def test_run_command(runner, monkeypatch):
from nonbonded.cli.projects.benchmark import run
monkeypatch.setattr(run, "_prepare_restart", lambda *args:
(None, successful_result()))
monkeypatch.setattr(run, "_load_force_field", lambda *args: None)
monkeypatch.setattr(run, "_run_calculations",
lambda *args: RequestResult())
# Save a copy of the result model.
with temporary_cd():
# Create mock inputs
with open("server-config.json", "w") as file:
file.write(
EvaluatorServerConfig(backend_config=DaskLocalClusterConfig(
resources_per_worker=ComputeResources())).json())
RequestOptions().json("estimation-options.json")
result = runner.invoke(run_command())
with open("results.json") as file:
assert successful_result().json() == file.read()
if result.exit_code != 0:
raise result.exception
def __init__(self):
self.connection_options = ConnectionOptions()
self.estimation_options = RequestOptions()
self.data_set_path = ""
self.weights = {}
self.denominators = {}
self.polling_interval = 600
def main():
setup_timestamp_logging()
# Load in the force field
force_field_path = "smirnoff99Frosst-1.1.0.offxml"
force_field_source = SmirnoffForceFieldSource.from_path(force_field_path)
# Load in the data set containing the pure and binary properties.
data_set = PhysicalPropertyDataSet.from_json("pure_data_set.json")
data_set.merge(PhysicalPropertyDataSet.from_json("binary_data_set.json"))
# Set up a server object to run the calculations using.
server = setup_server(backend_type=BackendType.LocalGPU,
max_number_of_workers=1,
port=8001)
with server:
# Request the estimates.
property_estimator = EvaluatorClient(
ConnectionOptions(server_port=8001))
for calculation_layer in ["SimulationLayer", "ReweightingLayer"]:
options = RequestOptions()
options.calculation_layers = [calculation_layer]
parameter_gradient_keys = [
ParameterGradientKey(tag="vdW",
smirks="[#6X4:1]",
attribute="epsilon"),
ParameterGradientKey(tag="vdW",
smirks="[#6X4:1]",
attribute="rmin_half"),
]
request, _ = property_estimator.request_estimate(
property_set=data_set,
force_field_source=force_field_source,
options=options,
parameter_gradient_keys=parameter_gradient_keys,
)
# Wait for the results.
results, _ = request.results(True, 5)
layer_name = re.sub(r"(?<!^)(?=[A-Z])", "_",
calculation_layer).lower()
results.json(f"pure_binary_{layer_name}.json", True)
def from_json(cls, json_source):
"""Creates this class from a JSON string.
Parameters
-------
json_source: str or file-like object
The JSON representation of this class.
"""
if isinstance(json_source, str):
with open(json_source, "r") as file:
dictionary = json.load(file, cls=TypedJSONDecoder)
else:
dictionary = json.load(json_source, cls=TypedJSONDecoder)
if "polling_interval" not in dictionary:
dictionary["polling_interval"] = 600
assert (
"connection_options" in dictionary
and "estimation_options" in dictionary
and "data_set_path" in dictionary
and "weights" in dictionary
and "denominators" in dictionary
and "polling_interval" in dictionary
)
value = cls()
value.connection_options = ConnectionOptions()
value.connection_options.__setstate__(dictionary["connection_options"])
value.estimation_options = RequestOptions()
value.estimation_options.__setstate__(dictionary["estimation_options"])
value.data_set_path = dictionary["data_set_path"]
value.weights = {
property_name: dictionary["weights"][property_name]
for property_name in dictionary["weights"]
}
value.denominators = {
property_name: dictionary["denominators"][property_name]
for property_name in dictionary["denominators"]
}
value.polling_interval = dictionary["polling_interval"]
return value
def test_base_layer():
properties_to_estimate = [
create_dummy_property(Density),
create_dummy_property(Density),
]
dummy_options = RequestOptions()
batch = server.Batch()
batch.queued_properties = properties_to_estimate
batch.options = dummy_options
batch.force_field_id = ""
batch.options.calculation_schemas = {
"Density": {
"DummyCalculationLayer": CalculationLayerSchema()
}
}
with tempfile.TemporaryDirectory() as temporary_directory:
with temporarily_change_directory(temporary_directory):
