def train(sppmi_mat, data_dir=DATA_DIR):
'''
Train
'''
# load file
n_users = len(uid2idx)
print('n_users:{}'.format(n_users))
n_items = len(sid2idx)
print('n_items:{}'.format(n_items))
fn_train = os.path.join(data_dir, 'data_train.txt')
fn_dev = os.path.join(data_dir, 'data_dev.txt')
fn_test = os.path.join(data_dir, 'data_test.txt')
train_data = util.load_input_data(fn_train, shape=(n_users, n_items))
vad_data = util.load_input_data(fn_dev, shape=(n_users, n_items))
test_data = util.load_input_data(fn_test, shape=(n_users, n_items))
# train model
coder = cofacto.CoFacto(n_components=N_COMPONENTS,
max_iter=max_iter,
batch_size=1000,
init_std=0.01,
n_jobs=N_JOBS,
random_state=98765,
save_params=True,
save_dir=save_dir,
early_stopping=True,
verbose=True,
lam_theta=lam_theta,
lam_beta=lam_beta,
lam_gamma=lam_gamma,
c0=c0,
c1=c1)
coder.fit(train_data,
sppmi_mat,
vad_data=vad_data,
batch_users=5000,
k=100)
# test model
n_params = len(glob.glob(os.path.join(save_dir, '*.npz')))
last_iter_num = n_params - 1
params = np.load(
os.path.join(save_dir,
'CoFacto_K%d_iter%d.npz' % (N_COMPONENTS, last_iter_num)))
U, V = params['U'], params['V']
print('Test Recall@20: %.4f' % rec_eval.recall_at_k(
train_data, test_data, U, V, k=20, vad_data=vad_data))
print('Test Recall@50: %.4f' % rec_eval.recall_at_k(
train_data, test_data, U, V, k=50, vad_data=vad_data))
print('Test NDCG@100: %.4f' % rec_eval.normalized_dcg_at_k(
train_data, test_data, U, V, k=100, vad_data=vad_data))
print('Test MAP@100: %.4f' % rec_eval.map_at_k(
train_data, test_data, U, V, k=100, vad_data=vad_data))
# save
model_save_fn = os.path.join(
DATA_DIR, 'Model_K{}_{}.npz'.format(N_COMPONENTS, DATA_SET_NAME))
np.savez(model_save_fn, U=U, V=V)
print('saved')
c0 = 1. * scale
c1 = 10. * scale
save_dir = os.path.join(DATA_DIR, 'ML20M_ns%d_scale%1.2E' % (k_ns, scale))
# In[29]:
reload(cofacto)
coder = cofacto.CoFacto(n_components=n_components,
max_iter=max_iter,
batch_size=1000,
init_std=0.01,
n_jobs=n_jobs,
random_state=98765,
save_params=True,
save_dir=save_dir,
early_stopping=True,
verbose=True,
lam_theta=lam_theta,
lam_beta=lam_beta,
lam_gamma=lam_gamma,
c0=c0,
c1=c1)
cofacto.CoFacto()
# In[30]:
coder.fit(train_data, M_ns, vad_data=vad_data, batch_users=5000, k=100)
# In[31]: