learning.py

    return cross_validation(learner, size, dataset, k=len(dataset.examples))


def learningcurve(learner, dataset, trials=10, sizes=None):
    if sizes is None:
        sizes = list(range(2, len(dataset.examples) - 10, 2))

    def score(learner, size):
        random.shuffle(dataset.examples)
        return train_and_test(learner, dataset, 0, size)
    return [(size, mean([score(learner, size) for t in range(trials)]))
            for size in sizes]

# ______________________________________________________________________________
# The rest of this file gives datasets for machine learning problems.


orings = DataSet(name='orings', target='Distressed',
                 attrnames="Rings Distressed Temp Pressure Flightnum")


zoo = DataSet(name='zoo', target='type', exclude=['name'],
              attrnames="name hair feathers eggs milk airborne aquatic " +
              "predator toothed backbone breathes venomous fins legs tail " +
              "domestic catsize type")


iris = DataSet(name="iris", target="class",
               attrnames="sepal-len sepal-width petal-len petal-width class")

# ______________________________________________________________________________
# The Restaurant example from [Figure 18.2]


def RestaurantDataSet(examples=None):
    """Build a DataSet of Restaurant waiting examples. [Figure 18.3]"""
    return DataSet(name='restaurant', target='Wait', examples=examples,
                   attrnames='Alternate Bar Fri/Sat Hungry Patrons Price ' +
                   'Raining Reservation Type WaitEstimate Wait')


restaurant = RestaurantDataSet()


def T(attrname, branches):
    branches = {value: (child if isinstance(child, DecisionFork)
                        else DecisionLeaf(child))
                for value, child in branches.items()}
    return DecisionFork(restaurant.attrnum(attrname), attrname, branches)


""" [Figure 18.2]
A decision tree for deciding whether to wait for a table at a hotel.
"""

waiting_decision_tree = T('Patrons',
                          {'None': 'No', 'Some': 'Yes',
                           'Full': T('WaitEstimate',
                                     {'>60': 'No', '0-10': 'Yes',
                                      '30-60': T('Alternate',
                                                 {'No': T('Reservation',
                                                          {'Yes': 'Yes',
                                                           'No': T('Bar', {'No': 'No',
                                                                           'Yes': 'Yes'})}),
                                                  'Yes': T('Fri/Sat', {'No': 'No', 'Yes': 'Yes'})}
                                                 ),
                                      '10-30': T('Hungry',
                                                 {'No': 'Yes',
                                                  'Yes': T('Alternate',
                                                           {'No': 'Yes',
                                                            'Yes': T('Raining',
                                                                     {'No': 'No',
                                                                      'Yes': 'Yes'})})})})})


def SyntheticRestaurant(n=20):
    """Generate a DataSet with n examples."""
    def gen():
        example = list(map(random.choice, restaurant.values))
        example[restaurant.target] = waiting_decision_tree(example)
        return example
    return RestaurantDataSet([gen() for i in range(n)])

# ______________________________________________________________________________
# Artificial, generated datasets.


def Majority(k, n):
    """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 i 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 i 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 i in '12']
        examples.append([x, y, int(x) != int(y)])
    return DataSet(name="continuous xor", examples=examples)

# ______________________________________________________________________________


def compare(algorithms=[PluralityLearner, NaiveBayesLearner,
                        NearestNeighborLearner, DecisionTreeLearner],
            datasets=[iris, orings, zoo, restaurant, SyntheticRestaurant(20),
                      Majority(7, 100), Parity(7, 100), Xor(100)],
            k=10, trials=1):
    """Compare various learners on various datasets using cross-validation.
    Print results as a table."""
    print_table([[a.__name__.replace('Learner', '')] +
                 [cross_validation(a, d, k, trials) for d in datasets]
                 for a in algorithms],
                header=[''] + [d.name[0:7] for d in datasets], numfmt='%.2f')