def fit(
real,
known,
latent_d=1,
ret_pmf=False,
subtract_mean=False,
sig_u=1e10,
sig_v=1e10,
sig=1,
do_bayes=False,
burnin=10,
samps=200,
stop_thresh=1e-10,
min_learning_rate=1e-20,
):
ratings = np.zeros((known.sum(), 3))
for idx, (i, j) in enumerate(np.transpose(known.nonzero())):
ratings[idx] = [i, j, real[i, j]]
pmf = ProbabilisticMatrixFactorization(ratings, latent_d, subtract_mean)
pmf.sigma_sq = sig
pmf.sigma_u_sq = sig_u
pmf.sigma_v_sq = sig_v
pmf.stop_thresh = stop_thresh
pmf.min_learning_rate = min_learning_rate
pmf.fit()
if not do_bayes:
pred = pmf.predicted_matrix()
return (pmf, pred) if ret_pmf else pred
else:
bpmf = BayesianPMF(ratings, 1)
bpmf.__setstate__(pmf.__getstate__())
sampler = bpmf.samples()
# do burn-in
next(islice(sampler, burnin, burnin), None)
pred = bpmf.predict(islice(sampler, samps))
return (bpmf, pred) if ret_pmf else pred
def fit(real,
known,
latent_d=1,
ret_pmf=False,
subtract_mean=False,
sig_u=1e10,
sig_v=1e10,
sig=1,
do_bayes=False,
burnin=10,
samps=200,
stop_thresh=1e-10,
min_learning_rate=1e-20):
ratings = np.zeros((known.sum(), 3))
for idx, (i, j) in enumerate(np.transpose(known.nonzero())):
ratings[idx] = [i, j, real[i, j]]
pmf = ProbabilisticMatrixFactorization(ratings, latent_d, subtract_mean)
pmf.sigma_sq = sig
pmf.sigma_u_sq = sig_u
pmf.sigma_v_sq = sig_v
pmf.stop_thresh = stop_thresh
pmf.min_learning_rate = min_learning_rate
pmf.fit()
if not do_bayes:
pred = pmf.predicted_matrix()
return (pmf, pred) if ret_pmf else pred
else:
bpmf = BayesianPMF(ratings, 1)
bpmf.__setstate__(pmf.__getstate__())
sampler = bpmf.samples()
# do burn-in
next(islice(sampler, burnin, burnin), None)
pred = bpmf.predict(islice(sampler, samps))
return (bpmf, pred) if ret_pmf else pred
print("Loading data")
opener = gzip.open if args.data_file.endswith('.gz') else open
with opener(args.data_file, 'rb') as f:
data = np.load(f)
if isinstance(data, np.ndarray):
known = data > 0
ratings = np.zeros((known.sum(), 3))
for idx, (i, j) in enumerate(np.transpose(known.nonzero())):
ratings[idx, :] = i, j, data[i, j]
else:
ratings = data['_ratings']
bpmf = BayesianPMF(ratings, args.latent_d)
print("Doing initial MAP fit")
for train, valid in bpmf.fit_minibatches_until_validation(
args.batch_size, args.validation_size, do_yield=True, stop_thresh=args.stop_thresh):
print("\t{} {:.5} {:.5}".format(datetime.datetime.now().time(), train, valid))
print("Saving model")
with open(args.out + '_model.pkl', 'wb') as f:
pickle.dump(bpmf, f)
print("Getting MCMC samples")
num_samps = 2000
u_samps = np.empty((num_samps, bpmf.num_users, bpmf.latent_d)); u_samps.fill(np.nan)
v_samps = np.empty((num_samps, bpmf.num_items, bpmf.latent_d)); v_samps.fill(np.nan)
for idx, (u, v) in enumerate(itertools.islice(bpmf.samples(), num_samps)):
