chore(release): 1.7.0

.gitignore

@@ -145,3 +145,5 @@ cython_debug/
 *.csv
 
 local_scripts/
+
+.vscode

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/__init__.py

@@ -0,0 +1,5 @@
+from deepdog.cli.subset_sim_probs.main import wrapped_main
+
+__all__ = [
+	"wrapped_main",
+]

deepdog/cli/subset_sim_probs/args.py

@@ -0,0 +1,52 @@
+import argparse
+import os
+
+
+def parse_args() -> argparse.Namespace:
+	def dir_path(path):
+		if os.path.isdir(path):
+			return path
+		else:
+			raise argparse.ArgumentTypeError(f"readable_dir:{path} is not a valid path")
+
+	parser = argparse.ArgumentParser(
+		"subset_sim_probs",
+		description="Calculating probability from finished subset sim run",
+	)
+	parser.add_argument(
+		"--log-file",
+		type=str,
+		help="A filename for logging to, if not provided will only log to stderr",
+		default=None,
+	)
+	parser.add_argument(
+		"--results-directory",
+		"-d",
+		type=dir_path,
+		help="The directory to search for bayesrun files, defaulting to cwd if not passed",
+		default=".",
+	)
+	parser.add_argument(
+		"--indexify-json",
+		help="A json file with the indexify config for parsing job indexes. Will skip if not present",
+		default="",
+	)
+	parser.add_argument(
+		"--outfile",
+		"-o",
+		type=str,
+		help="output filename for coalesced data. If not provided, will not be written",
+		default=None,
+	)
+	confirm_outfile_overwrite_group = parser.add_mutually_exclusive_group()
+	confirm_outfile_overwrite_group.add_argument(
+		"--never-overwrite-outfile",
+		action="store_true",
+		help="If a duplicate outfile is detected, skip confirmation and automatically exit early",
+	)
+	confirm_outfile_overwrite_group.add_argument(
+		"--force-overwrite-outfile",
+		action="store_true",
+		help="Skips checking for duplicate outfiles and overwrites",
+	)
+	return parser.parse_args()

