The Path to Predictive Analytics and Machine Learning

Appendix A. Appendix

Sample code that generates data, runs a linear regression, and plots the results:

import numpy as np
import matplotlib.pyplot as plt
from scipy import stats

x = np.arange(1,15)

delta = np.random.uniform(-2,2, size=(14,))

y = .9 * x + 1 +  delta

plt.scatter(x,y, s=50)

slope, int, r_val, p_val, err = stats.linregress(x, y)

plt.plot(x, slope * x + intercept)
plt.xlim(0)
plt.ylim(0)

# calling show() will open your plot in a window
# you can save rather than opening the plot using savefig()
plt.show()

Sample code that generates data, runs a clustering algorithm, and plots the results:

import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
from scipy.cluster.vq import vq, kmeans

data = np.vstack((np.random.rand(200,2) + \
       np.array([.5, .5]),np.random.rand(200,2)))

centroids2, _ = kmeans(data, 2)
idx2,_ = vq(data,centroids2)

# scatter plot without centroids
plt.figure(1)

plt.plot(data[:,0],data[:,1], 'o')

# scatter plot with 2 centroids
plt.figure(2)

plt.plot(data[:,0],data[:,1],'o')
plt.plot(centroids2[:,0],centroids2[:,1],'sm',markersize=16)

# scatter plot with 2 centroids and point colored by cluster
plt.figure(3)

plt.plot(data[idx2==0,0],data[idx2==0,1],'ob',data[idx2==1,0], \
         data[idx2==1,1],'or')
plt.plot(centroids2[:,0],centroids2[:,1],'sm',markersize=16)

centroids3, _ = kmeans(data, 3)
idx3,_ = vq(data,centroids3)

# scatter plot with 3 centroids and points colored by cluster
plt.figure(4)

plt.plot(data[idx3==0,0],data[idx3==0,1],'ob',