chore(deps): update dependency mypy to ^0.991

CHANGELOG.md

@@ -2,6 +2,13 @@
 
 All notable changes to this project will be documented in this file. See [standard-version](https://github.com/conventional-changelog/standard-version) for commit guidelines.
 
+### [0.7.3](https://gitea.deepak.science:2222/physics/deepdog/compare/0.7.2...0.7.3) (2023-07-27)
+
+
+### Features
+
+* adds utility options and avoids memory leak ([598dad1](https://gitea.deepak.science:2222/physics/deepdog/commit/598dad1e6dc8fc0b7a5b4a90c8e17bf744e8d98c))
+
 ### [0.7.2](https://gitea.deepak.science:2222/physics/deepdog/compare/0.7.1...0.7.2) (2023-07-24)
 
 

deepdog/bayes_run_with_ss.py

@@ -70,6 +70,7 @@ class BayesRunWithSubspaceSimulation:
 		ss_default_r_step=0.01,
 		ss_default_w_log_step=0.01,
 		ss_default_upper_w_log_step=4,
+		ss_dump_last_generation=False,
 	) -> None:
 		self.dot_inputs = pdme.inputs.inputs_with_frequency_range(
 			dot_positions, frequency_range
@@ -133,6 +134,7 @@ class BayesRunWithSubspaceSimulation:
 		self.ss_default_r_step = ss_default_r_step
 		self.ss_default_w_log_step = ss_default_w_log_step
 		self.ss_default_upper_w_log_step = ss_default_upper_w_log_step
+		self.ss_dump_last_generation = ss_dump_last_generation
 
 		self.run_count = run_count
 
@@ -172,6 +174,8 @@ class BayesRunWithSubspaceSimulation:
 					self.ss_default_r_step,
 					self.ss_default_w_log_step,
 					self.ss_default_upper_w_log_step,
+					keep_probs_list=False,
+					dump_last_generation_to_file=self.ss_dump_last_generation,
 				)
 				results.append(subset_run.execute())
 
@@ -196,7 +200,9 @@ class BayesRunWithSubspaceSimulation:
 			for (name, result) in zip(self.model_names, results):
 				if result.over_target_likelihood is None:
 					clamped_likelihood = result.probs_list[-1][0] / CLAMPING_FACTOR
-					_logger.warning(f"got a none result, clamping to {clamped_likelihood}")
+					_logger.warning(
+						f"got a none result, clamping to {clamped_likelihood}"
+					)
 				else:
 					clamped_likelihood = result.over_target_likelihood
 				likelihoods.append(clamped_likelihood)

deepdog/subset_simulation/subset_simulation_impl.py

@@ -17,6 +17,7 @@ class SubsetSimulationResult:
 	over_target_likelihood: Optional[float]
 	under_target_cost: Optional[float]
 	under_target_likelihood: Optional[float]
+	lowest_likelihood: Optional[float]
 
 
 class SubsetSimulation:
@@ -37,6 +38,8 @@ class SubsetSimulation:
 		default_r_step=0.01,
 		default_w_log_step=0.01,
 		default_upper_w_log_step=4,
+		keep_probs_list=True,
+		dump_last_generation_to_file=False,
 	):
 		name, model = model_name_pair
 		self.model_name = name
@@ -79,6 +82,9 @@ class SubsetSimulation:
 		self.target_cost = target_cost
 		_logger.info(f"will stop at target cost {target_cost}")
 
+		self.keep_probs_list = keep_probs_list
+		self.dump_last_generations = dump_last_generation_to_file
+
 	def execute(self) -> SubsetSimulationResult:
 
 		probs_list = []
@@ -116,15 +122,27 @@ class SubsetSimulation:
 		for i in range(self.m_max):
 			next_seeds = all_chains[-self.n_c:]
 
-			for cost_index, cost_chain in enumerate(all_chains[: -self.n_c]):
-				probs_list.append(
-					(
-						((self.n_c * self.n_s - cost_index) / (self.n_c * self.n_s))
-						/ (self.n_s ** (i)),
-						cost_chain[0],
-						i + 1,
+			if self.dump_last_generations:
+				_logger.info("writing out csv file")
+				next_dipoles_seed_dipoles = numpy.array([n[1] for n in next_seeds])
+				for n in range(self.model.n):
+					_logger.info(f"{next_dipoles_seed_dipoles[:, n].shape}")
+					numpy.savetxt(
+						f"generation_{self.n_c}_{self.n_s}_{i}_dipole_{n}.csv",
+						next_dipoles_seed_dipoles[:, n],
+						delimiter=",",
+					)
+
+			if self.keep_probs_list:
+				for cost_index, cost_chain in enumerate(all_chains[: -self.n_c]):
+					probs_list.append(
+						(
+							((self.n_c * self.n_s - cost_index) / (self.n_c * self.n_s))
+							/ (self.n_s ** (i)),
+							cost_chain[0],
+							i + 1,
+						)
 					)
-				)
 
 			next_seeds_as_array = numpy.array([s for _, s in next_seeds])
 
@@ -169,14 +187,18 @@ class SubsetSimulation:
 
 				shorter_probs_list = []
 				for cost_index, cost_chain in enumerate(all_chains):
-					probs_list.append(
-						(
-							((self.n_c * self.n_s - cost_index) / (self.n_c * self.n_s))
-							/ (self.n_s ** (i)),
-							cost_chain[0],
-							i + 1,
+					if self.keep_probs_list:
+						probs_list.append(
+							(
+								(
+									(self.n_c * self.n_s - cost_index)
+									/ (self.n_c * self.n_s)
+								)
+								/ (self.n_s ** (i)),
+								cost_chain[0],
+								i + 1,
+							)
 						)
-					)
 					shorter_probs_list.append(
 						(
 							cost_chain[0],
@@ -191,21 +213,23 @@ class SubsetSimulation:
 					over_target_likelihood=shorter_probs_list[over_index - 1][1],
 					under_target_cost=shorter_probs_list[over_index][0],
 					under_target_likelihood=shorter_probs_list[over_index][1],
+					lowest_likelihood=shorter_probs_list[-1][1],
 				)
 				return result
 
 			# _logger.debug([c[0] for c in all_chains[-n_c:]])
 			_logger.info(f"doing level {i + 1}")
 
-		for cost_index, cost_chain in enumerate(all_chains):
-			probs_list.append(
-				(
-					((self.n_c * self.n_s - cost_index) / (self.n_c * self.n_s))
-					/ (self.n_s ** (self.m_max)),
-					cost_chain[0],
-					self.m_max + 1,
+		if self.keep_probs_list:
+			for cost_index, cost_chain in enumerate(all_chains):
+				probs_list.append(
+					(
+						((self.n_c * self.n_s - cost_index) / (self.n_c * self.n_s))
+						/ (self.n_s ** (self.m_max)),
+						cost_chain[0],
+						self.m_max + 1,
+					)
 				)
-			)
 		threshold_cost = all_chains[-self.n_c][0]
 		_logger.info(
 			f"final threshold cost: {threshold_cost}, at P = (1 / {self.n_s})^{self.m_max + 1}"
@@ -215,12 +239,16 @@ class SubsetSimulation:
 		# for prob, prob_cost in probs_list:
 		# 	_logger.info(f"\t{prob}: {prob_cost}")
 		probs_list.sort(key=lambda c: c[0], reverse=True)
+
+		min_likelihood = ((1) / (self.n_c * self.n_s)) / (self.n_s ** (self.m_max + 1))
+
 		result = SubsetSimulationResult(
 			probs_list=probs_list,
 			over_target_cost=None,
 			over_target_likelihood=None,
 			under_target_cost=None,
 			under_target_likelihood=None,
+			lowest_likelihood=min_likelihood,
 		)
 		return result
 

poetry.lock

@@ -461,11 +461,11 @@ testing = ["argcomplete", "attrs (>=19.2.0)", "hypothesis (>=3.56)", "mock", "no
 
 [[package]]
 name = "pytest-cov"
-version = "3.0.0"
+version = "4.1.0"
 description = "Pytest plugin for measuring coverage."
 category = "dev"
 optional = false
-python-versions = ">=3.6"
+python-versions = ">=3.7"
 
 [package.dependencies]
 coverage = {version = ">=5.2.1", extras = ["toml"]}
@@ -730,7 +730,7 @@ testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "flake8 (<5)", "pytest-co
 [metadata]
 lock-version = "1.1"
 python-versions = ">=3.8.1,<3.10"
-content-hash = "0161af7edf18c16819f1ce083ab491c17c9809f2770219725131451b1a16a970"
+content-hash = "111972d04616ce3ddfc9039a0b38c7eb7c4a41f10390139b27e958aedac7e979"
 
 [metadata.files]
 black = []

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "deepdog"
-version = "0.7.2"
+version = "0.7.3"
 description = ""
 authors = ["Deepak Mallubhotla <dmallubhotla+github@gmail.com>"]
 
@@ -13,8 +13,8 @@ scipy = "1.10"
 [tool.poetry.dev-dependencies]
 pytest = ">=6"
 flake8 = "^4.0.1"
-pytest-cov = "^3.0.0"
-mypy = "^0.971"
+pytest-cov = "^4.1.0"
+mypy = "^0.991"
 python-semantic-release = "^7.24.0"
 black = "^22.3.0"