将伯特编码应用于熊猫数据的所有值

Question

我正在尝试获取数据格式中所有值的bert嵌入。

我的代码看起来是：

from sentence_transformers import SentenceTransformer, util
model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
import pandas as pd

sentences =[ ["I'm happy", "I'm full of happiness"], ["I am sam", "I am good"]]

df = pd.DataFrame(sentences)

encoded_df = df.applymap(model.encode(convert_to_tensor=True))

面对以下错误：

encode() missing 1 required positional argument: 'sentences'

有什么方法可以做到这一点吗？

Answer 1

您可以使用

encoded_df = df.applymap(lambda x: model.encode(x, convert_to_tensor=True))