搜狗新闻文本分类完整代码/数据集/实验报告

 数据集

http://t.csdnimg.cn/rP6qxhttp://t.csdnimg.cn/rP6qx实验报告

http://t.csdnimg.cn/1NuSahttp://t.csdnimg.cn/1NuSa

import os
import re

import pandas as pd
import jieba
import numpy as np
#from keras.src.optimizers import Adam
#from keras.optimizer_v1 import Adam
from tensorflow.keras.optimizers import Adam
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, f1_score, roc_auc_score
from sklearn.svm import SVC
from xgboost import XGBClassifier
from sklearn.preprocessing import LabelEncoder
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import matplotlib
import numpy as np
from keras.models import Sequential
from keras.layers import Dense, LSTM, Embedding, SpatialDropout1D
#from keras.utils import to_categorical
from sklearn.model_selection import train_test_split
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
matplotlib.rcParams['font.sans-serif'] = ['SimHei'] #中文字体"SimHei"
matplotlib.rcParams['axes.unicode_minus'] = False  # 解决保存图像是负号'-'显示为方块的问题
from prettytable import PrettyTable
import tensorflow as tf



# 读取数据
data_path = 'CH10data/搜狗文本分类语料库迷你版'  # 更改为你的数据集路径
categories = ['体育', '健康', '军事', '教育',