chore(release): 1.7.0

CHANGELOG.md

@@ -2,6 +2,43 @@
 
 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.
 
+## [1.7.0](https://gitea.deepak.science:2222/physics/deepdog/compare/1.6.0...1.7.0) (2025-02-27)
+
+
+### Features
+
+* adds configurable skip if file exists ([24c6e31](https://gitea.deepak.science:2222/physics/deepdog/commit/24c6e311c1d3067eb98cc60e6ca38d76373bf08e))
+
+## [1.6.0](https://gitea.deepak.science:2222/physics/deepdog/compare/1.5.0...1.6.0) (2025-02-27)
+
+
+### Features
+
+* Adds ability to parse bayesruns without timestamps ([46f6b6c](https://gitea.deepak.science:2222/physics/deepdog/commit/46f6b6cdf15c67aedf0c871d201b8db320bccbdf))
+* allows negative log magnitude strings in models ([c8435b4](https://gitea.deepak.science:2222/physics/deepdog/commit/c8435b4b2a6e4b89030f53b5734eb743e2003fb7))
+
+## [1.5.0](https://gitea.deepak.science:2222/physics/deepdog/compare/1.4.0...1.5.0) (2024-12-30)
+
+
+### Features
+
+* add configurable max number of dipoles to write ([a1b59cd](https://gitea.deepak.science:2222/physics/deepdog/commit/a1b59cd18b30359328a09210d9393f211aab30c2))
+* add configurable max number of dipoles to write ([53f8993](https://gitea.deepak.science:2222/physics/deepdog/commit/53f8993f2b155228fff5cbee84f10c62eb149a1f))
+
+## [1.4.0](https://gitea.deepak.science:2222/physics/deepdog/compare/1.3.0...1.4.0) (2024-09-04)
+
+
+### Features
+
+* add subset sim probs command for bayes for subset simulation results ([c881da2](https://gitea.deepak.science:2222/physics/deepdog/commit/c881da28370a1e51d062e1a7edaa62af6eb98d0a))
+* allows some betetr matching for single_dipole runs ([5425ce1](https://gitea.deepak.science:2222/physics/deepdog/commit/5425ce1362919af4cc4dbd5813df3be8d877b198))
+* indexifier now has len ([d962ecb](https://gitea.deepak.science:2222/physics/deepdog/commit/d962ecb11e929de1d9aa458b5d8e82270eff0039))
+
+
+### Bug Fixes
+
+* update log file arg names in cli scripts ([6a5c593](https://gitea.deepak.science:2222/physics/deepdog/commit/6a5c5931d4fc849d0d6a0f2b971523a0f039d559))
+
 ## [1.3.0](https://gitea.deepak.science:2222/physics/deepdog/compare/1.2.1...1.3.0) (2024-05-20)
 
 

deepdog/cli/probs/args.py

@@ -13,7 +13,7 @@ def parse_args() -> argparse.Namespace:
 		"probs", description="Calculating probability from finished bayesrun"
 	)
 	parser.add_argument(
-		"--log_file",
+		"--log-file",
 		type=str,
 		help="A filename for logging to, if not provided will only log to stderr",
 		default=None,

deepdog/cli/subset_sim_probs/args.py

@@ -14,7 +14,7 @@ def parse_args() -> argparse.Namespace:
 		description="Calculating probability from finished subset sim run",
 	)
 	parser.add_argument(
-		"--log_file",
+		"--log-file",
 		type=str,
 		help="A filename for logging to, if not provided will only log to stderr",
 		default=None,

