def test_concept_active_learner():
n_features = 3
hyp_space_type = "boundary"
active_learner = ConceptActiveLearner(n_features, hyp_space_type)
active_learner.update_posterior()
active_learner_prob = active_learner.expected_information_gain()
first_feature_prob = np.array([np.log2(4) - 3/4 * np.log2(3),
np.log2(4) - np.log2(2),
np.log2(4) - 3/4 * np.log2(3)])
assert np.allclose(first_feature_prob,
active_learner_prob)
def run_three_feature_line_simulations():
hyp_space_type = "line"
n_hyp = 6
n_features = 3
n_labels = 2
sampling = "max"
# feature, label pairs
xs = [0, 0, 1, 1, 2, 2]
ys = [0, 1, 0, 1, 0, 1]
figure, ax = plt.subplots()
al = ConceptActiveLearner(n_features, hyp_space_type, sampling)
active_learning_prob_one = np.array(
[al.expected_information_gain(x) for x in range(n_features)])
# normalize
active_learning_prob_one = active_learning_prob_one / \
np.sum(active_learning_prob_one)
# get predictions from self-teaching model
st = ConceptSelfTeacher(n_features, hyp_space_type, sampling)
st.update_learner_posterior()
st.update_self_teaching_posterior()
self_teacher_prob_one = st.self_teaching_posterior[0, :, 0]
plt.figure()
plt.plot(
np.arange(1, n_features + 1),
active_learning_prob_one,
color='red',
# linestyle=':',
label="Information Gain model")
plt.plot(np.arange(1, n_features + 1),
self_teacher_prob_one,
color='blue',
label="Self-teaching model")
axes = plt.gca()
# axes.set_ylim([0.1, 0.15])
plt.xticks(np.arange(1, n_features + 1), fontsize=16)
plt.yticks(fontsize=16)
axes.set_ylim([0, 0.4])
handles, labels = ax.get_legend_handles_labels()
plt.legend(loc='lower center', fontsize=16)
plt.xlabel("Feature", fontsize=16)
plt.ylabel("Probability of selecting feature", fontsize=16)
plt.tight_layout()
plt.savefig('figures/concept_learning_line_three_features.png')
def run_eight_feature_line_simulations():
hyp_space_type = "line"
n_hyp = 36
n_features = 8
figure, ax = plt.subplots()
al = ConceptActiveLearner(n_features, hyp_space_type)
al.update_posterior()
active_learning_prob_one = al.expected_information_gain()
# normalize
active_learning_prob_one = active_learning_prob_one / \
np.sum(active_learning_prob_one)
# get predictions from self-teaching model
st = ConceptSelfTeacher(n_features, hyp_space_type)
st.update_learner_posterior()
st.update_self_teaching_posterior()
self_teacher_prob_one = st.self_teaching_posterior
plt.figure()
plt.plot(
np.arange(1, n_features + 1),
active_learning_prob_one,
color='red',
# linestyle=':',
label="Information Gain model")
plt.plot(np.arange(1, n_features + 1),
self_teacher_prob_one,
color='blue',
label="Self-teaching model")
axes = plt.gca()
axes.set_ylim([0, 0.2])
plt.xticks(np.arange(1, n_features + 1), fontsize=16)
plt.yticks(fontsize=16)
handles, labels = ax.get_legend_handles_labels()
plt.legend(loc='lower center', fontsize=16)
plt.xlabel("Feature", fontsize=16)
plt.ylabel("Probability of selecting feature", fontsize=16)
plt.tight_layout()
plt.savefig('figures/concept_learning_line_eight_features.png')
def run_second_feature_boundary_simulations():
hyp_space_type = "boundary"
n_hyp = 4
n_features = 3
n_labels = 2
sampling = "max"
# feature, label pairs
xs = [0, 1, 1, 2]
ys = [1, 0, 1, 0]
figure, ax = plt.subplots()
figure.set_size_inches(10, 10)
for i, (x, y) in enumerate(zip(xs, ys)):
# get predictions from active learning model
al = ConceptActiveLearner(n_features, hyp_space_type, sampling)
active_learning_prob_one = np.array(
[al.expected_information_gain(x) for x in range(n_features)])
# normalize
active_learning_prob_one = active_learning_prob_one / \
np.sum(active_learning_prob_one)
# perform update
al.update(x=x, y=y)
active_learning_prob_two = np.array(
[al.expected_information_gain(x) for x in range(n_features)])
# normalize
denom = np.sum(active_learning_prob_two)
active_learning_prob_two = np.divide(active_learning_prob_two,
denom,
where=denom != 0)
active_learning_prob_two[np.isclose(denom, 0)] = 0
# get predictions from self-teaching model
st = ConceptSelfTeacher(n_features, hyp_space_type, sampling)
st.update_learner_posterior()
st.update_self_teaching_posterior()
self_teacher_prob_one = st.self_teaching_posterior[0, :, 0]
# update learner posterior after a single observation
updated_learner_posterior = st.learner_posterior[:, x, y]
st.learner_posterior = np.repeat(updated_learner_posterior,
n_labels * n_features).reshape(
n_hyp, n_features, n_labels)
# update learner and self-teacher after a single observation
st.update_learner_posterior()
st.update_self_teaching_posterior()
self_teacher_prob_two = st.self_teaching_posterior[0, :, 0]
# plot second feature prob
plt.subplot(2, 2, i + 1)
plt.plot(
np.arange(1, n_features + 1),
active_learning_prob_two,
color='red',
# linestyle=':',
label="Information Gain model")
plt.plot(np.arange(1, n_features + 1),
self_teacher_prob_two,
color='blue',
label="Self-teaching model")
axes = plt.gca()
axes.set_ylim([0, 1])
plt.xlabel("Feature", fontsize=16)
plt.ylabel("Probability of selecting feature", fontsize=16)
plt.title('x = {}, y = {}'.format(x + 1, y), fontsize=18)
plt.xticks([1, 2, 3], fontsize=16)
plt.yticks(fontsize=16)
handles, labels = ax.get_legend_handles_labels()
plt.legend(fontsize=12)
plt.tight_layout()
plt.savefig('figures/concept_learning_boundary_second_feature_prob.png')