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 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

normalizedData = (data - data.mean(axis=0)) / data.std(axis=0, ddof=1)

from sklearn import datasets
iris = datasets.load_iris()
from scipy.spatial.distance import pdist, squareform
print squareform(pdist(iris.data, 'mahalanobis'))