param.requires_grad = True self.fc = nn.Linear(config.hidden_size, config.num_classes) def forward(self, x): context = x[0] # 输入的句子 mask = x[2] # 对padding部分进行mask，和句子一个size，padding部分用0表示，如：[1, 1, 1, 1, 0, 0] _, pooled = self.bert(context, attention_mask=mask, output_all_encoded_layers=False) out = self.fc(pooled) return out
`bert_CNN.py`
# coding: UTF-8 import torch import torch.nn as nn import torch.nn.functional as F from pytorch_pretrained import BertModel, BertTokenizer class Config(object): """配置参数""" def __init__(self, dataset): self.model_name = 'bert' self.train_path = dataset + '/data/train.txt' # 训练集 self.dev_path = dataset + '/data/dev.txt' # 验证集 self.test_path = dataset + '/data/test.txt' # 测试集 self.class_list = [x.strip() for x in open( dataset + '/data/class.txt').readlines()] # 类别名单 self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt' # 模型训练结果 self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # 设备 self.require_improvement = 1000 # 若超过1000batch效果还没提升，则提前结束训练 self.num_classes = len(self.class_list) # 类别数 self.num_epochs = 3 # epoch数 self.batch_size = 128//4 # mini-batch大小 self.pad_size = 32 # 每句话处理成的长度(短填长切) self.learning_rate = 5e-5 # 学习率 self.bert_path = './bert_pretrain' self.tokenizer = BertTokenizer.from_pretrained(self.bert_path) self.hidden_size = 768 self.filter_sizes = (2, 3, 4) # 卷积核尺寸 self.num_filters = 256 # 卷积核数量(channels数) self.dropout = 0.1 class Model(nn.Module): def __init__(self, config): super(Model, self).__init__() self.bert = BertModel.from_pretrained(config.bert_path) for param in self.bert.parameters(): param.requires_grad = True self.convs = nn.ModuleList( [nn.Conv2d(1, config.num_filters, (k, config.hidden_size)) for k in config.filter_sizes]) self.dropout = nn.Dropout(config.dropout) self.fc_cnn = nn.Linear(config.num_filters * len(config.filter_sizes), config.num_classes) def conv_and_pool(self, x, conv): x = F.relu(conv(x)).squeeze(3) x = F.max_pool1d(x, x.size(2)).squeeze(2) return x def forward(self, x): context = x[0] # 输入的句子 mask = x[2] # 对padding部分进行mask，和句子一个size，padding部分用0表示，如：[1, 1, 1, 1, 0, 0] encoder_out, text_cls = self.bert(context, attention_mask=mask, output_all_encoded_layers=False) out = encoder_out.unsqueeze(1) out = torch.cat([self.conv_and_pool(out, conv) for conv in self.convs], 1) out = self.dropout(out) out = self.fc_cnn(out) return out
`bert_DPCNN.py`
# coding: UTF-8 import torch import torch.nn as nn import torch.nn.functional as F # from pytorch_pretrained_bert import BertModel, BertTokenizer from pytorch_pretrained import BertModel, BertTokenizer class Config(object): """配置参数""" def __init__(self, dataset): self.model_name = 'bert' self.train_path = dataset + '/data/train.txt' # 训练集 self.dev_path = dataset + '/data/dev.txt' # 验证集 self.test_path = dataset + '/data/test.txt' # 测试集 self.class_list = [x.strip() for x in open( dataset + '/data/class.txt').readlines()] # 类别名单 self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt' # 模型训练结果 self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # 设备 self.require_improvement = 1000 # 若超过1000batch效果还没提升，则提前结束训练 self.num_classes = len(self.class_list) # 类别数 self.num_epochs = 3 # epoch数 self.batch_size = 128//4 # mini-batch大小 self.pad_size = 32 # 每句话处理成的长度(短填长切) self.learning_rate = 5e-5 # 学习率 self.bert_path = './bert_pretrain' self.tokenizer = BertTokenizer.from_pretrained(self.bert_path) self.hidden_size = 768 self.num_filters = 250 # 卷积核数量(channels数) class Model(nn.Module): def __init__(self, config): super(Model, self).__init__() self.bert = BertModel.from_pretrained(config.bert_path) for param in self.bert.parameters(): param.requires_grad = True # self.fc = nn.Linear(config.hidden_size, config.num_classes) self.conv_region = nn.Conv2d(1, config.num_filters, (3, config.hidden_size), stride=1) self.conv = nn.Conv2d(config.num_filters, config.num_filters, (3, 1), stride=1) self.max_pool = nn.MaxPool2d(kernel_size=(3, 1), stride=2) self.padding1 = nn.ZeroPad2d((0, 0, 1, 1)) # top bottom self.padding2 = nn.ZeroPad2d((0, 0, 0, 1)) # bottom self.relu = nn.ReLU() self.fc = nn.Linear(config.num_filters, config.num_classes) def forward(self, x): context = x[0] # 输入的句子 mask = x[2] # 对padding部分进行mask，和句子一个size，padding部分用0表示，如：[1, 1, 1, 1, 0, 0] encoder_out, text_cls = self.bert(context, attention_mask=mask, output_all_encoded_layers=False) x = encoder_out.unsqueeze(1) # [batch_size, 1, seq_len, embed] x = self.conv_region(x) # [batch_size, 250, seq_len-3+1, 1] x = self.padding1(x) # [batch_size, 250, seq_len, 1] x = self.relu(x) x = self.conv(x) # [batch_size, 250, seq_len-3+1, 1] x = self.padding1(x) # [batch_size, 250, seq_len, 1] x = self.relu(x) x = self.conv(x) # [batch_size, 250, seq_len-3+1, 1] while x.size()[2] > 2: x = self._block(x) x = x.squeeze() # [batch_size, num_filters(250)] x = self.fc(x) return x def _block(self, x): x = self.padding2(x) px = self.max_pool(x) x = self.padding1(px) x = F.relu(x) x = self.conv(x) x = self.padding1(x) x = F.relu(x) x = self.conv(x) x = x + px # short cut return x
`bert_RCNN.py`
# coding: UTF-8 import torch import torch.nn as nn import torch.nn.functional as F from pytorch_pretrained import BertModel, BertTokenizer class Config(object): """配置参数""" def __init__(self, dataset): self.model_name = 'bert' self.train_path = dataset + '/data/train.txt' # 训练集 self.dev_path = dataset + '/data/dev.txt' # 验证集 self.test_path = dataset + '/data/test.txt' # 测试集 self.class_list = [x.strip() for x in open( dataset + '/data/class.txt').readlines()] # 类别名单 self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt' # 模型训练结果 self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # 设备 self.require_improvement = 1000 # 若超过1000batch效果还没提升，则提前结束训练 self.num_classes = len(self.class_list) # 类别数 self.num_epochs = 3 # epoch数 self.batch_size = 128//4 # mini-batch大小 self.pad_size = 32 # 每句话处理成的长度(短填长切) self.learning_rate = 5e-5 # 学习率 self.bert_path = './bert_pretrain' self.tokenizer = BertTokenizer.from_pretrained(self.bert_path) self.hidden_size = 768 self.filter_sizes = (2, 3, 4) # 卷积核尺寸 self.num_filters = 256 # 卷积核数量(channels数) self.dropout = 0.1 self.rnn_hidden = 256 self.num_layers = 2 class Model(nn.Module): def __init__(self, config): super(Model, self).__init__() self.bert = BertModel.from_pretrained(config.bert_path) for param in self.bert.parameters(): param.requires_grad = True self.lstm = nn.LSTM(config.hidden_size, config.rnn_hidden, config.num_layers, bidirectional=True, batch_first=True, dropout=config.dropout) self.maxpool = nn.MaxPool1d(config.pad_size) self.fc = nn.Linear(config.rnn_hidden * 2 + config.hidden_size, config.num_classes) def forward(self, x): context = x[0] # 输入的句子 mask = x[2] # 对padding部分进行mask，和句子一个size，padding部分用0表示，如：[1, 1, 1, 1, 0, 0] encoder_out, text_cls = self.bert(context, attention_mask=mask, output_all_encoded_layers=False) out, _ = self.lstm(encoder_out) out = torch.cat((encoder_out, out), 2) out = F.relu(out) out = out.permute(0, 2, 1) out = self.maxpool(out).squeeze() out = self.fc(out) return out
`bert_RNN.py`
# coding: UTF-8 import torch import torch.nn as nn import torch.nn.functional as F from pytorch_pretrained import BertModel, BertTokenizer class Config(object): """配置参数""" def __init__(self, dataset): self.model_name = 'bert' self.train_path = dataset + '/data/train.txt' # 训练集 self.dev_path = dataset + '/data/dev.txt' # 验证集 self.test_path = dataset + '/data/test.txt' # 测试集 self.class_list = [x.strip() for x in open( dataset + '/data/class.txt').readlines()] # 类别名单 self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt' # 模型训练结果 self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # 设备 self.require_improvement = 1000 # 若超过1000batch效果还没提升，则提前结束训练 self.num_classes = len(self.class_list) # 类别数 self.num_epochs = 3 # epoch数 self.batch_size = 128//4 # mini-batch大小 self.pad_size = 32 # 每句话处理成的长度(短填长切) self.learning_rate = 5e-5 # 学习率 self.bert_path = './bert_pretrain' self.tokenizer = BertTokenizer.from_pretrained(self.bert_path) self.hidden_size = 768 self.filter_sizes = (2, 3, 4) # 卷积核尺寸 self.num_filters = 256 # 卷积核数量(channels数) self.dropout = 0.1 self.rnn_hidden = 768 self.num_layers = 2 class Model(nn.Module): def __init__(self, config): super(Model, self).__init__() self.bert = BertModel.from_pretrained(config.bert_path) for param in self.bert.parameters(): param.requires_grad = True self.lstm = nn.LSTM(config.hidden_size, config.rnn_hidden, config.num_layers, bidirectional=True, batch_first=True, dropout=config.dropout) self.dropout = nn.Dropout(config.dropout) self.fc_rnn = nn.Linear(config.rnn_hidden * 2, config.num_classes) def forward(self, x): context = x[0] # 输入的句子 mask = x[2] # 对padding部分进行mask，和句子一个size，padding部分用0表示，如：[1, 1, 1, 1, 0, 0] encoder_out, text_cls = self.bert(context, attention_mask=mask, output_all_encoded_layers=False) out, _ = self.lstm(encoder_out) out = self.dropout(out) out = self.fc_rnn(out[:, -1, :]) # 句子最后时刻的 hidden state return out
`ERNIE.py`
