def check_generate(name): check_cm(name) cm = ComponentModel(name) cm.realize_hp() params = cm.generate_post() b = BasicDistribution(name, pm=params) b.sample_data()
def check_ss_io(name): check_cm(name) cm = ComponentModel(name) cm.realize_hp() assert_equal(ComponentModel(name, ss=cm.dump_ss()).dump_ss(), cm.dump_ss()) cm.add_data(cm.sample_data()) assert_equal(ComponentModel(name, ss=cm.dump_ss()).dump_ss(), cm.dump_ss())
def check_ss_io(name): check_cm(name) cm = ComponentModel(name) cm.realize_hp() assert_equal(ComponentModel(name, ss=cm.dump_ss()).dump_ss(), cm.dump_ss()) cm.add_data(cm.sample_data()) assert_equal(ComponentModel(name, ss=cm.dump_ss()).dump_ss(), cm.dump_ss())
def check_generate(name): check_cm(name) cm = ComponentModel(name) cm.realize_hp() params = cm.generate_post() b = BasicDistribution(name, pm=params) b.sample_data()
def check_dd(impl, data_count, D): check_cm(impl) data = histogram(np.random.randint(D, size=data_count), bin_count=D) cm = ComponentModel( impl, ss={'counts': data}, p={'D': D}) cm.realize_hp() _check_discrete(cm)
def check_sums(name): check_cm(name) cm = ComponentModel(name) cm.realize_hp() values = [cm.sample_data() for _ in range(COUNT)] score = 0. for value in values: score += cm.pred_prob(value) cm.add_data(value) assert_almost_equal(score, cm.data_prob())
def check_sums(name): check_cm(name) cm = ComponentModel(name) cm.realize_hp() values = [cm.sample_data() for _ in range(COUNT)] score = 0. for value in values: score += cm.pred_prob(value) cm.add_data(value) assert_almost_equal(score, cm.data_prob())
def check_probs(a, b): check_cm(a) check_cm(b) a = ComponentModel(a) a.realize_hp() b = ComponentModel(b, hp=a.dump_hp()) dps = [a.sample_data() for _ in range(DPS)] for y in dps: assert_almost_equal(a.data_prob(), b.data_prob()) assert_almost_equal(a.pred_prob(y), b.pred_prob(y)) a.add_data(y) b.add_data(y)
def check_sample_data_seed(name): check_cm(name) n = 10 seed(0) cm1 = ComponentModel(name) cm1.realize_hp() data_values1 = [cm1.sample_data() for _ in range(n)] seed(0) cm2 = ComponentModel(name) cm2.realize_hp() data_values2 = [cm2.sample_data() for _ in range(n)] for i in range(n): assert_almost_equal(data_values1[i], data_values2[i])
def check_sample_data_seed(name): check_cm(name) n = 10 seed(0) cm1 = ComponentModel(name) cm1.realize_hp() data_values1 = [cm1.sample_data() for _ in range(n)] seed(0) cm2 = ComponentModel(name) cm2.realize_hp() data_values2 = [cm2.sample_data() for _ in range(n)] for i in range(n): assert_almost_equal(data_values1[i], data_values2[i])
def check_ss(a, b): check_cm(a) check_cm(b) a = ComponentModel(a) a.realize_hp() b = ComponentModel(b, hp=a.dump_hp()) dps = [a.sample_data() for _ in range(DPS)] assert_equal(a.dump_ss(), b.dump_ss()) for y in dps: a.add_data(y) b.add_data(y) assert_close(a.dump_ss(), b.dump_ss()) for y in dps: a.remove_data(y) b.remove_data(y) assert_close(a.dump_ss(), b.dump_ss())
def check_exchangeable(name): check_cm(name) cm = ComponentModel(name) cm.realize_hp() values = [cm.sample_data() for _ in range(COUNT)] p1 = permutation(COUNT) p2 = permutation(COUNT) for i in range(COUNT): cm.add_data(values[p1[i]]) prob1 = cm.data_prob() for i in range(COUNT): cm.remove_data(values[p1[i]]) assert_almost_equal(cm.data_prob(), 0.) for i in range(COUNT): cm.add_data(values[p2[i]]) prob2 = cm.data_prob() assert_almost_equal(prob1, prob2)