deepdog/direct_monte_carlo/direct_mc.py

@@ -1,3 +1,5 @@
+import re
+import pathlib
 import csv
 import pdme.model
 import pdme.measurement
@@ -36,9 +38,35 @@ class DirectMonteCarloConfig:
 	tag: str = ""
 	cap_core_count: int = 0  # 0 means cap at num cores - 1
 	chunk_size: int = 50
-	write_bayesrun_file = True
-	bayesrun_file_timestamp = True
 	# chunk size of some kind
+	write_bayesrun_file: bool = True
+	bayesrun_file_timestamp: bool = True
+	skip_if_exists: bool = False
+
+	def get_filename(self) -> str:
+		"""
+		Generate a filename for the output of this run.
+		"""
+		# set starting execution timestamp
+		timestamp = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
+
+		if self.bayesrun_file_timestamp:
+			timestamp_str = f"{timestamp}-"
+		else:
+			timestamp_str = ""
+		filename = f"{timestamp_str}{self.tag}.realdata.fast_filter.bayesrun.csv"
+		_logger.debug(f"Got filename {filename}")
+		return filename
+
+	def get_filename_regex(self) -> str:
+		"""
+		Generate a regex for the output of this run.
+		"""
+
+		# having both timestamp and the hyphen separately optional is a bit of a hack
+		# too loose, but will never matter
+		pattern = rf"(?P<timestamp>\d{{8}}-\d{{6}})?-?{self.tag}\.realdata\.fast_filter\.bayesrun\.csv"
+		return pattern
 
 
 # Aliasing dict as a generic data container
@@ -145,15 +173,21 @@ class DirectMonteCarloRun:
 		single run wrapped up for multiprocessing call.
 
 		takes in a tuple of arguments corresponding to
-		(model_name_pair, seed)
+		(model_name_pair, seed, return_configs)
+
+		return_configs is a boolean, if true then will return tuple of (count, [matching configs])
+		if false, return (count, [])
 		"""
 		# here's where we do our work
 
-		model_name_pair, seed = args
+		model_name_pair, seed, return_configs = args
 		cycle_success_configs = self._single_run(model_name_pair, seed)
 		cycle_success_count = len(cycle_success_configs)
 
-		return cycle_success_count
+		if return_configs:
+			return (cycle_success_count, cycle_success_configs)
+		else:
+			return (cycle_success_count, [])
 
 	def execute_no_multiprocessing(self) -> Sequence[DirectMonteCarloResult]:
 
@@ -198,9 +232,11 @@ class DirectMonteCarloRun:
 							)
 							dipole_count = numpy.array(cycle_success_configs).shape[1]
 							for n in range(dipole_count):
+								number_dipoles_to_write = self.config.target_success * 5
+								_logger.info(f"Limiting to {number_dipoles_to_write=}")
 								numpy.savetxt(
 									f"{self.config.tag}_{step_count}_{cycle_i}_dipole_{n}.csv",
-									sorted_by_freq[:, n],
+									sorted_by_freq[:number_dipoles_to_write, n],
 									delimiter=",",
 								)
 					total_success += cycle_success_count
@@ -222,8 +258,27 @@ class DirectMonteCarloRun:
 
 	def execute(self) -> Sequence[DirectMonteCarloResult]:
 
-		# set starting execution timestamp
-		timestamp = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
+		filename = self.config.get_filename()
+		if self.config.skip_if_exists:
+			_logger.info(f"Checking if {filename} exists")
+			cwd = pathlib.Path.cwd()
+			if (cwd / filename).exists():
+				_logger.info(f"File {filename} exists, skipping")
+				return []
+			if self.config.bayesrun_file_timestamp:
+				_logger.info(
+					"Also need to check file endings because of possible past or current timestamps, check only occurs if writing timestamp is set"
+				)
+				pattern = self.config.get_filename_regex()
+				for file in cwd.iterdir():
+					match = re.match(pattern, file.name)
+					if match is not None:
+						_logger.info(f"Matched {file.name} to {pattern}")
+						_logger.info(f"File {filename} exists, skipping")
+						return []
+				_logger.info(
+					f"Finished checking against pattern {pattern}, hopefully didn't take too long!"
+				)
 
 		count_per_step = (
 			self.config.monte_carlo_count_per_cycle * self.config.monte_carlo_cycles
@@ -259,15 +314,71 @@ class DirectMonteCarloRun:
 
 					seeds = seed_sequence.spawn(self.config.monte_carlo_cycles)
 
-					pool_results = sum(
+					raw_pool_results = list(
 						pool.imap_unordered(
 							self._wrapped_single_run,
-							[(model_name_pair, seed) for seed in seeds],
+							[
+								(
+									model_name_pair,
+									seed,
+									self.config.write_successes_to_file,
+								)
+								for seed in seeds
+							],
 							self.config.chunk_size,
 						)
 					)
+
+					pool_results = sum(result[0] for result in raw_pool_results)
+
 					_logger.debug(f"Pool results: {pool_results}")
 
