def test_build_tree(self):
tree_str = """
<Tree name = "test">
<node var ="Gender">
<edge var ="Female" num="2">
<node var = "Bush Approval">
<edge var = "Approve" num="2" >
<decision end = "2" choice = "McCain" p = "0.9"/>
</edge>
<edge var = "Disapprove" num="1">
<decision end = "1" choice="Obama" p = "0.95"/>
</edge>
</node>
</edge>
<edge var = "Male" num="1">
<node var = "Ideology">
<edge var = "Liberal" num = "1">
<decision end = "1" choice ="Obama" p = "0.99"/>
</edge>
<edge var = "Moderate" num="2">
<decision end = "1" choice = "Obama" p = "0.7"/>
</edge>
<edge var = "Conservative" num ="3">
<decision end = "2" choice = "McCain" p = "0.95"/>
</edge>
</node>
</edge>
</node>
</Tree>
"""
root = model.build_tree(tree_str)
self.assertEqual(root.name, "Gender")
self.assertEqual(len(root.edges.keys()), 2)
# Gender = Female
node = root.edges['Female']
self.assertEqual(node.name, "Bush Approval")
self.assertEqual(len(node.edges.keys()), 2)
self.assertEqual(node.edges['Approve'], Label("McCain"))
self.assertEqual(node.edges['Disapprove'], Label("Obama"))
# Gender = Male
node = root.edges['Male']
self.assertEqual(node.name, "Ideology")
self.assertEqual(len(node.edges.keys()), 3)
self.assertEqual(node.edges['Liberal'], Label("Obama"))
self.assertEqual(node.edges['Moderate'], Label("Obama"))
self.assertEqual(node.edges['Conservative'], Label("McCain"))
tree = Node("Gender",
("Female", Node("Bush Approval",
("Approve", Label("McCain")),
("Disapprove", Label("Obama")))),
("Male", Node("Ideology",
("Liberal", Label("Obama")),
("Moderate", Label("Obama")),
("Conservative", Label("McCain")))))
self.assertEqual(root, tree)
def test_stringify_tree(self):
tree = Node("Gender",
("Female", Node("Bush Approval",
("Approve", Label("McCain")),
("Disapprove", Label("Obama")))),
("Male", Node("Ideology",
("Liberal", Label("Obama")),
("Moderate", Label("Obama")),
("Conservative", Label("McCain")))))
xml_tree = model.stringify_tree(tree)
self.assertEqual(tree, model.build_tree(xml_tree))
def main(to_classify_csv, decision_tree_xml, restrictionstxt, has_label_column):
# how are we supposed to determine if this has a label column or not?
# I guess we could look at the number of unique edge labels in decision tree
# to determine features/
tree = model.build_tree(decision_tree_xml.read())
restrictions = dataset.restrictions_from_text(restrictionstxt)
cols, data = dataset.read(to_classify_csv.read(), has_label_column,
restrictions)
predicted_classes = [tree.classify(x[0], cols) for x in data]
labels = [x[1] for x in data]
if has_label_column:
print('Records:', len(data))
print('Correctly classified:',
sum(1 for p,l in zip(predicted_classes, labels) if p==l))
print('Incorrectly classified:',
sum(1 for p,l in zip(predicted_classes, labels) if p!=l))
print('Accuracy:', sampling.accuracy(labels, predicted_classes))
print('Error:', sampling.error_rate(labels, predicted_classes))
print('Confusion matrix:')
print(sampling.confusion_matrix(labels, predicted_classes))
else:
for i in range(len(predicted_classes)):
print(data[i][0], predicted_classes[i])