def test_synthetic_EQW_5(self):
d = EqualWidth(5, 0)
p2t = {1: []}
p2t[1] = [TimeStamp(-75, 1, 1, 0), TimeStamp(25, 1, 1, 0)] # min = -75, max = 25
expected_cutpoints = {1: [-55,-35,-15,5]}
d.discretize_property_without_abstracting({}, {}, p2t, 1)
real_cutpoints = d.bins_cutpoints
res, msg = assert_almost_equality(expected_cutpoints, real_cutpoints)
self.assertTrue(res, msg)
def test_synthetic_stress_EQW_2(self):
d = EqualWidth(2, 0)
p2t = {1:[]}
p2t[1] = [TimeStamp(3, 1, 1, 0)] * STRESS_VALUE_COUNT + [TimeStamp(-75, 1, 1, 0)] + [TimeStamp(3, 1, 1,
0)] * STRESS_VALUE_COUNT + [
TimeStamp(25, 1, 1, 0)] + [TimeStamp(3, 1, 1, 0)] * STRESS_VALUE_COUNT # min = -75, max = 25
expected_cutpoints = {1:[-25]}
d.discretize_property_without_abstracting({},{},p2t,1)
real_cutpoints = d.bins_cutpoints
res, msg = assert_almost_equality(expected_cutpoints,real_cutpoints)
self.assertTrue(res,msg)
def test_write_output_c2e_no_information_loss(self):
out_folder = "test_files_folder"
if not exists(out_folder):
mkdir(out_folder)
msg = ""
for p in properties:
m = {}
d = EqualWidth(3, 0)
d.property_folder = PARTITIONS_PATH
d.load_class_to_entity(m, p)
write_partition_float({}, m, {}, out_folder, p)
lines = []
msg = check_file_similiarity(lines, msg, out_folder, p)
self.assertTrue(msg == "", msg)
def test_syntetic_cutpoint_generation(self):
res = True
msg = ""
for c in range(2,1000):
d = EqualWidth(c,0)
p2t = {1: []}
p2t[1] = [TimeStamp(-75, 1, 1, 0), TimeStamp(25, 1, 1, 0)] # min = -75, max = 25
interval = 100/c
expected_cutpoints = {1: [-75+interval*i for i in range(1,c)]}
d.discretize_property_without_abstracting({}, {}, p2t, 1)
real_cutpoints = d.bins_cutpoints
t_res, t_msg = assert_almost_equality(expected_cutpoints, real_cutpoints)
res &= t_res
msg += t_msg
self.assertTrue(res, msg)
def test_cutpoints(MAX, MIN, PROPERTY_ID):
res = True
msg = ""
m1 = {}
m2 = {}
m3 = {}
for c in range(2, 1000):
d = EqualWidth(c, 0)
d.property_folder = PARTITIONS_PATH
expected_cutpoints = {PROPERTY_ID: generate_cutpoints(MIN, MAX, c)}
d.discretize_property_without_abstracting(m1, m2, m3, PROPERTY_ID)
real_cutpoints = d.bins_cutpoints
t_res, t_msg = assert_almost_equality(expected_cutpoints, real_cutpoints)
res &= t_res
msg += t_msg
return msg, res
def test_PAA_Discretization_Difference(self):
msg = ""
res = True
d = EqualWidth(2, 0, window_size=1)
p2t = {1: []}
p2t[1] = [
TimeStamp(-75, 1, 1, 0),
TimeStamp(-25, 2, 2, 0),
TimeStamp(1, 3, 3, 0),
TimeStamp(25, 4, 4, 0)
] # min = -75, max = 25
expected_cutpoints = {1: [-25]}
d.discretize_property({}, {}, p2t, 1)
real_cutpoints = d.bins_cutpoints
t_res, t_msg = assert_almost_equality(expected_cutpoints,
real_cutpoints)
msg += t_msg
res &= t_res
no_paa_cutpoints = real_cutpoints
d = EqualWidth(2, 0, window_size=2)
p2t = {1: []}
p2t[1] = [
TimeStamp(-75, 1, 1, 0),
TimeStamp(-25, 2, 2, 0),
TimeStamp(1, 3, 3, 0),
TimeStamp(25, 4, 4, 0)
] # min = -50 max = 13
expected_cutpoints = {1: [-50 + 63 / 2]}
d.discretize_property({}, {}, p2t, 1)
real_cutpoints = d.bins_cutpoints
t_res, t_msg = assert_almost_equality(expected_cutpoints,
real_cutpoints)
if t_msg != "":
t_msg = "\n" + t_msg
msg += t_msg
res &= t_res
paa_cutpoints = real_cutpoints
t_res, t_msg = assert_almost_equality({1: no_paa_cutpoints},
{1: paa_cutpoints})
if t_res:
msg += "\nExpected different cutpoints with PAA! Got %s" % no_paa_cutpoints
res = False
self.assertTrue(res, msg)
_entity_element = entity_elements[i]
f.write(
str(_entity_element[0]) + ',' +
str(_entity_element[1]) + ',' +
str(_entity_element[2]) + ',' +
str(_entity_element[3]))
karma_output.write(
str(_entity_element[0]) + ',' +
str(_entity_element[1]) + ',' +
str(property_to_base[_entity_element[3]] +
_entity_element[2]) + ',' +
str(_entity_element[3]))
if i + 1 != len(entity_elements):
f.write(';')
karma_output.write(';')
f.write('\n')
karma_output.write('\n')
if __name__ == '__main__':
test_path = r'D:\test_stuff.txt'
dataset_path = r'..\..\datasets\SAGender/SAGender.csv'
m1, m2, m3 = get_maps_from_file(dataset_path, 55)
d = EqualWidth(4)
# _m1, _m2, _m3 = d.get_copy_of_maps(m1, m2, m3)
_m1, _m2, _m3 = d.discretize(m1, m2, m3)
convert_cutpoints_to_output(_m2, "D:\\", 'SAGender',
d.get_discretization_name())