超简单之推特文本情感13分类baseline

NLP秋季开胃菜，推特文本情感13分类， nlp入门的不二选择

AI Studio

845人浏览 · 2021-11-13 08:56:31

AI Studio · 2021-11-13 08:56:31 发布

一、推特文本情感分类

练习赛地址：https://www.heywhale.com/home/activity/detail/611cbe90ba12a0001753d1e9/content

此练习赛情感分类位13类，故得分较低。。。。。。

Twitter 的推文有许多特点，首先，与 Facebook 不同的是，推文是基于文本的，可以通过 Twitter 接口注册下载，便于作为自然语言处理所需的语料库。其次，Twitter 规定了每一个推文不超过 140 个字，实际推文中的文本长短不一、长度一般较短，有些只有一个句子甚至一个短语，这对其开展情感分类标注带来许多困难。再者，推文常常是随性所作，内容中包含情感的元素较多，口语化内容居多，缩写随处都在，并且使用了许多网络用语，情绪符号、新词和俚语随处可见。因此，与正式文本非常不同。如果采用那些适合处理正式文本的情感分类方法来对 Twitter 推文进行情感分类，效果将不尽人意。

公众情感在包括电影评论、消费者信心、政治选举、股票走势预测等众多领域发挥着越来越大的影响力。面向公共媒体内容开展情感分析是分析公众情感的一项基础工作。

二、数据说明

数据集基于推特用户发表的推文数据集，并且针对部分字段做出了一定的调整，所有的字段信息请以本练习赛提供的字段信息为准
字段信息内容参考如下：

tweet_id string 推文数据的唯一ID，比如test_0，train_1024
content string 推特内容
label int 推特情感的类别，共13种情感

其中训练集train.csv包含3w条数据，字段包括tweet_id,content,label；测试集test.csv包含1w条数据，字段包括tweet_id,content。

tweet_id,content,label
tweet_1,Layin n bed with a headache  ughhhh...waitin on your call...,1
tweet_2,Funeral ceremony...gloomy friday...,1
tweet_3,wants to hang out with friends SOON!,2
tweet_4,"@dannycastillo We want to trade with someone who has Houston tickets, but no one will.",3
tweet_5,"I should be sleep, but im not! thinking about an old friend who I want. but he's married now. damn, &amp; he wants me 2! scandalous!",1
tweet_6,Hmmm. 
http://www.djhero.com/ is down,4
tweet_7,@charviray Charlene my love. I miss you,1
tweet_8,cant fall asleep,3

!head data/data107057/train.csv

!head data/data107057/test.csv

!head data/data107057/submission.csv

三、数据集定义

# 目前aistudio默认最新的位2.0.7，也可以更新到2.0.8
# !pip install -U paddlenlp

# 自定义PaddleNLP dataset的read方法
import pandas as pd
train = pd.read_csv('data/data107057/train.csv')
test = pd.read_csv('data/data107057/test.csv')
sub = pd.read_csv('data/data107057/submission.csv')
print(max(train['content'].str.len()))
train.head()

	tweet_id	content	label
0	tweet_0	@tiffanylue i know i was listenin to bad habi...	0
1	tweet_1	Layin n bed with a headache ughhhh...waitin o...	1
2	tweet_2	Funeral ceremony...gloomy friday...	1
3	tweet_3	wants to hang out with friends SOON!	2
4	tweet_4	@dannycastillo We want to trade with someone w...	3

def read(pd_data):
    for index, item in pd_data.iterrows():       
        yield {'text': item['content'], 'label': item['label'], 'qid': item['tweet_id'].strip('tweet_')}

# 分割训练集、测试机
from paddle.io import Dataset, Subset
from paddlenlp.datasets import MapDataset
from paddlenlp.datasets import load_dataset

dataset = load_dataset(read, pd_data=train,lazy=False)
dev_ds = Subset(dataset=dataset, indices=[i for i in range(len(dataset)) if i % 5 == 1])
train_ds = Subset(dataset=dataset, indices=[i for i in range(len(dataset)) if i % 5 != 1])

for i in range(5):
    print(train_ds[i])

{'text': '@tiffanylue i know  i was listenin to bad habit earlier and i started freakin at his part =[', 'label': 0, 'qid': '0'}
{'text': 'Funeral ceremony...gloomy friday...', 'label': 1, 'qid': '2'}
{'text': 'wants to hang out with friends SOON!', 'label': 2, 'qid': '3'}
{'text': '@dannycastillo We want to trade with someone who has Houston tickets, but no one will.', 'label': 3, 'qid': '4'}
{'text': "I should be sleep, but im not! thinking about an old friend who I want. but he's married now. damn, &amp; he wants me 2! scandalous!", 'label': 1, 'qid': '5'}

