foussats/TP_Clustering
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Creation of git and reorganisation of the code

Browse source
This commit is contained in:
Foussats Morgane 2021-10-28 17:41:43 +02:00
commit 3c778aedc1
12 changed files with 700 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

36
artificial/agglomerative.py Normal file
View file

@ -0,0 +1,36 @@
from scipy.io import arff
import numpy as np
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
from sklearn import metrics
from sklearn.cluster import AgglomerativeClustering
from sklearn.cluster import DBSCAN
import hdbscan
n_clusters = 2
data = arff.loadarff('diamond9.arff')[0]
data_final = []
x_list = []
y_list = []
for (x, y, z) in data :
x_list.append(x)
y_list.append(y)
data_final.append([x,y])
clustering = AgglomerativeClustering(n_clusters = n_clusters, linkage='average').fit(data_final)
colors = clustering.labels_
plt.scatter(x_list, y_list, c=colors, s=5)
plt.show()
silh = metrics.silhouette_score(data_final, colors, metric='euclidean')
dbsc = metrics.davies_bouldin_score(data_final, colors)
caha = metrics.calinski_harabasz_score(data_final, colors)
print("Coefficient de silhouette : ", silh)
print("Indice de Davies Bouldin : ", dbsc)
print("Indice de calinski harabasz : ", caha)

30
artificial/dbscan.py Normal file
View file

@ -0,0 +1,30 @@
from scipy.io import arff
import numpy as np
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
from sklearn import metrics
from sklearn.cluster import DBSCAN
data = arff.loadarff('diamond9.arff')[0]
data_final = []
x_list = []
y_list = []
for (x, y, z) in data :
x_list.append(x)
y_list.append(y)
data_final.append([x,y])
clustering = DBSCAN(eps=0.5, min_samples=2).fit(data_final)
colors = clustering.labels_
plt.scatter(x_list, y_list, c=colors, s=5)
plt.show()
silh = metrics.silhouette_score(data_final, colors, metric='euclidean')
dbsc = metrics.davies_bouldin_score(data_final, colors)
caha = metrics.calinski_harabasz_score(data_final, colors)
print("Coefficient de silhouette : ", silh)
print("Indice de Davies Bouldin : ", dbsc)
print("Indice de calinski harabasz : ", caha)

34
artificial/hdbscan.py Normal file
View file

@ -0,0 +1,34 @@
from scipy.io import arff
import numpy as np
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
from sklearn import metrics
import hdbscan
#WARNING: rename the file and do not call it HDBSCAN
n_clusters = 2
data = arff.loadarff('diamond9.arff')[0]
data_final = []
x_list = []
y_list = []
for (x, y, z) in data :
x_list.append(x)
y_list.append(y)
data_final.append([x,y])
clustering = hdbscan.HDBSCAN(min_samples=10)
colors = clustering.fit_predict(data_final)
plt.scatter(x_list, y_list, c=colors, s=5)
plt.show()
silh = metrics.silhouette_score(data_final, colors, metric='euclidean')
dbsc = metrics.davies_bouldin_score(data_final, colors)
caha = metrics.calinski_harabasz_score(data_final, colors)
print("Coefficient de silhouette : ", silh)
print("Indice de Davies Bouldin : ", dbsc)
print("Indice de calinski harabasz : ", caha)

26
artificial/kmeans.py Normal file
View file

@ -0,0 +1,26 @@
from scipy.io import arff
import numpy as np
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
#K_means algorithm
n_clusters = 3
data = arff.loadarff('2d-4c-no9.arff')[0]
data_final = []
x_list = []
y_list = []
for (x, y, z) in data :
x_list.append(x)
y_list.append(y)
data_final.append([x,y])
kmeans = KMeans(n_clusters, init='k-means++').fit(data_final)
colors = kmeans.labels_
plt.scatter(x_list, y_list, c=colors, s=5)
plt.show()