deepdog/cli/subset_sim_probs/dicts.py

@@ -0,0 +1,136 @@
+import typing
+from deepdog.results import GeneralOutput
+import logging
+import csv
+import tqdm
+
+_logger = logging.getLogger(__name__)
+
+
+def build_model_dict(
+	general_outputs: typing.Sequence[GeneralOutput],
+) -> typing.Dict[
+	typing.Tuple, typing.Dict[typing.Tuple, typing.Dict["str", typing.Any]]
+]:
+	"""
+	Maybe someday do something smarter with the coalescing and stuff but don't want to so i won't
+	"""
+	# assume that everything is well formatted and the keys are the same across entire list and initialise list of keys.
+	# model dict will contain a model_key: {calculation_dict} where each calculation_dict represents a single calculation for that model,
+	# the uncoalesced version, keyed by the specific file keys
+	model_dict: typing.Dict[
+		typing.Tuple, typing.Dict[typing.Tuple, typing.Dict["str", typing.Any]]
+	] = {}
+
+	_logger.info("building model dict")
+	for out in tqdm.tqdm(general_outputs, desc="reading outputs", leave=False):
+		for model_result in out.results:
+			model_key = tuple(v for v in model_result.parsed_model_keys.values())
+			if model_key not in model_dict:
+				model_dict[model_key] = {}
+			calculation_dict = model_dict[model_key]
+			calculation_key = tuple(v for v in out.data.values())
+			if calculation_key not in calculation_dict:
+				calculation_dict[calculation_key] = {
+					"_model_key_dict": model_result.parsed_model_keys,
+					"_calculation_key_dict": out.data,
+					"num_finished_runs": int(
+						model_result.result_dict["num_finished_runs"]
+					),
+					"num_runs": int(model_result.result_dict["num_runs"]),
+					"estimated_likelihood": float(
+						model_result.result_dict["estimated_likelihood"]
+					),
+				}
+			else:
+				raise ValueError(
+					f"Got {calculation_key} twice for model_key {model_key}"
+				)
+
+	return model_dict
+
+
+def coalesced_dict(
+	uncoalesced_model_dict: typing.Dict[
+		typing.Tuple, typing.Dict[typing.Tuple, typing.Dict["str", typing.Any]]
+	],
+):
+	"""
+	pass in uncoalesced dict
+	the minimum_count field is what we use to make sure our probs are never zero
+	"""
+	coalesced_dict = {}
+
+	# we are already iterating so for no reason because performance really doesn't matter let's count the keys ourselves
+	num_keys = 0
+
+	# first pass coalesce
+	for model_key, model_dict in uncoalesced_model_dict.items():
+		num_keys += 1
+		for calculation in model_dict.values():
+			if model_key not in coalesced_dict:
+				coalesced_dict[model_key] = {
+					"_model_key_dict": calculation["_model_key_dict"].copy(),
+					"calculations_coalesced": 1,
+					"num_finished_runs": calculation["num_finished_runs"],
+					"num_runs": calculation["num_runs"],
+					"estimated_likelihood": calculation["estimated_likelihood"],
+				}
+			else:
+				_logger.error(f"We shouldn't be here! Double key for {model_key=}")
+				raise ValueError()
+
+	# second pass do probability calculation
+
+	prior = 1 / num_keys
+	_logger.info(f"Got {num_keys} model keys, so our prior will be {prior}")
+
+	total_weight = 0
+	for coalesced_model_dict in coalesced_dict.values():
+		model_weight = coalesced_model_dict["estimated_likelihood"] * prior
+		total_weight += model_weight
+
+	total_prob = 0
+	for coalesced_model_dict in coalesced_dict.values():
+		likelihood = coalesced_model_dict["estimated_likelihood"]
+		prob = likelihood * prior / total_weight
+		coalesced_model_dict["prob"] = prob
+		total_prob += prob
+
+	_logger.debug(
+		f"Got a total probability of {total_prob}, which should be close to 1 up to float/rounding error"
+	)
+	return coalesced_dict
+
+
+def write_coalesced_dict(
+	coalesced_output_filename: typing.Optional[str],
+	coalesced_model_dict: typing.Dict[typing.Tuple, typing.Dict["str", typing.Any]],
+):
+	if coalesced_output_filename is None or coalesced_output_filename == "":
+		_logger.warning("Not provided a uncoalesced filename, not going to try")
+		return
+
+	first_value = next(iter(coalesced_model_dict.values()))
+	model_field_names = set(first_value["_model_key_dict"].keys())
+	_logger.info(f"Detected model field names {model_field_names}")
+
+	collected_fieldnames = list(model_field_names)
+	collected_fieldnames.extend(
+		["calculations_coalesced", "num_finished_runs", "num_runs", "prob"]
+	)
+	with open(coalesced_output_filename, "w", newline="") as coalesced_output_file:
+		writer = csv.DictWriter(coalesced_output_file, fieldnames=collected_fieldnames)
+		writer.writeheader()
+
+		for model_dict in coalesced_model_dict.values():
+			row = model_dict["_model_key_dict"].copy()
+			row.update(
+				{
+					"calculations_coalesced": model_dict["calculations_coalesced"],
+					"num_finished_runs": model_dict["num_finished_runs"],
+					"num_runs": model_dict["num_runs"],
+					"prob": model_dict["prob"],
+				}
+			)
+			writer.writerow(row)