# 在转换为MapDataset类型
train_ds = MapDataset(train_ds)
dev_ds = MapDataset(dev_ds)
print(len(train_ds))
print(len(dev_ds))

24000
6000

四、模型选择 && 数据处理

!pip install regex

Looking in indexes: https://mirror.baidu.com/pypi/simple/
Requirement already satisfied: regex in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (2021.8.28)

from paddlenlp.transformers import SkepForSequenceClassification, SkepTokenizer
# 指定模型名称，一键加载模型
model = SkepForSequenceClassification.from_pretrained(pretrained_model_name_or_path="skep_ernie_2.0_large_en", num_classes=13)
# 同样地，通过指定模型名称一键加载对应的Tokenizer，用于处理文本数据，如切分token，转token_id等。
tokenizer = SkepTokenizer.from_pretrained(pretrained_model_name_or_path="skep_ernie_2.0_large_en")

[2021-09-08 10:46:03,535] [    INFO] - Already cached /home/aistudio/.paddlenlp/models/skep_ernie_2.0_large_en/skep_ernie_2.0_large_en.pdparams
[2021-09-08 10:46:15,190] [    INFO] - Found /home/aistudio/.paddlenlp/models/skep_ernie_2.0_large_en/skep_ernie_2.0_large_en.vocab.txt

from visualdl import LogWriter

writer = LogWriter("./log")

def convert_example(example,
                    tokenizer,
                    max_seq_length=512,
                    is_test=False):
   
    # 将原数据处理成model可读入的格式，enocded_inputs是一个dict，包含input_ids、token_type_ids等字段
    encoded_inputs = tokenizer(
        text=example["text"], max_seq_len=max_seq_length)

    # input_ids：对文本切分token后，在词汇表中对应的token id
    input_ids = encoded_inputs["input_ids"]
    # token_type_ids：当前token属于句子1还是句子2，即上述图中表达的segment ids
    token_type_ids = encoded_inputs["token_type_ids"]

    if not is_test:
        # label：情感极性类别
        label = np.array([example["label"]], dtype="int64")
        return input_ids, token_type_ids, label
    else:
        # qid：每条数据的编号
        qid = np.array([example["qid"]], dtype="int64")
        return input_ids, token_type_ids, qid

def create_dataloader(dataset,
                      trans_fn=None,
                      mode='train',
                      batch_size=1,
                      batchify_fn=None):
    
    if trans_fn:
        dataset = dataset.map(trans_fn)

    shuffle = True if mode == 'train' else False
    if mode == "train":
        sampler = paddle.io.DistributedBatchSampler(
            dataset=dataset, batch_size=batch_size, shuffle=shuffle)
    else:
        sampler = paddle.io.BatchSampler(
            dataset=dataset, batch_size=batch_size, shuffle=shuffle)
    dataloader = paddle.io.DataLoader(
        dataset, batch_sampler=sampler, collate_fn=batchify_fn)
    return dataloader

import numpy as np
import paddle

@paddle.no_grad()
def evaluate(model, criterion, metric, data_loader):

    model.eval()
    metric.reset()
    losses = []
    for batch in data_loader:
        input_ids, token_type_ids, labels = batch
        logits = model(input_ids, token_type_ids)
        loss = criterion(logits, labels)
        losses.append(loss.numpy())
        correct = metric.compute(logits, labels)
        metric.update(correct)
        accu = metric.accumulate()
    # print("eval loss: %.5f, accu: %.5f" % (np.mean(losses), accu))
    model.train()
    metric.reset()
    return  np.mean(losses), accu

import os
from functools import partial


import numpy as np
import paddle
import paddle.nn.functional as F
from paddlenlp.data import Stack, Tuple, Pad

# 批量数据大小
batch_size = 60
# 文本序列最大长度166
max_seq_length = 166

# 将数据处理成模型可读入的数据格式
trans_func = partial(
    convert_example,
    tokenizer=tokenizer,
    max_seq_length=max_seq_length)

