cas-pml/ML/unterlagen/06_Kmeans_Iris.ipynb

In [1]:

from sklearn import datasets
iris = datasets.load_iris()

from sklearn.cluster import KMeans
from sklearn import metrics

In [2]:

print(iris.target)

[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2
 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
 2 2]

In [3]:

kmeans = KMeans(n_clusters=3, init='random', n_init=1)
kmeans.fit(iris.data)

Out [3]:

KMeans(algorithm='auto', copy_x=True, init='random', max_iter=300,
    n_clusters=3, n_init=1, n_jobs=None, precompute_distances='auto',
    random_state=None, tol=0.0001, verbose=0)

In [5]:

print(list(zip(iris.target,kmeans.labels_)))

[(0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (1, 0), (1, 1), (1, 0), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 0), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 1), (2, 0), (2, 1), (2, 0), (2, 0), (2, 1), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 1)]

In [6]:

print(metrics.homogeneity_score(iris.target, kmeans.labels_))
print(metrics.completeness_score(iris.target, kmeans.labels_))
print(metrics.adjusted_rand_score(iris.target, kmeans.labels_))
print(metrics.silhouette_score(iris.data, kmeans.labels_))

0.7364192881252849
0.7474865805095326
0.7163421126838475
0.5511916046195915

In [7]:

kmeans_init = KMeans(n_clusters=3, init='random', n_init=10)
kmeans_init.fit(iris.data)

Out [7]:

KMeans(algorithm='auto', copy_x=True, init='random', max_iter=300,
    n_clusters=3, n_init=10, n_jobs=None, precompute_distances='auto',
    random_state=None, tol=0.0001, verbose=0)

In [8]:

print(list(zip(iris.target,kmeans.labels_)))

[(0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (1, 0), (1, 1), (1, 0), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 0), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 1), (2, 0), (2, 1), (2, 0), (2, 0), (2, 1), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 1)]

In [9]:

print(metrics.homogeneity_score(iris.target, kmeans_init.labels_))
print(metrics.completeness_score(iris.target, kmeans_init.labels_))
print(metrics.adjusted_rand_score(iris.target, kmeans_init.labels_))
print(metrics.silhouette_score(iris.data, kmeans_init.labels_))

0.7514854021988338
0.7649861514489815
0.7302382722834697
0.5528190123564091

In [10]:

kmeans2 = KMeans(n_clusters=3)
kmeans2.fit(iris.data)

Out [10]:

KMeans(algorithm='auto', copy_x=True, init='k-means++', max_iter=300,
    n_clusters=3, n_init=10, n_jobs=None, precompute_distances='auto',
    random_state=None, tol=0.0001, verbose=0)

In [11]:

print(list(zip(iris.target,kmeans.labels_)))

[(0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (0, 2), (1, 0), (1, 1), (1, 0), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 0), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (1, 1), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 1), (2, 0), (2, 1), (2, 0), (2, 0), (2, 1), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 0), (2, 1), (2, 0), (2, 0), (2, 1)]

In [12]:

print(metrics.homogeneity_score(iris.target, kmeans2.labels_))
print(metrics.completeness_score(iris.target, kmeans2.labels_))
print(metrics.adjusted_rand_score(iris.target, kmeans2.labels_))
print(metrics.silhouette_score(iris.data, kmeans2.labels_))

0.7514854021988338
0.7649861514489815
0.7302382722834697
0.5528190123564091

In [ ]: