['L10','T10']],
'Initial':[[0.1,350],
[10,350],
[100,350],
[1000,350],
[4090,350],
[4090,1],
[4090,10],
[4090,100],
[4090,300],
[4090,350]]}
#set up fixed design dictionary
#fixed_dict ={'Weight':0.5,'Design':init_design}
# generate the optimal discreteimate (relaxed) design
design_object = Design(model_object,fit_params,'D',
continuous_inputs = continuous_inputs)
#extract the relaxed design structure
relaxed_design = design_object.relaxed()
#***hidden_start****
print('')
print(relaxed_design)
print('')
#***hidden_end****
#set the sample size to 30
sample_size = 15
#generate a rounded exact design
exact_design = design_object.round(sample_size)
#***hidden_start****
print('')
print(exact_design)
print('')
# enter the function as a tuple with label indicating normal error, into observation list
observ_list = [(y,'Normal')]
#instantiate nloed model class
nloed_model = Model(observ_list,xnames,pnames)
####################################################################################################
# GENERATE OPTIMAL DESIGN
####################################################################################################
#set up the design algorithm to use continuous (continuous) optimization with two unique inputs points
continuous_inputs={'Inputs':['Light'],'Bounds':[(.1,5)],'Structure':[['x1'],['x2'],['x3'],['x4']]}
true_param = [1,5,2,1]
# generate the optimal discreteimate (relaxed) design
relaxed_design = Design(nloed_model,np.log(true_param),'D',continuous_inputs=continuous_inputs)
sample_size = 30
#generate a rounded exact design
exact_design = relaxed_design.round(sample_size)
print(exact_design)
####################################################################################################
# GENERATE SAMPLE DATA & FIT MODEL
####################################################################################################
#generate some data, to stand in for an initial experiment
data = nloed_model.sample(exact_design,np.log(true_param))
print(data)
#set up the design algorithm to use continuous (continuous) optimization with two unique inputs points
continuous_inputs = {
'Inputs': ['Light'],
'Bounds': [(.1, 4095.)],
'Structure': [['L1'], ['L2'], ['L3'], ['L4'], ['L5']],
'Initial': [[10], [200], [500], [1000], [4000]]
}
fixed_design = {'Weight': 0.5, 'Design': init_design}
opts = {'LockWeights': False}
# generate the optimal discreteimate (relaxed) design
design_object = Design(nloed_model,
nominal_params,
'D',
continuous_inputs=continuous_inputs,
fixed_design=fixed_design,
options=opts)
sample_size = 75000
relaxed_design = design_object.relaxed()
print(relaxed_design)
#generate a rounded exact design
opt_design = design_object.round(sample_size)
print(opt_design)
####################################################################################################
# EVALUATE DESIGN & PREDICT OUTPUT
####################################################################################################
#############################################
true_pars = np.log([0.5,0.01,0.1,0.4,0.01,0.2,0.1,0.1])
# continuous_inputs = {'Inputs':['ecoli_ic','salm_ic','prim_ic','sec_ic'],
# 'Bounds':[(0.1,1),(0.1,0.2),(1,5),(0.01,0.1)],
# 'Structure':[['ecoli_ic1','salm_ic1','prim_ic1','sec_ic1'],
# ['ecoli_ic2','salm_ic2','prim_ic2','sec_ic2'],
# ['ecoli_ic3','salm_ic3','prim_ic3','sec_ic3']]}
# continuous_inputs = {'Inputs':['ecoli_ic','salm_ic'],
# 'Bounds':[(0.01,0.1),(0.1,0.1)],
# 'Structure':[['ecoli_ic1','salm_ic1'],
# ['ecoli_ic2','salm_ic2'],
# ['ecoli_ic3','salm_ic3']]}
discrete_inputs = {'Inputs':['ecoli_ic','salm_ic'],
'Bounds':[(0.01,0.1),(0.01,0.1)]}
opt_design = Design(ode_model, true_pars, 'D', discrete_inputs=discrete_inputs)
sample_size = 30
exact_design = opt_design.round(sample_size)
print(exact_design)
####################################################################################################
# SAMPLE DESIGN AND FIT
####################################################################################################
#evaluate the proposed deign in terms of expected Covariance, Bias and MSE
opts = {'Covariance':True,'Bias':True,'MSE':True}
eval_dat = ode_model.evaluate(exact_design,true_pars,opts)
print(eval_dat)
####################################################################################################
# GENERATE DESIGN
####################################################################################################
true_pars = np.log([0.5,1.1,2.1,0.3])
# discrete_inputs = {'Inputs':['mrna_ic','prot_ic','cntrl_1','cntrl_2','cntrl_3'],
# 'Bounds':[(0,1),(0,1),(0,1),(0,1),(0,1)]}
# opt_design = Design(ode_model,true_pars,'D',discrete_inputs)
continuous_inputs = {'Inputs':['mrna_ic','prot_ic','cntrl_1','cntrl_2','cntrl_3'],
'Bounds':[(0,1),(0,1),(0,1),(0,1),(0,1),(0,1)],
'Structure':[['mrna_ic1','prot_ic1','c1_lvl1','c2_lvl1','c3_lvl1'],
['mrna_ic2','prot_ic2','c1_lvl2','c2_lvl2','c3_lvl2'],
['mrna_ic3','prot_ic3','c1_lvl3','c2_lvl3','c3_lvl3']]}
opt_design = Design(ode_model, true_pars, 'D', continuous_inputs=continuous_inputs)
sample_size = 30
exact_design = opt_design.round(sample_size)
print(exact_design)
####################################################################################################
# SAMPLE DESIGN AND FIT
####################################################################################################
#evaluate the proposed deign in terms of expected Covariance, Bias and MSE
