从实体中提取标签并将其添加到新列中

import pandas as pd
import spacy

# 加载英文语言模型
nlp = spacy.load('en_core_web_sm')

# 示例数据
data = {'text': ['John is a software engineer', 'Mary works at ABC Company']}
df = pd.DataFrame(data)

# 创建新列
df['labels'] = ''

# 实体识别和标签提取
for i, row in df.iterrows():
    doc = nlp(row['text'])
    labels = [ent.text for ent in doc.ents]
    df.at[i, 'labels'] = ', '.join(labels)

# 打印结果
print(df)

                          text        labels
0  John is a software engineer  John
1   Mary works at ABC Company  Mary, ABC Company