# CRF model
model_crf = sklearn_crfsuite.CRF(algorithm='lbfgs',
c1=0.25,
c2=0.01,
max_iterations=100,
all_possible_transitions=True)
# train the model
model_crf.fit(X_train, y_train)
labels = list(model_crf.classes_)
# preditcion of the labels of the test sequence
y_pred = model_crf.predict(X_test)
# print output time remarks
outputSteps(y_pred[0])
# calculate probability
def get_prob(y_prob):
prob_actions = []
for i in y_prob:
for x in i:
prob_actions.append(x[max(x, key=x.get)])
prob_seq = prod(prob_actions)
return prob_seq
# Probability to model sequence
y_prob = model_crf.predict_marginals(X_test)
prob_results.append(get_prob(y_prob))
# Probability to model random sequence
# flatten ground_truth of trainingsdata
y_train_ground_truth_flatten = [
item for sublist in y_train_ground_truth for item in sublist
]
# Gaussian Naive Bayes (GaussianNB)
model_bayes = GaussianNB()
# training
model_bayes.fit(X_train_flatten, y_train_ground_truth_flatten)
# state prediction
y_pred_bayes = model_bayes.predict(X_test_flatten)
# print output time remarks
outputSteps(y_pred_bayes)
# probability calculation
def get_prob(y_prob):
prob_actions = []
for i in y_prob:
prob_actions.append(max(i))
prob_seq = sum(prob_actions)
return prob_seq
# Probability to model sequence
y_prob = model_bayes.predict_log_proba(X_test_flatten)
prob_results.append(math.exp(get_prob(y_prob)))
# Probability to model random sequence
y_prob_random_seq = model_bayes.predict_log_proba(X_random)
# change type to array
seqlearn_X_train = np.array(X_train_flatten)
seqlearn_y_ground_truth = np.array(y_ground_truth_flatten)
# HMM seqlearn MultimodalHMM
model_seqlearn = MultinomialHMM()
# training
model_seqlearn.fit(seqlearn_X_train, seqlearn_y_ground_truth, len_train)
# state prediction
y_pred_seqlearn = model_seqlearn.predict(X_test_flatten)
# print output time remarks
outputSteps(y_pred_seqlearn)
#state prediction for random sequence
y_pred_seqlearn_random = model_seqlearn.predict(X_random)
# state prediction for heuristic sequence
y_pred_seqlearn_random = model_seqlearn.predict(X_heuristic)
# target names for evaluation
target_names = list(step_set)
target_names = sorted(target_names)
# confusion matrix
cnf_matrix = confusion_matrix(y_ground_truth, y_pred_seqlearn)
normalize = cnf_matrix.astype('float') / cnf_matrix.sum(axis=1)[:,
np.newaxis]