Beispiel #1
0
def accuracy_test(rows):
    """Performs cross-out-one validation methods on the dataset passed."""
    # Removing the label
    rows = rows[1:]

    total_accuracy = 0.0
    total_elements = len(rows)

    for i, row in enumerate(rows):
        singled_out = row
        rows.remove(row)
        remaining_rows = rows
        actual_label = row[-1]

        dt = DecisionTree(remaining_rows)
        node = dt.build_tree()
        #node = build_tree(remaining_rows)
        result = dt.classify(singled_out, node)

        # either 'yes' or 'no' prediction
        if len(result) == 1:
            if actual_label in result:
                total_accuracy += 1
                continue
            else:
                total_accuracy += 0
                continue
        # both 'yes' and 'no' prediction
        else:
            prob_correct = result[actual_label]
            if actual_label == 'yes':
                incorrect_label = 'no'
            else:
                incorrect_label = 'yes'
            prob_incorrect = result[incorrect_label]

            total_prob = prob_correct + prob_incorrect
            accuracy_for_this_test = prob_correct / total_prob

        total_accuracy += accuracy_for_this_test

        rows.append(singled_out)

    final_accuracy = (total_accuracy / total_elements)

    return final_accuracy
Beispiel #2
0
    final_accuracy = (total_accuracy / total_elements)

    return final_accuracy


if __name__ == '__main__':
    data, filename = process_file()
    print("This is a decision tree classifier program")
    print("\nThe dataset you've chosen is {}".format(filename))
    print("\nIf you wanted to experiment with a different dataset,")
    print("please quit this program and enter:")
    print("`python driver.py data_file.txt`")
    print("You can choose from any files under the 'dataset/' directory.")

    t = DecisionTree(data)
    t.build_tree()

    print("\n\n...Successfully built a classifer based on the datset")
    print("\nIf you want to print the tree, hit 1. Otherwise, hit `enter`:\n")
    see_tree = input()
    if see_tree == '1':
        print("Classification Tree from {} data".format(filename))
        print("=============================================================")
        t.print_tree()
        print("=============================================================")

    print(
        "You can randomly choose a data point, and this program can classify")
    print(
        "that data point for you. Hit 1 if you want to test a random example")
    print("Hit any key to skip.")