一个模型与 csv 矩阵的主题相似度

Topic Similarity in one model to csv Matrix

我想生成一个主题到主题矩阵,以便使用来自 gensim LDA 的函数 gensim.models.ldamodel.diff 找到类似的主题来生成内部集群。 如何将生成的数据保存到 csv 中,其中包含主题和单元格中的距离(在本例中为 hellinger 距离)? 此代码对我不起作用:

from gensim import models
import pandas

dateiname_model1 = "lda.model"
model1 =  models.LdaModel.load(dateiname_model1)

topic_over_topic = model1.diff(model1, annotation=True)

topic_over_topic_speicherpfad = "topic_over_topic_similarity.csv"
pandas.DataFrame(topic_over_topic).to_csv(topic_over_topic_speicherpfad, sep=';')

它适用于代码 topic_over_topic, annotation = model1.diff(model1, annotation=True):

from gensim import models
import pandas

dateiname_model1 = "lda.model"
model1 =  models.LdaModel.load(dateiname_model1)

topic_over_topic, annotation = model1.diff(model1, annotation=True)

topic_over_topic_speicherpfad = "topic_over_topic_similarity.csv"
pandas.DataFrame(topic_over_topic).to_csv(topic_over_topic_speicherpfad, sep=';')