77
real_world/2D/agglomerative2D.py Normal file
View file

@ -0,0 +1,77 @@
from scipy.io import arff
import numpy as np
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
from sklearn import metrics
from sklearn.cluster import AgglomerativeClustering
from sklearn.cluster import DBSCAN
import hdbscan
n_clusters = 2
data_final = []
x_list = []
y_list = []
silhouette = []
calinski = []
davies = []
data = np.loadtxt('tr.data')
for (x, y) in data :
x_list.append(x)
y_list.append(y)
data_final.append([x,y])
for n in range(2, 20):
clustering = AgglomerativeClustering(n_clusters = n , linkage='average').fit(data_final)
colors = clustering.labels_
silh = metrics.silhouette_score(data_final, colors, metric='euclidean')
silhouette.append(silh)
dbsc = metrics.davies_bouldin_score(data_final, colors)
davies.append(dbsc)
caha = metrics.calinski_harabasz_score(data_final, colors)
calinski.append(caha)
#silhouettte coefficient
#get the index of the best result
m = max(silhouette)
indice = [i for i, j in enumerate(silhouette) if j == m][0] +2
print("Silhouette : ", indice)
plt.subplot(3,1,1)
#display the best obtained result
clustering = AgglomerativeClustering(n_clusters = indice , linkage='average').fit(data_final)
colors = clustering.fit_predict(data_final)
plt.scatter(x_list, y_list, c=colors, s=5)
#davies bouldin metrics
#get the index of the best result
m = min(davies)
indice = [i for i, j in enumerate(davies) if j == m][0] +2
print("Davies Bouldin : ", indice)
plt.subplot(3,1,2)
#display the best obtained result with davies bouldin metrics
clustering = AgglomerativeClustering(n_clusters = indice , linkage='average').fit(data_final)
colors = clustering.fit_predict(data_final)
plt.scatter(x_list, y_list, c=colors, s=5)
#calinski metrics
#get the index of the best result
m = max(calinski)
indice = [i for i, j in enumerate(calinski) if j == m][0] +2
print("Calinski Harabasz : ", indice)
plt.subplot(3,1,3)
#display the best obtained result
clustering = AgglomerativeClustering(n_clusters = indice , linkage='average').fit(data_final)
colors = clustering.fit_predict(data_final)
plt.scatter(x_list, y_list, c=colors, s=5)
plt.show()

43
real_world/2D/dbscan2D.py Normal file
View file

@ -0,0 +1,43 @@
from scipy.io import arff
import numpy as np
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
from sklearn import metrics
from sklearn.cluster import AgglomerativeClustering
from sklearn.cluster import DBSCAN
import hdbscan
n_clusters = 2
data_final = []
x_list = []
y_list = []
silhouette = []
calinski = []
davies = []
data = np.loadtxt('zgo.data')
for (x, y) in data :
x_list.append(x)
y_list.append(y)
data_final.append([x,y])
clustering = DBSCAN(eps=0.35, min_samples=10).fit(data_final)
colors = clustering.labels_
silh = metrics.silhouette_score(data_final, colors, metric='euclidean')
dbsc = metrics.davies_bouldin_score(data_final, colors)
caha = metrics.calinski_harabasz_score(data_final, colors)
print("Coefficient de silhouette : ", silh)
print("Indice de Davies Bouldin : ", dbsc)
print("Indice de calinski harabasz : ", caha)
plt.scatter(x_list, y_list, c=colors, s=5)
plt.show()

