def crossvalidation(self, fold, v, k):
error = 0
data = Data(k, 0, 0)
data.importDataFromMat()
data.normalize()
n = data.train_cat.shape[1]
all_indices = sp.arange(n)
data.shuffleData()
sq = SquaredErrorLinearClassifier(v,k)
dataset_indices = sp.split(all_indices, fold)
for i in range(fold):
set_without_D_i_indices = sp.concatenate(dataset_indices[0:i]+dataset_indices[i+1:fold])
#print "-"*30+"train"+"-"*30
sq.train(data.train_left[:,set_without_D_i_indices], data.train_right[:,set_without_D_i_indices], data.train_cat[:,set_without_D_i_indices])
#print "-"*30+"classify"+"-"*30
results, classes = sq.classify(data.train_left[:,dataset_indices[i]], data.train_right[:,dataset_indices[i]])
#print "-"*30+"error"+"-"*30
err, _ = sq.error(results, data.train_cat[:,dataset_indices[i]].T)
error += fold/(n*1.0)*err
error = error / fold
with open("results/crossvalidation.txt", "a") as myfile:
toWrite = "v="+str(v)+" error="+str(error)
myfile.write(toWrite)
def testSquaredError():
k = 5
data = Data(k, 0, 0)
data.importDataFromMat()
data.normalize()
sq = SquaredErrorLinearClassifier(2 ** 10, k)
sq.train(data.train_left, data.train_right, data.train_cat)
results, cat = sq.classify(data.test_left, data.test_right)
sq.confusion_matrix(cat, data.test_cat.argmax(axis=0))
err = Error()
err, misclass = err.norm_total_error(results.T, data.test_cat, k)
print "Error on the test set " + str(err)
print "Misclassification ratio on the test set " + str(misclass)
