def test_n_zero(self):
# Tests the corner case of n == 0 for the binomial distribution.
# binomial(0, p) should be zero for any p in [0, 1].
# This test addresses issue #3480.
zeros = np.zeros(2, dtype='int')
for p in [0, .5, 1]:
assert_(rnd.binomial(0, p) == 0)
np.testing.assert_array_equal(rnd.binomial(zeros, p), zeros)
def make_propensity_based_simulated_labeler(treat_strength, con_strength, noise_level,
base_propensity_scores, example_indices, exogeneous_con=0.,
setting="simple", seed=42):
np.random.seed(seed)
all_noise = random.normal(0, 1, base_propensity_scores.shape[0]).astype(np.float32)
all_threshholds = np.array(random.uniform(0, 1, base_propensity_scores.shape[0]), dtype=np.float32)
extra_confounding = random.normal(0, 1, base_propensity_scores.shape[0]).astype(np.float32)
all_propensity_scores = expit((1.-exogeneous_con)*logit(base_propensity_scores) + exogeneous_con * extra_confounding).astype(np.float32)
all_treatments = random.binomial(1, all_propensity_scores).astype(np.int32)
# indices in dataset refer to locations in entire corpus,
# but propensity scores will typically only inlcude a subset of the examples
reindex_hack = np.zeros(12000, dtype=np.int32)
reindex_hack[example_indices] = np.arange(example_indices.shape[0], dtype=np.int32)
def labeler(data):
index = data['index']
index_hack = tf.gather(reindex_hack, index)
treatment = tf.gather(all_treatments, index_hack)
confounding = 3.0 * (tf.gather(all_propensity_scores, index_hack) - 0.25)
noise = tf.gather(all_noise, index_hack)
y, y0, y1 = outcome_sim(treat_strength, con_strength, noise_level, tf.cast(treatment, tf.float32), confounding, noise, setting=setting)
simulated_prob = tf.nn.sigmoid(y)
y0 = tf.nn.sigmoid(y0)
y1 = tf.nn.sigmoid(y1)
threshold = tf.gather(all_threshholds, index)
simulated_outcome = tf.cast(tf.greater(simulated_prob, threshold), tf.int32)
return {**data, 'outcome': simulated_outcome, 'y0': y0, 'y1': y1, 'treatment': treatment}
return labeler
def make_propensity_based_simulated_labeler(treat_strength,
con_strength,
noise_level,
base_propensity_scores,
example_indices,
exogeneous_con=0.,
setting="simple",
seed=42):
np.random.seed(seed)
all_noise = random.normal(0, 1, base_propensity_scores.shape[0]).astype(
np.float32)
# extra_confounding = random.binomial(1, 0.5*np.ones_like(base_propensity_scores)).astype(np.float32)
extra_confounding = random.normal(
0, 1, base_propensity_scores.shape[0]).astype(np.float32)
all_propensity_scores = expit((1. - exogeneous_con) *
logit(base_propensity_scores) +
exogeneous_con * extra_confounding).astype(
np.float32)
all_treatments = random.binomial(1, all_propensity_scores).astype(np.int32)
# indices in dataset refer to locations in entire corpus,
# but propensity scores will typically only inlcude a subset of the examples
reindex_hack = np.zeros(422206, dtype=np.int32)
reindex_hack[example_indices] = np.arange(example_indices.shape[0],
dtype=np.int32)
def labeler(data):
index = data['index']
index_hack = tf.gather(reindex_hack, index)
treatment = tf.gather(all_treatments, index_hack)
confounding = tf.gather(all_propensity_scores, index_hack) - 0.5
noise = tf.gather(all_noise, index_hack)
simulated_score, y0, y1 = outcome_sim(treat_strength,
con_strength,
noise_level,
tf.cast(treatment, tf.float32),
confounding,
noise,
setting=setting)
return {
**data, 'outcome': simulated_score,
'y0': y0,
'y1': y1,
'treatment': treatment
}
return labeler
def test_binomial(self):
rnd.seed(self.seed, self.brng)
actual = rnd.binomial(100.123, .456, size=(3, 2))
desired = np.array([[43, 48], [55, 48], [46, 53]])
np.testing.assert_array_equal(actual, desired)