Python rng.rng函数代码示例

def test_explicit_exceptions():
    """ValueError should be rasied for bad assignments
    """
    prng = rng()
    N, V = 3, 7
    defn = model_definition(N, V)
    data = [[0, 1, 2, 3], [0, 1, 4], [0, 1, 5, 6]]

    # We should get an error if we leave out a dish assignment for a given table
    table_assignments = [[1, 2, 1, 2], [1, 1, 1], [3, 3, 3, 1]]
    dish_assignments = [[0, 1, 2], [0, 3], [0, 1, 2]]

    assert_raises(ValueError,
                  initialize,
                  defn, data,
                  table_assignments=table_assignments,
                  dish_assignments=dish_assignments)

    # We should get an error if we leave out a table assignment for a given word
    table_assignments = [[1, 2, 1, 2], [1, 1, 1], [3, 3, 3]]
    dish_assignments = [[0, 1, 2], [0, 3], [0, 1, 2, 1]]

    assert_raises(ValueError,
                  initialize,
                  defn, data,
                  table_assignments=table_assignments,
                  dish_assignments=dish_assignments)

def test_kernel_gibbs_hp():
    _test_kernel_gibbs_hp(initialize,
                          numpy_dataview,
                          bind,
                          gibbs_hp,
                          'grid_gibbs_hp_samples_pdf',
                          rng())

def _test_runner_simple(defn, kc_fn):
    views = map(numpy_dataview, toy_dataset(defn))
    kc = kc_fn(defn)
    prng = rng()
    latent = model.initialize(defn, views, prng)
    r = runner.runner(defn, views, latent, kc)
    r.run(prng, 10)

def test_slice_theta_mm():
    N = 100
    data = np.array(
        [(np.random.random() < 0.8,) for _ in xrange(N)],
        dtype=[('', bool)])
    defn = model_definition(N, [bbnc])
    r = rng()
    prior = {'alpha': 1.0, 'beta': 9.0}
    view = numpy_dataview(data)
    s = initialize(
        defn,
        view,
        cluster_hp={'alpha': 1., 'beta': 9.},
        feature_hps=[prior],
        r=r,
        assignment=[0] * N)

    heads = len([1 for y in data if y[0]])
    tails = N - heads

    alpha1 = prior['alpha'] + heads
    beta1 = prior['beta'] + tails

    bs = bind(s, view)
    params = {0: {'p': 0.05}}

    def sample_fn():
        theta(bs, r, tparams=params)
        return s.get_suffstats(0, 0)['p']

    rv = beta(alpha1, beta1)
    assert_1d_cont_dist_approx_sps(sample_fn, rv, nsamples=50000)

def test_multivariate_models_cxx():
    _test_multivariate_models(
        initialize,
        numpy_dataview,
        bind,
        gibbs_assign,
        rng())

def _test_convergence_bb_cxx(N,
                             D,
                             kernel,
                             preprocess_data_fn=None,
                             nonconj=False,
                             burnin_niters=10000,
                             skip=10,
                             ntries=50,
                             nsamples=1000,
                             kl_places=2):
    r = rng()
    cluster_hp = {'alpha': 2.0}
    feature_hps = [{'alpha': 1.0, 'beta': 1.0}] * D
    defn = model_definition(N, [bb] * D)
    nonconj_defn = model_definition(N, [bbnc] * D)
    Y, posterior = data_with_posterior(
        defn, cluster_hp, feature_hps, preprocess_data_fn)
    data = numpy_dataview(Y)
    s = initialize(nonconj_defn if nonconj else defn,
                   data,
                   cluster_hp=cluster_hp,
                   feature_hps=feature_hps,
                   r=r)
    bs = bind(s, data)
    wrapped_kernel = lambda s: kernel(s, r)
    _test_convergence(bs,
                      posterior,
                      wrapped_kernel,
                      burnin_niters,
                      skip,
                      ntries,
                      nsamples,
                      kl_places)

def test_cxx_sample_post_pred_given_data():
    assert D == 5
    y_new = ma.masked_array(
        np.array([(True, False, True, True, True)], dtype=[('', np.bool)] * 5),
        mask=[(False, False, True, True, True)])[0]
    _test_sample_post_pred(
        cxx_initialize, cxx_numpy_dataview, y_new, rng(543234))

def test_cant_serialize():
    N, V = 10, 20
    defn = model_definition(N, V)
    data = toy_dataset(defn)
    prng = rng()
    s = initialize(defn, data, prng)
    s.serialize()

def test_slice_theta_irm():
    N = 10
    defn = model_definition([N], [((0, 0), bbnc)])
    data = np.random.random(size=(N, N)) < 0.8
    view = numpy_dataview(data)
    r = rng()
    prior = {'alpha': 1.0, 'beta': 9.0}

    s = initialize(
        defn,
        [view],
        r=r,
        cluster_hps=[{'alpha': 2.0}],
        relation_hps=[prior],
        domain_assignments=[[0] * N])

    bs = bind(s, 0, [view])

    params = {0: {'p': 0.05}}

    heads = len([1 for y in data.flatten() if y])
    tails = len([1 for y in data.flatten() if not y])

    alpha1 = prior['alpha'] + heads
    beta1 = prior['beta'] + tails

    def sample_fn():
        theta(bs, r, tparams=params)
        return s.get_suffstats(0, [0, 0])['p']

    rv = beta(alpha1, beta1)
    assert_1d_cont_dist_approx_sps(sample_fn, rv, nsamples=50000)

def test_alpha_numeric():
    docs = [list('abcd'), list('cdef')]
    defn = model_definition(len(docs), v=6)
    prng = rng()
    s = initialize(defn, docs, prng)
    assert_equals(s.nentities(), len(docs))
    assert_equals(s.nwords(), 6)