+					if self.config.write_successes_to_file:
+
+						_logger.info("Writing dipole results")
+
+						cycle_success_configs = numpy.concatenate(
+							[result[1] for result in raw_pool_results]
+						)
+
+						dipole_count = numpy.array(cycle_success_configs).shape[1]
+
+						max_number_dipoles_to_write = self.config.target_success * 5
+						_logger.debug(
+							f"Limiting to {max_number_dipoles_to_write=}, have {len(cycle_success_configs)}"
+						)
+
+						if len(cycle_success_configs):
+							sorted_by_freq = numpy.array(
+								[
+									pdme.subspace_simulation.sort_array_of_dipoles_by_frequency(
+										dipole_config
+									)
+									for dipole_config in cycle_success_configs[
+										:max_number_dipoles_to_write
+									]
+								]
+							)
+
+							for n in range(dipole_count):
+
+								dipole_filename = (
+									f"{self.config.tag}_{step_count}_dipole_{n}.csv"
+								)
+								_logger.debug(
+									f"Writing {min(len(cycle_success_configs), max_number_dipoles_to_write)} to {dipole_filename}"
+								)
+
+								numpy.savetxt(
+									dipole_filename,
+									sorted_by_freq[:, n],
+									delimiter=",",
+								)
+						else:
+							_logger.debug(
+								"Instructed to write results, but none obtained"
+							)
+
 					total_success += pool_results
 					total_count += count_per_step
 					_logger.debug(
@@ -285,14 +396,6 @@ class DirectMonteCarloRun:
 
 		if self.config.write_bayesrun_file:
 
-			if self.config.bayesrun_file_timestamp:
-				timestamp_str = f"{timestamp}-"
-			else:
-				timestamp_str = ""
-			filename = (
-				f"{timestamp_str}{self.config.tag}.realdata.fast_filter.bayesrun.csv"
-			)
-
 			_logger.info(f"Going to write to file [{filename}]")
 			# row: Dict[str, Union[int, float, str]] = {}
 			row = {}

deepdog/indexify/__init__.py

@@ -36,6 +36,10 @@ class Indexifier:
 	def indexify(self, n: int) -> typing.Dict[str, typing.Any]:
 		return self.product_dict[n]
 
+	def __len__(self) -> int:
+		weights = [len(v) for v in self.dict.values()]
+		return math.prod(weights)
+
 	def _indexify_indices(self, n: int) -> typing.Sequence[int]:
 		"""
 		legacy indexify from old scripts, copypast.

deepdog/results/__init__.py

@@ -19,6 +19,11 @@ FILENAME_REGEX = re.compile(
 	r"(?P<timestamp>\d{8}-\d{6})-(?P<filename_slug>.*)\.realdata\.fast_filter\.bayesrun\.csv"
 )
 
+# probably a better way but who cares
+NO_TIMESTAMP_FILENAME_REGEX = re.compile(
+	r"(?P<filename_slug>.*)\.realdata\.fast_filter\.bayesrun\.csv"
+)
+
 
 SUBSET_SIM_FILENAME_REGEX = re.compile(
 	r"(?P<filename_slug>.*)-(?:no_adaptive_steps_)?(?P<num_ss_runs>\d+)-nc_(?P<n_c>\d+)-ns_(?P<n_s>\d+)-mmax_(?P<mmax>\d+)\.multi\.subsetsim\.csv"
@@ -46,15 +51,23 @@ class GeneralOutput:
 	results: typing.Sequence[GeneralModelResult]
 
 
+def _parse_string_output_filename(
+	filename: str,
+) -> typing.Tuple[typing.Optional[str], str]:
+	if match := FILENAME_REGEX.match(filename):
+		groups = match.groupdict()
+		return (groups["timestamp"], groups["filename_slug"])
+	elif match := NO_TIMESTAMP_FILENAME_REGEX.match(filename):
+		groups = match.groupdict()
+		return (None, groups["filename_slug"])
+	else:
+		raise ValueError(f"Could not parse {filename} as a bayesrun output filename")
+
+
 def _parse_output_filename(file: pathlib.Path) -> BayesrunOutputFilename:
 	filename = file.name
-	match = FILENAME_REGEX.match(filename)
-	if not match:
-		raise ValueError(f"{filename} was not a valid bayesrun output")
-	groups = match.groupdict()
-	return BayesrunOutputFilename(
-		timestamp=groups["timestamp"], filename_slug=groups["filename_slug"], path=file
-	)
+	timestamp, slug = _parse_string_output_filename(filename)
+	return BayesrunOutputFilename(timestamp=timestamp, filename_slug=slug, path=file)
 
 
 def _parse_ss_output_filename(file: pathlib.Path) -> BayesrunOutputFilename:

deepdog/results/filename.py

@@ -8,6 +8,7 @@ FILE_SLUG_REGEXES = [
 		r"(?P<tag>\w+)-(?P<job_index>\d+)",
 		r"mock_tarucha-(?P<job_index>\d+)",
 		r"(?:(?P<mock>mock)_)?tarucha(?:_(?P<tarucha_run_id>\d+))?-(?P<job_index>\d+)",
+		r"(?P<tag>\w+)-(?P<included_dots>[\w,]+)-(?P<target_cost>\d*\.?\d+)-(?P<job_index>\d+)",
 	]
 ]
 

deepdog/results/read_csv.py

@@ -8,6 +8,8 @@ MODEL_REGEXES = [
 		r"geom_(?P<xmin>-?\d+)_(?P<xmax>-?\d+)_(?P<ymin>-?\d+)_(?P<ymax>-?\d+)_(?P<zmin>-?\d+)_(?P<zmax>-?\d+)-orientation_(?P<orientation>free|fixedxy|fixedz)-dipole_count_(?P<avg_filled>\d+)_(?P<field_name>\w*)",
 		r"geom_(?P<xmin>-?\d+)_(?P<xmax>-?\d+)_(?P<ymin>-?\d+)_(?P<ymax>-?\d+)_(?P<zmin>-?\d+)_(?P<zmax>-?\d+)-magnitude_(?P<log_magnitude>\d*\.?\d+)-orientation_(?P<orientation>free|fixedxy|fixedz)-dipole_count_(?P<avg_filled>\d+)_(?P<field_name>\w*)",
 		r"geom_(?P<xmin>-?\d*\.?\d+)_(?P<xmax>-?\d*\.?\d+)_(?P<ymin>-?\d*\.?\d+)_(?P<ymax>-?\d*\.?\d+)_(?P<zmin>-?\d*\.?\d+)_(?P<zmax>-?\d*\.?\d+)-magnitude_(?P<log_magnitude>\d*\.?\d+)-orientation_(?P<orientation>free|fixedxy|fixedz)-dipole_count_(?P<avg_filled>\d+)_(?P<field_name>\w*)",
+		r"geom_(?P<xmin>-?\d+)_(?P<xmax>-?\d+)_(?P<ymin>-?\d+)_(?P<ymax>-?\d+)_(?P<zmin>-?\d+)_(?P<zmax>-?\d+)-magnitude_(?P<log_magnitude>-?\d*\.?\d+)-orientation_(?P<orientation>free|fixedxy|fixedz)-dipole_count_(?P<avg_filled>\d+)_(?P<field_name>\w*)",
+		r"geom_(?P<xmin>-?\d*\.?\d+)_(?P<xmax>-?\d*\.?\d+)_(?P<ymin>-?\d*\.?\d+)_(?P<ymax>-?\d*\.?\d+)_(?P<zmin>-?\d*\.?\d+)_(?P<zmax>-?\d*\.?\d+)-magnitude_(?P<log_magnitude>-?\d*\.?\d+)-orientation_(?P<orientation>free|fixedxy|fixedz)-dipole_count_(?P<avg_filled>\d+)_(?P<field_name>\w*)",
 	]
 ]
 

