机器学习基于组平均的AGNES算法,支持多维数组,距离用欧式距离
Posted Laura科技
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了机器学习基于组平均的AGNES算法,支持多维数组,距离用欧式距离相关的知识,希望对你有一定的参考价值。
如果需要完整代码可以关注下方公众号,后台回复“代码”即可获取,阿光期待着您的光临~
文章目录
2021人工智能领域新星创作者,带你从入门到精通,该博客每天更新,逐渐完善各个知识体系的文章,帮助大家更高效学习。
自己实现基于组平均的AGNES算法,语言不限。要能支持多维数组,距离用欧式距离
- numpy实现
- 相似性度量方式:average-cluster
- 绘制层次树图
编程实现
"""
* Created with PyCharm
* 作者: Laura
* 日期: 2021/11/6
* 时间: 12:10
* 描述: 基于组平均的AGNES算法,支持多维数组,距离用欧式距离
"""
import numpy as np
import pandas as pd
from scipy.cluster.hierarchy import dendrogram,linkage
from scipy.spatial.distance import squareform
import matplotlib.pyplot as plt
import random
class AGNES():
def __init__(self, data, cluster = 2):
self.cluster = cluster
self.data = data
self.distance_matrix = []
self.dic = {}
self.dic_ = {}
self.index = ['A', 'B', 'C', 'D', 'E']
self.columns = ['A', 'B', 'C', 'D', 'E']
def init_data(self, data, dic):
dic={i:[chr(ord('A')+i)] for i in range(len(data))}
data = self.calculate_distance(data)
self.distance_matrix = data.copy()
row, col = np.diag_indices_from(data)
temp = data.max() + 1
data[row, col] = temp
row_, col_ = np.triu_indices_from(data, k = 0)
data[row_, col_] = temp
return data, dic
def train(self, cluster, method='train'):
data = self.data.copy()
dic = {}
data, dic = self.init_data(data, dic)
k = 0
while k < len(data) - cluster:
location = np.where(data == data.min()) # 找到此时矩阵距离最小值的坐标
x, y = location[0][0], location[1][0] # 分别获取横纵坐标
x_ = self.index[x]
y_ = self.columns[y] # 获取对应样本信息
x_key = '-'
y_key = '-'
for key, value in dic.items():
if x_ in value:
x_key = key
if y_ in value:
y_key = key
dic[y_key].extend(dic[x_key])
dic.pop(x_key)
slic = dic[y_key] # 更新簇的样本
num = len(dic[y_key]) # 簇内样本的数目
data_sum = np.zeros(5)
for item in slic:
data_sum += data[:, self.index.index(item)]
data_sum /= num
for item in slic:
# data[index.index(item)]=data_sum
data[:, self.index.index(item)] = data_sum
row, col = np.diag_indices_from(data)
temp = data.max() + 999
data[row, col] = temp
row_,col_ = np.triu_indices_from(data, k=0)
data[row_, col_] = temp
k += 1
if method == 'train':
self.dic = dic
else:
self.dic_ = dic
def draw(self):
dists = squareform(self.distance_matrix)
linkage_type = 'average' # single,complete,average不同方式
linkage_matrix = linkage(dists, linkage_type)
dendrogram(linkage_matrix, labels = self.index)
plt.show()
def process(self):
for cluster in range(1, self.distance_matrix.shape[0] + 1):
self.train(cluster, 'other')
print('簇数:', cluster, self.dic_)
def calculate_distance(self, data):
distance_matrix = np.zeros((data.shape[0],data.shape[1]))
for i in range(data.shape[0]):
for j in range(data.shape[1]):
distance_matrix[i][j] = np.sum((data[i] - data[j])**2)
return distance_matrix
data = np.random.rand(5, 5)
model = AGNES(data)
model.train(cluster = 2)
model.process()
model.draw()
以上是关于机器学习基于组平均的AGNES算法,支持多维数组,距离用欧式距离的主要内容,如果未能解决你的问题,请参考以下文章