python聚类结果可视化_【Python】使用BIRCH算法对KDDCUP99数据集的聚类结果进行可视化/计算香农熵...

# coding='utf-8'

from sklearn.cluster import Birch

from time import time

import numpy as np

import matplotlib.pyplot as plt

import pandas as pd

from sklearn import datasets

from sklearn.manifold import TSNE

# 用来正常显示中文标签

plt.rcParams['font.sans-serif'] = ['SimHei']

# 用来正常显示负号

plt.rcParams['axes.unicode_minus'] = False

def get_tsne_data(dataname=u"../datasets/one_hot_kdd_tsne.csv"):

data_tsen = pd.read_csv(dataname, encoding="utf-8", header=None, nrows=10000)

return data_tsen

def get_data(dataname=u"../datasets/one_hot_kdd.csv"):

data_label = pd.read_csv(dataname, encoding="utf-8", header=None, nrows=10000)

dataset, label = data_label, data_label.pop(38)

return dataset, label

def birch(data, tsnedata):

X = data

birch = Birch(n_clusters=4, threshold=0.6)

##训练数据

labels = birc