def test_fit(self):
seed = 666
file_ = "tests/files/libsvm/2"
x, y = ds.load_svmlight_file(file_, (10, 300), 780, False)
csvm = CascadeSVM(cascade_arity=3,
max_iter=5,
tol=1e-4,
kernel='linear',
c=2,
gamma=0.1,
check_convergence=True,
random_state=seed,
verbose=False)
csvm.fit(x, y)
self.assertTrue(csvm.converged)
csvm = CascadeSVM(cascade_arity=3,
max_iter=1,
tol=1e-4,
kernel='linear',
c=2,
gamma=0.1,
check_convergence=False,
random_state=seed,
verbose=False)
csvm.fit(x, y)
self.assertFalse(csvm.converged)
self.assertEqual(csvm.iterations, 1)
def test_score(self, collect):
seed = 666
# negative points belong to class 1, positives to 0
p1, p2, p3, p4 = [1, 2], [2, 1], [-1, -2], [-2, -1]
x = ds.array(np.array([p1, p4, p3, p2]), (2, 2))
y = ds.array(np.array([0, 1, 1, 0]).reshape(-1, 1), (2, 1))
csvm = CascadeSVM(cascade_arity=3,
max_iter=10,
tol=1e-4,
kernel='rbf',
c=2,
gamma=0.1,
check_convergence=True,
random_state=seed,
verbose=False)
csvm.fit(x, y)
# points are separable, scoring the training dataset should have 100%
# accuracy
x_test = ds.array(np.array([p1, p2, p3, p4]), (2, 2))
y_test = ds.array(np.array([0, 0, 1, 1]).reshape(-1, 1), (2, 1))
accuracy = csvm.score(x_test, y_test, collect)
if not collect:
accuracy = compss_wait_on(accuracy)
self.assertEqual(accuracy, 1.0)
def test_predict(self):
seed = 666
# negative points belong to class 1, positives to 0
p1, p2, p3, p4 = [1, 2], [2, 1], [-1, -2], [-2, -1]
x = ds.array(np.array([p1, p4, p3, p2]), (2, 2))
y = ds.array(np.array([0, 1, 1, 0]).reshape(-1, 1), (2, 1))
csvm = CascadeSVM(cascade_arity=3,
max_iter=10,
tol=1e-4,
kernel='linear',
c=2,
gamma=0.1,
check_convergence=False,
random_state=seed,
verbose=False)
csvm.fit(x, y)
# p5 should belong to class 0, p6 to class 1
p5, p6 = np.array([1, 1]), np.array([-1, -1])
x_test = ds.array(np.array([p1, p2, p3, p4, p5, p6]), (2, 2))
y_pred = csvm.predict(x_test)
l1, l2, l3, l4, l5, l6 = y_pred.collect()
self.assertTrue(l1 == l2 == l5 == 0)
self.assertTrue(l3 == l4 == l6 == 1)
def test_fit_default_gamma(self):
""" Tests that the fit method converges when using gamma=auto on a
toy dataset """
seed = 666
file_ = "tests/files/libsvm/2"
x, y = ds.load_svmlight_file(file_, (10, 300), 780, False)
csvm = CascadeSVM(cascade_arity=3,
max_iter=5,
tol=1e-4,
kernel='linear',
c=2,
check_convergence=True,
random_state=seed,
verbose=False)
csvm.fit(x, y)
self.assertTrue(csvm.converged)
csvm = CascadeSVM(cascade_arity=3,
max_iter=1,
tol=1e-4,
kernel='linear',
c=2,
gamma=0.1,
check_convergence=False,
random_state=seed,
verbose=False)
csvm.fit(x, y)
self.assertFalse(csvm.converged)
self.assertEqual(csvm.iterations, 1)
def test_duplicates(self):
""" Tests that C-SVM does not generate duplicate support vectors """
x = ds.array(
np.array([[0, 1], [1, 1], [0, 1], [1, 2], [0, 0], [2, 2], [2, 1],
[1, 0]]), (2, 2))
y = ds.array(np.array([1, 0, 1, 0, 1, 0, 0, 1]).reshape(-1, 1), (2, 1))
csvm = CascadeSVM(c=1, random_state=1, max_iter=100, tol=0)
csvm.fit(x, y)
csvm._collect_clf()
self.assertEqual(csvm._clf.support_vectors_.shape[0], 6)
def test_decision_func(self):
seed = 666
# negative points belong to class 1, positives to 0
# all points are in the x-axis
p1, p2, p3, p4 = [0, 2], [0, 1], [0, -2], [0, -1]
x = ds.array(np.array([p1, p4, p3, p2]), (2, 2))
y = ds.array(np.array([0, 1, 1, 0]).reshape(-1, 1), (2, 1))
csvm = CascadeSVM(cascade_arity=3,
max_iter=10,
tol=1e-4,
kernel='rbf',
c=2,
gamma=0.1,
check_convergence=False,
random_state=seed,
verbose=False)
csvm.fit(x, y)
# p1 should be equidistant to p3, and p2 to p4
x_test = ds.array(np.array([p1, p2, p3, p4]), (2, 2))
y_pred = csvm.decision_function(x_test)
d1, d2, d3, d4 = y_pred.collect()
self.assertTrue(np.isclose(abs(d1) - abs(d3), 0))
self.assertTrue(np.isclose(abs(d2) - abs(d4), 0))
# p5 and p6 should be in the decision function (distance=0)
p5, p6 = np.array([1, 0]), np.array([-1, 0])
x_test = ds.array(np.array([p5, p6]), (1, 2))
y_pred = csvm.decision_function(x_test)
d5, d6 = y_pred.collect()
self.assertTrue(np.isclose(d5, 0))
self.assertTrue(np.isclose(d6, 0))
def test_fit_private_params(self):
kernel = 'rbf'
c = 2
gamma = 0.1
seed = 666
file_ = "tests/files/libsvm/2"
x, y = ds.load_svmlight_file(file_, (10, 300), 780, False)
csvm = CascadeSVM(kernel=kernel, c=c, gamma=gamma, random_state=seed)
csvm.fit(x, y)
self.assertEqual(csvm._clf_params['kernel'], kernel)
