import random import jieba from keras.utils import np_utils from keras.models import Sequential from keras.layers import Dense from keras.preprocessing.text import Tokenizer def getStopWords(): with open('./Data/stopwords.dic', 'r', encoding='utf-8') as fr: stopWords = fr.read().split('\n')[:-1] return set(stopWords) def keywordExtraction(sentence, stopWords): allWords = list(jieba.cut(sentence)) return [word for word in allWords if word not in stopWords and ~word.isdigit()] def neuralNetworkClassify(vectorX, vectorY): index = [i for i in range(len(vectorX))] random.shuffle(index) vectorX = vectorX[index] vectorY = vectorY[index] model = Sequential() model.add(Dense(64, input_shape=(13835,), activation='relu'))#全连接层 model.add(Dense(64, activation='relu')) model.add(Dense(3, activation='softmax')) model.comp
基于Keras的MLP模型(情感分析)
最新推荐文章于 2024-08-29 17:05:54 发布
该博客介绍了一个基于Keras的情感分析模型。首先,通过jieba分词并去除停用词来提取关键词。然后,利用Tokenizer进行文本预处理,将文本转换为二进制矩阵。最后,构建了一个包含两个隐藏层的全连接神经网络,并使用adam优化器进行训练。
摘要由CSDN通过智能技术生成