def folds(self, nfolds=10, seed=None):
"""
Get (training,testing) datasets for cross-validation.
Arguments:
nfolds (int, optional): Number of folds. Default value is
10.
seed (int, optional): Seed value for shuffling
dataset. Default value is random int 0 <= x <= 10000.
Returns:
list of (Instances,Instances) tuples: Each list element is
a pair of (training,testing) datasets, respectively.
"""
seed = seed or randint(0, 10000)
rnd = WekaRandom(seed)
fold_size = labmath.ceil(self.instances.num_instances / nfolds)
# Shuffle the dataset.
instances = WekaInstances.copy_instances(self.instances)
instances.randomize(rnd)
folds = []
for i in range(nfolds):
offset = i * fold_size
testing_end = min(offset + fold_size, instances.num_instances - 1)
# Calculate dataset indices for testing and training data.
testing_range = (offset, testing_end - offset)
left_range = (0, offset)
right_range = (testing_end, instances.num_instances - testing_end)
# If there's nothing to test, move on.
if testing_range[1] < 1: continue
# Create testing and training folds.
testing = WekaInstances.copy_instances(instances, *testing_range)
left = WekaInstances.copy_instances(instances, *left_range)
right = WekaInstances.copy_instances(instances, *right_range)
training = WekaInstances.append_instances(left, right)
# Add fold to collection.
folds.append((training, testing))
return folds
def test_ceil_bad_params(self):
with self.assertRaises(TypeError):
self._test(None, labmath.ceil(None))
with self.assertRaises(TypeError):
self._test(None, labmath.ceil("abc"))
def test_ceil(self):
self._test(int, type(labmath.ceil(1)))
self._test(1, labmath.ceil(1))
self._test(2, labmath.ceil(1.1))
self._test(3, labmath.ceil(2.5))
self._test(4, labmath.ceil(3.9))