def online():
datareader = Datareader(mode='online', only_load=True)
print('NLP...')
stopwords = STOP_WORDS
token_weights = np.array(TOKEN_WEIGHTS)
nlp = NLP(datareader, stopwords=[])
ucm = nlp.get_ucm()
#ucm = bm25_row(ucm)
#inplace_csr_column_scale(ucm, token_weights)
urm = datareader.get_urm_shrinked()[0]
print('Computing similarity...')
start = time.time()
# Compute similarity
similarity = tversky_similarity(ucm, shrink=200, alpha=0.1, beta=1)
similarity = similarity.tocsr()
print(time.time() - start)
print('Computing eurm...')
start = time.time()
# Compute eurm
eurm_nlp = dot_product(similarity, urm, k=500)
eurm_nlp = eurm_nlp.tocsr()
print(eurm_nlp.shape)
eurm_nlp = eurm_nlp[-10000:, :]
sparse.save_npz(ROOT_DIR + '/data/eurm_nlp_no_stop_online.npz', eurm_nlp)
complete_name = mode+"_"+name+"_knn="+str(knn)+"_topk="+str(topk)\
+ '_' + datetime.datetime.now().strftime("%Y-%m-%d_%H-%M")
if mode=="offline":
complete_name+="_test="+str(test_num)
bot = Bot_v1(complete_name)
try:
######################SHRINKED
dr = Datareader(mode=mode, test_num=test_num, train_format="50k", only_load=True)
ev = Evaluator(dr)
pids = dr.get_test_pids()
urm, dictns, dict2 = dr.get_urm_shrinked()
urm_evaluation = dr.get_evaluation_urm()[pids]
pids_converted = np.array([dictns[x] for x in pids], dtype=np.int32)
slim = MultiThreadDSLIM_RMSE(urm.T)
slim.fit(l1_penalty=l1, l2_penalty=l2, positive_only=True, beta=beta, topK=topk)
evaluate_shrinked(W_sparse= slim.W_sparse, urm_shrinked= urm, pids_shrinked= pids_converted)
sps.save_npz(complete_name+".npz",slim.W_sparse,)
except Exception as e:
bot.error("Exception "+str(e))
dr = Datareader(mode=mode,
verbose=True,
train_format=train_format,
only_load=True)
if mode == 'offline':
if len(train_format > 0):
####### DATA INIZIALIZATION SHRINKED #################
dr = Datareader(mode=mode,
train_format=train_format,
only_load=True)
ev = Evaluator(dr)
pids = dr.get_test_pids()
urm, dict_n_to_s, dict2 = dr.get_urm_shrinked()
urm_evaluation = dr.get_evaluation_urm()
urm_evaluation = urm_evaluation[pids]
pids_converted = np.array([dict_n_to_s[x] for x in pids],
dtype=np.int32)
else:
####### DATA INIZIALIZATION FULL #################
dr = Datareader(mode=mode, only_load=True, verbose=False)
ev = Evaluator(dr)
pids = dr.get_test_pids()
urm = dr.get_urm()
urm_evaluation = dr.get_evaluation_urm()
urm_evaluation = urm_evaluation[pids]
urm_evaluation = None