chore(deps): update dependency flake8 to v7

Reviewed-on: #37

.gitignore

@@ -143,3 +143,5 @@ dmypy.json
 cython_debug/
 
 *.csv
+
+local_scripts/

CHANGELOG.md

@@ -2,6 +2,63 @@
 
 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.
 
+### [0.8.1](https://gitea.deepak.science:2222/physics/deepdog/compare/0.8.0...0.8.1) (2024-04-28)
+
+### [0.8.1](https://gitea.deepak.science:2222/physics/deepdog/compare/0.8.0...0.8.1) (2024-04-28)
+
+## [0.8.0](https://gitea.deepak.science:2222/physics/deepdog/compare/0.7.10...0.8.0) (2024-04-28)
+
+
+### ⚠ BREAKING CHANGES
+
+* fixes the spin qubit frequency phase shift calculation which had an index problem
+
+### Bug Fixes
+
+* fixes the spin qubit frequency phase shift calculation which had an index problem ([f9646e3](https://gitea.deepak.science:2222/physics/deepdog/commit/f9646e33868e1a0da8ab663230c0c692ac25bb74))
+
+### [0.7.10](https://gitea.deepak.science:2222/physics/deepdog/compare/0.7.9...0.7.10) (2024-04-28)
+
+
+### Features
+
+* adds cli probs ([4b2e573](https://gitea.deepak.science:2222/physics/deepdog/commit/4b2e57371546731137b011461849bb849d4d4e0f))
+* better management of cli wrapper ([b0ad4be](https://gitea.deepak.science:2222/physics/deepdog/commit/b0ad4bead0d4762eb7f848f6e557f6d9b61200b9))
+
+### [0.7.9](https://gitea.deepak.science:2222/physics/deepdog/compare/0.7.8...0.7.9) (2024-04-21)
+
+
+### Features
+
+* adds ability to write custom dmc filters ([ea080ca](https://gitea.deepak.science:2222/physics/deepdog/commit/ea080ca1c7068042ce1e0a222d317f785a6b05f4))
+* adds tarucha phase calculation, using spin qubit precession rate noise ([3ae0783](https://gitea.deepak.science:2222/physics/deepdog/commit/3ae0783d00cbe6a76439c1d671f2cff621d8d0a8))
+
+### [0.7.8](https://gitea.deepak.science:2222/physics/deepdog/compare/0.7.7...0.7.8) (2024-02-29)
+
+
+### Bug Fixes
+
+* uses correct measurements ([5f534a6](https://gitea.deepak.science:2222/physics/deepdog/commit/5f534a60cc7c4838fcacee11a7e58b97d34e154a))
+
+### [0.7.7](https://gitea.deepak.science:2222/physics/deepdog/compare/0.7.6...0.7.7) (2024-02-29)
+
+
+### Bug Fixes
+
+* fixes phase calculation issue with setting input array ([48e41cb](https://gitea.deepak.science:2222/physics/deepdog/commit/48e41cbd2c58d4c4d2747822d618d7d55257643d))
+
+### [0.7.6](https://gitea.deepak.science:2222/physics/deepdog/compare/0.7.5...0.7.6) (2024-02-28)
+
+
+### Features
+
+* adds ability to use phase measurements only for correlations ([bb72e90](https://gitea.deepak.science:2222/physics/deepdog/commit/bb72e903d14704a3783daf2dbc1797b90880aa85))
+
+
+### Bug Fixes
+
+* fixes typeerror vs indexerror on bare float as cost in subset simulation ([65e1948](https://gitea.deepak.science:2222/physics/deepdog/commit/65e19488359d7f5656660da7da8f32ed474989c3))
+
 ### [0.7.5](https://gitea.deepak.science:2222/physics/deepdog/compare/0.7.4...0.7.5) (2023-12-09)
 
 

README.md

@@ -5,7 +5,7 @@
 [![Jenkins](https://img.shields.io/jenkins/build?jobUrl=https%3A%2F%2Fjenkins.deepak.science%2Fjob%2Fgitea-physics%2Fjob%2Fdeepdog%2Fjob%2Fmaster&style=flat-square)](https://jenkins.deepak.science/job/gitea-physics/job/deepdog/job/master/)
 ![Jenkins tests](https://img.shields.io/jenkins/tests?compact_message&jobUrl=https%3A%2F%2Fjenkins.deepak.science%2Fjob%2Fgitea-physics%2Fjob%2Fdeepdog%2Fjob%2Fmaster%2F&style=flat-square)
 ![Jenkins Coverage](https://img.shields.io/jenkins/coverage/cobertura?jobUrl=https%3A%2F%2Fjenkins.deepak.science%2Fjob%2Fgitea-physics%2Fjob%2Fdeepdog%2Fjob%2Fmaster%2F&style=flat-square)
-![Maintenance](https://img.shields.io/maintenance/yes/2023?style=flat-square)
+![Maintenance](https://img.shields.io/maintenance/yes/2024?style=flat-square)
 
 The DiPole DiaGnostic tool.
 
