kmeans_iris.py

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from sklearn import datasets
from sklearn.cluster import KMeans


# Loads the iris dataset
iris = datasets.load_iris()

iris_data = pd.DataFrame(iris.data, columns=iris['feature_names'])
iris_target = pd.DataFrame(iris.target, columns=['target'])

# Map encoded target values to target names
def map_target(target_num):
    return iris.target_names[int(target_num)]

iris_target_name = iris_target.apply(map_target, 1)

# Fit a K-Means model to the data
kmeans_3 = KMeans(n_clusters=3)
kmeans_iris = kmeans_3.fit(iris_data[['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)']])

fig = plt.figure(1, figsize=(4, 3))
ax = Axes3D(fig, rect=[0, 0, .95, 1], elev=48, azim=134)

labels = kmeans_iris.labels_

ax.scatter(iris_data.ix[:, 3], iris_data.ix[:, 0], iris_data.ix[:, 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')

plt.show()

# Plot the ground truth
fig = plt.figure(2, figsize=(4, 3))
ax = Axes3D(fig, rect=[0, 0, .95, 1], elev=48, azim=134)

for name, label in [('Setosa', 0),
                    ('Versicolour', 1),
                    ('Virginica', 2)]:
    ax.text3D(iris_data.ix[iris_target.target == label, 3].mean(),
              iris_data.ix[iris_target.target == label, 0].mean() + 1.5,
              iris_data.ix[iris_target.target == label, 2].mean(), name,
              horizontalalignment='center',
              bbox=dict(alpha=.5, edgecolor='w', facecolor='w'))
# Reorder the labels to have colors matching the cluster results
y = np.choose(iris_target.target, [1, 2, 0]).astype(np.float)
ax.scatter(iris_data.ix[:, 3], iris_data.ix[:, 0], iris_data.ix[:, 2], c=y)

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')
plt.show()