我想从pyspark ml-clustering包中保存LDA模型，并在保存后将其应用于训练和测试数据集。然而，尽管播下了种子，结果却有所不同。我的代码如下：
1）导入包
from pyspark.ml.clustering import LocalLDAModel, DistributedLDAModel
from pyspark.ml.feature import CountVectorizer , IDF
2）准备数据集
countVectors = CountVectorizer(inputCol="requester_instruction_words_filtered_complete", outputCol="raw_features", vocabSize=5000, minDF=10.0)
cv_model = countVectors.fit(tokenized_stopwords_sample_df)
result_tf = cv_model.transform(tokenized_stopwords_sample_df)
vocabArray = cv_model.vocabulary
idf = IDF(inputCol="raw_features", outputCol="features")
idfModel = idf.fit(result_tf)
result_tfidf = idfModel.transform(result_tf)
result_tfidf = result_tfidf.withColumn("id", monotonically_increasing_id())
corpus = result_tfidf.select("id", "features")
3）训练LDA模型
lda = LDA(k=number_of_topics, maxIter=100, docConcentration = [alpha], topicConcentration = beta, seed = 123)
model = lda.fit(corpus)
model.save("LDA_model_saved")
topics = model.describeTopics(words_in_topic)
topics_rdd = topics.rdd
modelled_corpus = model.transform(corpus)
4）复制模型
#Prepare the data set …