def test_storage_opt_result():
minimize_result = create_optimization_result()
with tempfile.TemporaryDirectory(dir=".") as tmpdirname:
result_file_name = os.path.join(tmpdirname, "a", "b", "result.h5")
opt_result_writer = OptimizationResultHDF5Writer(result_file_name)
opt_result_writer.write(minimize_result)
opt_result_reader = OptimizationResultHDF5Reader(result_file_name)
read_result = opt_result_reader.read()
for i, opt_res in enumerate(minimize_result.optimize_result.list):
for key in opt_res:
if isinstance(opt_res[key], np.ndarray):
np.testing.assert_array_equal(
opt_res[key], read_result.optimize_result.list[i][key])
else:
assert (opt_res[key] == read_result.optimize_result.list[i]
[key])
def test_storage_opt_result_update(hdf5_file):
minimize_result = create_optimization_result()
minimize_result_2 = create_optimization_result()
result_file_name = hdf5_file
opt_result_writer = OptimizationResultHDF5Writer(result_file_name)
opt_result_writer.write(minimize_result)
opt_result_writer.write(minimize_result_2, overwrite=True)
opt_result_reader = OptimizationResultHDF5Reader(result_file_name)
read_result = opt_result_reader.read()
for i, opt_res in enumerate(minimize_result_2.optimize_result.list):
for key in opt_res:
if isinstance(opt_res[key], np.ndarray):
np.testing.assert_array_equal(
opt_res[key], read_result.optimize_result.list[i][key])
else:
assert opt_res[key] == read_result.optimize_result.list[i][key]
def store_and_plot_pretraining(result: Result, pretraindir: str, prefix: str):
"""
Store optimziation results in HDF5 as well as csv for later reuse. Also
saves some visualization for debugging purposes.
:param result:
result from pretraining
:param pretraindir:
directory in which results and plots will be stored
:param prefix:
prefix for file names that can be used to differentiate between
different pretraining stages as well as models/datasets.
"""
# store full results as hdf5
rfile = os.path.join(pretraindir, prefix + '.hdf5')
if os.path.exists(rfile):
# temp bugfix for https://github.com/ICB-DCM/pyPESTO/issues/529
os.remove(rfile)
writer = OptimizationResultHDF5Writer(rfile)
writer.write(result, overwrite=True)
# store parameter values, this will be used in subsequent steps
parameter_df = pd.DataFrame(
[r for r in result.optimize_result.get_for_key('x') if r is not None],
columns=result.problem.x_names)
parameter_df.to_csv(os.path.join(pretraindir, prefix + '.csv'))
# do plotting
waterfall(result, scale_y='log10', offset_y=0.0)
plt.tight_layout()
plt.savefig(os.path.join(pretraindir, prefix + '_waterfall.pdf'))
if result.problem.dim_full < 2e3:
parameters(result)
plt.tight_layout()
plt.savefig(os.path.join(pretraindir, prefix + '_parameters.pdf'))
)
return problem
# set all your code into this if condition.
# This way only one core performs the code
# and distributes the work of the optimization.
if __name__ == '__main__':
# set number of starts
n_starts = 2
# create problem
problem = setup_rosen_problem()
# create optimizer
optimizer = optimize.FidesOptimizer(verbose=0)
# result is the way to call the optimization with MPIPoolEngine.
result = optimize.minimize(
problem=problem,
optimizer=optimizer,
n_starts=n_starts,
engine=MPIPoolEngine(),
filename=None,
)
# saving optimization results to hdf5
file_name = 'temp_result.h5'
opt_result_writer = OptimizationResultHDF5Writer(file_name)
problem_writer = ProblemHDF5Writer(file_name)
problem_writer.write(problem)
opt_result_writer.write(result)
report_hess=False)
# do the optimization
ref = visualize.create_references(
x=np.asarray(petab_problem.x_nominal_scaled)[np.asarray(
petab_problem.x_free_indices)],
fval=problem.objective(
np.asarray(petab_problem.x_nominal_scaled)[np.asarray(
petab_problem.x_free_indices)]))
print(f'Reference fval: {ref[0]["fval"]}')
hdf_results_file = os.path.join('results', prefix + '.hdf5')
result = optimize.minimize(
problem=problem,
optimizer=optimizer,
n_starts=N_STARTS,
engine=engine,
options=options,
progress_bar=False,
filename=None,
)
visualize.waterfall(result, reference=ref, scale_y='log10')
plt.tight_layout()
plt.savefig(os.path.join('results', prefix + '_waterfall.pdf'))
writer = OptimizationResultHDF5Writer(hdf_results_file)
writer.write(result, overwrite=True)