def dnn_concat(data,
configfile,
layers=[16, 8],
activation='tanhlecun',
initrange=1e-3,
bn=True,
keep_prob=.95,
concat_size=24,
uembed=32,
iembed=32,
learnrate=.00001,
verbose=True,
epochs=10,
maxbadcount=20,
mb=2000,
eval_rate=500):
with tf.name_scope('ant_graph'):
ant = config.AntGraph(configfile,
data=data.dev.features,
marker='-',
graph_name='dnn_concat',
variable_bindings={
'layers': layers,
'activation': activation,
'initrange': initrange,
'bn': bn,
'keep_prob': keep_prob,
'concat_size': concat_size,
'uembed': uembed,
'iembed': iembed,
})
y = ant.tensor_out
y_ = tf.placeholder("float", [None, None], name='Target')
ant.placeholderdict[
'ratings'] = y_ # put the new placeholder in the graph for training
with tf.name_scope('objective'):
objective = tf.reduce_sum(tf.square(y_ - y))
with tf.name_scope('dev_rmse'):
dev_rmse = tf.sqrt(
tf.div(tf.reduce_sum(tf.square(y - y_)), data.dev.num_examples))
with tf.name_scope('training'):
model = generic_model.Model(objective,
ant.placeholderdict,
mb=mb,
learnrate=learnrate,
verbose=verbose,
maxbadcount=maxbadcount,
epochs=epochs,
evaluate=dev_rmse,
predictions=y,
model_name='res_concat',
make_histograms=False,
save=False,
tensorboard=False)
model.train(data.train, dev=data.dev, eval_schedule=eval_rate)
return model
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,
train_dev_eval_factor=3):
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})
y = ant.tensor_out
y_ = tf.placeholder("float", [None, None], name='Target')
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'):
_rmse = node_ops.rmse(y_, y)
mae = node_ops.mae(y_, y)
model = generic_model.Model(objective, ant.placeholderdict,
mb=mb,
learnrate=learnrate,
verbose=verbose,
maxbadcount=maxbadcount,
epochs=epochs,
evaluate=_rmse,
train_evaluate=_rmse,
predictions=y,
model_name='mf',
random_seed=random_seed,
save_tensors={'mae': mae})
model.train(data.train, dev=data.dev, eval_schedule=eval_rate,train_dev_eval_factor= train_dev_eval_factor)
return model
def tensorfactor(data,
configfile,
lamb=.001,
kfactors=1000,
learnrate=0.01,
verbose=True,
epochs=1000,
maxbadcount=20,
mb=500,
initrange=1,
eval_rate=500,
random_seed=None):
with tf.name_scope('ant_graph'):
ant = config.AntGraph(configfile,
data=data.dev.features,
marker='-',
graph_name='basic_mf',
variable_bindings={
'kfactors': kfactors,
'initrange': initrange,
'lamb': lamb
})
y = ant.tensor_out
y_ = tf.placeholder("float", [None, None], name='Target')
ant.placeholderdict['ratings'] = y_
with tf.name_scope('objective'):
objective = (tf.reduce_sum(tf.square(y_ - y)))
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=200)
return model
def dssm(data,
configfile,
layers=[10, 10, 10],
bn=True,
keep_prob=.95,
act='tanhlecun',
initrange=1,
kfactors=10,
lamb=.1,
mb=500,
learnrate=0.0001,
verbose=True,
maxbadcount=10,
epochs=100,
model_name='dssm',
random_seed=500,
eval_rate=500):
datadict = data.user.features.copy()
datadict.update(data.item.features)
configdatadict = data.dev.features.copy()
configdatadict.update(datadict)
with tf.name_scope('ant_graph'):
ant = config.AntGraph(configfile,
data=configdatadict,
marker='-',
graph_name='basic_mf',
variable_bindings={
'initrange': initrange,
'kfactors': kfactors
})
y_ = tf.placeholder("float", [None, None], name='Target')
ant.placeholderdict['ratings'] = y_
with tf.name_scope('objective'):
if type(ant.tensor_out) is list:
objective = tf.reduce_sum(tf.square(y_ - ant.tensor_out[0]))
for i in range(1, len(ant.tensor_out)):
objective += tf.reduce_sum(tf.square(y_ - ant.tensor_out[i]))
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(ant.tensor_out[0], y_)
model = generic_model.Model(objective,
ant.placeholderdict,