deepdog/cli/subset_sim_probs/main.py

@@ -0,0 +1,113 @@
+import logging
+import argparse
+import json
+
+import deepdog.cli.subset_sim_probs.args
+import deepdog.cli.subset_sim_probs.dicts
+import deepdog.cli.util
+import deepdog.results
+import deepdog.indexify
+import pathlib
+import tqdm
+import os
+import tqdm.contrib.logging
+
+
+_logger = logging.getLogger(__name__)
+
+
+def set_up_logging(log_file: str):
+
+	log_pattern = "%(asctime)s | %(levelname)-7s | %(name)s:%(lineno)d | %(message)s"
+	if log_file is None:
+		handlers = [
+			logging.StreamHandler(),
+		]
+	else:
+		handlers = [logging.StreamHandler(), logging.FileHandler(log_file)]
+	logging.basicConfig(
+		level=logging.DEBUG,
+		format=log_pattern,
+		# it's okay to ignore this mypy error because who cares about logger handler types
+		handlers=handlers,  # type: ignore
+	)
+	logging.captureWarnings(True)
+
+
+def main(args: argparse.Namespace):
+	"""
+	Main function with passed in arguments and no additional logging setup in case we want to extract out later
+	"""
+
+	with tqdm.contrib.logging.logging_redirect_tqdm():
+		_logger.info(f"args: {args}")
+
+		if "outfile" in args and args.outfile:
+			if os.path.exists(args.outfile):
+				if args.never_overwrite_outfile:
+					_logger.warning(
+						f"Filename {args.outfile} already exists, and never want overwrite, so aborting."
+					)
+					return
+				elif args.force_overwrite_outfile:
+					_logger.warning(f"Forcing overwrite of {args.outfile}")
+				else:
+					# need to confirm
+					confirm_overwrite = deepdog.cli.util.confirm_prompt(
+						f"Filename {args.outfile} exists, overwrite?"
+					)
+					if not confirm_overwrite:
+						_logger.warning(
+							f"Filename {args.outfile} already exists and do not want overwrite, aborting."
+						)
+						return
+					else:
+						_logger.warning(f"Overwriting file {args.outfile}")
+
+		indexifier = None
+		if args.indexify_json:
+			with open(args.indexify_json, "r") as indexify_json_file:
+				indexify_spec = json.load(indexify_json_file)
+				indexify_data = indexify_spec["indexes"]
+				if "seed_spec" in indexify_spec:
+					seed_spec = indexify_spec["seed_spec"]
+					indexify_data[seed_spec["field_name"]] = list(
+						range(seed_spec["num_seeds"])
+					)
+				# _logger.debug(f"Indexifier data looks like {indexify_data}")
+				indexifier = deepdog.indexify.Indexifier(indexify_data)
+
+		results_dir = pathlib.Path(args.results_directory)
+		out_files = [
+			f for f in results_dir.iterdir() if f.name.endswith("subsetsim.csv")
+		]
+		_logger.info(
+			f"Reading {len(out_files)} subsetsim.csv files in directory {args.results_directory}"
+		)
+		# _logger.info(out_files)
+		parsed_output_files = [
+			deepdog.results.read_subset_sim_file(f, indexifier)
+			for f in tqdm.tqdm(out_files, desc="reading files", leave=False)
+		]
+
+		# Refactor here to allow for arbitrary likelihood file sources
+		_logger.info("building uncoalesced dict")
+		uncoalesced_dict = deepdog.cli.subset_sim_probs.dicts.build_model_dict(
+			parsed_output_files
+		)
+
+		_logger.info("building coalesced dict")
+		coalesced = deepdog.cli.subset_sim_probs.dicts.coalesced_dict(uncoalesced_dict)
+
+		if "outfile" in args and args.outfile:
+			deepdog.cli.subset_sim_probs.dicts.write_coalesced_dict(
+				args.outfile, coalesced
+			)
+		else:
+			_logger.info("Skipping writing coalesced")
+
+
+def wrapped_main():
+	args = deepdog.cli.subset_sim_probs.args.parse_args()
+	set_up_logging(args.log_file)
+	main(args)

deepdog/cli/util/__init__.py

@@ -0,0 +1,3 @@
+from deepdog.cli.util.confirm import confirm_prompt
+
+__all__ = ["confirm_prompt"]

deepdog/cli/util/confirm.py

@@ -0,0 +1,23 @@
+_RESPONSE_MAP = {
+	"yes": True,
+	"ye": True,
+	"y": True,
+	"no": False,
+	"n": False,
+	"nope": False,
+	"true": True,
+	"false": False,
+}
+
+
+def confirm_prompt(question: str) -> bool:
+	"""Prompt with the question and returns yes or no based on response."""
+	prompt = question + " [y/n]: "
+
+	while True:
+		choice = input(prompt).lower()
+
+		if choice in _RESPONSE_MAP:
+			return _RESPONSE_MAP[choice]
+		else:
+			print('Respond with "yes" or "no"')

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
+		filename = self.config.get_filename()
-		timestamp = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
+		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

@@ -5,6 +5,13 @@ import logging
 import deepdog.indexify
 import pathlib
 import csv
+from deepdog.results.read_csv import (
+	parse_bayesrun_row,
+	BayesrunModelResult,
+	parse_general_row,
+	GeneralModelResult,
+)
+from deepdog.results.filename import parse_file_slug
 
 _logger = logging.getLogger(__name__)
 
@@ -12,67 +19,24 @@ FILENAME_REGEX = re.compile(
 	r"(?P<timestamp>\d{8}-\d{6})-(?P<filename_slug>.*)\.realdata\.fast_filter\.bayesrun\.csv"
 )
 
-MODEL_REGEXES = [
+# probably a better way but who cares
-	re.compile(pattern)
+NO_TIMESTAMP_FILENAME_REGEX = re.compile(
-	for pattern in [
+	r"(?P<filename_slug>.*)\.realdata\.fast_filter\.bayesrun\.csv"
-		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*)",
-	]
-]
 
-FILE_SLUG_REGEXES = [
-	re.compile(pattern)
-	for pattern in [
-		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+)",
-	]
-]
 
-SIMPLE_TAG_REGEX = re.compile(r"\w+-\d+")
+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"
+)
 
 
 @dataclasses.dataclass
 class BayesrunOutputFilename:
-	timestamp: str
+	timestamp: typing.Optional[str]
 	filename_slug: str
 	path: pathlib.Path
 
 
-class BayesrunColumnParsed:
-	"""
-	class for parsing a bayesrun while pulling certain special fields out
-	"""
-
-	def __init__(self, groupdict: typing.Dict[str, str]):
-		self.column_field = groupdict["field_name"]
-		self.model_field_dict = {
-			k: v for k, v in groupdict.items() if k != "field_name"
-		}
-		self._groupdict_str = repr(groupdict)
-
-	def __str__(self):
-		return f"BayesrunColumnParsed[{self.column_field}: {self.model_field_dict}]"
-
-	def __repr__(self):
-		return f"BayesrunColumnParsed({self._groupdict_str})"
-
-	def __eq__(self, other):
-		if isinstance(other, BayesrunColumnParsed):
-			return (self.column_field == other.column_field) and (
-				self.model_field_dict == other.model_field_dict
-			)
-		return NotImplemented
-
-
-@dataclasses.dataclass
-class BayesrunModelResult:
-	parsed_model_keys: typing.Dict[str, str]
-	success: int
-	count: int
-
-
 @dataclasses.dataclass
 class BayesrunOutput:
 	filename: BayesrunOutputFilename
@@ -80,88 +44,52 @@ class BayesrunOutput:
 	results: typing.Sequence[BayesrunModelResult]
 
 
-def _batch_iterable_into_chunks(iterable, n=1):
+@dataclasses.dataclass
-	"""
+class GeneralOutput:
-	utility for batching bayesrun files where columns appear in threes
+	filename: BayesrunOutputFilename
-	"""
+	data: typing.Dict["str", typing.Any]
-	for ndx in range(0, len(iterable), n):
+	results: typing.Sequence[GeneralModelResult]
-		yield iterable[ndx : min(ndx + n, len(iterable))]
 
