def uncertainty_values(self, data, target, X_train, y_train, X_full,
y_full, train_idx):
print("START: ST")
# initializing the active learner
learner = ActiveLearner(estimator=RandomForestClassifier(),
query_strategy=margin_sampling,
X_training=X_train,
y_training=y_train)
print('%f' % learner.score(X_full, y_full))
index = 0
# learning until the accuracy reaches a given threshold
while learner.score(X_full, y_full) < 0.90:
stream_idx = np.random.choice(range(len(X_full)))
if classifier_uncertainty(learner, X_full[stream_idx].reshape(
1, -1)) >= 0.4:
print("[ %1.3f, %1.3f]" %
(classifier_uncertainty(
learner, X_full[stream_idx].reshape(1, -1))[0],
classifier_margin(learner, X_full[stream_idx].reshape(
1, -1))[0]))
learner.teach(X_full[stream_idx].reshape(1, -1),
y_full[stream_idx].reshape(-1, ))
learner_score = learner.score(X_full, y_full)
# print('Item no. %d queried, new accuracy: %f' % (stream_idx, learner_score))
# print('%f' % (learner_score))
if index == 50:
break
index = index + 1
print("START: ST")
def jetze_sampler(classifier, X, n_instances=1, **uncertainty_measure_kwargs):
"""
Sample randomly with weights based on the margin
:param classifier:
:param X:
:param n_instances:
:param uncertainty_measure_kwargs:
:return:
"""
margin = classifier_margin(classifier, X, **uncertainty_measure_kwargs)
sample_weights = margin / np.sum(margin)
query_idx = np.random.choice(range(len(margin)),
size=n_instances,
p=sample_weights)
return query_idx, X[query_idx]
# linear_combination will return 1.0*classifier_uncertainty + 1.0*classifier_margin
linear_combination = make_linear_combination(
classifier_uncertainty, classifier_margin,
weights=[1.0, 1.0]
)
# product will return (classifier_uncertainty**0.5)*(classifier_margin**0.1)
product = make_product(
classifier_uncertainty, classifier_margin,
exponents=[0.5, 0.1]
)
# visualizing the different utility metrics
with plt.style.context('seaborn-white'):
utilities = [
(1, classifier_uncertainty(learner, X), 'Classifier uncertainty'),
(2, classifier_margin(learner, X), 'Classifier margin'),
(3, linear_combination(learner, X), '1.0*uncertainty + 1.0*margin'),
(4, product(learner, X), '(uncertainty**0.5)*(margin**0.5)')
]
plt.figure(figsize=(18, 14))
for idx, utility, title in utilities:
plt.subplot(2, 2, idx)
plt.scatter(x=X[:, 0], y=X[:, 1], c=utility, cmap='viridis', s=50)
plt.title(title)
plt.colorbar()
plt.show()
# defining the custom query strategy, which uses the linear combination of
