parser.add_argument("epochs", metavar="EPOCHS", type=int,
help="The maximum number of epochs to train for.")
parser.add_argument("modelID", metavar="MODEL_ID", type=int,
help="A unique integer for saving model results during distributed runs model parameters.")
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,
def svdplus(data,
lamb_bias=0.005,
lambfactor=0.015,
kfactors=20,
learnrate=0.01,
verbose=True,
epochs=1000,
maxbadcount=20,
mb=500,
initrange=1,
eval_rate=500,
random_seed=None,
develop=False):
data = loader.read_data_sets(data,
folders=['train', 'dev', 'item'],
hashlist=['user', 'item', 'ratings'])
data.train.labels['ratings'] = loader.center(data.train.labels['ratings'])
data.dev.labels['ratings'] = loader.center(data.dev.labels['ratings'])
utility_matrix = sps.csr_matrix(
(numpy.ones(data.train.features['user'].vec.shape[0]),
(data.train.features['user'].vec, data.train.features['item'].vec)),
shape=(data.train.features['user'].dim,
data.train.features['item'].dim))
data.item.features['util'] = utility_matrix
xuser = tf.placeholder(tf.int32, [None])
xitem = tf.placeholder(tf.int32, [None])
xutil = tf.placeholder(tf.float32, [None, None])
wuser = initrange * tf.Variable(
tf.truncated_normal([data.dev.features['user'].dim, kfactors]))
witem = initrange * tf.Variable(
tf.truncated_normal([data.dev.features['item'].dim, kfactors]))
wplus = initrange * tf.Variable(
tf.truncated_normal([data.dev.features['item'].dim, kfactors]))
ubias = initrange * tf.Variable(
tf.truncated_normal([data.dev.features['user'].dim]))
ibias = initrange * tf.Variable(
tf.truncated_normal([data.dev.features['item'].dim]))
i_bias = tf.nn.embedding_lookup(ibias, xitem)
u_bias = tf.nn.embedding_lookup(ubias, xuser)
huser = tf.nn.embedding_lookup(wuser, xuser)
hitem = tf.nn.embedding_lookup(witem, xitem)
hplus = tf.nn.embedding_lookup(xutil, xuser)
plus = tf.mul(
tf.matmul(hplus, wplus, a_is_sparse=True),
tf.rsqrt(tf.reduce_sum(hplus, reduction_indices=1, keep_dims=True)))
huserplus = huser + plus
y = node_ops.x_dot_y([huserplus, hitem, i_bias, u_bias])
y_ = tf.placeholder("float", [None, None], name='Target')
with tf.name_scope('objective'):
objective = (tf.reduce_sum(tf.square(y_ - y)) +
lambfactor * tf.reduce_sum(tf.square(huser)) +
lambfactor * tf.reduce_sum(tf.square(hitem)) +
lambfactor * tf.reduce_sum(tf.square(wplus)) +
lamb_bias * tf.reduce_sum(tf.square(i_bias)) +
lamb_bias * tf.reduce_sum(tf.square(u_bias)))
placeholderdict = {
'ratings': y_,
'util': xutil,
'user': xuser,
'item': xitem
}
mae = node_ops.mae(y_, y)
with tf.name_scope('dev_rmse'):
dev_rmse = node_ops.rmse(y_, y)
model = generic_model.Model(objective,
placeholderdict,
mb=mb,
learnrate=learnrate,
verbose=verbose,
maxbadcount=maxbadcount,
epochs=epochs,
evaluate=dev_rmse,
predictions=y,
model_name='svdplus',
random_seed=random_seed,
decay=(500, 0.999),
save_tensors={'mae': mae})
model.train(data.train,
dev=data.dev,
supplement=data.item.features,
eval_schedule=eval_rate)
return model
"A unique integer for saving model results during distributed runs model parameters."
)
parser.add_argument("random_seed",
metavar="RANDOM_SEED",
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,
"-eval_rate",
metavar="EVAL_RATE",
type=int,
default=500,
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,
hashlist=['user', 'item', 'ratings'],
folders=['train', 'test', 'dev'])
data.train.labels['ratings'] = loader.center(data.train.labels['ratings'])
data.dev.labels['ratings'] = loader.center(data.dev.labels['ratings'])
x = dnn_concat_model.dnn_concat(data,
args.config,
layers=args.layers,
activation=args.act,
initrange=args.initrange,
bn=args.bn,
keep_prob=args.kp,
concat_size=args.cs,
uembed=args.uembed,
iembed=args.iembed,
mb=args.mb,
learnrate=args.learnrate,
verbose=args.verbose,
maxbadcount=args.maxbadcount,
def tensorfactor(data,
context_key='occ',
lamb=0.01,
learnrate=0.0001,
verbose=True,
epochs=5,
maxbadcount=20,
mb=500,
initrange=0.0001,
eval_rate=10000,
random_seed=None,
uembed=50,
iembed=50,
cembed=50):
data = loader.read_data_sets(data,
folders=('train', 'dev', 'item', 'user'),
hashlist=('user', 'item', context_key,
'ratings'))
data.train.labels['ratings'] = loader.center(data.train.labels['ratings'])
data.dev.labels['ratings'] = loader.center(data.dev.labels['ratings'])
if context_key in data.item.features:
data.train.features[context_key] = data.item.features[context_key][
data.train.features['item']]
data.dev.features[context_key] = data.item.features[context_key][
data.dev.features['item']]
del data.item.features[context_key]
elif context_key in data.user.features:
data.train.features[context_key] = data.user.features[context_key][
data.train.features['user']]
data.dev.features[context_key] = data.user.features[context_key][
data.dev.features['user']]
del data.user.features[context_key]
data.show()
item = tf.placeholder(tf.int32, [None])
user = tf.placeholder(tf.int32, [None])
context = tf.placeholder(tf.int32, [None])
wuser = initrange * tf.Variable(
tf.truncated_normal([data.dev.features['user'].shape[1], uembed]))
witem = initrange * tf.Variable(
tf.truncated_normal([data.dev.features['item'].shape[1], iembed]))
wcontext = initrange * tf.Variable(
tf.truncated_normal([data.dev.features[context_key].shape[1], cembed]))
xuser = tf.nn.embedding_lookup(wuser, user)
xitem = tf.nn.embedding_lookup(witem, item)
xcontext = tf.nn.embedding_lookup(wcontext, context)
ibias = tf.Variable(
tf.truncated_normal([data.dev.features['item'].shape[1]]))
ubias = tf.Variable(
tf.truncated_normal([data.dev.features['user'].shape[1]]))
cbias = tf.Variable(
tf.truncated_normal([data.dev.features[context_key].shape[1]]))
i_bias = tf.nn.embedding_lookup(ibias, item)
u_bias = tf.nn.embedding_lookup(ubias, user)
c_bias = tf.nn.embedding_lookup(cbias, context)
y = node_ops.ternary_tensor_combine([xuser, xitem, xcontext],
initrange=initrange,
l2=lamb) + i_bias + u_bias
y_ = tf.placeholder("float", [None, None], name='Target')
placeholderdict = {
'user': user,
'item': item,
context_key: context,
'ratings': y_
}
with tf.name_scope('objective'):
objective = (tf.reduce_sum(tf.square(y_ - y)) +
lamb * tf.reduce_sum(tf.square(wcontext)) +
lamb * tf.reduce_sum(tf.square(xuser)) +
lamb * tf.reduce_sum(tf.square(xitem)) +
lamb * tf.reduce_sum(tf.square(i_bias)) +
lamb * tf.reduce_sum(tf.square(u_bias)) +
lamb * tf.reduce_sum(tf.square(c_bias)))
with tf.name_scope('dev_rmse'):
dev_rmse = node_ops.rmse(y_, y)
model = generic_model.Model(objective,
placeholderdict,
mb=mb,
learnrate=learnrate,
verbose=verbose,
maxbadcount=maxbadcount,
epochs=epochs,
evaluate=dev_rmse,
predictions=y,
model_name='tensorfactor',
random_seed=random_seed)
model.train(data.train, dev=data.dev, eval_schedule=eval_rate)
return model
help="For reproducible results.")
parser.add_argument("-eval_rate", metavar="EVAL_RATE", type=int, default=500,
help="How often (in terms of number of data points) to evaluate on dev.")
