如何在Python中对文本使用双正态分离

import numpy as np
from scipy.stats import norm
import matplotlib.pyplot as plt

text_data = ["This is the first text.", "This is the second text.", "This is the third text."]

from sklearn.feature_extraction.text import TfidfVectorizer

vectorizer = TfidfVectorizer()
text_vectors = vectorizer.fit_transform(text_data)

mean_values = np.mean(text_vectors, axis=1)
std_values = np.std(text_vectors, axis=1)

threshold = 0.5  # 设置分离阈值

# 根据均值和标准差计算分离点
separation_point = norm.ppf(threshold, loc=mean_values, scale=std_values)

# 根据分离点将文本分为两个类别
class1 = [text_data[i] for i, value in enumerate(text_vectors) if value <= separation_point[i]]
class2 = [text_data[i] for i, value in enumerate(text_vectors) if value > separation_point[i]]