83
real_world/2D/hdbscan2D.py Normal file
View file

@ -0,0 +1,83 @@
from scipy.io import arff
import numpy as np
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
from sklearn import metrics
from sklearn.cluster import AgglomerativeClustering
from sklearn.cluster import DBSCAN
import hdbscan
n_clusters = 2
data_final = []
x_list = []
y_list = []
silhouette = []
calinski = []
davies = []
data = np.loadtxt('zgo.data')
for (x, y) in data :
x_list.append(x)
y_list.append(y)
data_final.append([x,y])
#get the values of the different coefficients for different min_samples values from 2 to 20
for n in range(2, 20):
clustering = hdbscan.HDBSCAN(min_samples=n)
colors = clustering.fit_predict(data_final)
silh = metrics.silhouette_score(data_final, colors, metric='euclidean')
silhouette.append(silh)
dbsc = metrics.davies_bouldin_score(data_final, colors)
davies.append(dbsc)
caha = metrics.calinski_harabasz_score(data_final, colors)
calinski.append(caha)
#silhouettte coefficient
#get the index of the best result
m = max(silhouette)
indice = [i for i, j in enumerate(silhouette) if j == m][0] +2
print("Silhouette : ", indice)
plt.subplot(3,1,1)
#display the best obtained result
clustering = hdbscan.HDBSCAN(min_samples=indice)
colors = clustering.fit_predict(data_final)
plt.scatter(x_list, y_list, c=colors, s=5)
plt.show()
#davies bouldin metrics
#get the index of the best result
m = min(davies)
indice = [i for i, j in enumerate(davies) if j == m][0] +2
print("Davies Bouldin : ", indice)
plt.subplot(3,1,2)
#display the best obtained result with davies bouldin metrics
clustering = hdbscan.HDBSCAN(min_samples=indice)
colors = clustering.fit_predict(data_final)
plt.scatter(x_list, y_list, c=colors, s=5)
plt.show()
#calinski metrics
#get the index of the best result
m = max(calinski)
indice = [i for i, j in enumerate(calinski) if j == m][0] +2
print("Calinski Harabasz : ", indice)
plt.subplot(3,1,3)
#display the best obtained result
clustering = hdbscan.HDBSCAN(min_samples=indice)
colors = clustering.fit_predict(data_final)
plt.scatter(x_list, y_list, c=colors, s=5)
plt.show()

81
real_world/2D/kmeans2D.py Normal file
View file

@ -0,0 +1,81 @@
from scipy.io import arff
import numpy as np
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
from sklearn import metrics
from sklearn.cluster import AgglomerativeClustering
from sklearn.cluster import DBSCAN
import hdbscan
n_clusters = 2
data_final = []
x_list = []
y_list = []
silhouette = []
calinski = []
davies = []
data = np.loadtxt('zgo.data')
for (x, y) in data :
x_list.append(x)
y_list.append(y)
data_final.append([x,y])
for n in range(2, 20):
clustering = KMeans(n_clusters=n, init='k-means++').fit(data_final)
colors = clustering.labels_
silh = metrics.silhouette_score(data_final, colors, metric='euclidean')
silhouette.append(silh)
dbsc = metrics.davies_bouldin_score(data_final, colors)
davies.append(dbsc)
caha = metrics.calinski_harabasz_score(data_final, colors)
calinski.append(caha)
#silhouettte coefficient
#get the index of the best result
m = max(silhouette)
indice = [i for i, j in enumerate(silhouette) if j == m][0] +2
print("Silhouette : ", indice)
plt.subplot(3,1,1)
#display the best obtained result
clustering = KMeans(n_clusters=indice, init='k-means++').fit(data_final)
colors = clustering.fit_predict(data_final)
plt.scatter(x_list, y_list, c=colors, s=5)
plt.show()
#davies bouldin metrics
#get the index of the best result
m = min(davies)
indice = [i for i, j in enumerate(davies) if j == m][0] +2
print("Davies Bouldin : ", indice)
plt.subplot(3,1,2)
#display the best obtained result with davies bouldin metrics
clustering = KMeans(n_clusters=indice, init='k-means++').fit(data_final)
colors = clustering.fit_predict(data_final)
plt.scatter(x_list, y_list, c=colors, s=5)
plt.show()
#calinski metrics
#get the index of the best result
m = max(calinski)
indice = [i for i, j in enumerate(calinski) if j == m][0] +2
print("Calinski Harabasz : ", indice)
plt.subplot(3,1,3)
#display the best obtained result
clustering = KMeans(n_clusters=indice, init='k-means++').fit(data_final)
colors = clustering.fit_predict(data_final)
plt.scatter(x_list, y_list, c=colors, s=5)
plt.show()