mb=mb,
learnrate=learnrate,
verbose=verbose,
maxbadcount=maxbadcount,
epochs=epochs,
evaluate=dev_rmse,
predictions=ant.tensor_out[0],
model_name='dssm',
random_seed=random_seed)
model.train(data.train,
dev=data.dev,
supplement=datadict,
eval_schedule=eval_rate)
return model
def tree(data,
configfile,
lamb=0.001,
kfactors=20,
learnrate=0.0001,
verbose=True,
maxbadcount=20,
mb=500,
initrange=0.00001,
epochs=10,
random_seed=None,
eval_rate=500,
keep_prob=0.95,
act='tanh'):
datadict = data.user.features.copy()
datadict.update(data.item.features)
configdatadict = data.dev.features.copy()
configdatadict.update(datadict)
with tf.name_scope('ant_graph'):
ant = config.AntGraph(configfile,
data=configdatadict,
marker='-',
variable_bindings={
'kfactors': kfactors,
'initrange': initrange,
'keep_prob': keep_prob,
'act': act
},
graph_name='tree')
y = ant.tensor_out
y_ = tf.placeholder("float", [None, None], name='Target')
ant.placeholderdict[
'ratings'] = y_ # put the new placeholder in the graph for training
with tf.name_scope('objective'):
objective = (tf.reduce_sum(tf.square(y_ - y)) +
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 = tf.sqrt(
tf.div(tf.reduce_sum(tf.square(y - y_)), data.dev.num_examples))
with tf.name_scope('training'):
model = generic_model.Model(objective,
ant.placeholderdict,
mb=mb,
learnrate=learnrate,
verbose=verbose,
maxbadcount=maxbadcount,
epochs=epochs,
evaluate=dev_rmse,
predictions=y,
model_name='tree')
model.train(data.train,
dev=data.dev,
supplement=datadict,
eval_schedule=eval_rate)
return model
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'])
datadict = data.user.features.copy()
datadict.update(data.item.features)
configdatadict = data.dev.features.copy()
configdatadict.update(datadict)
with tf.variable_scope('mfgraph'):
ant = config.AntGraph('tree.config',
data=configdatadict,
marker='-',
variable_bindings={
'kfactors': 100,
'initrange': 0.0001
},
develop=False)
y = ant.tensor_out
y_ = tf.placeholder("float", [None, None], name='Target')
ant.placeholderdict[
'ratings'] = y_ # put the new placeholder in the graph for training
objective = tf.reduce_sum(tf.square(y_ - y))
dev_rmse = node_ops.rmse(y, y_)
model = generic_model.Model(objective,
ant.placeholderdict,
mb=500,
learnrate=0.00001,
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
def dsadd(data,
configfile,
initrange=0.1,
kfactors=20,
lamb=.01,
mb=500,
learnrate=0.003,
verbose=True,
maxbadcount=10,
epochs=100,
model_name='dssm',
random_seed=500,
eval_rate=500):
datadict = data.user.features.copy()
datadict.update(data.item.features)
configdatadict = data.dev.features.copy()
configdatadict.update(datadict)
with tf.name_scope('ant_graph'):
ant = config.AntGraph(configfile,
data=configdatadict,
marker='-',
graph_name='basic_mf',
variable_bindings={
'initrange': initrange,
'kfactors': kfactors
})
y_ = tf.placeholder("float", [None, None], name='Target')
ant.placeholderdict['ratings'] = y_
with tf.name_scope('objective'):
if type(ant.tensor_out) is list:
scalars = tf.Variable(
0.001 * tf.truncated_normal([len(ant.tensor_out), 1]))
prediction = tf.mul(ant.tensor_out[0],
tf.slice(scalars, [0, 0], [1, 1]))
for i in range(1, len(ant.tensor_out)):
with tf.variable_scope('predictor%d' % i):
prediction = prediction + tf.mul(
ant.tensor_out[i], tf.slice(scalars, [i, 0], [1, 1]))
prediction = tf.square(y_ - prediction)
objective = (
tf.reduce_sum(prediction) +
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'])) +
lamb * tf.reduce_sum(tf.square(tf.concat(1, ant.tensor_out))))
with tf.name_scope('dev_rmse'):
dev_rmse = tf.sqrt(
tf.div(tf.reduce_sum(prediction), data.dev.num_examples))
model = generic_model.Model(objective,
