import numpy as np

from sklearn.mixture import GMM

f=open('RD0073_escape_fraction.txt','r')
lines = f.readlines()
f.close()

data=[]
for i in xrange(1,len(lines)):
    l = lines[i]
    if float(l.split()[5]) > 0 and float(l.split()[2]) > 1.0e7 and float(l.split()[4]) > 0:
      data.append([np.log10(float(l.split()[2])),np.log10(float(l.split()[3])),np.log10(float(l.split()[4])),np.log10(float(l.split()[5])),float(l.split()[6]),float(l.split()[7])]) 

data = np.asarray(data).reshape(-1,6)

gmm = GMM(n_components=2)

gmm.fit(data)

print gmm.predict(data)