【人工智能项目】Bert实现泰迪杯论坛文本分类任务

【人工智能项目】Bert实现泰迪杯论坛文本分类任务

本次又是bert任务，用bert来实现论文文本分类的任务。那么接着走起走起走起！！！

运行环境

本次运行环境在google colab白嫖的gpu进行加速训练。

!nvidia-smi

导包

#! -*- coding:utf-8 -*-
import re, os, json, codecs, gc
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import os
import time
import datetime

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.utils import class_weight as cw

from keras import Sequential

from keras.models import Model

from keras.layers import LSTM,Activation,Dense,Dropout,Input,Embedding,BatchNormalization,Add,concatenate,Flatten
from keras.layers import Conv1D,Conv2D,Convolution1D,MaxPool1D,SeparableConv1D,SpatialDropout1D,GlobalAvgPool1D,GlobalMaxPool1D,GlobalMaxPooling1D
from keras.layers.pooling import _GlobalPooling1D
from keras.layers import MaxPooling2D,GlobalMaxPooling2D,GlobalAveragePooling2D

from keras.optimizers import RMSprop,Adam

from keras.preprocessing.text import Tokenizer
from keras.preprocessing import sequence

from keras.utils import to_categorical

from keras.callbacks import EarlyStopping
from keras.callbacks import ModelCheckpoint
from keras.callbacks import ReduceLROnPlateau

%matplotlib inline

import warnings
warnings.filterwarnings("ignore")

读取文件

import xlrd

train_dataset_path = "train.xlsx"
test_dataset_path = "test.xlsx"

train_content=xlrd.open_workbook(filename=train_dataset_path,encoding_override='gbk')
test_content=xlrd.open_workbook(filename=test_dataset_path,encoding_override='gbk')

train_df=pd.read_excel(train_content,engine='xlrd',header=0,names=["id","user_id","target","time","text","labels"])
test_df=pd.read_excel(test_content,engine='xlrd',header=0,names=["id","user_id","target","time","text","labels"])

train_df

test_df

合并

train_df["ocr"] = train_df["target"] + "  " + train_df["text"]
test_df["ocr"] = test_df["target"] + "  " + test_df["text"]

train_df

标签统计

sns.countplot(train_df["labels"])
plt.xlabel("Label")
plt.title("News sentiment analysis")

train_df["labels"].unique()

array([’__label__城乡建设’, ‘__label__环境保护’, ‘__label__交通运输’, ‘__label__教育文体’,
‘__label__劳动和社会保障’, ‘__label__商贸旅游’, ‘__label__卫生计生’], dtype=object)

# 统计新闻数据中情感，正面情绪对应0 中性情绪对应1 负面情绪对应2
dit = {'__label__城乡建设':0,'__label__环境保护':1,"__label__交通运输":2,"__label__教育文体":3,"__label__劳动和社会保障":4,"__label__商贸旅游":5,"__label__卫生计生":6}
train_df['label'] = train_df['labels'].map(dit)

sns.countplot(train_df["label"])
plt.xlabel("Label")
plt.title("News sentiment analysis")

最终数据集

train_df = train_df[["ocr","label"]]

from sklearn.utils import shuffle
train_df = shuffle(train_df).reset_index(drop=True)

安装bert

!pip install keras_bert

下载预训练的模型权重

!wget -c https://storage.googleapis.com/chineseglue/pretrain_models/roeberta_zh_L-24_H-1024_A-16.zip

解压缩文件

!unzip roeberta_zh_L-24_H-1024_A-16.zip

训练

#! -*- coding:utf-8 -*-
import re, os, json, codecs, gc
import numpy as np
import pandas as pd
from random import choice
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import KFold
from keras_bert import load_trained_model_from_checkpoint, Tokenizer


from keras.layers import *
from keras.callbacks import *
from keras.models import Model
import keras.backend as K
from keras.optimizers import Adam

maxlen = 256
config_path = './bert_config_large.json'
# checkpoint_path = '/export/home/liuyuzhong/kaggle/bert/chinese_L-12_H-768_A-12/bert_model.ckpt'
checkpoint_path = './roberta_zh_large_model.ckpt'
dict_path = './vocab.txt'

token_dict = {}
with codecs.open(dict_path, 'r', 'utf8') as reader:
    for line in reader:
        token = line.strip()
        token_dict[token] = len(token_dict)

class OurTokenizer(Tokenizer):
    def _tokenize(self, text):
        R = []
        for c in text:
            if c in self._token_dict:
                R.append(c)
            elif self._is_space(c):
                R.append('[unused1]') # space类用未经训练的[unused1]表示
            else:
                R.append('[UNK]') # 剩余的字符是[UNK]
        return R

tokenizer = OurTokenizer(token_dict)

def seq_padding(X, padding=0):
    L = [len(x) for x in X]
    ML = max(L)
    return np.array([
        np.concatenate([x, [padding] * (ML - len(x))]) if len(x) < ML else x for x in X
    ])

class data_generator:
    def __init__(self, data, batch_size=4, shuffle=True):
        self.data = data
        self.batch_size = batch_size
        self.shuffle = shuffle
        self.steps = len(self.data) // self.batch_size
        if len(self.data) % self.batch_size != 0:
            self.steps += 1
    def __len__(self):
        return self.steps
    def __iter__(self):
        while True:
            idxs = list(range(len(self.data)))
            
            if self.shuffle:
                np.random.shuffle(idxs)
            