opts = {'Covariance':True,'Bias':True,'MSE':True}
eval_dat = ode_model.evaluate(exact_design,true_pars,opts)
print(eval_dat)
}
init_design = pd.DataFrame({
'Light': [.1] * 9 + [63] * 9 + [254] * 9 + [1022] * 9 + [4095] * 9,
'Time': [0.5, 1.8, 6] * 15,
'Variable': ['GFP'] * 45,
'Replicats': [1] * 45
})
fixed_design = {'Weight': 0.5, 'Design': init_design}
opts = {'LockWeights': True}
# generate the optimal discreteimate (relaxed) design
relaxed_design = Design(nloed_model,
fit_params,
'D',
continuous_inputs=continuous_inputs,
fixed_design=fixed_design,
options=opts)
sample_size = 45
#generate a rounded exact design
exact_design = relaxed_design.round(sample_size)
print(exact_design)
opt_design_tot = pd.concat([init_design, exact_design], ignore_index=True)
#get estimated covariance, bias and MSE of parameter fit (use asymptotic method here)
opts = {
'Method': 'MonteCarlo',
'Covariance': True,
'Bias': True,
print(predictions)
print('')
print('')
####################################################################################################
# GENERATE DESIGN
####################################################################################################
true_param = [1,1,1,1]
#discrete_inputs={'Inputs':['x1'],'Candidates':[[-1],[-.5],[0],[.5],[1]]}
#continuous_inputs={'Inputs':['x2'],'Bounds':[(-1,1)],'Structure':[['level1'],['level2']]}
discrete_inputs={'Inputs':['x1','x2'],'Candidates':[[-1, 0, 1],[-1, 0, 1]]}
#discrete_inputs={'Inputs':['x1','x2'],'Grid':[[-1,-1],[0,-1],[1,-1],[-1,0],[0,0],[1,0],[-1,1],[0,1],[1,1],[3,3]]}
## continuous_inputs={'Inputs':['x1','x2'],'Bounds':[(-1,1),(-1,1)],'Structure':[['x1_lvl1','x2_lvl1'],['x1_lvl1','x2_lvl2'],['x1_lvl2','x2_lvl2']]}
design_object = Design(lin_model, true_param, 'D', discrete_inputs)
relaxed_design = design_object.relaxed()
print('')
print('')
print(relaxed_design)
print('')
print('')
sample_size = 10
exact_design = design_object.round(sample_size)
print('')
print('')
observ_list = [(y,'Normal')]
#instantiate nloed model class
nloed_model = Model(observ_list,xnames,pnames)
####################################################################################################
# GENERATE OPTIMAL DESIGN
####################################################################################################
#set up the design algorithm to use continuous (continuous) optimization with two unique inputs points
continuous_inputs={'Inputs':['x'],'Bounds':[(-1,1)],'Structure':[['x1'],['x2']]}
#set up the design algorithm to use continuous (continuous) optimization with two unique inputs points
#discrete_inputs={'Inputs':['x'],'Grid':[[-1.5,-0.1,0.1,1.5]]}
# generate the optimal approximate (relaxed) design
relaxed_design = Design(nloed_model,[1,1],'D',continuous_inputs=continuous_inputs)
# generate the optimal approximate (relaxed) design
#relaxed_design = Design(nloed_model,[1,1],'D',discrete_inputs=discrete_inputs)
sample_size = 10
#generate a rounded exact design
exact_design = relaxed_design.round(sample_size)
print(exact_design)
####################################################################################################
# GENERATE SAMPLE DATA & FIT MODEL
####################################################################################################
#generate some data, to stand in for an initial experiment
data = nloed_model.sample(exact_design,[1,1])
####################################################################################################
# GENERATE DESIGN
####################################################################################################
true_param = [1, 1, 1, 1]
discrete_inputs = {'Inputs': ['x1'], 'Bounds': [(-1, 1)]}
continuous_inputs = {
'Inputs': ['x2'],
'Bounds': [(-1, 1)],
'Structure': [['level1'], ['level2']]
}
## discrete_inputs={'Inputs':['x1','x2'],'Bounds':[(-1,1),(-1,1)]}
## continuous_inputs={'Inputs':['x1','x2'],'Bounds':[(-1,1),(-1,1)],'Structure':[['x1_lvl1','x2_lvl1'],['x1_lvl1','x2_lvl2'],['x1_lvl2','x2_lvl2']]}
opt_design = Design(lin_model, true_param, 'D', discrete_inputs,
continuous_inputs)
sample_size = 10
exact_design = opt_design.round(sample_size)
print(exact_design)
####################################################################################################
# GENERATE SAMPLE DATA & FIT MODEL
####################################################################################################
#generate some data, to stand in for an initial experiment
data = lin_model.sample(exact_design, true_param)
print(data)
'Replicates': [1] * (15 * 2 + 14)
})
#set up the design algorithm to use continuous (continuous) optimization with two unique inputs points
continuous_inputs = {
'Inputs': ['Light'],
'Bounds': [(.01, 4095)],
'Structure': [['x1'], ['x2'], ['x3'], ['x4'], ['x5']],
'Initial': [[0.1], [100], [300], [1000], [4000]]
}
#set up fixed design dictionary
fixed_dict = {'Weight': .75, 'Design': init_design}
# generate the optimal discreteimate (relaxed) design
design_object = Design(static_model,
fit_params,
'D',
fixed_design=fixed_dict,
continuous_inputs=continuous_inputs)
#extract the relaxed design structure
relaxed_design = design_object.relaxed()
#***hidden_start****
print('')
print(relaxed_design)
print('')
#***hidden_end****
#set the sample size to 30
sample_size = 16
#generate a rounded exact design
exact_design = design_object.round(sample_size)
#***hidden_start****
print('')