ant.placeholderdict,
mb=500,
learnrate=0.000001,
verbose=True,
maxbadcount=10,
epochs=100,
evaluate=dev_rmse,
predictions=ant.tensor_out[0],
model_name='dssm',
random_seed=500)
model.train(data.train,
dev=data.dev,
supplement=datadict,
eval_schedule=eval_rate)
return model
loader.maybe_download('ml100k.tar.gz', '.',
'http://sw.cs.wwu.edu/~tuora/aarontuor/ml100k.tar.gz')
loader.untar('ml100k.tar.gz')
data = loader.read_data_sets('ml100k',
folders=['dev', 'train'],
hashlist=['item', 'user', 'ratings'])
data.show()
data.train.labels['ratings'] = loader.center(data.train.labels['ratings'])
data.dev.labels['ratings'] = loader.center(data.dev.labels['ratings'])
with tf.variable_scope('mfgraph'):
ant = config.AntGraph('mf2.config',
data=data.dev.features,
marker='-',
variable_bindings={
'kfactors': 100,
'initrange': 0.001,
'l2': 0.1
})
y = ant.tensor_out
y_ = tf.placeholder("float", [None, None], name='Target')
ant.placeholderdict[
'ratings'] = y_ # put the new placeholder in the graph for training
objective = tf.reduce_sum(tf.square(y_ - y))
dev_rmse = node_ops.rmse(y, y_)
dev_mae = node_ops.mae(y, y_)
model = generic_model.Model(objective,
ant.placeholderdict,
mb=500,
# [-nlayers NUM_HIDDEN_LAYERS]
def deep(data, configfile,
epochs=10,
learnrate=0.001
layers=[10, 10, 10],
act='tanh',
opt='grad',
mb=500,
type='r')
with tf.name_scope('ant_graph'):
ant = config.AntGraph(configfile,
data=data.dev.features,
marker='-',
graph_name='deep',
variable_bindings = {'layers': layers,
'act': act})
y = ant.tensor_out
y_ = tf.placeholder("float", [None, None], name='Target')
ant.placeholderdict['targets'] = y_
if type == 'r':
objective = node_ops.mse(y, y_)
if type == 'c':
objective = node_ops.accuracy(y, y_)
with tf.name_scope('objective'):
objective = (tf.reduce_sum(tf.square(y_ - y)) +
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'])) +
def tree(data,
configfile,
lamb=0.001,
kfactors=50,
learnrate=0.00001,
verbose=True,
maxbadcount=20,
mb=500,
initrange=0.00001,
epochs=10,
random_seed=None,
eval_rate=500,
keep_prob=0.95,
act='tanh'):
datadict = data.user.features.copy()
datadict.update(data.item.features)
configdatadict = data.dev.features.copy()
configdatadict.update(datadict)
with tf.name_scope('ant_graph'):
ant = config.AntGraph(configfile,
data=configdatadict,
marker='-',
variable_bindings={
'kfactors': kfactors,
'initrange': initrange,
'keep_prob': keep_prob,
'act': act
},
graph_name='tree')
# ant.display_graph()
alpha = node_ops.weights('tnorm', [1, 1], l2=1.0)
beta = node_ops.weights('tnorm', [1, 1], l2=1.0)
print(ant.tensor_out)
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, ant.placeholderdict['item'])
u_bias = tf.nn.embedding_lookup(ubias, ant.placeholderdict['user'])
y = alpha * ant.tensor_out[0] + beta * ant.tensor_out[1] + u_bias + i_bias
y_ = tf.placeholder("float", [None, None], name='Target')
ant.placeholderdict[
'ratings'] = y_ # put the new placeholder in the graph for training
with tf.name_scope('objective'):
objective = (
tf.reduce_sum(tf.square(y_ - y)) +
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['huser2'])) +
lamb * tf.reduce_sum(tf.square(ant.tensordict['hitem2'])) +
lamb * tf.reduce_sum(tf.square(u_bias)) +
lamb * tf.reduce_sum(tf.square(i_bias)))
with tf.name_scope('dev_rmse'):
dev_rmse = node_ops.rmse(y_, y)
with tf.name_scope('training'):
model = generic_model.Model(objective,
ant.placeholderdict,
mb=mb,
learnrate=learnrate,
verbose=verbose,
maxbadcount=maxbadcount,
epochs=epochs,
evaluate=dev_rmse,
predictions=y,
model_name='tree',
train_evaluate=dev_rmse)
model.train(data.train,
dev=data.dev,
supplement=datadict,
eval_schedule=eval_rate,
train_dev_eval_factor=5)
return model