@@ -13,6 +13,13 @@ The DiPole DiaGnostic tool.
 
 `poetry install` to start locally
 
-Commit using [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/), and when commits are on master, release with `doo release`.
+Commit using [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/), and when commits are on master, release with `just release`.
 
+In general `just --list` has some of the useful stuff for figuring out what development tools there are.
 
+Poetry as an installer is good, even better is using Nix (maybe with direnv to automatically pick up the `devShell` from `flake.nix`).
+In either case `just` should handle actually calling things in a way that's agnostic to poetry as a runner or through nix.
+
+### local scripts
+`local_scripts` folder allows for scripts to be run using this code, but that probably isn't the most auditable for actual usage.
+The API is still only something I'm using so there's no guarantees yet that it will be stable; overall semantic versioning should help with API breaks.

deepdog/cli/probs/__init__.py

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

deepdog/cli/probs/args.py

@@ -0,0 +1,63 @@
+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(
+		"probs", description="Calculating probability from finished bayesrun"
+	)
+	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(
+		"--bayesrun-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(
+		"--seed-index",
+		type=int,
+		help='take an integer to append as a "seed" key with range at end of indexify dict. Skip if <= 0',
+		default=0,
+	)
+	parser.add_argument(
+		"--seed-fieldname",
+		type=str,
+		help='if --seed-index is set, the fieldname to append to the indexifier. "seed" by default',
+		default="seed",
+	)
+	parser.add_argument(
+		"--coalesced-keys",
+		type=str,
+		help="A comma separated list of strings over which to coalesce data. By default coalesce over all fields within model names, ignore file level names",
+		default="",
+	)
+	parser.add_argument(
+		"--uncoalesced-outfile",
+		type=str,
+		help="output filename for uncoalesced data. If not provided, will not be written",
+		default=None,
+	)
+	parser.add_argument(
+		"--coalesced-outfile",
+		type=str,
+		help="output filename for coalesced data. If not provided, will not be written",
+		default=None,
+	)
+	return parser.parse_args()

