learning.py

    """
    Return a DataSet with n k-bit examples of the majority problem:
    k random bits followed by a 1 if more than half the bits are 1, else 0.
    """
    examples = []
    for i in range(n):
        bits = [random.choice([0, 1]) for _ in range(k)]
        bits.append(int(sum(bits) > k / 2))
        examples.append(bits)
    return DataSet(name='majority', examples=examples)


def Parity(k, n, name='parity'):
    """
    Return a DataSet with n k-bit examples of the parity problem:
    k random bits followed by a 1 if an odd number of bits are 1, else 0.
    """
    examples = []
    for i in range(n):
        bits = [random.choice([0, 1]) for _ in range(k)]
        bits.append(sum(bits) % 2)
        examples.append(bits)
    return DataSet(name=name, examples=examples)


def Xor(n):
    """Return a DataSet with n examples of 2-input xor."""
    return Parity(2, n, name='xor')


def ContinuousXor(n):
    """2 inputs are chosen uniformly from (0.0 .. 2.0]; output is xor of ints."""
    examples = []
    for i in range(n):
        x, y = [random.uniform(0.0, 2.0) for _ in '12']
        examples.append([x, y, x != y])
    return DataSet(name='continuous xor', examples=examples)


def compare(algorithms=None, datasets=None, k=10, trials=1):
    """
    Compare various learners on various datasets using cross-validation.
    Print results as a table.
    """
    # default list of algorithms
    algorithms = algorithms or [PluralityLearner, NaiveBayesLearner, NearestNeighborLearner, DecisionTreeLearner]

    # default list of datasets
    datasets = datasets or [iris, orings, zoo, restaurant, SyntheticRestaurant(20),
                            Majority(7, 100), Parity(7, 100), Xor(100)]

    print_table([[a.__name__.replace('Learner', '')] + [cross_validation(a, d, k=k, trials=trials) for d in datasets]
                 for a in algorithms], header=[''] + [d.name[0:7] for d in datasets], numfmt='%.2f')