def load_dataset(fileprefix):
dataset_filename = "%s_dataset_dict.pck" % fileprefix
global dataset_dict
global text
print "Loading dataset..."
if exists(dataset_filename):
print " Reading dataset from %s..." % dataset_filename
dataset_dict = unpickle(dataset_filename)
else:
print " Computing dataset..."
dataset_dict = {}
for i in xrange(1, 11):
item_size = substring_size(i)
dataset_dict[i] = get_random_substring_list(\
text, LIST_SIZE, item_size)
print " Writing dataset to %s..." % dataset_filename
picklefy(dataset_filename, dataset_dict)
print " Done."
def test_substring_size_for_1_is_5(self):
i = 1
expected = 5
computed = substring_size(i)
self.assertEquals(computed, expected)
def test_substring_size_for_3_is_20(self):
i = 3
expected = 20
computed = substring_size(i)
self.assertEquals(computed, expected)
def test_substring_size_for_2_is_10(self):
i = 2
expected = 10
computed = substring_size(i)
self.assertEquals(computed, expected)
def test_substring_size_for_1_is_5(self):
i = 1
expected = 5
computed = substring_size(i)
self.assertEquals(computed, expected)
def test_substring_size_for_3_is_20(self):
i = 3
expected = 20
computed = substring_size(i)
self.assertEquals(computed, expected)
def test_substring_size_for_2_is_10(self):
i = 2
expected = 10
computed = substring_size(i)
self.assertEquals(computed, expected)