81
real_world/3D/agglomerative3D.py Normal file
View file

@ -0,0 +1,81 @@
from scipy.io import arff
import numpy as np
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
from sklearn import metrics
from sklearn.cluster import AgglomerativeClustering
from sklearn.cluster import DBSCAN
import hdbscan
n_clusters = 2
data_final = []
x_list = []
y_list = []
z_list = []
silhouette = []
calinski = []
davies = []
data = np.loadtxt('t.data')
for (x, y, z) in data :
x_list.append(x)
y_list.append(y)
z_list.append(z)
data_final.append([x,y])
for n in range(2, 20):
clustering = AgglomerativeClustering(n_clusters = n , linkage='single').fit(data_final)
colors = clustering.labels_
silh = metrics.silhouette_score(data_final, colors, metric='euclidean')
silhouette.append(silh)
dbsc = metrics.davies_bouldin_score(data_final, colors)
davies.append(dbsc)
caha = metrics.calinski_harabasz_score(data_final, colors)
calinski.append(caha)
#silhouettte coefficient
#get the index of the best result
m = max(silhouette)
indice = [i for i, j in enumerate(silhouette) if j == m][0] +2
print("Silhouette : ", indice)
plt.subplot(3,1,1)
#display the best obtained result
clustering = AgglomerativeClustering(n_clusters = indice , linkage='average').fit(data_final)
colors = clustering.fit_predict(data_final)
plt.axes(projection='3d').scatter3D(x_list, y_list, z_list, c=colors)
plt.show()
#davies bouldin metrics
#get the index of the best result
m = min(davies)
indice = [i for i, j in enumerate(davies) if j == m][0] +2
print("Davies Bouldin : ", indice)
plt.subplot(3,1,2)
#display the best obtained result with davies bouldin metrics
clustering = AgglomerativeClustering(n_clusters = indice , linkage='average').fit(data_final)
colors = clustering.fit_predict(data_final)
plt.axes(projection='3d').scatter3D(x_list, y_list, z_list, c=colors)
plt.show()
#calinski metrics
#get the index of the best result
m = max(calinski)
indice = [i for i, j in enumerate(calinski) if j == m][0] +2
print("Calinski Harabasz : ", indice)
plt.subplot(3,1,3)
#display the best obtained result
clustering = AgglomerativeClustering(n_clusters = indice , linkage='average').fit(data_final)
colors = clustering.fit_predict(data_final)
plt.axes(projection='3d').scatter3D(x_list, y_list, z_list, c=colors)
plt.show()

45
real_world/3D/dbscan3D.py Normal file
View file

@ -0,0 +1,45 @@
from scipy.io import arff
import numpy as np
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
from sklearn import metrics
from sklearn.cluster import AgglomerativeClustering
from sklearn.cluster import DBSCAN
import hdbscan
n_clusters = 2
data_final = []
x_list = []
y_list = []
z_list = []
silhouette = []
calinski = []
davies = []
data = np.loadtxt('t.data')
for (x, y, z) in data :
x_list.append(x)
y_list.append(y)
z_list.append(z)
data_final.append([x,y])
clustering = DBSCAN(eps=0.25, min_samples=10).fit(data_final)
colors = clustering.labels_
silh = metrics.silhouette_score(data_final, colors, metric='euclidean')
dbsc = metrics.davies_bouldin_score(data_final, colors)
caha = metrics.calinski_harabasz_score(data_final, colors)
print("Coefficient de silhouette : ", silh)
print("Indice de Davies Bouldin : ", dbsc)
print("Indice de calinski harabasz : ", caha)
plt.axes(projection='3d').scatter3D(x_list, y_list, z_list, c=colors)
plt.show()