def test_dense_vs_sparse():
    # XXX: really belongs in irm test cases, but kernels has a nice cluster
    # enumeration iterator

    r = rng()

    n = 5
    raw = ma.array(
        np.random.choice(np.arange(20), size=(n, n)),
        mask=np.random.choice([False, True], size=(n, n)))

    dense = [relation_numpy_dataview(raw)]
    sparse = [sparse_relation_dataview(_tocsr(raw))]

    domains = [n]
    relations = [((0, 0), gp)]
    defn = irm_definition(domains, relations)

    def score_fn(data):
        def f(assignments):
            s = irm_initialize(defn, data, r=r, domain_assignments=assignments)
            assign = sum(s.score_assignment(i)
                         for i in xrange(len(assignments)))
            likelihood = s.score_likelihood(r)
            return assign + likelihood
        return f

    product_assignments = tuple(map(list, map(permutation_iter, domains)))

    dense_posterior = scores_to_probs(
        np.array(map(score_fn(dense), it.product(*product_assignments))))
    sparse_posterior = scores_to_probs(
        np.array(map(score_fn(sparse), it.product(*product_assignments))))

    assert_1d_lists_almost_equals(dense_posterior, sparse_posterior, places=3)

def test_runner_multiprocessing_convergence():
    N, D = 4, 5
    defn = model_definition(N, [bb] * D)
    prng = rng()
    Y, posterior = data_with_posterior(defn, r=prng)
    view = numpy_dataview(Y)
    latents = [model.initialize(defn, view, prng)
               for _ in xrange(mp.cpu_count())]
    runners = [runner.runner(defn, view, latent, ['assign'])
               for latent in latents]
    r = parallel.runner(runners)
    r.run(r=prng, niters=1000)  # burnin
    idmap = {C: i for i, C in enumerate(permutation_iter(N))}

    def sample_iter():
        r.run(r=prng, niters=10)
        for latent in r.get_latents():
            yield idmap[tuple(permutation_canonical(latent.assignments()))]

    ref = [None]

    def sample_fn():
        if ref[0] is None:
            ref[0] = sample_iter()
        try:
            return next(ref[0])
        except StopIteration:
            ref[0] = None
        return sample_fn()

    assert_discrete_dist_approx(sample_fn, posterior, ntries=100, kl_places=2)

def test_runner_multiprocessing_convergence():
    domains = [4]
    defn = model_definition(domains, [((0, 0), bb)])
    prng = rng()
    relations, posterior = data_with_posterior(defn, prng)
    views = map(numpy_dataview, relations)
    latents = [model.initialize(defn, views, prng)
               for _ in xrange(mp.cpu_count())]
    kc = [('assign', range(len(domains)))]
    runners = [runner.runner(defn, views, latent, kc) for latent in latents]
    r = parallel.runner(runners)
    r.run(r=prng, niters=10000)  # burnin
    product_assignments = tuple(map(list, map(permutation_iter, domains)))
    idmap = {C: i for i, C in enumerate(it.product(*product_assignments))}

    def sample_iter():
        r.run(r=prng, niters=10)
        for latent in r.get_latents():
            key = tuple(tuple(permutation_canonical(latent.assignments(i)))
                        for i in xrange(len(domains)))
            yield idmap[key]

    ref = [None]

    def sample_fn():
        if ref[0] is None:
            ref[0] = sample_iter()
        try:
            return next(ref[0])
        except StopIteration:
            ref[0] = None
        return sample_fn()

    assert_discrete_dist_approx(sample_fn, posterior, ntries=100, kl_places=2)

def test_posterior_predictive_statistic():
    N, D = 10, 4  # D needs to be even
    defn = model_definition(N, [bb] * D)
    Y = toy_dataset(defn)
    prng = rng()
    view = numpy_dataview(Y)
    latents = [model.initialize(defn, view, prng) for _ in xrange(10)]
    q = ma.masked_array(
        np.array([(False,) * D], dtype=[('', bool)] * D),
        mask=[(False,) * (D / 2) + (True,) * (D / 2)])

    statistic = query.posterior_predictive_statistic(q, latents, prng)
    assert_equals(statistic.shape, (1,))
    assert_equals(len(statistic.dtype), D)

    statistic = query.posterior_predictive_statistic(
        q, latents, prng, merge='mode')
    assert_equals(statistic.shape, (1,))
    assert_equals(len(statistic.dtype), D)

    statistic = query.posterior_predictive_statistic(
        q, latents, prng, merge=['mode', 'mode', 'avg', 'avg'])
    assert_equals(statistic.shape, (1,))
    assert_equals(len(statistic.dtype), D)

    q = ma.masked_array(
        np.array([(False,) * D] * 3, dtype=[('', bool)] * D),
        mask=[(False,) * (D / 2) + (True,) * (D / 2)] * 3)
    statistic = query.posterior_predictive_statistic(q, latents, prng)
    assert_equals(statistic.shape, (3,))
    assert_equals(len(statistic.dtype), D)

def data_with_posterior(defn,
                        cluster_hp=None,
                        feature_hps=None,
                        preprocess_data_fn=None,
                        r=None):
    # XXX(stephentu): should only accept conjugate models
    if r is None:
        r = rng()
    Y_clusters, _ = sample(defn, cluster_hp, feature_hps, r)
    Y = np.hstack(Y_clusters)
    if preprocess_data_fn:
        Y = preprocess_data_fn(Y)
    data = numpy_dataview(Y)

    def score_fn(assignment):
        s = initialize(defn,
                       data,
                       r,
                       cluster_hp=cluster_hp,
                       feature_hps=feature_hps,
                       assignment=assignment)
        return s.score_joint(r)

    posterior = dist_on_all_clusterings(score_fn, defn.n())
    return Y, posterior