            X1, X2, Y = [], [], []
            for i in idxs:
                d = self.data[i]
                text = d[0][:maxlen]
                x1, x2 = tokenizer.encode(first=text)
                y = d[1]
                X1.append(x1)
                X2.append(x2)
                Y.append([y])
                if len(X1) == self.batch_size or i == idxs[-1]:
                    X1 = seq_padding(X1)
                    X2 = seq_padding(X2)
                    Y = seq_padding(Y)
                    yield [X1, X2], Y[:, 0, :]
                    [X1, X2, Y] = [], [], []


from keras.metrics import top_k_categorical_accuracy
# 
def acc_top5(y_true, y_pred):
    return top_k_categorical_accuracy(y_true, y_pred, k=5)
# 模型           
def build_bert(nclass):
    bert_model = load_trained_model_from_checkpoint(config_path, checkpoint_path, seq_len=None)

    for l in bert_model.layers:
        l.trainable = True

    x1_in = Input(shape=(None,))
    x2_in = Input(shape=(None,))

    x = bert_model([x1_in, x2_in])
    x = Lambda(lambda x: x[:, 0])(x)
    p = Dense(nclass, activation='softmax')(x)

    model = Model([x1_in, x2_in], p)
    model.compile(loss='categorical_crossentropy', 
                  optimizer=Adam(1e-5),
                  metrics=['accuracy', acc_top5])
    print(model.summary())
    return model
    

from keras.utils import to_categorical

DATA_LIST = []
# 改
for data_row in train_df.iloc[:].itertuples():
    DATA_LIST.append((data_row.ocr, to_categorical(data_row.label, 7)))
DATA_LIST = np.array(DATA_LIST)

DATA_LIST_TEST = []
for data_row in test_df.iloc[:].itertuples():
    DATA_LIST_TEST.append((data_row.ocr, to_categorical(0, 7)))
DATA_LIST_TEST = np.array(DATA_LIST_TEST)

# k者交叉验证
def run_cv(nfold, data, data_label, data_test):
    kf = KFold(n_splits=nfold, shuffle=True, random_state=520).split(data)
    # 改
    train_model_pred = np.zeros((len(data), 7))
    test_model_pred = np.zeros((len(data_test), 7))
    k = 0
    for i, (train_fold, test_fold) in enumerate(kf):
        X_train, X_valid, = data[train_fold, :], data[test_fold, :]
        # 改
        model = build_bert(7)
        # 
        early_stopping = EarlyStopping(monitor='val_acc', patience=3)
        plateau = ReduceLROnPlateau(monitor="val_acc", verbose=1, mode='max', factor=0.5, patience=2)
        checkpoint = ModelCheckpoint('./bert_dump/' + str(i) + '.hdf5', monitor='val_acc', 
                                         verbose=2, save_best_only=True, mode='max',save_weights_only=True)
        
        train_D = data_generator(X_train, shuffle=True)
        valid_D = data_generator(X_valid, shuffle=True)
        test_D = data_generator(data_test, shuffle=False)
        
        history = model.fit_generator(
            train_D.__iter__(),
            steps_per_epoch=len(train_D),
            epochs=2,
            validation_data=valid_D.__iter__(),
            validation_steps=len(valid_D),
            callbacks=[early_stopping, plateau, checkpoint],
        )
 

        # return model
        train_model_pred[test_fold, :] =  model.predict_generator(valid_D.__iter__(), steps=len(valid_D),verbose=1)
        test_model_pred += model.predict_generator(test_D.__iter__(), steps=len(test_D),verbose=1)
        
        if k == 0:
          break

        del model; gc.collect()
        K.clear_session()
        
        # break
        
    return train_model_pred, test_model_pred,history

train_model_pred, test_model_pred,history = run_cv(2, DATA_LIST, None, DATA_LIST_TEST)

绘制训练过程中的loss和acc

# 绘制训练过程中的 loss 和 acc 变化曲线
import matplotlib.pyplot as plt
%matplotlib inline

def history_plot(history_fit):
    plt.figure(figsize=(12,6))
    
    # summarize history for accuracy
    plt.subplot(121)
    plt.plot(history_fit.history["accuracy"])
    plt.plot(history_fit.history["val_accuracy"])
    plt.title("model accuracy")
    plt.ylabel("accuracy")
    plt.xlabel("epoch")
    plt.legend(["train", "valid"], loc="upper left")
    
    # summarize history for loss
    plt.subplot(122)
    plt.plot(history_fit.history["loss"])
    plt.plot(history_fit.history["val_loss"])
    plt.title("model loss")
    plt.ylabel("loss")
    plt.xlabel("epoch")
    plt.legend(["train", "valid"], loc="upper left")
    
    plt.show()

history_plot(history)

test_pred = [np.argmax(x) for x in test_model_pred]
test_df['labels'] = test_pred

test_df['labels']

test_df

# 统计新闻数据中情感，正面情绪对应0 中性情绪对应1 负面情绪对应2
dit = {0:'__label__城乡建设',1:'__label__环境保护',2:"__label__交通运输",3:"__label__教育文体",4:"__label__劳动和社会保障",5:"__label__商贸旅游",6:"__label__卫生计生"}
test_df['label'] = test_df['labels'].map(dit)

test_df

predict_df = test_df[["id","label"]]

predict_df

predict_df.to_csv('res.csv',index=None,encoding='utf_8_sig')

那么本次到此结束，回头见！！！