In [3]:

    

# Code source: Gaël Varoquaux
# Modified for documentation by Jaques Grobler
# License: BSD 3 clause

import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D


from sklearn.cluster import KMeans
from sklearn import datasets

np.random.seed(5)

centers = [[1, 1], [-1, -1], [1, -1]]
iris = datasets.load_iris()
X = iris.data
y = iris.target

estimators = {'k_means_iris_3': KMeans(n_clusters=3),
              'k_means_iris_8': KMeans(n_clusters=8),
              'k_means_iris_bad_init': KMeans(n_clusters=3, n_init=1,
                                              init='random')}


fignum = 1


    

In [5]:

    

for name, est in estimators.items():
    fig = plt.figure(fignum, figsize=(4, 3))
    plt.clf()
    ax = Axes3D(fig, rect=[0, 0, .95, 1], elev=48, azim=134)

    plt.cla()
    est.fit(X)
    labels = est.labels_

    ax.scatter(X[:, 3], X[:, 0], X[:, 2], c=labels.astype(np.float))

    ax.w_xaxis.set_ticklabels([])
    ax.w_yaxis.set_ticklabels([])
    ax.w_zaxis.set_ticklabels([])
    ax.set_xlabel('Petal width')
    ax.set_ylabel('Sepal length')
    ax.set_zlabel('Petal length')
    fignum = fignum + 1


    

In [7]:

    

for name, est in estimators.items():
    fig = plt.figure(fignum, figsize=(4, 3))
    plt.clf()
    ax = Axes3D(fig, rect=[0, 0, .95, 1], elev=48, azim=134)

    print plt.cla()
    est.fit(X)
    print est
    labels = est.labels_
    print labels


    

    




None
KMeans(copy_x=True, init=k-means++, max_iter=300, n_clusters=8, n_init=10,
    n_jobs=1, precompute_distances=True, random_state=None, tol=0.0001,
    verbose=0)
[1 7 7 7 1 1 7 1 7 7 1 7 7 7 1 1 1 1 1 1 1 1 7 1 7 7 1 1 1 7 7 1 1 1 7 7 1
 7 7 1 1 7 7 1 1 7 1 7 1 7 4 4 4 0 4 0 4 6 4 0 6 0 0 4 0 4 0 0 4 0 5 0 5 4
 4 4 4 4 4 6 6 6 0 5 0 4 4 4 0 0 0 4 0 6 0 0 0 4 6 0 2 5 3 2 2 3 0 3 2 3 2
 5 2 5 5 2 2 3 3 5 2 5 3 5 2 3 5 5 2 3 3 3 2 5 5 3 2 2 5 2 2 2 5 2 2 2 5 2
 2 5]
None
KMeans(copy_x=True, init=k-means++, max_iter=300, n_clusters=3, n_init=10,
    n_jobs=1, precompute_distances=True, random_state=None, tol=0.0001,
    verbose=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 0 0 2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
 0 0 0 2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2 0 2 2 2 2 0 2 2 2 2
 2 2 0 0 2 2 2 2 0 2 0 2 0 2 2 0 0 2 2 2 2 2 0 2 2 2 2 0 2 2 2 0 2 2 2 0 2
 2 0]
None
KMeans(copy_x=True, init=random, max_iter=300, n_clusters=3, n_init=1,
    n_jobs=1, precompute_distances=True, random_state=None, tol=0.0001,
    verbose=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 0 1 2 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 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 2 1 1 1 1 2 1 1 1 1
 1 1 2 2 1 1 1 1 2 1 2 1 2 1 1 2 2 1 1 1 1 1 2 1 1 1 1 2 1 1 1 2 1 1 1 2 1
 1 2]






    

In [12]:

    

iris.data[:5]


    

    
Out[12]:





array([[ 5.1,  3.5,  1.4,  0.2],
       [ 4.9,  3. ,  1.4,  0.2],
       [ 4.7,  3.2,  1.3,  0.2],
       [ 4.6,  3.1,  1.5,  0.2],
       [ 5. ,  3.6,  1.4,  0.2]])

In [19]:

    

iris.feature_names


    

    
Out[19]:





['sepal length (cm)',
 'sepal width (cm)',
 'petal length (cm)',
 'petal width (cm)']

In [24]:

    

iris.data[:, 0].std()


    

    
Out[24]:





0.82530129178514089

In [ ]: