physics/deepdog
2
0
Fork 0
Code Issues 2 Pull Requests 9 Projects Releases Wiki Activity

feat: Adds end threshold for early abort

Browse Source
This commit is contained in:
Deepak Mallubhotla 2022-02-14 09:27:40 -06:00
parent 63cecba824
commit 3d3b1a83f6
Signed by: deepak
GPG Key ID: BEBAEBF28083E022
1 changed files with 14 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
deepdog/bayes_run.py
View File

@ -41,7 +41,7 @@ class BayesRun():
run_count: int run_count: int
The number of runs to do. The number of runs to do.
''' '''
def __init__(self, dot_inputs: Sequence[DotInput], discretisations_with_names: Sequence[Tuple[str, pdme.model.Discretisation]], actual_model: pdme.model.Model, filename_slug: str, run_count: int, max_frequency: float = None) -> None: def __init__(self, dot_inputs: Sequence[DotInput], discretisations_with_names: Sequence[Tuple[str, pdme.model.Discretisation]], actual_model: pdme.model.Model, filename_slug: str, run_count: int, max_frequency: float = None, end_threshold: float = None) -> None:
self.dot_inputs = dot_inputs self.dot_inputs = dot_inputs
self.discretisations = [disc for (_, disc) in discretisations_with_names] self.discretisations = [disc for (_, disc) in discretisations_with_names]
self.model_names = [name for (name, _) in discretisations_with_names] self.model_names = [name for (name, _) in discretisations_with_names]
@ -50,7 +50,6 @@ class BayesRun():
self.run_count = run_count self.run_count = run_count
self.csv_fields = ["dipole_moment", "dipole_location", "dipole_frequency"] self.csv_fields = ["dipole_moment", "dipole_location", "dipole_frequency"]
self.compensate_zeros = True self.compensate_zeros = True
for name in self.model_names: for name in self.model_names:
self.csv_fields.extend([f"{name}_success", f"{name}_count", f"{name}_prob"]) self.csv_fields.extend([f"{name}_success", f"{name}_count", f"{name}_prob"])
@ -60,6 +59,13 @@ class BayesRun():
self.filename = f"{timestamp}-{filename_slug}.csv" self.filename = f"{timestamp}-{filename_slug}.csv"
self.max_frequency = max_frequency self.max_frequency = max_frequency
if end_threshold is not None:
if 0 < self.end_threshold < 1:
self.end_threshold: float = end_threshold
self.use_end_threshold = True
else:
raise ValueError(f"{end_threshold} should be between 0 and 1")
def go(self) -> None: def go(self) -> None:
with open(self.filename, "a", newline="") as outfile: with open(self.filename, "a", newline="") as outfile:
writer = csv.DictWriter(outfile, fieldnames=self.csv_fields, dialect="unix") writer = csv.DictWriter(outfile, fieldnames=self.csv_fields, dialect="unix")
@ -111,3 +117,9 @@ class BayesRun():
with open(self.filename, "a", newline="") as outfile: with open(self.filename, "a", newline="") as outfile:
writer = csv.DictWriter(outfile, fieldnames=self.csv_fields, dialect="unix") writer = csv.DictWriter(outfile, fieldnames=self.csv_fields, dialect="unix")
writer.writerow(row) writer.writerow(row)
if self.use_end_threshold:
max_prob = max(self.probabilities)
if max_prob > self.end_threshold:
_logger.info(f"Aborting early, because {max_prob} is greater than {self.end_threshold}")
break