根据数据将一个主题划分为不同的主题

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

# 示例数据
data = [
    "Machine learning is fascinating.",
    "Natural language processing is a subfield of artificial intelligence.",
    "Topic modeling helps in discovering hidden topics in text data.",
    "Deep learning is a subset of machine learning.",
    "Information retrieval is important for finding relevant information."
]

# 数据预处理
vectorizer = CountVectorizer(stop_words='english')
X = vectorizer.fit_transform(data)

# 主题建模
lda = LatentDirichletAllocation(n_components=3, random_state=42)
lda.fit(X)

# 输出每个主题的关键词
feature_names = vectorizer.get_feature_names_out()
for topic_idx, topic in enumerate(lda.components_):
    print(f"Topic #{topic_idx + 1}:")
    print(" ".join([feature_names[i] for i in topic.argsort()[:-10 - 1:-1]]))

# 输出每个文档的主题分布
for doc_idx, doc in enumerate(X):
    print(f"Document #{doc_idx + 1}:")
    print(lda.transform(doc.reshape(1, -1)))