parser.add_argument("random_seed", metavar="RANDOM_SEED", type=int,
help="For reproducible results.")
parser.add_argument("eval_rate", metavar="EVAL_RATE", type=int,
help="How often (in terms of number of data points) to evaluate on dev.")
return parser
if __name__ == '__main__':
args = return_parser().parse_args()
data = loader.read_data_sets(args.datadir, folders=['train', 'test', 'dev', 'user', 'item'])
data.train.labels['ratings'] = loader.center(data.train.labels['ratings'], axis=None)
data.dev.labels['ratings'] = loader.center(data.dev.labels['ratings'], axis=None)
data.user.features['age'] = loader.center(data.user.features['age'], axis=None)
data.item.features['year'] = loader.center(data.item.features['year'], axis=None)
data.user.features['age'] = loader.maxnormalize(data.user.features['age'])
data.item.features['year'] = loader.maxnormalize(data.item.features['year'])
x = tree_model.tree(data, args.config,data, args.config,
initrange=args.initrange,
kfactors=args.kfactors,
lamb =args.lamb,
mb=args.mb,
learnrate=args.learnrate,
verbose=args.verbose,
maxbadcount=args.maxbadcount,
epochs=args.epochs,
random_seed=args.random_seed,
eval_rate=args.eval_rate)
#print stuff here to file.
type=int,
help="For reproducible results.")
return parser
if __name__ == '__main__':
args = return_parser().parse_args()
data = loader.read_data_sets(
args.datadir, folders=['train', 'test', 'dev', 'user', 'item'])
data.train.labels['ratings'] = loader.center(data.train.labels['ratings'])
data.dev.labels['ratings'] = loader.center(data.dev.labels['ratings'])
data.user.features['age'] = loader.center(data.user.features['age'])
data.item.features['year'] = loader.center(data.item.features['year'])
data.user.features['age'] = loader.maxnormalize(data.user.features['age'])
data.item.features['year'] = loader.maxnormalize(
data.item.features['year'])
x = dsaddmodel.dsadd(data,
args.config,
initrange=args.initrange,
kfactors=args.kfactors,
lamb=args.lamb,
mb=args.mb,
learnrate=args.learnrate,
verbose=args.verbose,
maxbadcount=args.maxbadcount,
epochs=args.epochs,
random_seed=args.random_seed,
eval_rate=args.eval_rate)
type=str,
help="Name of experiment (for resolving results path).")
return parser
if __name__ == '__main__':
args = return_parser().parse_args()
data = loader.read_data_sets(
args.datadir, folders=['train', 'test', 'dev', 'user', 'item'])
data.train.labels['ratings'] = loader.center(data.train.labels['ratings'])
data.dev.labels['ratings'] = loader.center(data.dev.labels['ratings'])
data.user.features['age'] = loader.center(data.user.features['age'])
#data.item.features['year'] = loader.center(data.item.features['year'])
data.user.features['age'] = loader.maxnormalize(data.user.features['age'])
#data.item.features['year'] = loader.maxnormalize(data.item.features['year'])
x = dssm_model.dssm(data,
args.config,
initrange=args.initrange,
kfactors=args.kfactors,
lamb=args.lamb,
mb=args.mb,
learnrate=args.learnrate,
verbose=args.verbose,
maxbadcount=args.maxbadcount,
epochs=args.epochs,
random_seed=args.random_seed,
eval_rate=args.eval_rate)
#print stuff here to file.
help="Loss file for spearmint_condor $lossfn argument.")
parser.add_argument("expname", metavar="EXPNAME", type=str,
help="Name of experiment (for resolving results path).")
return parser
if __name__ == '__main__':
args = return_parser().parse_args()
data = loader.read_data_sets(args.datadir,
folders=['train', 'test', 'dev', 'user', 'item'])
data.train.labels['ratings'] = loader.center(data.train.labels['ratings'])
data.dev.labels['ratings'] = loader.center(data.dev.labels['ratings'])
data.user.features['age'] = loader.center(data.user.features['age'])
#data.item.features['year'] = loader.center(data.item.features['year'])
data.user.features['age'] = loader.maxnormalize(data.user.features['age'])
#data.item.features['year'] = loader.maxnormalize(data.item.features['year'])
x = dssm_model.dssm(data, args.config,
initrange=args.initrange,
kfactors=args.kfactors,
lamb =args.lamb,
mb=args.mb,
learnrate=args.learnrate,
verbose=args.verbose,
maxbadcount=args.maxbadcount,
epochs=args.epochs,
random_seed=args.random_seed,
eval_rate=args.eval_rate)
#print stuff here to file.
lfile = str(args.lossfile)
def test_max_sparse_test_axis1():
assert np.array_equal(loader.maxnormalize(
y, axis=1), [[0.0, 0.0, 1.0], [.5, 1, .5], [1.0 / 3.0, 1.0, 0.0]])
def test_max_sparse_test_axis0():
assert np.array_equal(
loader.maxnormalize(y, axis=0),
[[0.0, 0.0, 1.0], [1.0, 2.0 / 3.0, 1.0 / 3.0], [1.0, 1.0, 0.0]])
