def test_ray():
"""Test the ray result matches the sequential one
"""
for n, p in [[100, 10], [1000, 30], [1000, 100]]:
X, y = make_classification(n_samples=n,
n_features=p,
n_informative=int(0.1 * p),
n_redundant=0,
n_repeated=0,
n_classes=2,
n_clusters_per_class=1,
flip_y=0.1,
shift=0.0,
scale=1.0,
shuffle=False,
random_state=123)
y = y[:, np.newaxis]
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=123)
bnn = BnnBinaryClassifier(verbose=0).fit(X_train, y_train)
M_F, V_F = bnn.logit_posterior(X_test)
seq_result = rate(X_test, M_F, V_F)
ray_seq_result = RATE_ray(X_test, M_F, V_F, n_jobs=1)
ray_par_result = RATE_ray(X_test, M_F, V_F, n_jobs=2)
assert np.array_equal(seq_result, ray_seq_result)
assert np.array_equal(seq_result, ray_par_result)
gbm_mimic, gbm_mimic_time = train_mimic(
RandomizedSearchCV(
GradientBoostingRegressor(),
gbm_param_grid(p),
n_iter=n_search_iter,
cv=k,
n_jobs=n_jobs),
bnn, X_train, bnn_soft_predictions, X_test, n_mc_samples, True
)
variable_importances = add_importance_scores(
"gradient boosting machine mimic", gbm_mimic.best_estimator_.feature_importances_, dict_key, repeat_idx)
timings = add_timing("gradient boosting machine mimic", gbm_mimic_time, dict_key, repeat_idx)
# RATE
M_F, V_F = bnn.logit_posterior(X_test)
rate_vals, rate_time = RATE2(X_test, M_F, V_F, return_time=True)
variable_importances = add_importance_scores("RATE", rate_vals, dict_key, repeat_idx)
timings = add_timing("RATE", rate_time, dict_key, repeat_idx)
# Saliency-style maps, averaged over examples to give global importance. Average is of absolute value
with DeepExplain(session=K.get_session()) as de:
input_tensor = nn.layers[0].input
target_tensor = Model(inputs=input_tensor, outputs=nn.layers[-2].output)(input_tensor)
for attr_method in ["grad*input", "saliency", "intgrad", "elrp", "occlusion", "shapley_sampling"]:
arg_dict = {'samples' : 10} if "attr_method"=="shapley_sampling" else {}
s_time = time.time()
imp_vals = de.explain(
attr_method,
target_tensor, input_tensor,