来自两个数据帧的共现矩阵。Python

import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer

# 创建两个数据帧
df1 = pd.DataFrame({'text': ['I love cloud computing', 'Cloud computing is the future']})
df2 = pd.DataFrame({'text': ['Cloud computing is amazing', 'I want to learn cloud computing']})

# 将两个数据帧中的文本合并
corpus = df1['text'].tolist() + df2['text'].tolist()

# 使用CountVectorizer计算共现矩阵
vectorizer = CountVectorizer()
co_occurrence_matrix = vectorizer.fit_transform(corpus).T.dot(vectorizer.fit_transform(corpus))

# 打印共现矩阵
print(co_occurrence_matrix)