Question

Could you guys please tell me how I can make the following code more pythonic?

The code is correct. Full disclosure – it’s problem 1b in Handout #4 of this machine learning course. I’m supposed to use newton’s algorithm on the two data sets for fitting a logistic hypothesis. But they use matlab & I’m using scipy

Eg one question i have is the matrixes kept rounding to integers until I initialized one value to 0.0. Is there a better way?

Thanks

import os.path
import math
from numpy import matrix
from scipy.linalg import inv #, det, eig

x = matrix( '0.0;0;1'  )
y = 11
grad = matrix( '0.0;0;0'  )
hess = matrix('0.0,0,0;0,0,0;0,0,0')
theta = matrix( '0.0;0;0'  ) 


# run until convergence=6or7
for i in range(1, 6):
  #reset
  grad = matrix( '0.0;0;0'  )
  hess = matrix('0.0,0,0;0,0,0;0,0,0')

  xfile = open("q1x.dat", "r")
  yfile = open("q1y.dat", "r")


  #over whole set=99 items  
  for i in range(1, 100):    
    xline = xfile.readline()
    s= xline.split("  ")
    x[0] = float(s[1])
    x[1] = float(s[2])
    y = float(yfile.readline())

    hypoth = 1/ (1+ math.exp(-(theta.transpose() * x)))

    for j in range(0,3):
      grad[j] = grad[j] + (y-hypoth)* x[j]      
      for k in range(0,3):
        hess[j,k] = hess[j,k] - (hypoth *(1-hypoth)*x[j]*x[k])


  theta = theta - inv(hess)*grad #update theta after construction

  xfile.close()
  yfile.close()

print "done"
print theta

Answer 1

x = matrix([[0.],[0],[1]])
theta = matrix(zeros([3,1]))
for i in range(5):
  grad = matrix(zeros([3,1]))
  hess = matrix(zeros([3,3]))
  [xfile, yfile] = [open('q1'+a+'.dat', 'r') for a in 'xy']
  for xline, yline in zip(xfile, yfile):
    x.transpose()[0,:2] = [map(float, xline.split("  ")[1:3])]
    y = float(yline)
    hypoth = 1 / (1 + math.exp(theta.transpose() * x))
    grad += (y - hypoth) * x
    hess -= hypoth * (1 - hypoth) * x * x.transpose()
  theta += inv(hess) * grad
print "done"
print theta