python 机器学习 (数据挖掘 —— 无监督学习（聚类）

数据挖掘 —— 无监督学习（聚类）

1. K-means1.1 生成指定形状的随机数据1.2 进行聚类1.3 结果

2. 系统聚类2.1 代码2.2 结果

3 DBSCAN3.1 参数选择3.2 代码3.3 结果

1. K-means

K-Means为基于切割的聚类算法

1.1 生成指定形状的随机数据

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.cluster import KMeans

# *************** 生成指定形状的随机数据 *****************

from sklearn.datasets import make_circles,make_moons,make_blobs

n_samples = 1000

# 生成环装数据

circles = make_circles(n_samples = n_samples,factor = 0.5,noise = 0.05)

"""

n_samples: 为样本点个数

factor:为大圆与小圆的间距

"""

# 生成月牙形数据

moons = make_moons(n_samples = n_samples,noise = 0.05)

# 生成簇状数据

blobs = make_blobs(n_samples = n_samples,random_state = 100,center_box = (-10,10),cluster_std = 1,centers = 3)

"""

random_state: 随机数种子，多少代保持随机数不变

center_box: 中心确定后的数据边界 默认(-10,10)

cluster_std：数据分布的标准差，决定各类数据的紧凑程度,默认为1.0

centers：产生数据点中心的个数 默认为3

"""

# 产生随机数

random_data = np.random.rand(n_samples,2),np.array([0 for i in range(n_samples)])

datasets = [circles,moons,blobs,random_data]

fig = plt.figure(figsize=(20,8))

1.2 进行聚类

colors = "rgbykcm"

for index,data in enumerate(datasets):

X = data[0]

Y_old = data[1]

km_cluster = KMeans(n_clusters = 2)

km_cluster.fit(X)

Y_new = km_cluster.labels_

fig.add_subplot(2,len(datasets),index+1)

[plt.scatter(X[i,0],X[i,1],color = colors[Y_old[i]]) for i in range(len(X[:,0]))]

fig.add_subplot(2,len(datasets),index+5)

[plt.scatter(X[i,0],X[i,1],color = colors[Y_new[i]]) for i in range(len(X[:,0]))]

1.3 结果

2. 系统聚类

2.1 代码

AgglomerativeClustering(n_clusters,affinity,linkage)

affinity:

“euclidean”,欧几里得距离“l1”, “l2”,“manhattan”, 曼哈顿距离“cosine”, 余弦距离“precomputed”预输入 需要输出距离矩阵

linkage：{“ward”, “complete”, “average”, “single”}, default=”ward”

from sklearn.datasets import make_circles,make_blobs,make_moons

from sklearn.cluster import AgglomerativeClustering

import matplotlib.pyplot as plt

import numpy as np

import pandas as pd

# 准备数据

n_samples = int(1e3)

circles = make_circles(n_samples = n_samples,noise = 0.05,factor = 0.5,random_state = 10)

moons = make_moons(n_samples = n_samples,noise = 0.05,random_state = 10)

blobs = make_blobs(n_samples=n_samples,centers = 4,cluster_std = 0.1,center_box = (-1,1),random_state = 10)

np.random.seed(10)

random_data = (np.random.rand(n_samples,2),np.zeros((n_samples)).astype(np.int))

datasets = [circles,moons,blobs,random_data]

fig = plt.figure(figsize = (20,8),dpi = 72)

colors = "rgbk"

for index,data in enumerate(datasets):

X = data[0]

Y = data[1]

agg_cluster = AgglomerativeClustering(n_clusters = 2,affinity = "euclidean",linkage = "average")

Y_predict = agg_cluster.fit(X).labels_

fig.add_subplot(2,len(datasets),index + 1)

[plt.scatter(X[i,0],X[i,1],color = colors[Y[i]]) for i in range(len(X[:,0]))]

fig.add_subplot(2,len(datasets),index + 5)

[plt.scatter(X[i,0],X[i,1],color = colors[Y_predict[i]]) for i in range(len(X[:,0]))]

2.2 结果

3 DBSCAN

3.1 参数选择

半径：k距离帮助设置半径，也就是要找到突变点， 即选中一个点，计算它和所有其他点的距离， 从小到大排序，发现距离突变点。 需要做大量实验观察。MinPts：先设置偏小一些，然后进行多次尝试

3.2 代码

# 导入聚类数据

n_samples = 1000

from sklearn.datasets import make_circles,make_moons,make_blobs

from sklearn.cluster import DBSCAN

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

circles = make_circles(n_samples = n_samples,noise = 0.05,factor = 0.5,random_state = 10)

moons = make_moons(n_samples = n_samples,noise = 0.05,random_state = 10)

blobs = make_blobs(n_samples = n_samples,centers = 3,cluster_std = 0.1,center_box = (-1,1),random_state = 10)

np.random.seed(10)

random_data = (np.random.rand(n_samples,2),np.zeros((n_samples)).astype(np.int))

datasets = [circles,moons,blobs,random_data]

fig = plt.figure(figsize = (20,8),dpi = 72)

colors = "rgbky"

for index,data in enumerate(datasets):

X = data[0]

Y_old = data[1]

dbscan_model = DBSCAN(eps = 0.1,min_samples = 20)

dbscan_model.fit(X)

Y_new = dbscan_model.labels_

fig.add_subplot(2,len(datasets),index+1)

[plt.scatter(X[i,0],X[i,1],color = colors[Y_old[i]]) for i in range(len(X[:,0]))]

plt.title("original algorithm")

fig.add_subplot(2,len(datasets),index + 5)

[plt.scatter(X[i,0],X[i,1],color = colors[Y_new[i]]) for i in range(len(X[:,0]))]

plt.title("DBSCA algorithm")

3.3 结果

by CyrusMay 2022 04 05

推荐阅读

 您阅读本篇文章共花了：