# Create a simple calculation backend to test with.
test_backend = DaskLocalCluster()
test_backend.start()
# Create a simple storage backend to test with.
test_storage = LocalFileStorage()
layer_directory = "dummy_layer"
makedirs(layer_directory)
def dummy_callback(returned_request):
assert len(returned_request.estimated_properties) == 1
assert len(returned_request.exceptions) == 2
dummy_layer = DummyCalculationLayer()
dummy_layer.schedule_calculation(
test_backend,
test_storage,
layer_directory,
batch,
dummy_callback,
True,
)
def test_same_component_batching():
thermodynamic_state = ThermodynamicState(temperature=1.0 * unit.kelvin,
pressure=1.0 * unit.atmosphere)
data_set = PhysicalPropertyDataSet()
data_set.add_properties(
Density(
thermodynamic_state=thermodynamic_state,
substance=Substance.from_components("O", "C"),
value=0.0 * unit.kilogram / unit.meter**3,
),
EnthalpyOfVaporization(
thermodynamic_state=thermodynamic_state,
substance=Substance.from_components("O", "C"),
value=0.0 * unit.kilojoule / unit.mole,
),
Density(
thermodynamic_state=thermodynamic_state,
substance=Substance.from_components("O", "CO"),
value=0.0 * unit.kilogram / unit.meter**3,
),
EnthalpyOfVaporization(
thermodynamic_state=thermodynamic_state,
substance=Substance.from_components("O", "CO"),
value=0.0 * unit.kilojoule / unit.mole,
),
)
options = RequestOptions()
submission = EvaluatorClient._Submission()
submission.dataset = data_set
submission.options = options
with DaskLocalCluster() as calculation_backend:
server = EvaluatorServer(calculation_backend)
batches = server._batch_by_same_component(submission, "")
assert len(batches) == 2
assert len(batches[0].queued_properties) == 2
assert len(batches[1].queued_properties) == 2
def test_launch_batch():
# Set up a dummy data set
data_set = PhysicalPropertyDataSet()
data_set.add_properties(create_dummy_property(Density),
create_dummy_property(Density))
batch = Batch()
batch.force_field_id = ""
batch.options = RequestOptions()
batch.options.calculation_layers = ["QuickCalculationLayer"]
batch.options.calculation_schemas = {
"Density": {
"QuickCalculationLayer": CalculationLayerSchema()
}
}
batch.parameter_gradient_keys = []
batch.queued_properties = [*data_set]
batch.validate()
with tempfile.TemporaryDirectory() as directory:
with temporarily_change_directory(directory):
with DaskLocalCluster() as calculation_backend:
server = EvaluatorServer(
calculation_backend=calculation_backend,
working_directory=directory,
)
server._queued_batches[batch.id] = batch
server._launch_batch(batch)
while len(batch.queued_properties) > 0:
sleep(0.01)
assert len(batch.estimated_properties) == 1
assert len(batch.unsuccessful_properties) == 1
def main():
setup_timestamp_logging()
# Load in the force field
force_field_path = "smirnoff99Frosst-1.1.0.offxml"
force_field_source = SmirnoffForceFieldSource.from_path(force_field_path)
# Create a data set containing three solvation free energies.
data_set = PhysicalPropertyDataSet.from_json("hydration_data_set.json")
data_set.json("hydration_data_set.json", format=True)
# Set up a server object to run the calculations using.
server = setup_server(backend_type=BackendType.LocalGPU,
max_number_of_workers=1,
port=8002)
with server:
# Request the estimates.
property_estimator = EvaluatorClient(
ConnectionOptions(server_port=8002))
options = RequestOptions()
options.calculation_layers = ["SimulationLayer"]
options.add_schema("SimulationLayer", "SolvationFreeEnergy",
_get_fixed_lambda_schema())
request, _ = property_estimator.request_estimate(
property_set=data_set,
force_field_source=force_field_source,
options=options,
)
# Wait for the results.
results, _ = request.results(True, 60)
# Save the result to file.
results.json("results.json", True)
def test_workflow_layer():
"""Test the `WorkflowLayer` calculation layer. As the `SimulationLayer`
is the simplest implementation of the abstract layer, we settle for
testing this."""