self.assertEqual(csvm._clf_params['C'], c)
self.assertEqual(csvm._clf_params['gamma'], gamma)
kernel, c = 'linear', 0.3
csvm = CascadeSVM(kernel=kernel, c=c, random_state=seed)
csvm.fit(x, y)
self.assertEqual(csvm._clf_params['kernel'], kernel)
self.assertEqual(csvm._clf_params['C'], c)
def test_sparse(self):
""" Tests that C-SVM produces the same results with sparse and dense
data"""
seed = 666
train = "tests/files/libsvm/3"
x_sp, y_sp = ds.load_svmlight_file(train, (10, 300), 780, True)
x_d, y_d = ds.load_svmlight_file(train, (10, 300), 780, False)
csvm_sp = CascadeSVM(random_state=seed)
csvm_sp.fit(x_sp, y_sp)
csvm_d = CascadeSVM(random_state=seed)
csvm_d.fit(x_d, y_d)
sv_d = csvm_d._clf.support_vectors_
sv_sp = csvm_sp._clf.support_vectors_.toarray()
self.assertTrue(np.array_equal(sv_d, sv_sp))
coef_d = csvm_d._clf.dual_coef_
coef_sp = csvm_sp._clf.dual_coef_.toarray()
self.assertTrue(np.array_equal(coef_d, coef_sp))
def main():
parser = argparse.ArgumentParser()
parser.add_argument("--svmlight", help="read files in SVMLight format",
action="store_true")
parser.add_argument("-dt", "--detailed_times",
help="get detailed execution times (read and fit)",
action="store_true")
parser.add_argument("-k", "--kernel", metavar="KERNEL", type=str,
help="linear or rbf (default is rbf)",
choices=["linear", "rbf"], default="rbf")
parser.add_argument("-a", "--arity", metavar="CASCADE_ARITY", type=int,
help="default is 2", default=2)
parser.add_argument("-b", "--block_size", metavar="BLOCK_SIZE", type=str,
help="two comma separated ints that represent the "
"size of the blocks in which to divide the input "
"data (default is 100,100)",
default="100,100")
parser.add_argument("-i", "--iteration", metavar="MAX_ITERATIONS",
type=int, help="default is 5", default=5)
parser.add_argument("-g", "--gamma", metavar="GAMMA", type=float,
help="(only for rbf kernel) default is 1 / n_features",
default=None)
parser.add_argument("-c", metavar="C", type=float, default=1,
help="Penalty parameter C of the error term. "
"Default:1")
parser.add_argument("-f", "--features", metavar="N_FEATURES",
help="number of features of the input data "
"(only for SVMLight files)",
type=int, default=None, required=False)
parser.add_argument("-t", "--test-file", metavar="TEST_FILE_PATH",
help="test file path", type=str, required=False)
parser.add_argument("-o", "--output_file", metavar="OUTPUT_FILE_PATH",
help="output file path", type=str, required=False)
parser.add_argument("--convergence", help="check for convergence",
action="store_true")
parser.add_argument("--dense", help="store data in dense format (only "
"for SVMLight files)",
action="store_true")
parser.add_argument("train_data",
help="input file in CSV or SVMLight format", type=str)
parser.add_argument("-v", "--verbose", action="store_true")
parser.add_argument("-s", "--shuffle", help="shuffle input data",
action="store_true")
args = parser.parse_args()
train_data = args.train_data
s_time = time.time()
read_time = 0
if not args.gamma:
gamma = "auto"
else:
gamma = args.gamma
sparse = not args.dense
bsize = args.block_size.split(",")
block_size = (int(bsize[0]), int(bsize[1]))
if args.svmlight:
x, y = ds.load_svmlight_file(train_data, block_size, args.features,
sparse)
else:
x = ds.load_txt_file(train_data, block_size)
y = x[:, x.shape[1] - 2: x.shape[1] - 1]
x = x[:, :x.shape[1] - 1]
if args.shuffle:
x, y = shuffle(x, y)
if args.detailed_times:
barrier()
read_time = time.time() - s_time
s_time = time.time()
csvm = CascadeSVM(cascade_arity=args.arity, max_iter=args.iteration,
c=args.c, gamma=gamma,
check_convergence=args.convergence, verbose=args.verbose)
csvm.fit(x, y)
barrier()
fit_time = time.time() - s_time
out = [args.kernel, args.arity, args.part_size, csvm._clf_params["gamma"],
args.c, csvm.iterations, csvm.converged, read_time, fit_time]
if os.path.isdir(train_data):
n_files = os.listdir(train_data)
out.append(len(n_files))
if args.test_file:
if args.svmlight:
x_test, y_test = ds.load_svmlight_file(args.test_file, block_size,
args.features,
sparse)
else:
x_test = ds.load_txt_file(args.test_file, block_size)
y_test = x_test[:, x_test.shape[1] - 1: x_test.shape[1]]
x_test = x_test[:, :x_test.shape[1] - 1]
out.append(compss_wait_on(csvm.score(x_test, y_test)))
if args.output_file:
with open(args.output_file, "ab") as f:
wr = csv.writer(f)
wr.writerow(out)
else:
print(out)