In [6]:

    

from mpl_toolkits.mplot3d import axes3d
import matplotlib.pyplot as plt
%matplotlib inline
import urllib2
import numpy as np

np.set_printoptions(precision=3, suppress=True)
url = ('https://raw.githubusercontent.com/Upward-Spiral-Science'
       '/data/master/syn-density/output.csv')
data = urllib2.urlopen(url)
csv = np.genfromtxt(data, delimiter=",")[1:]

def check_condition(row):
    if row[3] == 0:
        return False
    return True

a = np.apply_along_axis(check_condition, 1, csv)
a = np.where(a == True)[0]
nonZeroMask = csv[a, :]

synDividedMask = np.divide(nonZeroMask[:,4],nonZeroMask[:,3])
synDividedMask = synDividedMask * (64**3)
accurateDataT = np.vstack((nonZeroMask[:,0],nonZeroMask[:,1],nonZeroMask[:,2],synDividedMask))
accurateData = accurateDataT.T

cleaned = accurateData[accurateData[:,0] >= 409]
cleaned = cleaned[cleaned[:,0] <= 3529]
cleaned = cleaned[cleaned[:,1] >= 1564]
cleaned = cleaned[cleaned[:,1] <= 3124]


    

In [10]:

    

import sklearn.mixture as mixture
import sklearn.preprocessing as preprocess
import matplotlib as mpl
mpl.rcParams['font.size'] = 25
mpl.rc('font',family='Times New Roman')

max_clusters = 15
bic = np.array([])
i = np.array(range(1, max_clusters))
for idx in range(1, max_clusters):
    print "Fitting and evaluating model with " + str(idx) + " clusters."
    gmm = mixture.GMM(n_components=idx,n_iter=1000,covariance_type='diag')
    gmm.fit(cleaned)
    bic = np.append(bic, gmm.bic(cleaned))
print bic
plt.figure(figsize=(7,7))
plt.plot(i, 1.0/bic)
plt.title('BIC')
plt.ylabel('score')
plt.xlabel('number of clusters')
plt.subplots_adjust(bottom = 0.2)
plt.subplots_adjust(left = 0.2)
plt.savefig('Fig10.pdf', format='pdf', dpi=1000)
plt.show()


    

    




Fitting and evaluating model with 1 clusters.
Fitting and evaluating model with 2 clusters.
Fitting and evaluating model with 3 clusters.
Fitting and evaluating model with 4 clusters.
Fitting and evaluating model with 5 clusters.
Fitting and evaluating model with 6 clusters.
Fitting and evaluating model with 7 clusters.
Fitting and evaluating model with 8 clusters.
Fitting and evaluating model with 9 clusters.
Fitting and evaluating model with 10 clusters.
Fitting and evaluating model with 11 clusters.
Fitting and evaluating model with 12 clusters.
Fitting and evaluating model with 13 clusters.
Fitting and evaluating model with 14 clusters.
[ 2100389.837  2094880.867  2089231.581  2082505.977  2082821.711
  2080562.744  2079112.377  2074626.562  2074235.343  2073329.125
  2070431.847  2069995.057  2068058.277  2067265.002]






    

In [ ]: