Esempio n. 1
0
 def train(self, X, Y):
     # Get relevant data
     idx = Y==self.i
     jdx = Y==self.j
     ijdx = np.logical_or(idx, jdx)
     x = X[ijdx]
     y = Y[ijdx]
     # Project y onto {-1, +1}
     y[y==self.i] = -1.0
     y[y==self.j] = 1.0
     # Train SMO
     self.w, self.b = train(x, y, C=1e-5, tol=1e-2, eps=1e-3)
Esempio n. 2
0
def proc((c,code)):
    print c,code
    coded_labels = train_labels.copy()
    
    # Create the code-mapped label vector
    for i, label in enumerate(train_labels):
        coded_labels[i] = code[int(label)]
    
    # SVM for this code
    w, b = train(train_data, coded_labels, C=0.00001, tol=0.00001, eps=1e-2)

    # Hypothesis
    h_train = hypothesis(train_data, w, b)
    h_test = hypothesis(test_data, w, b)

    return c, h_train, h_test
Esempio n. 3
0
data_file = "../data/spambase/spambase.data"
dmat = []
f = open(data_file, "r")
for line in f:
    x = line.split(',')
    x = [float(e) for e in x]
    dmat.append(x)
data = np.array(dmat)

# k-folds xvalidation
k = 10 
kfolder = KFolder(data, k, standard=True, shuffle=False)
for i in range(1):
    print "Fold:", i+1
    
    # Get data and labels at fold k
    X,Y = kfolder.training(i)
    
    # Get the testing data
    Xi,Yi = kfolder.testing(i)
    Yi[Yi==0] = -1.0
    
    # Train
    Y[Y==0] = -1.0
    w, b = train(X, Y.ravel())

    # Test
    print "Training accuracy:", test(X, Y, w, b)
    print "Testing accuracy:", test(Xi, Yi, w, b)