from experiment.hyper_param_opt import GridSearch
from models.tensorflow.model import Model
from models.tensorflow.tf_train_eval import TfTrainEvalModelFactory
if __name__ == '__main__':
exp = Experiment('density/synthetic/sin_normal')
conf.num_workers = 4
conf.visible_device_list = [0,1]
conf.eval_batch_size = {'0': 10000, '1': 10000}
exp.data_loader = registry.sin_normal_noise()
exp.model_factory = TfTrainEvalModelFactory(Model(name="MDN"))
exp.hyper_param_search = GridSearch([
Categorical([16,64,128], name='nm'),
Categorical([32,64, 128], name='sh'),
Categorical([1,2,3], name='nh'),
Categorical([128], name='bs'),
Categorical([1], name='rs'),
Categorical(['AdamOptimizer'], name='opt'),
Categorical([1e-4,1e-3,1e-2], name='opt_lr'),
])
exp.early_stopping = EarlyStop(monitor_every_epoch=1, patience=[30])
exp.run()
from experiment.experiment import Experiment
from experiment.hyper_param_opt import GridSearch
from models.tensorflow.model import Model
from models.tensorflow.tf_train_eval import TfTrainEvalModelFactory
if __name__ == '__main__':
exp = Experiment('density/synthetic/inv_sin_normal')
conf.num_workers = 4
conf.visible_device_list = [0,1]
conf.eval_batch_size = {'0': 10000, '1': 10000}
exp.data_loader = registry.inv_sin_normal()
exp.model_factory = TfTrainEvalModelFactory(Model(name="RNADE_normal"))
exp.hyper_param_search = GridSearch([
Categorical([1, 16, 32, 64, 128], name='km'),
Categorical([1, 16, 32, 64, 128], name='sh'),
Categorical([128], name='bs'),
Categorical([1], name='rs'),
Categorical(['AdamOptimizer'], name='opt'),
Categorical([1e-3], name='opt_lr'),
])
exp.early_stopping = EarlyStop(monitor_every_epoch=1, patience=[30])
exp.run()
from models.tensorflow.tf_train_eval import TfTrainEvalModelFactory
if __name__ == '__main__':
exp = Experiment('density/synthetic/inv_sin_t')
conf.num_workers = 4
conf.visible_device_list = [0, 1]
conf.eval_batch_size = {'0': 10000, '1': 10000}
exp.data_loader = registry.inv_sin_t()
exp.model_factory = TfTrainEvalModelFactory(
Model(name="MONDE_copula_const_cov"))
exp.hyper_param_search = GridSearch([
Categorical([32, 64, 128], name='hxy_sh'),
Categorical([1, 2, 3], name='hxy_nh'),
Categorical([32, 64, 128], name='x_sh'),
Categorical([1, 2, 3], name='x_nh'),
Categorical([16, 32], name='hxy_x'),
Categorical([0.05, 0.01], name='clr'),
Categorical([128], name='bs'),
Categorical([1], name='rs'),
Categorical(['AdamOptimizer'], name='opt'),
Categorical([1e-4, 1e-3, 1e-2], name='opt_lr'),
])
exp.early_stopping = EarlyStop(monitor_every_epoch=1, patience=[30])
exp.run()
from experiment.experiment import Experiment
from experiment.hyper_param_opt import GridSearch
from models.tensorflow.model import Model
from models.tensorflow.tf_train_eval import TfTrainEvalModelFactory
if __name__ == '__main__':
exp = Experiment('density/synthetic/sin_normal')
conf.num_workers = 4
conf.visible_device_list = [0,1]
conf.eval_batch_size = {'0': 10000, '1': 10000}
exp.data_loader = registry.sin_normal_noise()
exp.model_factory = TfTrainEvalModelFactory(Model(name="RNADE_laplace"))
exp.hyper_param_search = GridSearch([
Categorical([1,20,50,100,150,200], name='km'),
Categorical([20,60,100,140,200], name='sh'),
Categorical([128], name='bs'),
Categorical([1], name='rs'),
Categorical(['AdamOptimizer'], name='opt'),
Categorical([1e-4,1e-3,1e-2], name='opt_lr'),
])
exp.early_stopping = EarlyStop(monitor_every_epoch=1, patience=[30])
exp.run()
exp.data_loader = fx(x_slice=slice(None, -3),
y_slice=slice(-3, None),
ar_terms=1,
start='2018-01-01',
end='2018-03-31',
symbols=symbols,
predicted_idx=None,
resample="1min",
data_transforms={
'labels':
PercentileAnyGreaterLabelTransform(percentile=95)
})
exp.model_factory = TfSimpleTrainEvalModelFactory(NNClassifier())
exp.hyper_param_search = GridSearch([
Categorical([2, 3, 5], name='nl'),
Categorical([50, 100], name='sl'),
Categorical([128], name='bs'),
Categorical([1], name='rs'),
Categorical([3], name='bsi'),
Categorical([20], name='bsip'),
Categorical(['AdamOptimizer'], name='opt'),
Categorical([1e-3], name='opt_lr'),
])
exp.early_stopping = EarlyStop(monitor_every_epoch=1, patience=[30])
exp.run()
from experiment.hyper_param_opt import GridSearch
