def test_part_discrete_data(self):
train_data, test_data = load_project_data('example')
examples = [ex for ex in train_data] + [ex for ex in test_data]
data = ExampleSet(examples)
n = Node()
H_x, H_y_x, part_data = n.partition_data(data, 1)
self.assertAlmostEqual(0.61219, H_y_x, 3)
self.assertAlmostEqual(1.5849, H_x, 3)
H_x, H_y_x, part_data = n.partition_data(data, 3)
self.assertAlmostEqual(0.61219, H_y_x, 3)
self.assertAlmostEqual(1.5849, H_x, 3)
attr_index, part_data = n.max_GR(examples, [1, 3])
self.assertEqual(attr_index, 1)
part_data_test = {}
for ex in examples:
part_data_test.setdefault(ex[1], []).append(ex)
self.assertEqual(part_data_test, part_data)
attr_index, part_data = n.max_GR(examples, [3, 1])
self.assertEqual(attr_index, 3)
part_data_test = {}
for ex in examples:
part_data_test.setdefault(ex[3], []).append(ex)
self.assertEqual(part_data_test, part_data)
def test_part_discrete_data(self):
train_data, test_data = load_project_data('example')
examples = [ex for ex in train_data] + [ex for ex in test_data]
data = ExampleSet(examples)
n = Node()
H_x,H_y_x, part_data = n.partition_data(data,1)
self.assertAlmostEqual(0.61219,H_y_x,3)
self.assertAlmostEqual(1.5849,H_x,3)
H_x,H_y_x, part_data = n.partition_data(data,3)
self.assertAlmostEqual(0.61219,H_y_x,3)
self.assertAlmostEqual(1.5849,H_x,3)
attr_index,part_data = n.max_GR(examples,[1,3])
self.assertEqual(attr_index,1)
part_data_test = {}
for ex in examples:
part_data_test.setdefault(ex[1],[]).append(ex)
self.assertEqual(part_data_test,part_data)
attr_index,part_data = n.max_GR(examples,[3,1])
self.assertEqual(attr_index,3)
part_data_test = {}
for ex in examples:
part_data_test.setdefault(ex[3],[]).append(ex)
self.assertEqual(part_data_test,part_data)
def test_is_partable_data(self):
train_data, test_data = load_project_data('example')
examples = [ex for ex in train_data] + [ex for ex in test_data]
data = ExampleSet(examples)
n = Node()
self.assertTrue(n.check_ex_set(examples,[1,3]))
self.assertTrue(n.check_ex_set(examples,[1,3]))
index,part_data = n.max_GR(examples,[1,3])
self.assertEqual(index,1)
test_part_data = [ex for ex in examples if ex[1]=='red']
self.assertEqual(set(test_part_data),set(part_data['red']))
self.assertTrue(n.check_ex_set(part_data['red'],[3,])[1])
index,sub_data = n.max_GR(part_data['red'],[3])
self.assertEqual(index,3)
test_part_data = [ex for ex in examples if ex[1]=='green']
self.assertEqual(set(test_part_data),set(part_data['green']))
self.assertFalse(n.check_ex_set(part_data['green'],[3,])[1])
test_part_data = [ex for ex in examples if ex[1]=='blue']
self.assertEqual(set(test_part_data),set(part_data['blue']))
self.assertTrue(n.check_ex_set(part_data['blue'],[3,])[1])
index,sub_data = n.max_GR(part_data['blue'],[3])
self.assertEqual(index,3)
index,sub_data = n.max_GR(examples,[3,1])
self.assertEqual(index,3)
def test_is_partable_data(self):
train_data, test_data = load_project_data('example')
examples = [ex for ex in train_data] + [ex for ex in test_data]
data = ExampleSet(examples)
n = Node()
self.assertTrue(n.check_ex_set(examples, [1, 3]))
self.assertTrue(n.check_ex_set(examples, [1, 3]))
index, part_data = n.max_GR(examples, [1, 3])
self.assertEqual(index, 1)
test_part_data = [ex for ex in examples if ex[1] == 'red']
self.assertEqual(set(test_part_data), set(part_data['red']))
self.assertTrue(n.check_ex_set(part_data['red'], [
3,
])[1])
index, sub_data = n.max_GR(part_data['red'], [3])
self.assertEqual(index, 3)
test_part_data = [ex for ex in examples if ex[1] == 'green']
self.assertEqual(set(test_part_data), set(part_data['green']))
self.assertFalse(n.check_ex_set(part_data['green'], [
3,
])[1])
test_part_data = [ex for ex in examples if ex[1] == 'blue']
self.assertEqual(set(test_part_data), set(part_data['blue']))
self.assertTrue(n.check_ex_set(part_data['blue'], [
3,
])[1])
index, sub_data = n.max_GR(part_data['blue'], [3])
self.assertEqual(index, 3)
index, sub_data = n.max_GR(examples, [3, 1])
self.assertEqual(index, 3)