 
-def _parse_bayesrun_column(
+def _parse_string_output_filename(
-	column: str,
+	filename: str,
-) -> typing.Optional[BayesrunColumnParsed]:
+) -> typing.Tuple[typing.Optional[str], str]:
-	"""
+	if match := FILENAME_REGEX.match(filename):
-	Tries one by one all of a predefined list of regexes that I might have used in the past.
+		groups = match.groupdict()
-	Returns the groupdict for the first match, or None if no match found.
+		return (groups["timestamp"], groups["filename_slug"])
-	"""
+	elif match := NO_TIMESTAMP_FILENAME_REGEX.match(filename):
-	for pattern in MODEL_REGEXES:
+		groups = match.groupdict()
-		match = pattern.match(column)
+		return (None, groups["filename_slug"])
-		if match:
-			return BayesrunColumnParsed(match.groupdict())
 	else:
-		return None
+		raise ValueError(f"Could not parse {filename} as a bayesrun output filename")
-
-
-def _parse_bayesrun_row(
-	row: typing.Dict[str, str],
-) -> typing.Sequence[BayesrunModelResult]:
-
-	results = []
-	batched_keys = _batch_iterable_into_chunks(list(row.keys()), 3)
-	for model_keys in batched_keys:
-		parsed = [_parse_bayesrun_column(column) for column in model_keys]
-		values = [row[column] for column in model_keys]
-		if parsed[0] is None:
-			raise ValueError(f"no viable success row found for keys {model_keys}")
-		if parsed[1] is None:
-			raise ValueError(f"no viable count row found for keys {model_keys}")
-		if parsed[0].column_field != "success":
-			raise ValueError(f"The column {model_keys[0]} is not a success field")
-		if parsed[1].column_field != "count":
-			raise ValueError(f"The column {model_keys[1]} is not a count field")
-		parsed_keys = parsed[0].model_field_dict
-		success = int(values[0])
-		count = int(values[1])
-		results.append(
-			BayesrunModelResult(
-				parsed_model_keys=parsed_keys,
-				success=success,
-				count=count,
-			)
-		)
-	return results
 
 
 def _parse_output_filename(file: pathlib.Path) -> BayesrunOutputFilename:
 	filename = file.name
-	match = FILENAME_REGEX.match(filename)
+	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:
+	filename = file.name
+	match = SUBSET_SIM_FILENAME_REGEX.match(filename)
 	if not match:
-		raise ValueError(f"{filename} was not a valid bayesrun output")
+		raise ValueError(f"{filename} was not a valid subset sim output")
 	groups = match.groupdict()
 	return BayesrunOutputFilename(
-		timestamp=groups["timestamp"], filename_slug=groups["filename_slug"], path=file
+		filename_slug=groups["filename_slug"], path=file, timestamp=None
 	)
 
 
-def _parse_file_slug(slug: str) -> typing.Optional[typing.Dict[str, str]]:
+def read_subset_sim_file(
-	for pattern in FILE_SLUG_REGEXES:
-		match = pattern.match(slug)
-		if match:
-			return match.groupdict()
-	else:
-		return None
-
-
-def read_output_file(
 	file: pathlib.Path, indexifier: typing.Optional[deepdog.indexify.Indexifier]
-) -> BayesrunOutput:
+) -> GeneralOutput:
 
-	parsed_filename = tag = _parse_output_filename(file)
+	parsed_filename = tag = _parse_ss_output_filename(file)
-	out = BayesrunOutput(filename=parsed_filename, data={}, results=[])
+	out = GeneralOutput(filename=parsed_filename, data={}, results=[])
 
 	out.data.update(dataclasses.asdict(tag))
-	parsed_tag = _parse_file_slug(parsed_filename.filename_slug)
+	parsed_tag = parse_file_slug(parsed_filename.filename_slug)
 	if parsed_tag is None:
 		_logger.warning(
 			f"Could not parse {tag} against any matching regexes. Going to skip tag parsing"
@@ -186,8 +114,53 @@ def read_output_file(
 			row = rows[0]
 		else:
 			raise ValueError(f"Confused about having multiple rows in {file.name}")
-	results = _parse_bayesrun_row(row)
+	results = parse_general_row(
+		row, ("num_finished_runs", "num_runs", None, "estimated_likelihood")
+	)
 