84
real_world/3D/hdbscan3D.py Normal file
View file

@ -0,0 +1,84 @@
from scipy.io import arff
import numpy as np
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
from sklearn import metrics
from sklearn.cluster import AgglomerativeClustering
from sklearn.cluster import DBSCAN
import hdbscan
n_clusters = 2
data_final = []
x_list = []
y_list = []
z_list = []
silhouette = []
calinski = []
davies = []
data = np.loadtxt('a.data')
for (x, y, z) in data :
x_list.append(x)
y_list.append(y)
z_list.append(z)
data_final.append([x,y])
#get the values of the different coefficients for different min_samples values from 2 to 20
for n in range(2, 20):
clustering = hdbscan.HDBSCAN(min_samples=n)
colors = clustering.fit_predict(data_final)
silh = metrics.silhouette_score(data_final, colors, metric='euclidean')
silhouette.append(silh)
dbsc = metrics.davies_bouldin_score(data_final, colors)
davies.append(dbsc)
caha = metrics.calinski_harabasz_score(data_final, colors)
calinski.append(caha)
#silhouettte coefficient
#get the index of the best result
m = max(silhouette)
indice = [i for i, j in enumerate(silhouette) if j == m][0] +2
print("Silhouette : ", indice)
plt.subplot(3,1,1)
#display the best obtained result
clustering = hdbscan.HDBSCAN(min_samples=indice)
colors = clustering.fit_predict(data_final)
plt.axes(projection='3d').scatter3D(x_list, y_list, z_list, c=colors)
plt.show()
#davies bouldin metrics
#get the index of the best result
m = min(davies)
indice = [i for i, j in enumerate(davies) if j == m][0] +2
print("Davies Bouldin : ", indice)
plt.subplot(3,1,2)
#display the best obtained result with davies bouldin metrics
clustering = hdbscan.HDBSCAN(min_samples=indice)
colors = clustering.fit_predict(data_final)
plt.axes(projection='3d').scatter3D(x_list, y_list, z_list, c=colors)
plt.show()
#calinski metrics
#get the index of the best result
m = max(calinski)
indice = [i for i, j in enumerate(calinski) if j == m][0] +2
print("Calinski Harabasz : ", indice)
plt.subplot(3,1,3)
#display the best obtained result
clustering = hdbscan.HDBSCAN(min_samples=indice)
colors = clustering.fit_predict(data_final)
plt.axes(projection='3d').scatter3D(x_list, y_list, z_list, c=colors)
plt.show()

80
real_world/3D/kmeans3D.py Normal file
View file

@ -0,0 +1,80 @@
from scipy.io import arff
import numpy as np
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
from sklearn import metrics
from sklearn.cluster import AgglomerativeClustering
from sklearn.cluster import DBSCAN
import hdbscan
n_clusters = 2
data_final = []
x_list = []
y_list = []
z_list = []
silhouette = []
calinski = []
davies = []
data = np.loadtxt('t.data')
for (x, y, z) in data :
x_list.append(x)
y_list.append(y)
z_list.append(z)
data_final.append([x,y])
for n in range(2, 20):
clustering = KMeans(n_clusters=n, init='k-means++').fit(data_final)
colors = clustering.labels_
silh = metrics.silhouette_score(data_final, colors, metric='euclidean')
silhouette.append(silh)
dbsc = metrics.davies_bouldin_score(data_final, colors)
davies.append(dbsc)
caha = metrics.calinski_harabasz_score(data_final, colors)
calinski.append(caha)
#silhouettte coefficient
#get the index of the best result
m = max(silhouette)
indice = [i for i, j in enumerate(silhouette) if j == m][0] +2
print("Silhouette : ", indice)
plt.subplot(3,1,1)
#display the best obtained result
clustering = KMeans(n_clusters=indice, init='k-means++').fit(data_final)
colors = clustering.fit_predict(data_final)
plt.axes(projection='3d').scatter3D(x_list, y_list, z_list, c=colors)
plt.show()
#davies bouldin metrics
#get the index of the best result
m = min(davies)
indice = [i for i, j in enumerate(davies) if j == m][0] +2
print("Davies Bouldin : ", indice)
plt.subplot(3,1,2)
#display the best obtained result with davies bouldin metrics
clustering = KMeans(n_clusters=indice, init='k-means++').fit(data_final)
colors = clustering.fit_predict(data_final)
plt.axes(projection='3d').scatter3D(x_list, y_list, z_list, c=colors)
plt.show()
#calinski metrics
#get the index of the best result
m = max(calinski)
indice = [i for i, j in enumerate(calinski) if j == m][0] +2
print("Calinski Harabasz : ", indice)
plt.subplot(3,1,3)
#display the best obtained result
clustering = KMeans(n_clusters=indice, init='k-means++').fit(data_final)
colors = clustering.fit_predict(data_final)
plt.axes(projection='3d').scatter3D(x_list, y_list, z_list, c=colors)
plt.show()