from models.tensorflow.model import Model
from models.tensorflow.tf_train_eval import TfTrainEvalModelFactory
if __name__ == '__main__':
exp = Experiment('density/synthetic/mv_nonlinear')
conf.num_workers = 4
conf.visible_device_list = [0, 1]
conf.eval_batch_size = {'0': 10000, '1': 10000}
exp.data_loader = registry.mv_nonlinear()
exp.model_factory = TfTrainEvalModelFactory(Model(name="MAF"))
exp.hyper_param_search = GridSearch([
Categorical([1, 2, 3, 4, 5], name='nb'),
Categorical([128, 256, 512], name='sh'),
Categorical([1, 2, 3], name='nh'),
Categorical([64, 128], name='shc'),
Categorical([True, False], name='bn'),
Categorical([128], name='bs'),
Categorical([1], name='rs'),
Categorical(['AdamOptimizer'], name='opt'),
Categorical([1e-4, 1e-3, 1e-2], name='opt_lr'),
])
exp.early_stopping = EarlyStop(monitor_every_epoch=1, patience=[30])
exp.run()
ar_terms=1,
start='2018-01-01',
end='2018-03-31',
symbols=symbols,
predicted_idx=None,
resample="1min")
exp.model_factory = TfSimpleTrainEvalModelFactory(Pumonde2())
exp.hyper_param_search = GridSearch([
Categorical([3, 4], name='nl1'),
Categorical([50, 100], name='sl1'),
Categorical([3, 4], name='nl2'),
Categorical([50, 100], name='sl2'),
Categorical([30], name='sxl2'),
Categorical([3, 4], name='nl3'),
Categorical([50, 100], name='sl3'),
Categorical(['square'], name='pt'),
Categorical([128], name='bs'),
Categorical([1], name='rs'),
Categorical([3], name='bsi'),
Categorical([20], name='bsip'),
Categorical(['AdamOptimizer'], name='opt'),
Categorical([1e-3], name='opt_lr'),
])
exp.early_stopping = EarlyStop(monitor_every_epoch=1, patience=[30])
exp.run()
from experiment.early_stop import EarlyStop
from experiment.experiment import Experiment
from experiment.hyper_param_opt import GridSearch
from models.tensorflow.model import Model
from models.tensorflow.tf_train_eval import TfTrainEvalModelFactory
if __name__ == '__main__':
exp = Experiment('density/synthetic/uci_large/power')
conf.num_workers = 2
conf.visible_device_list = [0, 1]
conf.eval_batch_size = {'0': 50000, '1': 50000}
exp.data_loader = registry.power(x_slice=slice(0), y_slice=slice(None))
exp.model_factory = TfTrainEvalModelFactory(Model(name="MONDE_AR_BLOCK"))
exp.hyper_param_search = GridSearch([
Categorical([8, 10], name='nl'),
Categorical([40, 60], name='nb'),
Categorical(['tanh'], name='tr'),
Categorical([128], name='bs'),
Categorical([1], name='rs'),
Categorical(['AdamOptimizer'], name='opt'),
Categorical([1e-3], name='opt_lr'),
])
exp.early_stopping = EarlyStop(monitor_every_epoch=1, patience=[30])
exp.run()
from models.tensorflow.tf_train_eval import TfTrainEvalModelFactory
if __name__ == '__main__':
exp = Experiment('density/synthetic/mv_nonlinear')
conf.num_workers = 4
conf.visible_device_list = [0, 1]
conf.eval_batch_size = {'0': 10000, '1': 10000}
exp.data_loader = registry.mv_nonlinear()
exp.model_factory = TfTrainEvalModelFactory(Model(name="PumondePFor"))
exp.hyper_param_search = GridSearch([
Categorical([64, 128, 256], name='xs'),
Categorical([1, 2, 3], name='xn'),
Categorical([64, 128, 256], name='hxys'),
Categorical([1, 2, 3], name='hxyn'),
Categorical([0, 16], name='hxyxs'),
Categorical([64, 128, 256], name='xycs'),
Categorical([1, 2, 3], name='xycn'),
Categorical([128], name='bs'),
Categorical([1], name='rs'),
Categorical(['AdamOptimizer'], name='opt'),
Categorical([1e-4, 1e-3, 1e-2], name='opt_lr'),
])
exp.early_stopping = EarlyStop(monitor_every_epoch=1, patience=[30])
exp.run()
]
exp.data_loader = registry.fx(x_slice=slice(None, -3),
y_slice=slice(-3, None),
ar_terms=1,
start='2018-01-01',
end='2018-03-31',
symbols=symbols,
predicted_idx=None,
resample="1min")
exp.model_factory = TfTrainEvalModelFactory(
Model(name="MONDE_copula_const_cov"))
exp.hyper_param_search = GridSearch([
Categorical([50, 100], name='hxy_sh'),
Categorical([2, 4], name='hxy_nh'),
Categorical([50, 100], name='x_sh'),
Categorical([2, 4], name='x_nh'),
Categorical([30], name='hxy_x'),
Categorical([0.05], name='clr'),
Categorical([128], name='bs'),
Categorical([1], name='rs'),
Categorical(['AdamOptimizer'], name='opt'),
Categorical([1e-3], name='opt_lr'),
])
exp.early_stopping = EarlyStop(monitor_every_epoch=1, patience=[30])
exp.run()