 	out.results = results
 
 	return out
+
+
+def read_output_file(
+	file: pathlib.Path, indexifier: typing.Optional[deepdog.indexify.Indexifier]
+) -> BayesrunOutput:
+
+	parsed_filename = tag = _parse_output_filename(file)
+	out = BayesrunOutput(filename=parsed_filename, data={}, results=[])
+
+	out.data.update(dataclasses.asdict(tag))
+	parsed_tag = parse_file_slug(parsed_filename.filename_slug)
+	if parsed_tag is None:
+		_logger.warning(
+			f"Could not parse {tag} against any matching regexes. Going to skip tag parsing"
+		)
+	else:
+		out.data.update(parsed_tag)
+		if indexifier is not None:
+			try:
+				job_index = parsed_tag["job_index"]
+				indexified = indexifier.indexify(int(job_index))
+				out.data.update(indexified)
+			except KeyError:
+				# This isn't really that important of an error, apart from the warning
+				_logger.warning(
+					f"Parsed tag to {parsed_tag}, and attempted to indexify but no job_index key was found. skipping and moving on"
+				)
+
+	with file.open() as input_file:
+		reader = csv.DictReader(input_file)
+		rows = [r for r in reader]
+		if len(rows) == 1:
+			row = rows[0]
+		else:
+			raise ValueError(f"Confused about having multiple rows in {file.name}")
+	results = parse_bayesrun_row(row)
+
+	out.results = results
+
+	return out
+
+
+__all__ = ["read_output_file", "BayesrunOutput"]

deepdog/results/filename.py

@@ -0,0 +1,22 @@
+import re
+import typing
+
+
+FILE_SLUG_REGEXES = [
+	re.compile(pattern)
+	for pattern in [
+		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+)",
+	]
+]
+
+
+def parse_file_slug(slug: str) -> typing.Optional[typing.Dict[str, str]]:
+	for pattern in FILE_SLUG_REGEXES:
+		match = pattern.match(slug)
+		if match:
+			return match.groupdict()
+	else:
+		return None

deepdog/results/read_csv.py

@@ -0,0 +1,141 @@
+import typing
+import re
+import dataclasses
+
+MODEL_REGEXES = [
+	re.compile(pattern)
+	for pattern in [
+		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*)",
+	]
+]
+
+
+@dataclasses.dataclass
+class BayesrunModelResult:
+	parsed_model_keys: typing.Dict[str, str]
+	success: int
+	count: int
+
+
+@dataclasses.dataclass
+class GeneralModelResult:
+	parsed_model_keys: typing.Dict[str, str]
+	result_dict: typing.Dict[str, str]
+
+
+class BayesrunColumnParsed:
+	"""
+	class for parsing a bayesrun while pulling certain special fields out
+	"""
+
+	def __init__(self, groupdict: typing.Dict[str, str]):
+		self.column_field = groupdict["field_name"]
+		self.model_field_dict = {
+			k: v for k, v in groupdict.items() if k != "field_name"
+		}
+		self._groupdict_str = repr(groupdict)
+
+	def __str__(self):
+		return f"BayesrunColumnParsed[{self.column_field}: {self.model_field_dict}]"
+
+	def __repr__(self):
+		return f"BayesrunColumnParsed({self._groupdict_str})"
+
+	def __eq__(self, other):
+		if isinstance(other, BayesrunColumnParsed):
+			return (self.column_field == other.column_field) and (
+				self.model_field_dict == other.model_field_dict
+			)
+		return NotImplemented
+
+
+def _parse_bayesrun_column(
+	column: str,
+) -> typing.Optional[BayesrunColumnParsed]:
+	"""
+	Tries one by one all of a predefined list of regexes that I might have used in the past.
+	Returns the groupdict for the first match, or None if no match found.
+	"""
+	for pattern in MODEL_REGEXES:
+		match = pattern.match(column)
+		if match:
+			return BayesrunColumnParsed(match.groupdict())
+	else:
+		return None
+
+
+def _batch_iterable_into_chunks(iterable, n=1):
+	"""
+	utility for batching bayesrun files where columns appear in threes
+	"""
+	for ndx in range(0, len(iterable), n):
+		yield iterable[ndx : min(ndx + n, len(iterable))]
+
+
+def parse_general_row(
+	row: typing.Dict[str, str],
+	expected_fields: typing.Sequence[typing.Optional[str]],
+) -> typing.Sequence[GeneralModelResult]:
+	results = []
+	batched_keys = _batch_iterable_into_chunks(list(row.keys()), len(expected_fields))
+	for model_keys in batched_keys:
+		parsed = [_parse_bayesrun_column(column) for column in model_keys]
+		values = [row[column] for column in model_keys]
+
+		result_dict = {}
+		parsed_keys = None
+		for expected_field, parsed_field, value in zip(expected_fields, parsed, values):
+			if expected_field is None:
+				continue
+			if parsed_field is None:
+				raise ValueError(
+					f"No viable row found for {expected_field=} in {model_keys=}"
+				)
+			if parsed_field.column_field != expected_field:
+				raise ValueError(
+					f"The column {parsed_field.column_field} does not match expected {expected_field}"
+				)
+			result_dict[expected_field] = value
+			if parsed_keys is None:
+				parsed_keys = parsed_field.model_field_dict
+
+		if parsed_keys is None:
+			raise ValueError(f"Somehow parsed keys is none here, for {row=}")
+		results.append(
+			GeneralModelResult(parsed_model_keys=parsed_keys, result_dict=result_dict)
+		)
+	return results
+
+
+def parse_bayesrun_row(
+	row: typing.Dict[str, str],
+) -> typing.Sequence[BayesrunModelResult]:
+
+	results = []
+	batched_keys = _batch_iterable_into_chunks(list(row.keys()), 3)
+	for model_keys in batched_keys:
+		parsed = [_parse_bayesrun_column(column) for column in model_keys]
+		values = [row[column] for column in model_keys]
+		if parsed[0] is None:
+			raise ValueError(f"no viable success row found for keys {model_keys}")
+		if parsed[1] is None:
+			raise ValueError(f"no viable count row found for keys {model_keys}")
+		if parsed[0].column_field != "success":
+			raise ValueError(f"The column {model_keys[0]} is not a success field")
+		if parsed[1].column_field != "count":
+			raise ValueError(f"The column {model_keys[1]} is not a count field")
+		parsed_keys = parsed[0].model_field_dict
+		success = int(values[0])
+		count = int(values[1])
+		results.append(
+			BayesrunModelResult(
+				parsed_model_keys=parsed_keys,
+				success=success,
+				count=count,
+			)
+		)
+	return results