properties_to_estimate = [
create_dummy_property(Density),
create_dummy_property(Density),
]
# Create a very simple workflow which just returns some placeholder
# value.
estimated_value = Observable(
(1 * unit.kelvin).plus_minus(0.1 * unit.kelvin))
protocol_a = DummyProtocol("protocol_a")
protocol_a.input_value = estimated_value
schema = WorkflowSchema()
schema.protocol_schemas = [protocol_a.schema]
schema.final_value_source = ProtocolPath("output_value", protocol_a.id)
layer_schema = SimulationSchema()
layer_schema.workflow_schema = schema
options = RequestOptions()
options.add_schema("SimulationLayer", "Density", layer_schema)
batch = server.Batch()
batch.queued_properties = properties_to_estimate
batch.options = options
with tempfile.TemporaryDirectory() as directory:
with temporarily_change_directory(directory):
# Create a directory for the layer.
layer_directory = "simulation_layer"
os.makedirs(layer_directory)
# Set-up a simple storage backend and add a force field to it.
force_field = SmirnoffForceFieldSource.from_path(
"smirnoff99Frosst-1.1.0.offxml")
storage_backend = LocalFileStorage()
batch.force_field_id = storage_backend.store_force_field(
force_field)
# Create a simple calculation backend to test with.
with DaskLocalCluster() as calculation_backend:
def dummy_callback(returned_request):
assert len(returned_request.estimated_properties) == 2
assert len(returned_request.exceptions) == 0
simulation_layer = SimulationLayer()
simulation_layer.schedule_calculation(
calculation_backend,
storage_backend,
layer_directory,
batch,
dummy_callback,
True,
)
def _generate(
cls,
model: Benchmark,
conda_environment,
max_time,
evaluator_preset,
evaluator_port,
n_evaluator_workers,
include_results,
reference_data_sets: Optional[List[Union[DataSet, QCDataSet]]],
optimization_result: Optional[OptimizationResult],
):
from openff.evaluator.client import RequestOptions
super(BenchmarkInputFactory, cls)._generate(
model=model,
conda_environment=conda_environment,
max_time=max_time,
evaluator_preset=evaluator_preset,
evaluator_port=evaluator_port,
n_evaluator_workers=n_evaluator_workers,
include_results=include_results,
reference_data_sets=reference_data_sets,
optimization_result=optimization_result,
)
# Save the benchmark definition in the directory
benchmark_path = "benchmark.json"
with open(benchmark_path, "w") as file:
file.write(model.json())
# Retrieve the force field.
cls._retrieve_force_field(model, optimization_result)
# Retrieve the data sets.
cls._retrieve_data_sets(model, reference_data_sets)
# Create an Evaluator server configuration
evaluator_configuration = cls._generate_evaluator_config(
preset_name=evaluator_preset,
conda_environment=conda_environment,
n_workers=n_evaluator_workers,
port=evaluator_port,
)
with open("server-config.json", "w") as file:
file.write(evaluator_configuration.json())
# Create a job submission file
cls._generate_submission_script(
"bench",
conda_environment,
evaluator_preset,
max_time,
[
"nonbonded benchmark run --restart true",
"nonbonded benchmark analyze",
],
)
# Generate a set of request options
request_options = RequestOptions()
request_options.calculation_layers = ["SimulationLayer"]
request_options.json("estimation-options.json", format=True)
# Optionally retrieve any previously generated results.
if include_results:
cls._retrieve_results(model)
def main():
setup_timestamp_logging()
# Retrieve the current version.
version = evaluator.__version__.replace(".", "-").replace("v", "")
if "+" in version:
version = "latest"
