网站设计分享,接网站建设_网站设计,山西省建设厅网站,管理咨询公司好不好做平台#xff1a;window10#xff0c;python3.11.4#xff0c;pycharm
框架#xff1a;keras
编写日期#xff1a;20230903
数据集#xff1a;英语#xff0c;自编#xff0c;训练集和测试集分别有4个样本#xff0c;标签有积极和消极两种
环境搭建
新建文件夹window10python3.11.4pycharm
框架keras
编写日期20230903
数据集英语自编训练集和测试集分别有4个样本标签有积极和消极两种
环境搭建
新建文件夹进入目录
创建虚拟环境
virtualenv venv
激活虚拟环境
venv\Scripts\activate
安装依赖库
pip install tensorflow
代码编写
目录下创建main.py进入pycharm打开文件夹编写代码
包引入
import numpy as np
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
from keras.models import Sequential
from keras.layers import SimpleRNN, Dense
数据集处理
# 训练集
train_texts [I love this movie,This is the worst film I have ever seen.,An enjoyable and thought-provoking experience.,I think it is boring]train_labels np.array([1, 0, 1, 0]) # 0代表消极1代表积极# 测试集
test_texts [What a waste of my time,One of the best movies Ive seen in a long time,Amazing acting!,This movie look awful]
test_labels np.array([0, 1, 1, 0])
# 构建分词器
tokenizer Tokenizer(num_words100)
# 用训练集与测试集训练分词器
tokenizer.fit_on_texts(train_texts test_texts)
# 数据集序列化将文本转成数字便于机器处理
train_sequences tokenizer.texts_to_sequences(train_texts)
test_sequences tokenizer.texts_to_sequences(test_texts)
# 数据填充到20超过的就截断post在末尾填充
# 由于每个训练文本有不同的单词数需要统一
train_data pad_sequences(train_sequences, maxlen20, paddingpost)
test_data pad_sequences(test_sequences, maxlen20, paddingpost)
模型搭建和训练
# 创建一个线性模型容器
model Sequential()
#添加RNN层神经元数量为100输入数据形状为201
model.add(SimpleRNN(100, input_shape(20, 1)))
# 添加1个输出激活函数为sigmoid的全连接层
model.add(Dense(1, activationsigmoid))
# 优化器Adam损失计算方法二元交叉熵评估依据准确率
model.compile(optimizeradam, lossbinary_crossentropy, metrics[accuracy])
# 输出模型结构
model.summary()
#训练模型训练5轮每次训练2个样本
model.fit(train_data, train_labels, epochs5, batch_size2, validation_data(test_data, test_labels))模型评估
# 打印评估信息
print(Evaluating the model...)
#进行评估
model.evaluate(test_data, test_labels)
所有代码集合
import numpy as np
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
from keras.models import Sequential
from keras.layers import SimpleRNN, Densetrain_texts [I love this movie,This is the worst film I have ever seen.,An enjoyable and thought-provoking experience.,I think it is boring]
train_labels np.array([1, 0, 1, 0])test_texts [What a waste of my time,One of the best movies Ive seen in a long time,Amazing acting!,This movie look awful]
test_labels np.array([0, 1, 1, 0])tokenizer Tokenizer(num_words1000)
tokenizer.fit_on_texts(train_texts test_texts)train_sequences tokenizer.texts_to_sequences(train_texts)
test_sequences tokenizer.texts_to_sequences(test_texts)train_data pad_sequences(train_sequences, maxlen20, paddingpost)
test_data pad_sequences(test_sequences, maxlen20, paddingpost)model Sequential()
model.add(SimpleRNN(100, input_shape(20, 1)))
model.add(Dense(1, activationsigmoid))
model.compile(optimizeradam, lossbinary_crossentropy, metrics[accuracy])
model.summary()model.fit(train_data, train_labels, epochs5, batch_size2, validation_data(test_data, test_labels))print(Evaluating the model...)
model.evaluate(test_data, test_labels)运行图片截取
文件目录 控制台