# 将数据组成批量式数据，如
# 将不同长度的文本序列padding到批量式数据中最大长度
# 将每条数据label堆叠在一起
batchify_fn = lambda samples, fn=Tuple(
    Pad(axis=0, pad_val=tokenizer.pad_token_id),  # input_ids
    Pad(axis=0, pad_val=tokenizer.pad_token_type_id),  # token_type_ids
    Stack()  # labels
): [data for data in fn(samples)]
train_data_loader = create_dataloader(
    train_ds,
    mode='train',
    batch_size=batch_size,
    batchify_fn=batchify_fn,
    trans_fn=trans_func)
dev_data_loader = create_dataloader(
    dev_ds,
    mode='dev',
    batch_size=batch_size,
    batchify_fn=batchify_fn,
    trans_fn=trans_func)


import time

# 训练轮次
epochs = 10
# 训练过程中保存模型参数的文件夹
ckpt_dir = "skep_ckpt"
# len(train_data_loader)一轮训练所需要的step数
num_training_steps = len(train_data_loader) * epochs

# Adam优化器
optimizer = paddle.optimizer.AdamW(
    learning_rate=2e-5,
    parameters=model.parameters())
# 交叉熵损失函数
criterion = paddle.nn.loss.CrossEntropyLoss()
# accuracy评价指标
metric = paddle.metric.Accuracy()

五、训练

训练且保存最佳结果

# 开启训练
global_step = 0
best_val_acc=0
tic_train = time.time()
best_accu = 0
for epoch in range(1, epochs + 1):
    for step, batch in enumerate(train_data_loader, start=1):
        input_ids, token_type_ids, labels = batch
        # 喂数据给model
        logits = model(input_ids, token_type_ids)
        # 计算损失函数值
        loss = criterion(logits, labels)
        # 预测分类概率值
        probs = F.softmax(logits, axis=1)
        # 计算acc
        correct = metric.compute(probs, labels)
        metric.update(correct)
        acc = metric.accumulate()

        global_step += 1

        if global_step % 10 == 0:
            print(
                "global step %d, epoch: %d, batch: %d, loss: %.5f, accu: %.5f, speed: %.2f step/s"
                % (global_step, epoch, step, loss, acc,
                    10 / (time.time() - tic_train)))
            tic_train = time.time()

        # 反向梯度回传，更新参数
        loss.backward()
        optimizer.step()
        optimizer.clear_grad()

        if global_step % 100 == 0:
            # 评估当前训练的模型
            eval_loss, eval_accu = evaluate(model, criterion, metric, dev_data_loader)
            print("eval  on dev  loss: {:.8}, accu: {:.8}".format(eval_loss, eval_accu))
            # 加入eval日志显示
            writer.add_scalar(tag="eval/loss", step=global_step, value=eval_loss)
            writer.add_scalar(tag="eval/acc", step=global_step, value=eval_accu)
            # 加入train日志显示
            writer.add_scalar(tag="train/loss", step=global_step, value=loss)
            writer.add_scalar(tag="train/acc", step=global_step, value=acc)
            save_dir = "best_checkpoint"
            # 加入保存       
            if eval_accu>best_val_acc:
                if not os.path.exists(save_dir):
                    os.mkdir(save_dir)
                best_val_acc=eval_accu
                print(f"模型保存在 {global_step} 步， 最佳eval准确度为{best_val_acc:.8f}！")
                save_param_path = os.path.join(save_dir, 'best_model.pdparams')
                paddle.save(model.state_dict(), save_param_path)
                fh = open('best_checkpoint/best_model.txt', 'w', encoding='utf-8')
                fh.write(f"模型保存在 {global_step} 步， 最佳eval准确度为{best_val_acc:.8f}！")
                fh.close()

六、预测

训练完成后，重启环境，释放显存，开始预测

# 数据读取
import pandas as pd
from paddlenlp.datasets import load_dataset
from paddle.io import Dataset, Subset
from paddlenlp.datasets import MapDataset


test = pd.read_csv('data/data107057/test.csv')

def read_test(pd_data):
    for index, item in pd_data.iterrows():       
        yield {'text': item['content'], 'label': 0, 'qid': item['tweet_id'].strip('tweet_')}

test_ds =  load_dataset(read_test, pd_data=test,lazy=False)
# 在转换为MapDataset类型
test_ds = MapDataset(test_ds)
print(len(test_ds))

def convert_example(example,
                    tokenizer,
                    max_seq_length=512,
                    is_test=False):
   
    # 将原数据处理成model可读入的格式，enocded_inputs是一个dict，包含input_ids、token_type_ids等字段
    encoded_inputs = tokenizer(
        text=example["text"], max_seq_len=max_seq_length)

