View difference between Paste ID: 50AUePkt and 5hrvTeSJ

 #!/usr/bin/python
 #import cgitb
 #This script will extract the data from the .arff files and put the features in dataX and the score or the value to be predicted in dataY.
 import numpy as np
 import scipy
 #import arff
 import os
 #from matplotlib import pyplot as plt
 from sklearn.svm import NuSVR
 from sklearn.preprocessing import StandardScaler
 from scipy import sparse
 from sklearn.cross_validation import train_test_split
 from sklearn.grid_search import GridSearchCV
 from time import time,clock
 from time import gmtime, strftime
 import shlex
-barr = ''
+
-fname = './bruno/2_mid_pitch/TestFeatures/Vowels_To_UnvoicedFricatives.arff'
+#fname = './Vowels_To_UnvoicedFricatives.arff' # Comment this line and remove the comment from the next to change the datafile.
 fname = './Vowels_To_Nasals.arff'
 
 f = open(fname,'r')
 lines = f.readlines()[42:]
 f.close()
 
 floats = []
-for (x,y), value in np.ndenumerate(array):
+
     floats.append(shlex.split(line))
 array = np.asarray(floats)
 
-print 'Data size'
+for (x,y), value in np.ndenumerate(array): # To remove NaNs from the data
-print np.shape(array)
+
-scale = StandardScaler()
+
-array = scale.fit_transform(array)
+
-traiY = array[:,38]
+
-traiX = np.delete(array, [36,37,38,39],1)
+
-trainY, realY, trainX, testX = train_test_split(traiY,traiX,test_size=0.8,random_state=42)
+#scale = StandardScaler()
-Cost = np.power(2,np.arange(1,12));
+#array = scale.fit_transform(array) # A scaling of all the data takes place here
-g = [0.5,0.25,0.125,0.0625,0.03125,0.015625,0.0078125,0.00390625,0.001953125,0.0009765625,0.00048828125,0.00048828125]
+dataY = array[:,38]
-print '\nCost values'
+dataX = np.delete(array, [36,37,38,39],1)
-print Cost
+
-print '\ngamma values'
+print 'dataX size'
-print g
+print np.shape(dataX)
-scorebest = 0
+
-Cbest = 0
+print '\ndataY size'
-gammabest = 0
+print np.shape(dataY)