from spotpython.data.diabetes import Diabetes
from spotpython.hyperdict.light_hyper_dict import LightHyperDict
from spotpython.fun.hyperlight import HyperLight
from spotpython.utils.init import (fun_control_init, surrogate_control_init, design_control_init)
from spotpython.utils.eda import gen_design_table
from spotpython.spot import spot
from spotpython.utils.file import get_experiment_filename
from math import inf
from spotpython.hyperparameters.values import set_hyperparameter
PREFIX= "CondNet_01"
data_set = Diabetes()
input_dim = 10
output_dim = 1
cond_dim = 2
fun_control = fun_control_init(
PREFIX= PREFIX,
fun_evals= inf,
max_time= 1 ,
data_set = data_set,
core_model_name= "light.regression.NNCondNetRegressor" ,
hyperdict= LightHyperDict,
_L_in= input_dim - cond_dim,
_L_out= 1 ,
_L_cond= cond_dim,)
fun = HyperLight().fun
set_hyperparameter(fun_control, "optimizer" , [ "Adadelta" , "Adam" , "Adamax" ])
set_hyperparameter(fun_control, "l1" , [3 ,4 ])
set_hyperparameter(fun_control, "epochs" , [3 ,7 ])
set_hyperparameter(fun_control, "batch_size" , [4 ,5 ])
set_hyperparameter(fun_control, "dropout_prob" , [0.0 , 0.025 ])
set_hyperparameter(fun_control, "patience" , [2 ,3 ])
set_hyperparameter(fun_control, "lr_mult" , [0.1 , 20.0 ])
design_control = design_control_init(init_size= 10 )
print (gen_design_table(fun_control))
module_name: light
submodule_name: regression
model_name: NNCondNetRegressor
| name | type | default | lower | upper | transform |
|----------------|--------|-----------|---------|---------|-----------------------|
| l1 | int | 3 | 3 | 4 | transform_power_2_int |
| epochs | int | 4 | 3 | 7 | transform_power_2_int |
| batch_size | int | 4 | 4 | 5 | transform_power_2_int |
| act_fn | factor | ReLU | 0 | 5 | None |
| optimizer | factor | SGD | 0 | 2 | None |
| dropout_prob | float | 0.01 | 0 | 0.025 | None |
| lr_mult | float | 1.0 | 0.1 | 20 | None |
| patience | int | 2 | 2 | 3 | transform_power_2_int |
| batch_norm | factor | 0 | 0 | 1 | None |
| initialization | factor | Default | 0 | 4 | None |
spot_tuner = spot.Spot(fun= fun,fun_control= fun_control, design_control= design_control)
res = spot_tuner.run()
train_model result: {'val_loss': 24158.83203125, 'hp_metric': 24158.83203125}
train_model result: {'val_loss': 23447.546875, 'hp_metric': 23447.546875}
train_model result: {'val_loss': 5128.1162109375, 'hp_metric': 5128.1162109375}
train_model result: {'val_loss': 24131.58984375, 'hp_metric': 24131.58984375}
train_model result: {'val_loss': 22622.26953125, 'hp_metric': 22622.26953125}
train_model result: {'val_loss': 23945.794921875, 'hp_metric': 23945.794921875}
train_model result: {'val_loss': 23592.5, 'hp_metric': 23592.5}
train_model result: {'val_loss': 3970.03271484375, 'hp_metric': 3970.03271484375}
train_model result: {'val_loss': 22140.10546875, 'hp_metric': 22140.10546875}
train_model result: {'val_loss': 22977.068359375, 'hp_metric': 22977.068359375}
train_model result: {'val_loss': 9490.4794921875, 'hp_metric': 9490.4794921875}
spotpython tuning: 3970.03271484375 [----------] 3.88%
train_model result: {'val_loss': 4811.8203125, 'hp_metric': 4811.8203125}
spotpython tuning: 3970.03271484375 [#---------] 7.73%
train_model result: {'val_loss': 16126.7421875, 'hp_metric': 16126.7421875}
spotpython tuning: 3970.03271484375 [#---------] 10.92%
train_model result: {'val_loss': 5215.19384765625, 'hp_metric': 5215.19384765625}
spotpython tuning: 3970.03271484375 [##--------] 15.84%
train_model result: {'val_loss': 23775.759765625, 'hp_metric': 23775.759765625}
spotpython tuning: 3970.03271484375 [#####-----] 45.27%
train_model result: {'val_loss': 4698.92138671875, 'hp_metric': 4698.92138671875}
spotpython tuning: 3970.03271484375 [#####-----] 50.97%
train_model result: {'val_loss': 4691.24072265625, 'hp_metric': 4691.24072265625}
spotpython tuning: 3970.03271484375 [######----] 56.56%
train_model result: {'val_loss': 20540.259765625, 'hp_metric': 20540.259765625}
spotpython tuning: 3970.03271484375 [#########-] 87.58%
train_model result: {'val_loss': 5512.07861328125, 'hp_metric': 5512.07861328125}
spotpython tuning: 3970.03271484375 [#########-] 92.45%
train_model result: {'val_loss': 5099.7158203125, 'hp_metric': 5099.7158203125}
spotpython tuning: 3970.03271484375 [##########] 97.26%
train_model result: {'val_loss': 5745.54296875, 'hp_metric': 5745.54296875}
spotpython tuning: 3970.03271484375 [##########] 100.00% Done...