在Python/ R中查找LDA之后的不同主题的数量

import gensim
from gensim import corpora
from gensim.models import LdaModel
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize

# 加载停用词
stop_words = set(stopwords.words('english'))

# 加载数据集
data = ['Text document 1', 'Text document 2', 'Text document 3', ...]

# 数据预处理
processed_data = []
for doc in data:
    # 分词
    tokens = word_tokenize(doc)
    # 去除停用词、标点符号、数字等
    tokens = [token.lower() for token in tokens if token.isalpha() and token.lower() not in stop_words]
    # 词干化或词形还原
    # ...
    processed_data.append(tokens)

# 构建词袋模型
dictionary = corpora.Dictionary(processed_data)
corpus = [dictionary.doc2bow(doc) for doc in processed_data]

# 训练LDA模型
num_topics = 5  # 设置主题数量
lda_model = LdaModel(corpus, num_topics=num_topics, id2word=dictionary)

# 获取主题分布
topic_distribution = []
for doc in corpus:
    doc_topics = lda_model.get_document_topics(doc)
    topic_distribution.append(doc_topics)

# 统计不同主题的数量
topic_count = [len(set([topic for topic, _ in doc_topics])) for doc_topics in topic_distribution]

# 打印不同主题的数量
print(topic_count)