def main(domainxml, trainingsetcsv, manifold_value, restrictionstxt):
restrictions = dataset.restrictions_from_text(restrictionstxt)
cols, data = dataset.read(trainingsetcsv.read(), True, restrictions)
expected, actual, expected_hunked, actual_hunked = sampling.cross_validate(data, list(cols), manifold_value)
print("Overall confusion matrix:")
print(sampling.confusion_matrix(expected, actual))
print("\nOverall recall:")
print(sampling.recall(expected, actual, "Obama"))
print("\nOverall precision:")
print(sampling.precision(expected, actual, "Obama"))
print("\nOverall pf:")
print(sampling.pf(expected, actual, "Obama"))
print("\nOverall f-measure:")
print(sampling.f_measure(expected, actual, "Obama"))
print("\nOverall accuracy:")
print(sampling.accuracy(expected, actual))
print("\nAverage accuracy:")
print(sum(sampling.accuracy(e, a) for e, a in zip(expected_hunked, actual_hunked)) / len(expected_hunked))
print("\nOverall error rate:")
print(sampling.error_rate(expected, actual))
print("\nAverage error rate:")
print(sum(sampling.error_rate(e, a) for e, a in zip(expected_hunked, actual_hunked)) / len(expected_hunked))
def main(domainxml, trainingsetcsv, restrictionstxt):
restrictions = dataset.restrictions_from_text(restrictionstxt)
cols, data = dataset.read(trainingsetcsv.read(), restrictions)
# call train function with:
# `col_sets` - list of sets per column, NOT including class label
# `data` (list of ([train data], class))
tree = Node("swole", ("true", Label("protein and starches")),
("false", Label("sugar"))) # dummy temp tree
tree = c45.run(data, list(enumerate(cols)), 0)
tree_xml = stringify_tree(tree)
sys.stdout.buffer.write(tree_xml)
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])