加载数据集

def load_dataset(): # 样本数据 data = ['I love this movie!', 'This film is great', 'Amazing movie', 'I do not like this movie', 'This movie is terrible', 'I hate this film'] # 对应的标签 labels = [1, 1, 1, 0, 0, 0] # 1表示正面评价，0表示负面评价 return data, labels

对数据进行预处理，将文本转化为数字

def preprocess(data, labels): # 创建一个包含所有单词的词汇表 vocab = set(word for sentence in data for word in sentence.split()) # 将词汇表转化为数字 word_to_idx = {word: i for i, word in enumerate(vocab)} # 将每个句子转化为数字序列 data = [[word_to_idx[word] for word in sentence.split()] for sentence in data] # 将标签转化为Tensor类型 labels = torch.tensor(labels) # 返回数字化的数据和标签 return data, labels

加载数据集并进行预处理

data, labels = load_dataset() data, labels = preprocess(data, labels)

打印一条样本数据和标签

print('样本数据：', data[0]) print('标签：', labels[0])