基金的申购费和认购费有哪些不同?

import faiss

import numpy as np

import pandas as pd

from sklearn.feature_extraction.text import CountVectorizer

from sklearn.metrics.pairwise import cosine_similarity

加载数据

data = pd.read_csv('fund_data.csv')

数据预处理

data['Content'] = data['Content'].str.lower()

data['Content'] = data['Content'].str.replace('[^\w\s]','')

构建文本向量

vectorizer = CountVectorizer()

X = vectorizer.fit_transform(data['Content'])

features = vectorizer.get_feature_names()

计算相似度矩阵

similarity_matrix = cosine_similarity(X)

基于相似度矩阵进行聚类分析

index = faiss.IndexFlatL2(tfidf_matrix.shape[1])

index.add(tfidf_matrix.toarray())

k = 10 # 聚类个数

D, I = index.search(tfidf_matrix.toarray(), k)

输出聚类结果

for i in range(k):

cluster = []

for j in range(len(I)):

if I[j][0] == i:

cluster.append(data['Content'][j])

print(f"Cluster {i+1}:")

print(cluster)

print()