def run(n_models=10, n_iter=200, iter_step=10, n_needles=2, n_distractors=8,
n_rows=100, pairtype=None, pair_kws=None):
needle_idxs = [(2*i, 2*i+1,) for i in range(n_needles)]
needle_cols = list(range(n_needles*2))
distractor_cols = list(range(n_needles*2, n_needles*2+n_distractors))
combs = list(it.product(needle_cols, distractor_cols))
distractor_idxs = random.sample(combs, min(len(combs), 32))
df = _gen_data(n_needles, n_distractors, n_rows, pairtype, pair_kws)
engine = Engine(df, n_models=n_models)
engine.init_models()
# for model in engine._models:
# # XXX: emulates the log grid expected alpha
# # e.g. mean(exp(linspace(log(1/n_rows), log(rows))))
# # model['state_alpha'] = .5*(n_needles*2. + n_distractors)
# model['state_alpha'] = 100.
# no column_alpha transition
tlist = [b'row_assignment', b'column_assignment', b'row_alpha',
b'column_hypers']
n_steps = int(n_iter/iter_step)
needle_dps = np.zeros((n_needles, n_steps+1,))
distractor_dps = np.zeros((len(distractor_idxs), n_steps+1,))
for i in range(n_steps+1):
engine.run(iter_step, trans_kwargs={'transition_list': tlist})
# engine.run(iter_step)
for nidx, (a, b) in enumerate(needle_idxs):
a = df.columns[a]
b = df.columns[b]
needle_dps[nidx, i] = engine.dependence_probability(a, b)
for didx, (a, b) in enumerate(distractor_idxs):
a = df.columns[a]
b = df.columns[b]
distractor_dps[didx, i] = engine.dependence_probability(a, b)
iter_count = np.cumsum([1]+[iter_step]*n_steps)
for y in distractor_dps:
plt.plot(iter_count, y, color='gray', alpha=.3)
for y in needle_dps:
plt.plot(iter_count, y, color='crimson')
# plt.gca().set_xscale('log')
plt.ylim([-.05, 1.05])
plt.xlim([1, iter_count[-1]])
plt.show()
engine.heatmap('dependence_probability')
plt.show()
def test_dependence_probability():
x = np.random.randn(30)
s1 = pd.Series(x)
s2 = pd.Series(x + 1.0)
s3 = pd.Series(np.random.rand(30))
df = pd.concat([s1, s2, s3], axis=1)
df.columns = ['c0', 'c1', 'c2']
engine = Engine(df, n_models=20, use_mp=False)
engine.init_models()
engine.run(10)
depprob_01 = engine.dependence_probability('c0', 'c1')
depprob_02 = engine.dependence_probability('c0', 'c2')
depprob_12 = engine.dependence_probability('c1', 'c2')
assert depprob_01 > depprob_02
assert depprob_01 > depprob_12
def test_dependence_probability():
x = np.random.randn(30)
s1 = pd.Series(x)
s2 = pd.Series(x + 1.0)
s3 = pd.Series(np.random.rand(30))
df = pd.concat([s1, s2, s3], axis=1)
df.columns = ['c0', 'c1', 'c2']
engine = Engine(df, n_models=20, use_mp=False)
engine.init_models()
engine.run(10)
depprob_01 = engine.dependence_probability('c0', 'c1')
depprob_02 = engine.dependence_probability('c0', 'c2')
depprob_12 = engine.dependence_probability('c1', 'c2')
assert depprob_01 > depprob_02
assert depprob_01 > depprob_12