pyproject.toml

@@ -1,13 +1,13 @@
 [tool.poetry]
 name = "deepdog"
-version = "1.3.0"
+version = "1.7.0"
 description = ""
 authors = ["Deepak Mallubhotla <dmallubhotla+github@gmail.com>"]
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<3.10"
 pdme = "^1.5.0"
-numpy = "2.0.0"
+numpy = "1.22.3"
 scipy = "1.10"
 tqdm = "^4.66.2"
 

tests/direct_monte_carlo/test_config_filename.py

@@ -0,0 +1,26 @@
+import re
+import deepdog.direct_monte_carlo
+
+
+def test_config_check_self():
+	config = deepdog.direct_monte_carlo.DirectMonteCarloConfig(
+		tag="test_tag",
+		bayesrun_file_timestamp=False,
+	)
+	expected_filename = "test_tag.realdata.fast_filter.bayesrun.csv"
+	actual_filename = config.get_filename()
+	assert actual_filename == expected_filename
+	regex = config.get_filename_regex()
+	assert re.match(regex, actual_filename) is not None
+
+
+def test_config_check_self_with_timestamp():
+	config = deepdog.direct_monte_carlo.DirectMonteCarloConfig(
+		tag="test_tag",
+		bayesrun_file_timestamp=True,
+	)
+	expected_filename_ending = "test_tag.realdata.fast_filter.bayesrun.csv"
+	actual_filename = config.get_filename()
+	assert actual_filename.endswith(expected_filename_ending)
+	regex = config.get_filename_regex()
+	assert re.match(regex, actual_filename) is not None

tests/indexify/test_indexify.py

@@ -10,3 +10,12 @@ def test_indexifier():
 	_logger.debug(f"setting up indexifier {indexifier}")
 	assert indexifier.indexify(0) == {"key_1": 1, "key_2": "a"}
 	assert indexifier.indexify(5) == {"key_1": 2, "key_2": "c"}
+	assert len(indexifier) == 9
+
+
+def test_indexifier_length_short():
+	weight_dict = {"key_1": [1, 2, 3], "key_2": ["b", "c"]}
+	indexifier = deepdog.indexify.Indexifier(weight_dict)
+	_logger.debug(f"setting up indexifier {indexifier}")
+
+	assert len(indexifier) == 6

tests/results/test_column_results.py

@@ -48,6 +48,28 @@ def test_parse_groupdict_with_magnitude():
 	assert parsed == expected
 
 
+def test_parse_groupdict_with_negative_magnitude():
+	example_column_name = "geom_-20_20_-10_10_0_5-magnitude_-3.5-orientation_free-dipole_count_100_success"
+
+	parsed = deepdog.results.read_csv._parse_bayesrun_column(example_column_name)
+	assert parsed is not None
+	expected = deepdog.results.read_csv.BayesrunColumnParsed(
+		{
+			"xmin": "-20",
+			"xmax": "20",
+			"ymin": "-10",
+			"ymax": "10",
+			"zmin": "0",
+			"zmax": "5",
+			"orientation": "free",
+			"avg_filled": "100",
+			"log_magnitude": "-3.5",
+			"field_name": "success",
+		}
+	)
+	assert parsed == expected
+
+
 # def test_parse_no_match_column_name():
 # 	parsed = deepdog.results.parse_bayesrun_column("There's nothing here")
 # 	assert parsed is None

tests/results/test_parse_filename.py

@@ -0,0 +1,19 @@
+import deepdog.results
+import pytest
+
+
+def test_parse_bayesrun_filename():
+	valid1 = "20250226-204120-dot1-dot1-2-0.realdata.fast_filter.bayesrun.csv"
+
+	timestamp, slug = deepdog.results._parse_string_output_filename(valid1)
+	assert timestamp == "20250226-204120"
+	assert slug == "dot1-dot1-2-0"
+
+	valid2 = "dot1-dot1-2-0.realdata.fast_filter.bayesrun.csv"
+
+	timestamp, slug = deepdog.results._parse_string_output_filename(valid2)
+	assert timestamp is None
+	assert slug == "dot1-dot1-2-0"
+
+	with pytest.raises(ValueError):
+		deepdog.results._parse_string_output_filename("not_a_valid_filename")