    # input_ids：对文本切分token后，在词汇表中对应的token id
    input_ids = encoded_inputs["input_ids"]
    # token_type_ids：当前token属于句子1还是句子2，即上述图中表达的segment ids
    token_type_ids = encoded_inputs["token_type_ids"]

    if not is_test:
        # label：情感极性类别
        label = np.array([example["label"]], dtype="int64")
        return input_ids, token_type_ids, label
    else:
        # qid：每条数据的编号
        qid = np.array([example["qid"]], dtype="int64")
        return input_ids, token_type_ids, qid

def create_dataloader(dataset,
                      trans_fn=None,
                      mode='train',
                      batch_size=1,
                      batchify_fn=None):
    
    if trans_fn:
        dataset = dataset.map(trans_fn)

    shuffle = True if mode == 'train' else False
    if mode == "train":
        sampler = paddle.io.DistributedBatchSampler(
            dataset=dataset, batch_size=batch_size, shuffle=shuffle)
    else:
        sampler = paddle.io.BatchSampler(
            dataset=dataset, batch_size=batch_size, shuffle=shuffle)
    dataloader = paddle.io.DataLoader(
        dataset, batch_sampler=sampler, collate_fn=batchify_fn)
    return dataloader

from paddlenlp.transformers import SkepForSequenceClassification, SkepTokenizer
# 指定模型名称，一键加载模型
model = SkepForSequenceClassification.from_pretrained(pretrained_model_name_or_path="skep_ernie_2.0_large_en", num_classes=13)
# 同样地，通过指定模型名称一键加载对应的Tokenizer，用于处理文本数据，如切分token，转token_id等。
tokenizer = SkepTokenizer.from_pretrained(pretrained_model_name_or_path="skep_ernie_2.0_large_en")

[2021-09-08 15:32:48,977] [    INFO] - Downloading https://paddlenlp.bj.bcebos.com/models/transformers/skep/skep_ernie_2.0_large_en.pdparams and saved to /home/aistudio/.paddlenlp/models/skep_ernie_2.0_large_en
[2021-09-08 15:32:48,981] [    INFO] - Downloading skep_ernie_2.0_large_en.pdparams from https://paddlenlp.bj.bcebos.com/models/transformers/skep/skep_ernie_2.0_large_en.pdparams
100%|██████████| 1309197/1309197 [00:17<00:00, 73637.03it/s]
[2021-09-08 15:33:17,610] [    INFO] - Downloading skep_ernie_2.0_large_en.vocab.txt from https://paddlenlp.bj.bcebos.com/models/transformers/skep/skep_ernie_2.0_large_en.vocab.txt
100%|██████████| 227/227 [00:00<00:00, 1138.42it/s]

from functools import partial
import numpy as np
import paddle
import paddle.nn.functional as F
from paddlenlp.data import Stack, Tuple, Pad
batch_size=32
max_seq_length=166
# 处理测试集数据
trans_func = partial(
    convert_example,
    tokenizer=tokenizer,
    max_seq_length=max_seq_length,
    is_test=True)
batchify_fn = lambda samples, fn=Tuple(
    Pad(axis=0, pad_val=tokenizer.pad_token_id),  # input
    Pad(axis=0, pad_val=tokenizer.pad_token_type_id),  # segment
    Stack() # qid
): [data for data in fn(samples)]
test_data_loader = create_dataloader(
    test_ds,
    mode='test',
    batch_size=batch_size,
    batchify_fn=batchify_fn,
    trans_fn=trans_func)

import os

# 根据实际运行情况，更换加载的参数路径
params_path = 'best_checkpoint/best_model.pdparams'
if params_path and os.path.isfile(params_path):
    # 加载模型参数
    state_dict = paddle.load(params_path)
    model.set_dict(state_dict)
    print("Loaded parameters from %s" % params_path)

Loaded parameters from best_checkpoint/best_model.pdparams

results = []
# 切换model模型为评估模式，关闭dropout等随机因素
model.eval()
for batch in test_data_loader:
    input_ids, token_type_ids, qids = batch
    # 喂数据给模型
    logits = model(input_ids, token_type_ids)
    # 预测分类
    probs = F.softmax(logits, axis=-1)
    idx = paddle.argmax(probs, axis=1).numpy()
    idx = idx.tolist()
    qids = qids.numpy().tolist()
    results.extend(zip(qids, idx))

# 写入预测结果
with open( "submission.csv", 'w', encoding="utf-8") as f:
    # f.write("数据ID,评分\n")
    f.write("tweet_id,label\n")

    for (idx, label) in results:
axis=-1)
    idx = paddle.argmax(probs, axis=1).numpy()
    idx = idx.tolist()
    qids = qids.numpy().tolist()
    results.extend(zip(qids, idx))

# 写入预测结果
with open( "submission.csv", 'w', encoding="utf-8") as f:
    # f.write("数据ID,评分\n")
    f.write("tweet_id,label\n")

    for (idx, label) in results:
        f.write('tweet_'+str(idx[0])+","+str(label)+"\n")