###############################################################################
# Computing the results of the experiment
###############################################################################
test_score.append(naive.test_score(numpy.array(sets.lsa_vectors_test[i]), numpy.array(sets.robot_ids_test[i])))
probability = naive.classifier.predict_proba(sets.lsa_vectors_test[i])
for j in range(len(sets.lsa_vectors_test[i])):
predicted_class = naive.predict_new_robot_id(sets.lsa_vectors_test[i][j])[0]
r_class = sets.robot_ids_test[i][j]
if r_class != predicted_class:
print("Correct total prob", numpy.round(probability[j][r_class], 3))
print("Pred total prob", numpy.round(probability[j][predicted_class], 3))
print("Prob of real class:", numpy.round(math.exp(naive.classifier.class_log_prior_[r_class]), 3))
print("Prob of of predicted class:",
numpy.round(math.exp(naive.classifier.class_log_prior_[predicted_class]), 3))
for o in range(len(sets.lsa_vectors_test[i][j])):
if sets.lsa_vectors_test[i][j][o] > 0.1:
print("Term:" + lsa.features_utterance[o])
print("Prob of term given real class:",
math.exp(naive.classifier.feature_log_prob_[r_class][o]))
print("Prob of term given predicted class:",
math.exp(naive.classifier.feature_log_prob_[predicted_class][o]))
print(sets.lsa_vectors_test[i][j][o])
print('\n')
print("Human phrase: " + sets.test_phrases[i][j])
print("Correct phrase: " + db.get_robot_utterance(r_class))
print("Predicted phrase: " + db.get_robot_utterance(predicted_class))
print('\n'*3)
avg = numpy.round(numpy.average(numpy.array(test_score)), 2)
print("Test Score:", avg)
###############################################################################
###############################################################################
###############################################################################
# Computing the results of the experiment
###############################################################################
test_score.append(
naive.test_score(numpy.array(sets.lsa_vectors_test[i]),
numpy.array(sets.robot_ids_test[i])))
avg = numpy.round(numpy.average(numpy.array(test_score)), 2)
max_index = test_score.index(max(test_score))
print("Test Score:", avg)
print(max_index)
naive = NaiveBayesClassifier(alpha=ALPHA)
naive.learning_phase(numpy.array(sets.lsa_vectors_train[max_index]),
sets.robot_ids_train[max_index])
j = 0
for i in range(len(sets.lsa_vectors_test[max_index])):
if ((sets.robot_ids_test[max_index][i] == naive.predict_new_robot_id(
sets.lsa_vectors_test[max_index][i]))
and (sets.robot_ids_test[max_index][i] == j)):
print(sets.test_phrases[max_index][i])
print(db.get_robot_utterance(sets.robot_ids_test[max_index][i]))
j = j + 1
if j == 22:
break
###############################################################################