def get_data(self, data_file):
parser = DataParser(data_file)
sets = parser.get_training_sets(1)
#one set, so take the first of the trainings sets
#and take the first of that (i.e. not the test set)
self.training_set = sets[0][0]
self.test_set = parser.get_test_set()
def set_up(numNodes, comm):
'''Run by the master node, this method
sets up the ANNs, reads in the training
and test data sets, and scatters them to
all the other nodes.
'''
try:
in_layer = int(sys.argv[1])
hidden_layers = [int(sys.argv[2])]
if len(sys.argv) == 6:
hidden_layers.append(int(sys.argv[3]))
out_layer = int(sys.argv[4])
fileName = sys.argv[5]
else:
out_layer = int(sys.argv[3])
fileName = sys.argv[4]
except:
in_layer = 9
hidden_layers = [1]
out_layer = 1
fileName = 'breast_cancer.dat'
#break up data (for each node and into testing/training)
f = open(fileName)
parser = DataParser(f)
training_data = parser.get_training_sets(numNodes)
test_data = parser.get_test_set()
f.close()
# broadcast ANN architecture to all nodes
comm.bcast((in_layer, hidden_layers, out_layer, fileName), root=0)
return training_data, test_data, in_layer, hidden_layers, out_layer
def set_up(numNodes, comm):
'''Run by the master node, this method
sets up the ANNs, reads in the training
and test data sets, and scatters them to
all the other nodes.
'''
try:
in_layer = int(sys.argv[1])
hidden_layers = [int(sys.argv[2])]
if len(sys.argv) == 6:
hidden_layers.append(int(sys.argv[3]))
out_layer = int(sys.argv[4])
fileName = sys.argv[5]
else:
out_layer = int(sys.argv[3])
fileName = sys.argv[4]
except:
in_layer = 9
hidden_layers = [1]
out_layer = 1
fileName = 'breast_cancer.dat'
#break up data (for each node and into testing/training)
f = open(fileName)
parser = DataParser(f)
training_data = parser.get_training_sets(numNodes)
test_data = parser.get_test_set()
f.close()
# broadcast ANN architecture to all nodes
comm.bcast((in_layer, hidden_layers, out_layer, fileName), root=0)
return training_data, test_data, in_layer, hidden_layers, out_layer
def get_data(self, data_file):
parser = DataParser(data_file)
sets = parser.get_training_sets(1)
#one set, so take the first of the trainings sets
#and take the first of that (i.e. not the test set)
self.training_set = sets[0][0]
self.test_set = parser.get_test_set()
class TestDataParser(unittest.TestCase):
def setUp(self):
self.file = open('test/data.dat')
self.instance = DataParser(self.file)
def test_create_tuple(self):
nums = ['1','2','3','4']
output = self.instance._create_tuple(nums)
self.assertEqual(output, (1.0,2.0,3.0,4.0))
def test_parse_line(self):
line = "1,2,3,4,5,7"
output = self.instance._parse_line(line)
self.assertEqual(output, ((2,3,4,5),(7,)))
def test_parse_file(self):
#it gets randomized
pass
def test_get_training_sets(self):
sets = self.instance.get_training_sets(2)
self.assertEqual(len(sets), 2)
def test_divide_data(self):
self.assertEqual(len(self.instance.test), 1)
self.assertEqual(len(self.instance.training), 9)
def test_separate_training_test(self):
samples = [1,2,3,4,5,6,7,8,9,0]
out = self.instance.separate_training_test(samples)
self.assertEqual(([1,2,3,4,5,6,7,8], [9,0]), out)
samples = [1,2,3,4,5,6]
out = self.instance.separate_training_test(samples)
self.assertEqual(([1,2,3,4], [5,6]), out)
def test_whole(self):
inst = DataParser(open('breast_cancer.dat'))
print len(inst.get_training_sets(5)[1][0])
def tearDown(self):
pass
class TestDataParser(unittest.TestCase):
def setUp(self):
self.file = open('test/data.dat')
self.instance = DataParser(self.file)
def test_create_tuple(self):
nums = ['1', '2', '3', '4']
output = self.instance._create_tuple(nums)
self.assertEqual(output, (1.0, 2.0, 3.0, 4.0))
def test_parse_line(self):
line = "1,2,3,4,5,7"
output = self.instance._parse_line(line)
self.assertEqual(output, ((2, 3, 4, 5), (7, )))
def test_parse_file(self):
#it gets randomized
pass
def test_get_training_sets(self):
sets = self.instance.get_training_sets(2)
self.assertEqual(len(sets), 2)
def test_divide_data(self):
self.assertEqual(len(self.instance.test), 1)
self.assertEqual(len(self.instance.training), 9)
def test_separate_training_test(self):
samples = [1, 2, 3, 4, 5, 6, 7, 8, 9, 0]
out = self.instance.separate_training_test(samples)
self.assertEqual(([1, 2, 3, 4, 5, 6, 7, 8], [9, 0]), out)
samples = [1, 2, 3, 4, 5, 6]
out = self.instance.separate_training_test(samples)
self.assertEqual(([1, 2, 3, 4], [5, 6]), out)
def test_whole(self):
inst = DataParser(open('breast_cancer.dat'))
print len(inst.get_training_sets(5)[1][0])
def tearDown(self):
pass
def setUp(self):
self.file = open('test/data.dat')
self.instance = DataParser(self.file)
def test_whole(self):
inst = DataParser(open('breast_cancer.dat'))
print len(inst.get_training_sets(5)[1][0])
def setUp(self):
self.file = open('test/data.dat')
self.instance = DataParser(self.file)
def test_whole(self):
inst = DataParser(open('breast_cancer.dat'))
print len(inst.get_training_sets(5)[1][0])
