def test_get_max_class(self):
dict1 = {'a':10, 'b':11, 'c': 6}
dict2 = {'a':14, 'b':11, 'c': 6}
res1 = BNClassifier.get_max_class(dict1)
res2 = BNClassifier.get_max_class(dict2)
self.assertEquals('b', res1)
self.assertEquals('a', res2)
def test_counts(self):
cols = [1,2]
row = [0,1,0]
data = [[0,1,1], [0,1,0], [0,0,0], [0,1,1]]
classes = ['a', 'b', 'a', 'b']
poss = ['a', 'b']
counts = BNClassifier.counts(cols, row, data, classes, poss)
self.assertEquals(1, counts['a'])
self.assertEquals(2, counts['b'])
def test_get_list_of_cols(self):
n1 = BNNode([], [])
n1.col_index = 0
n2 = BNNode([], [])
n2.col_index = 1
n3 = BNNode([], [])
n3.col_index = 2
n1.parents.append(n2)
n1.parents.append(n3)
col_list = BNClassifier.get_list_of_cols(n1)
self.assertEquals(1, col_list[0])
self.assertEquals(2, col_list[1])
def test_get_count(self):
n1 = BNNode([], [])
n1.col_index = 0
n2 = BNNode([], [])
n2.col_index = 1
n3 = BNNode([], [])
n3.col_index = 2
n1.parents.append(n2)
n1.parents.append(n3)
cols = [1,2]
row = [0,1,0]
data = [[0,1,0], [0,1,0], [0,0,0], [0,1,0]]
classes = ['a', 'b', 'a', 'b']
poss = ['a', 'b']
counts = BNClassifier.get_count(row, n1, data, classes, poss)
BN.setup_node(node, nodes)
# initial confusion matrix
confusion = {'0':{'0':0, '1':0}, '1':{'0':0, '1':0}}
# do k-fold validation
total_count = 0
kfold = KFold(100, new_data, new_classes)
while kfold.has_next():
dat, cls = kfold.get_next()
correct_count = 0
for i in range(0, len(dat)):
row = dat[i]
guess = BNClassifier.classify(row, nodes, dat, cls, ['0', '1'])
if guess == cls[i]:
correct_count += 1
confusion[cls[i]][guess] += 1
total_count += correct_count
for node in nodes:
pind = ""
for pnode in node.parents:
pind += " "+str(pnode.col_index)
print "Node "+str(node.col_index)+" has parents: "+pind