def check_exchangeable(name): check_cm(name) cm = ComponentModel(name) cm.realize_hp() values = [cm.sample_data() for _ in range(COUNT)] p1 = permutation(COUNT) p2 = permutation(COUNT) for i in range(COUNT): cm.add_data(values[p1[i]]) prob1 = cm.data_prob() for i in range(COUNT): cm.remove_data(values[p1[i]]) assert_almost_equal(cm.data_prob(), 0.) for i in range(COUNT): cm.add_data(values[p2[i]]) prob2 = cm.data_prob() assert_almost_equal(prob1, prob2)
def test_vectorize(): for name in MODELS: check_cm(name) cm0 = ComponentModel(name) cm0.realize_hp() hp0 = cm0.dump_hp() cms = [ComponentModel(name, hp=hp0) for _ in range(COMPS)] for cm in cms: dps = [cm.sample_data() for _ in range(DPS)] for dp in dps: cm.add_data(dp) mod = cms[0].mod hp = cms[0].hp ss = [cm.ss for cm in cms] for cm in cms: y = cm.sample_data() scores = numpy.zeros(COMPS) mod.add_pred_probs(hp, ss, y, scores) for cm, score in zip(cms, scores): assert_almost_equal(score, cm.pred_prob(y))
def test_vectorize(): for name in MODELS: check_cm(name) cm0 = ComponentModel(name) cm0.realize_hp() hp0 = cm0.dump_hp() cms = [ComponentModel(name, hp=hp0) for _ in range(COMPS)] for cm in cms: dps = [cm.sample_data() for _ in range(DPS)] for dp in dps: cm.add_data(dp) mod = cms[0].mod hp = cms[0].hp ss = [cm.ss for cm in cms] for cm in cms: y = cm.sample_data() scores = numpy.zeros(COMPS) mod.add_pred_probs(hp, ss, y, scores) for cm, score in zip(cms, scores): assert_almost_equal(score, cm.pred_prob(y))
def add_remove_add(name, raw_hps, raw_ss0=None): ''' This tests add_data, remove_data, pred_prob, data_prob ''' DATA_COUNT = 20 for raw_hp in raw_hps: cm = ComponentModel(name, hp=raw_hp, ss=raw_ss0) cm.realize_hp() data = [] score = 0 for _ in range(DATA_COUNT): dp = cm.sample_data() data.append(dp) score += cm.pred_prob(dp) cm.add_data(dp) cm_all = ComponentModel(name, ss=cm.dump_ss()) assert_close( score, cm.data_prob(), err_msg='p(x1,...,xn) != p(x1) p(x2|x1) p(xn|...)') random.shuffle(data) for dp in data: cm.remove_data(dp) cm0 = ComponentModel(name, ss=raw_ss0) assert_close(cm.ss, cm0.ss, err_msg='ss + data - data != ss') random.shuffle(data) for dp in data: cm.add_data(dp) assert_close(cm.ss, cm_all.ss, err_msg='ss - data + data != ss')
def add_remove_add(name, raw_hps, raw_ss0=None): ''' This tests add_data, remove_data, pred_prob, data_prob ''' DATA_COUNT = 20 for raw_hp in raw_hps: cm = ComponentModel(name, hp=raw_hp, ss=raw_ss0) cm.realize_hp() data = [] score = 0 for _ in range(DATA_COUNT): dp = cm.sample_data() data.append(dp) score += cm.pred_prob(dp) cm.add_data(dp) cm_all = ComponentModel(name, ss=cm.dump_ss()) assert_close(score, cm.data_prob(), err_msg='p(x1,...,xn) != p(x1) p(x2|x1) p(xn|...)') random.shuffle(data) for dp in data: cm.remove_data(dp) cm0 = ComponentModel(name, ss=raw_ss0) assert_close(cm.ss, cm0.ss, err_msg='ss + data - data != ss') random.shuffle(data) for dp in data: cm.add_data(dp) assert_close(cm.ss, cm_all.ss, err_msg='ss - data + data != ss')
def check_hp_io(name): check_cm(name) cm = ComponentModel(name) cm.realize_hp() assert_equal(ComponentModel(name, hp=cm.dump_hp()).dump_hp(), cm.dump_hp())
def check_dd(impl, data_count, D): check_cm(impl) data = histogram(np.random.randint(D, size=data_count), bin_count=D) cm = ComponentModel(impl, ss={'counts': data}, p={'D': D}) cm.realize_hp() _check_discrete(cm)
def check_hp_io(name): check_cm(name) cm = ComponentModel(name) cm.realize_hp() assert_equal(ComponentModel(name, hp=cm.dump_hp()).dump_hp(), cm.dump_hp())