Stackoverflow mahalanobis numpy question

#! /usr/bin/python

import sys
from numpy import *
# data sets are { {sepal length, sepal width, petal length, petal width} ...}
# one data set per class

#returns the average euclidian distance between each vector in the data set
#data = [ [vector], [vector 2]....]
def euclid_dist(data):
   from scipy import spatial as spat
   count = 0
   avg  = 0
   for i in range(len(data)):
      for j in range(i + 1, len(data)):
         if(j == len(data)):
            break
         avg += spat.distance.euclidean(data[i], data[j])
         count += 1
   return avg / count

#returns the average mahalanobis distance between each vector in the data set
#data = [ [vector], [vector 2]....]
def mahalanobis(data):
   import numpy as np;
   import scipy.spatial.distance;
   avg   = 0
   count = 0

   covar = np.cov(data, rowvar=0);
   invcovar = np.linalg.inv(covar)

   for i in range(len(data)):
      for j in range(i + 1, len(data)):
         if(j == len(data)):
            break
         avg += scipy.spatial.distance.mahalanobis(data[i], data[j], invcovar)
         count += 1
   return avg / count

def hausdorf(data):
   return data

#normalizes data over columns. Expects a list of lists. each sub list needs to be of the same size
#this function can be found at http://stackoverflow.com/questions/8904694/how-to-normalize-a-2-dimensional-numpy-array-in-python-less-verbose
def normalize(data):
   import numpy as np
   row_sums = data.sum(axis=1)
   norm_data = np.zeros((50, 4))
   for i, (row, row_sum) in enumerate(zip(data, row_sums)):
      norm_data[i,:] = row / row_sum
   return norm_data

def main():
   if(len(sys.argv) < 2):
       print("No file name to open. USAGE: ./" + argv[0] + " \"file_name\"")
       exit(1);

   try:
       data_file = open(sys.argv[1])
   except IOError:
       print("Could not open file! Closing " + argv[0])

   with data_file:
      data = [] # each element in data is a data set of the form specified above
      norm = []
      data_set = []

      classification = "Iris-setosa"

      for line in data_file:
         line_data = []
         comma_pos = 0

         while True:
            comma_pos = line.find(',')
            if( comma_pos == -1):
               if(line.strip() != classification):
                  classification = line.strip()
                  data.append(array(data_set))
                  data_set = []
               break;
            line_data.append(float(line[:comma_pos]))
            line = line[comma_pos + 1:]
         data_set.append(line_data)


      #for data_set in data:
       #  for line in data_set:
        #    print(line)
         #print("start of new set")

      norm.append( normalize(data[0]))
      norm.append( normalize(data[1]))
      norm.append( normalize(data[2]))

      print(euclid_dist( data[0]))
      print(euclid_dist( data[1]))
      print(euclid_dist( data[2]))

      print(euclid_dist( norm[0]))
      print(euclid_dist( norm[1]))
      print(euclid_dist( norm[2]))

      print(mahalanobis( data[0]))
      print(mahalanobis( data[1]))
      print(mahalanobis( data[1]))

      print("")

      print(mahalanobis( norm[0]))
      print(mahalanobis( norm[1]))
      print(mahalanobis( norm[2]))

      #hausdorf( data[0])
      #hausdorf( data[1])
      #hausdorf( data[1])

      #hausdorf( norm[0])
      #hausdorf( norm[1])
      #hausdorf( norm[2])

main()