Train.py

#!/usr/bin/python
#import cgitb
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'
f = open(fname,'r')
lines = f.readlines()[42:]
f.close()
floats = []
for line in lines:
    floats.append(shlex.split(line))
array = np.asarray(floats)
for (x,y), value in np.ndenumerate(array):
    if value == 'NaN':
        array[x][y] = 0;
array = array.astype(np.float)
print 'Data size'
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)
Cost = np.power(2,np.arange(1,12));
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]
print '\nCost values'
print Cost
print '\ngamma values'
print g
scorebest = 0
Cbest = 0
gammabest = 0
model_to_set = NuSVR(C=128, cache_size=6144, coef0=0.0, degree=3, gamma=0.0625, kernel='rbf',
   max_iter=-1, nu=0.5, probability=False, shrinking=True, tol=0.001,
   verbose=True)
parameters = {'C':Cost,'gamma':g}#,'nu':[0.5],'kernel':['rbf'],'verbose':[True]}
#k =[0.5,1]#2,5,7,8];

trainY, realY, trainX, testX = train_test_split(traiY,traiX,test_size=(1-(0.1*33)),random_state=42)

start = time()
print '\n training start time'
print strftime("%a, %d %b %Y %H:%M:%S +0000", gmtime())
model_to_set.fit(trainX,trainY)
print '\n training end time'
print strftime("%a, %d %b %Y %H:%M:%S +0000", gmtime())
elapsed = (time() - start)
print elapsed/60

score1 = model_to_set.score(trainX,trainY)
print score1
score2 = model_to_set.score(testX,realY)
print score2