prev_reversed_item_dict, w_behavior, i)
list_prev_entries.append(prev_entry_dict)
list_freq_entries.append(prev_freq_dict)
list_reversed_entries.append(prev_reversed_item_dict)
list_trans_matrix.append(transition_matrix)
sp_matrix_path = model_name + '_transition_matrix_MC.npz'
# nb_item = len(item_dict)
# print('Density : %.6f' % (transition_matrix.nnz * 1.0 / nb_item / nb_item))
if not os.path.exists(o_dir):
os.makedirs(o_dir)
saved_file = os.path.join(o_dir, sp_matrix_path)
print("Save model in ", saved_file)
sp.save_npz(saved_file, transition_matrix)
mc_model = MarkovChain(item_dict, list_prev_entries[:-1],
list_freq_entries[:-1], list_reversed_entries[:-1],
list_trans_matrix, w_behavior, mc_order)
topk = 50
print('Predict to outfile')
predict_file = os.path.join(o_dir, 'predict_' + model_name + '.txt')
MC_utils.write_predict(predict_file, test_instances, topk, mc_model)
print('Predict done')
ground_truth, predict = MC_utils.read_predict(predict_file)
for topk in [5, 10, 15]:
print("Top : ", topk)
# hit_rate = MC_hit_ratio(test_instances, topk, mc_model)
# recall = MC_recall(test_instances, topk, mc_model)
hit_rate = MC_utils.hit_ratio(ground_truth, predict, topk)
recall = MC_utils.recall(ground_truth, predict, topk)
print("hit ratio: ", hit_rate)
print("recall: ", recall)
# transition_pair_dicts = MC_utils.multicore_calculate_transition_matrix(train_instances, item_dict, item_freq_dict, reversed_item_dict, w_behavior, mc_order)
row = []
col = []
data = []
for pair_dict in transition_pair_dicts:
print('Number pair in core: ', len(pair_dict))
row.extend([p[0] for p in pair_dict])
col.extend([p[1] for p in pair_dict])
data.extend([pair_dict[p] for p in pair_dict])
NB_ITEMS = len(item_dict)
transition_matrix = sp.csr_matrix((data, (row, col)), shape=(NB_ITEMS, NB_ITEMS), dtype="float32")
# transition_matrix
nb_nonzero = transition_matrix.getnnz()
density = nb_nonzero * 1.0 / NB_ITEMS / NB_ITEMS
print("Density of matrix: {:.6f}".format(density))
sp_matrix_path = model_name+'_transition_matrix_MC.npz'
# nb_item = len(item_dict)
# print('Density : %.6f' % (transition_matrix.nnz * 1.0 / nb_item / nb_item))
if not os.path.exists(o_dir):
os.makedirs(o_dir)
saved_file = os.path.join(o_dir, sp_matrix_path)
print("Save model in ", saved_file)
sp.save_npz(saved_file, transition_matrix)
mc_model = MarkovChain(item_dict, reversed_item_dict, item_freq_dict, w_behavior, transition_matrix, mc_order)
for topk in [5, 10, 15]:
print("Top : ", topk)
hit_rate = MC_hit_ratio(test_instances, topk, mc_model)
recall = MC_recall(test_instances, topk, mc_model)
print("hit ratio: ", hit_rate)
print("recall: ", recall)
from MC import MarkovChain
from bitarray import bitarray
from cryptography.fernet import Fernet
import sys
sys.setrecursionlimit(150000)
with open("../books/3001.txt", "r", encoding="utf-8") as myfile:
data = myfile.readlines()
m = MarkovChain()
for i in data:
m.learn(i)
length = 10000
m.babble(length)
def Encrypt(data):
key = Fernet.generate_key()
f = Fernet(key)
ciphertext = f.encrypt(data)
return (key, ciphertext)
def Decrypt(key_ciphertext):
f = Fernet(key_ciphertext[0])
decrypttext = f.decrypt(key_ciphertext[1])
return (decrypttext)
w_behavior = {'buy': 1, 'cart': 0.5, 'fav': 0.5, 'pv': 0.5}
else:
with open(w_behavior_file, 'r') as fp:
w_behavior = json.load(fp)
# 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, w_behavior)
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,
w_behavior, 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[-mc_model.mc_order - 1:-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 += [
p.split(':')[0]
for p in re.split('[\\s]+', prev_basket.strip())
]