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "deepdog"
-version = "1.3.0"
+version = "1.7.0"
 description = ""
 authors = ["Deepak Mallubhotla <dmallubhotla+github@gmail.com>"]
 
@@ -22,6 +22,7 @@ syrupy = "^4.0.8"
 
 [tool.poetry.scripts]
 probs = "deepdog.cli.probs:wrapped_main"
+subset_sim_probs = "deepdog.cli.subset_sim_probs:wrapped_main"
 
 [build-system]
 requires = ["poetry-core>=1.0.0"]

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

@@ -1,4 +1,4 @@
-import deepdog.results
+import deepdog.results.read_csv
 
 
 def test_parse_groupdict():
@@ -6,9 +6,9 @@ def test_parse_groupdict():
 		"geom_-20_20_-10_10_0_5-orientation_free-dipole_count_100_success"
 	)
 
-	parsed = deepdog.results._parse_bayesrun_column(example_column_name)
+	parsed = deepdog.results.read_csv._parse_bayesrun_column(example_column_name)
 	assert parsed is not None
-	expected = deepdog.results.BayesrunColumnParsed(
+	expected = deepdog.results.read_csv.BayesrunColumnParsed(
 		{
 			"xmin": "-20",
 			"xmax": "20",
@@ -29,9 +29,9 @@ def test_parse_groupdict_with_magnitude():
 		"geom_-20_20_-10_10_0_5-magnitude_3.5-orientation_free-dipole_count_100_success"
 	)
 
-	parsed = deepdog.results._parse_bayesrun_column(example_column_name)
+	parsed = deepdog.results.read_csv._parse_bayesrun_column(example_column_name)
 	assert parsed is not None
-	expected = deepdog.results.BayesrunColumnParsed(
+	expected = deepdog.results.read_csv.BayesrunColumnParsed(
 		{
 			"xmin": "-20",
 			"xmax": "20",
@@ -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")