parser.add_argument("lossfile", metavar="LOSSFILE", type=str,
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,
parser.add_argument("kfactors", metavar="KFACTORS", type=int,
help="kfactors hyperparameter")
parser.add_argument("learnrate", metavar="LEARNRATE", type=float,
help="learn rate hyperparameter")
parser.add_argument("mbsize", metavar="MBSIZE", type=int,
help="minibatch size")
parser.add_argument("irange", metavar="IRANGE", type=float,
help="initrange hyperparameter")
parser.add_argument("lossfile", metavar="LOSSFILE", type=str,
help="loss file for spearmint")
#if __name__ == '__main__':
args = parser.parse_args()
#data = loader.read_data_sets("/home/hutch_research/skomsks/prep/ydata/out", hashlist=['item', 'user', 'ratings'])
data = loader.read_data_sets(args.datadir, hashlist=['item', 'user', 'ratings'])
data.train.labels['ratings'] = loader.center(data.train.labels['ratings'])
data.dev.labels['ratings'] = loader.center(data.dev.labels['ratings'])
x = mfmodel.mf(data,
args.config,
lamb=args.lamb,
kfactors=args.kfactors,
verbose=True,
epochs=100,
maxbadcount=20,
mb=args.mbsize,
initrange=args.irange)
lfile = str(args.lossfile)
out = open(lfile, 'w')
x_err = x._best_dev_error
if x_err > 100 or x_err == float('inf') or x_err == float('nan'):
x_err = 100
"-eval_rate",
metavar="EVAL_RATE",
type=int,
default=500,
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)
x = tree_model.tree(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)
def test_center_dense_test_axis1():
np.testing.assert_array_almost_equal(
np.sum(loader.center(x, axis=1).mean(axis=1)), 0.0)
def test_center_sparse_test():
np.testing.assert_array_almost_equal(
np.sum(loader.center(y, axis=None).mean(axis=None)), 0.0)
def test_center_dense_test():
np.testing.assert_array_almost_equal(
loader.center(x, axis=None).mean(axis=None), 0.0)
def mf(data,
configfile,
lamb=0.001,
kfactors=20,
learnrate=0.01,
verbose=True,
epochs=1000,
maxbadcount=20,
mb=500,
initrange=1,
eval_rate=500,
random_seed=None,
develop=False):
data = loader.read_data_sets(data,
hashlist=['item', 'user', 'ratings'],
folders=['dev', 'train', 'item'])
data.train.labels['ratings'] = loader.center(data.train.labels['ratings'])
data.dev.labels['ratings'] = loader.center(data.dev.labels['ratings'])
with tf.name_scope('ant_graph'):
ant = config.AntGraph(configfile,
data=data.dev.features,
marker='-',
graph_name='basic_mf',
develop=develop,
variable_bindings={
'kfactors': kfactors,
'initrange': initrange,
'lamb': lamb
})
print(ant.tensor_out)
y = node_ops.x_dot_y(ant.tensor_out)
y_ = tf.placeholder("float", [None, None], name='Target')
data.item.features['util'] = utility_matrix
xuser = tf.placeholder(tf.int32, [None])
xitem = tf.placeholder(tf.int32, [None])
xutil = tf.placeholder(tf.float32, [None, None])
wuser = initrange * tf.Variable(
tf.truncated_normal([data.dev.features['user'].dim, kfactors]))
witem = initrange * tf.Variable(
tf.truncated_normal([data.dev.features['item'].dim, kfactors]))
wplus = initrange * tf.Variable(
tf.truncated_normal([data.dev.features['item'].dim, kfactors]))
ubias = initrange * tf.Variable(
tf.truncated_normal([data.dev.features['user'].dim]))
ibias = initrange * tf.Variable(
tf.truncated_normal([data.dev.features['item'].dim]))
i_bias = tf.nn.embedding_lookup(ibias, xitem)
u_bias = tf.nn.embedding_lookup(ubias, xuser)
huser = tf.nn.embedding_lookup(wuser, xuser)
hitem = tf.nn.embedding_lookup(witem, xitem)
hplus = tf.nn.embedding_lookup(xutil, xuser)
plus = tf.mul(
tf.matmul(hplus, wplus, a_is_sparse=True),
tf.rsqrt(tf.reduce_sum(hplus, reduction_indices=1,
keep_dims=True)))
huserplus = huser #+ plus
ant.placeholderdict['ratings'] = y_
with tf.name_scope('objective'):
objective = (tf.reduce_sum(tf.square(y_ - y)))
objective += (
lamb * tf.reduce_sum(tf.square(ant.tensordict['huser'])) +
lamb * tf.reduce_sum(tf.square(ant.tensordict['hitem'])) +
lamb * tf.reduce_sum(tf.square(ant.tensordict['ubias'])) +
lamb * tf.reduce_sum(tf.square(ant.tensordict['ibias'])))
with tf.name_scope('dev_rmse'):
dev_rmse = node_ops.rmse(y_, y)
model = generic_model.Model(objective,
ant.placeholderdict,
mb=mb,
learnrate=learnrate,
verbose=verbose,
maxbadcount=maxbadcount,
epochs=epochs,
evaluate=dev_rmse,
predictions=y,
model_name='mf',
random_seed=random_seed)
model.train(data.train, dev=data.dev, eval_schedule=eval_rate)
return model
parser.add_argument("-maxbadcount", metavar="MAXBADCOUNT", type=int, default=20,
help="The threshold for early stopping.")