# coding: UTF-8 import torch import torch.nn as nn # from pytorch_pretrained_bert import BertModel, BertTokenizer from pytorch_pretrained import BertModel, BertTokenizer class Config(object): """配置参数""" def __init__(self, dataset): self.model_name = 'ERNIE' self.train_path = dataset + '/data/train.txt' # 训练集 self.dev_path = dataset + '/data/dev.txt' # 验证集 self.test_path = dataset + '/data/test.txt' # 测试集 self.class_list = [x.strip() for x in open( dataset + '/data/class.txt').readlines()] # 类别名单 self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt' # 模型训练结果 self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # 设备 self.require_improvement = 1000 # 若超过1000batch效果还没提升，则提前结束训练 self.num_classes = len(self.class_list) # 类别数 self.num_epochs = 3 # epoch数 self.batch_size = 128//4 # mini-batch大小 self.pad_size = 32 # 每句话处理成的长度(短填长切) self.learning_rate = 5e-5 # 学习率 self.bert_path = './ERNIE_pretrain' self.tokenizer = BertTokenizer.from_pretrained(self.bert_path) print(self.tokenizer) self.hidden_size = 768 class Model(nn.Module): def __init__(self, config): super(Model, self).__init__() self.bert = BertModel.from_pretrained(config.bert_path) for param in self.bert.parameters(): param.requires_grad = True self.fc = nn.Linear(config.hidden_size, config.num_classes) def forward(self, x): context = x[0] # 输入的句子 mask = x[2] # 对padding部分进行mask，和句子一个size，padding部分用0表示，如：[1, 1, 1, 1, 0, 0] _, pooled = self.bert(context, attention_mask=mask, output_all_encoded_layers=False) out = self.fc(pooled) return out
`utils.py`
# coding: UTF-8 import torch from tqdm import tqdm import time from datetime import timedelta PAD, CLS = '[PAD]', '[CLS]' # padding符号, bert中综合信息符号 def build_dataset(config): 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() # print(lin) if not lin: continue label, content = lin.split('\t') token = config.tokenizer.tokenize(content) token = [CLS] + token seq_len = len(token) mask = [] token_ids = config.tokenizer.convert_tokens_to_ids(token) if pad_size: if len(token) < pad_size: mask = [1] * len(token_ids) + [0] * (pad_size - len(token)) token_ids += ([0] * (pad_size - len(token))) else: mask = [1] * pad_size token_ids = token_ids[:pad_size] seq_len = pad_size contents.append((token_ids, int(label), seq_len, mask)) return contents 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 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) mask = torch.LongTensor([_[3] for _ in datas]).to(self.device) return (x, seq_len, mask), 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)))
`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 pytorch_pretrained.optimization import BertAdam # 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 len(w.size()) < 2: continue 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): start_time = time.time() model.train() param_optimizer = list(model.named_parameters()) no_decay = ['bias', 'LayerNorm.bias', 'LayerNorm.weight'] optimizer_grouped_parameters = [ {'params': [p for n, p in param_optimizer if not any(nd in n for nd in no_decay)], 'weight_decay': 0.01}, {'params': [p for n, p in param_optimizer if any(nd in n for nd in no_decay)], 'weight_decay': 0.0}] # optimizer = torch.optim.Adam(model.parameters(), lr=config.learning_rate) optimizer = BertAdam(optimizer_grouped_parameters, lr=config.learning_rate, warmup=0.05, t_total=len(train_iter) * config.num_epochs) 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 model.train() for epoch in range(config.num_epochs): print('Epoch [{}/{}]'.format(epoch + 1, config.num_epochs)) for i, (trains, labels) in enumerate(train_iter): 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)) 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 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)
原paper为新闻公开数据集,本实验数据为个人独立收集,整理,使用自己的数据集,加载BERT/ERNIE预训练模型,实际微调效果都非常好!
