Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Reduce optimization example complexity to reduce CI execution time. #80

Merged
merged 2 commits into from
Jul 9, 2024
Merged

Reduce optimization example complexity to reduce CI execution time. #80

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4c22295
Reduce optimization example by removing random sampler case.
emmanuellujan Jul 9, 2024
b2e9a74
Small change in optimization example.
emmanuellujan Jul 9, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 8 additions & 24 deletions examples/Opt-ACE-aHfO2/fit-opt-ace-ahfo2.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,14 +52,16 @@ end;
model = ACE
pars = OrderedDict( :body_order => [2, 3, 4],
:polynomial_degree => [3, 4, 5],
:rcutoff => LinRange(3.5, 6.5, 10),
:wL => LinRange(0.3, 1.8, 10),
:csp => LinRange(0.3, 1.8, 10),
:r0 => LinRange(0.3, 1.8, 10));
:rcutoff => LinRange(4, 6, 10),
:wL => LinRange(0.5, 1.5, 10),
:csp => LinRange(0.5, 1.5, 10),
:r0 => LinRange(0.5, 1.5, 10));

# Use **random sampling** to find the optimal hyper-parameters.
# Use **latin hypercube sampling** to find the optimal hyper-parameters. Alternatively, use **random sampling** (sampler = RandomSampler()).
sampler = CLHSampler(dims=[Categorical(3), Categorical(3), Continuous(),
Continuous(), Continuous(), Continuous()])
iap, res = hyperlearn!(model, pars, conf_train;
n_samples = 10, sampler = RandomSampler(),
n_samples = 10, sampler = sampler,
loss = custom_loss, ws = [1.0, 1.0], int = true);

# Save and show results.
Expand All @@ -74,21 +76,3 @@ err_time = plot_err_time(res)
@save_fig res_path err_time
DisplayAs.PNG(err_time)

# Alternatively, use **latin hypercube sampling** to find the optimal hyper-parameters.
sampler = CLHSampler(dims=[Categorical(3), Categorical(3), Continuous(),
Continuous(), Continuous(), Continuous()])
iap2, res2 = hyperlearn!(model, pars, conf_train;
n_samples = 10, sampler = sampler,
loss = custom_loss, ws = [1.0, 1.0], int = true);

# Save and show results.
@save_var res_path iap2.β
@save_var res_path iap2.β0
@save_var res_path iap2.basis
@save_dataframe res_path res2
res2

# Plot error vs time.
err_time2 = plot_err_time(res2)
@save_fig res_path err_time2
DisplayAs.PNG(err_time2)
Loading