# Create a new directory to run the current versions results in.
os.makedirs(os.path.join(version, "results"))
with temporarily_change_directory(version):
with DaskLSFBackend(
minimum_number_of_workers=1,
maximum_number_of_workers=12,
resources_per_worker=QueueWorkerResources(
number_of_gpus=1,
preferred_gpu_toolkit=QueueWorkerResources.GPUToolkit.CUDA,
per_thread_memory_limit=5 * unit.gigabyte,
wallclock_time_limit="05:59",
),
setup_script_commands=[
f"conda activate openff-evaluator-{version}",
"module load cuda/10.0",
],
queue_name="gpuqueue",
) as calculation_backend:
with EvaluatorServer(
calculation_backend,
working_directory="outputs",
storage_backend=LocalFileStorage("cached-data"),
):
client = EvaluatorClient()
for allowed_layer in ["SimulationLayer", "ReweightingLayer"]:
data_set = define_data_set(
allowed_layer == "ReweightingLayer")
options = RequestOptions()
options.calculation_layers = [allowed_layer]
options.calculation_schemas = {
property_type: {}
for property_type in data_set.property_types
}
if allowed_layer == "SimulationLayer":
options.add_schema(
"SimulationLayer",
"SolvationFreeEnergy",
solvation_free_energy_schema(),
)
request, _ = client.request_estimate(
data_set,
ForceField("openff-1.2.0.offxml"),
options,
parameter_gradient_keys=[
ParameterGradientKey("vdW", smirks, attribute)
for smirks in [
"[#1:1]-[#6X4]",
"[#1:1]-[#6X4]-[#7,#8,#9,#16,#17,#35]",
"[#1:1]-[#8]",
"[#6X4:1]",
"[#8X2H1+0:1]",
"[#1]-[#8X2H2+0:1]-[#1]",
] for attribute in ["epsilon", "rmin_half"]
],
)
results, _ = request.results(synchronous=True,
polling_interval=60)
results.json(
os.path.join("results", f"{allowed_layer}.json"))
def _generate_request_options(
cls, target: EvaluatorTarget,
training_set: "PhysicalPropertyDataSet") -> "RequestOptions":
"""Generates the request options to use when estimating an evaluator
optimization targets.
Parameters
----------
target
The evaluator target which will spawn the request.
training_set
The training set which will be estimated.
Returns
-------
The request options.
"""
import inspect
from openff.evaluator.client import RequestOptions
from openff.evaluator.layers import registered_calculation_schemas
request_options = RequestOptions()
# Specify the calculation layers to use.
request_options.calculation_layers = []
if target.allow_reweighting:
request_options.calculation_layers.append("ReweightingLayer")
if target.allow_direct_simulation:
request_options.calculation_layers.append("SimulationLayer")
# Check if a non-default option has been specified.
if target.n_molecules is None and target.n_effective_samples is None:
return request_options
# Generate estimation schemas for each of the properties if a non-default
# option has been specified in the optimization options.
property_types = training_set.property_types
request_options.calculation_schemas = defaultdict(dict)
for property_type in property_types:
default_reweighting_schemas = registered_calculation_schemas.get(
"ReweightingLayer", {})
if (target.allow_reweighting
and target.n_effective_samples is not None
and property_type in default_reweighting_schemas
and callable(default_reweighting_schemas[property_type])):
default_schema = default_reweighting_schemas[property_type]
if "n_effective_samples" in inspect.getfullargspec(
default_schema).args:
default_schema = default_schema(
n_effective_samples=target.n_effective_samples)
request_options.calculation_schemas[property_type][
"ReweightingLayer"] = default_schema
default_simulation_schemas = registered_calculation_schemas.get(
"SimulationLayer", {})
if (target.allow_direct_simulation
and target.n_molecules is not None
and property_type in default_simulation_schemas
and callable(default_simulation_schemas[property_type])):
default_schema = default_simulation_schemas[property_type]
if "n_molecules" in inspect.getfullargspec(
default_schema).args:
default_schema = default_schema(
n_molecules=target.n_molecules)
request_options.calculation_schemas[property_type][
"SimulationLayer"] = default_schema
return request_options