# print(nb_test)
print("---------------------@Build knowledge-------------------------------")
MAX_SEQ_LENGTH, item_dict, reversed_item_dict, item_probs, item_freq_dict, user_dict = MC_utils.build_knowledge(train_instances+test_instances)
if not os.path.exists(o_dir):
os.makedirs(o_dir)
saved_file = os.path.join(o_dir, 'transition_matrix_MC.npz')
# print("Save model in ", saved_file)
transition_matrix = sp.load_npz(saved_file)
mc_model = MarkovChain(item_dict, reversed_item_dict, item_freq_dict, transition_matrix, mc_order)
if ex_file is not None:
ex_instances = MC_utils.read_instances_lines_from_file(ex_file)
else :
ex_instances = test_instances
for i in random.sample(ex_instances, nb_predict):
elements = i.split('|')
b_seq = elements[1:]
# prev_basket = [item for item in re.split('[\\s]+',b_seq[-2].strip())]
prev_item = []
for prev_basket in b_seq[:-1]:
prev_item += re.split('[\\s]+', prev_basket.strip())
target_basket = [item for item in re.split('[\\s]+',b_seq[-1].strip())]
topk_item = mc_model.top_predicted_item(prev_item, topk)
correct_set = set(topk_item).intersection(set(target_basket))
print("Input basket: ", prev_item)
print("Ground truth: ", target_basket)
print("Nb_correct: ", len(correct_set))
print("Predict topk: ", topk_item)
print("Items correct: ", list(correct_set))
print()