parser.add_argument("-epochs", metavar="EPOCHS", type=int, default=100,
help="The maximum number of epochs to train for.")
parser.add_argument("-random_seed", metavar="RANDOM_SEED", type=int, default=500,
help="For reproducible results.")
parser.add_argument("-eval_rate", metavar="EVAL_RATE", type=int, default=500,
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)
x = tree_model.tree(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.
def tensorfactor(data, lamb=0.01,
learnrate=0.0001,
verbose=True,
epochs=100,
maxbadcount=20,
mb=500,
initrange=0.0001,
eval_rate=10000,
random_seed=None,
uembed=50,
iembed=50,
gembed=50):
data = loader.read_data_sets(data, folders=('train', 'dev', 'item'),
hashlist=('user', 'item', 'genres', 'ratings'))
data.train.labels['ratings'] = loader.center(data.train.labels['ratings'])
data.dev.labels['ratings'] = loader.center(data.dev.labels['ratings'])
data.train.features['genre'] = data.item.features['genres'][data.train.features['item'].vec, :]
data.dev.features['genre'] = data.item.features['genres'][data.dev.features['item'].vec, :]
data.show()
item = tf.placeholder(tf.int32, [None])
user = tf.placeholder(tf.int32, [None])
genre = tf.placeholder(tf.float32, [None, data.dev.features['genre'].shape[1]])
wuser = initrange*tf.Variable(tf.truncated_normal([data.dev.features['user'].shape[1], uembed]))
witem = initrange*tf.Variable(tf.truncated_normal([data.dev.features['item'].shape[1], iembed]))
wgenre = initrange*tf.Variable(tf.truncated_normal([data.dev.features['genre'].shape[1], gembed]))
xuser = tf.nn.embedding_lookup(wuser, user)
xitem = tf.nn.embedding_lookup(witem, item)
xgenre = tf.matmul(genre, wgenre, a_is_sparse=True)
ibias = tf.Variable(tf.truncated_normal([data.dev.features['item'].shape[1]]))
ubias = tf.Variable(tf.truncated_normal([data.dev.features['user'].shape[1]]))
gbias = tf.Variable(tf.truncated_normal([data.dev.features['genre'].shape[1], 1]))
i_bias = tf.nn.embedding_lookup(ibias, item)
u_bias = tf.nn.embedding_lookup(ubias, user)
g_bias = tf.matmul(genre, gbias, a_is_sparse=True)
y = node_ops.ternary_tensor_combine([xuser, xitem, xgenre],
initrange=initrange,
l2=lamb) + i_bias + u_bias
y_ = tf.placeholder("float", [None, None], name='Target')
placeholderdict = {'user': user, 'item': item, 'genre': genre, 'ratings': y_}
with tf.name_scope('objective'):
objective = (tf.reduce_sum(tf.square(y_ - y)) +
lamb*tf.reduce_sum(tf.square(wgenre)) +
lamb*tf.reduce_sum(tf.square(xuser)) +
lamb*tf.reduce_sum(tf.square(xitem)) +
lamb*tf.reduce_sum(tf.square(i_bias)) +
lamb*tf.reduce_sum(tf.square(u_bias)))
with tf.name_scope('dev_rmse'):
dev_rmse = node_ops.rmse(y_, y)
model = generic_model.Model(objective, placeholderdict,
mb=mb,
learnrate=learnrate,
verbose=verbose,
maxbadcount=maxbadcount,
epochs=epochs,
evaluate=dev_rmse,
predictions=y,
model_name='tensorfactor',
random_seed=random_seed)
model.train(data.train, dev=data.dev, eval_schedule=eval_rate)
return model
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'],
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,
initrange=args.initrange,
kfactors=args.kfactors,
lamb=args.lamb,
mb=args.mb,
learnrate=args.learnrate,