deepdog/cli/probs/dicts.py

@@ -0,0 +1,178 @@
+import typing
+from deepdog.results import BayesrunOutput
+import logging
+import csv
+import tqdm
+
+_logger = logging.getLogger(__name__)
+
+
+def build_model_dict(
+	bayes_outputs: typing.Sequence[BayesrunOutput],
+) -> 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(bayes_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,
+					"success": model_result.success,
+					"count": model_result.count,
+				}
+			else:
+				raise ValueError(
+					f"Got {calculation_key} twice for model_key {model_key}"
+				)
+
+	return model_dict
+
+
+def write_uncoalesced_dict(
+	uncoalesced_output_filename: typing.Optional[str],
+	uncoalesced_model_dict: typing.Dict[
+		typing.Tuple, typing.Dict[typing.Tuple, typing.Dict["str", typing.Any]]
+	],
+):
+	if uncoalesced_output_filename is None or uncoalesced_output_filename == "":
+		_logger.warning("Not provided a uncoalesced filename, not going to try")
+		return
+
+	first_value = next(iter(next(iter(uncoalesced_model_dict.values())).values()))
+	model_field_names = set(first_value["_model_key_dict"].keys())
+	calculation_field_names = set(first_value["_calculation_key_dict"].keys())
+	if not (set(model_field_names).isdisjoint(calculation_field_names)):
+		_logger.info(f"Detected model field names {model_field_names}")
+		_logger.info(f"Detected calculation field names {calculation_field_names}")
+		raise ValueError(
+			f"model field names {model_field_names} and calculation {calculation_field_names} have an overlap, which is possibly a problem"
+		)
+	collected_fieldnames = list(model_field_names)
+	collected_fieldnames.extend(calculation_field_names)
+	collected_fieldnames.extend(["success", "count"])
+	_logger.info(f"Full uncoalesced fieldnames are {collected_fieldnames}")
+	with open(uncoalesced_output_filename, "w", newline="") as uncoalesced_output_file:
+		writer = csv.DictWriter(
+			uncoalesced_output_file, fieldnames=collected_fieldnames
+		)
+		writer.writeheader()
+
+		for model_dict in uncoalesced_model_dict.values():
+			for calculation in model_dict.values():
+				row = calculation["_model_key_dict"].copy()
+				row.update(calculation["_calculation_key_dict"].copy())
+				row.update(
+					{
+						"success": calculation["success"],
+						"count": calculation["count"],
+					}
+				)
+				writer.writerow(row)
+
+
+def coalesced_dict(
+	uncoalesced_model_dict: typing.Dict[
+		typing.Tuple, typing.Dict[typing.Tuple, typing.Dict["str", typing.Any]]
+	],
+	minimum_count: float = 0.1,
+):
+	"""
+	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": 0,
+					"count": 0,
+					"success": 0,
+				}
+			sub_dict = coalesced_dict[model_key]
+			sub_dict["calculations_coalesced"] += 1
+			sub_dict["count"] += calculation["count"]
+			sub_dict["success"] += calculation["success"]
+
+	# 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 = (
+			max(minimum_count, coalesced_model_dict["success"])
+			/ coalesced_model_dict["count"]
+		) * prior
+		total_weight += model_weight
+
+	total_prob = 0
+	for coalesced_model_dict in coalesced_dict.values():
+		model_weight = (
+			max(minimum_count, coalesced_model_dict["success"])
+			/ coalesced_model_dict["count"]
+		)
+		prob = model_weight * 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", "success", "count", "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"],
+					"success": model_dict["success"],
+					"count": model_dict["count"],
+					"prob": model_dict["prob"],
+				}
+			)
+			writer.writerow(row)

deepdog/cli/probs/main.py

@@ -0,0 +1,95 @@
+import logging
+import argparse
+import json
+import deepdog.cli.probs.args
+import deepdog.cli.probs.dicts
+import deepdog.results
+import deepdog.indexify
+import pathlib
+import tqdm
+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}")
+
+		try:
+			if args.coalesced_keys:
+				raise NotImplementedError(
+					"Currently not supporting coalesced keys, but maybe in future"
+				)
+		except AttributeError:
+			# we don't care if this is missing because we don't actually want it to be there
+			pass
+
+		indexifier = None
+		if args.indexify_json:
+			with open(args.indexify_json, "r") as indexify_json_file:
+				indexify_data = json.load(indexify_json_file)
+				if args.seed_index > 0:
+					indexify_data[args.seed_fieldname] = list(range(args.seed_index))
+				# _logger.debug(f"Indexifier data looks like {indexify_data}")
+				indexifier = deepdog.indexify.Indexifier(indexify_data)
+
+		bayes_dir = pathlib.Path(args.bayesrun_directory)
+		out_files = [f for f in bayes_dir.iterdir() if f.name.endswith("bayesrun.csv")]
+		_logger.info(
+			f"Reading {len(out_files)} bayesrun.csv files in directory {args.bayesrun_directory}"
+		)
+		# _logger.info(out_files)
+		parsed_output_files = [
+			deepdog.results.read_output_file(f, indexifier)
+			for f in tqdm.tqdm(out_files, desc="reading files", leave=False)
+		]
+
+		_logger.info("building uncoalesced dict")
+		uncoalesced_dict = deepdog.cli.probs.dicts.build_model_dict(parsed_output_files)
+
+		if "uncoalesced_outfile" in args and args.uncoalesced_outfile:
+			deepdog.cli.probs.dicts.write_uncoalesced_dict(
+				args.uncoalesced_outfile, uncoalesced_dict
+			)
+		else:
+			_logger.info("Skipping writing uncoalesced")
+
+		_logger.info("building coalesced dict")
+		coalesced = deepdog.cli.probs.dicts.coalesced_dict(uncoalesced_dict)
+
+		if "coalesced_outfile" in args and args.coalesced_outfile:
+			deepdog.cli.probs.dicts.write_coalesced_dict(
+				args.coalesced_outfile, coalesced
+			)
+		else:
+			_logger.info("Skipping writing coalesced")
+
+
+def wrapped_main():
+	args = deepdog.cli.probs.args.parse_args()
+	set_up_logging(args.log_file)
+	main(args)

deepdog/direct_monte_carlo/compose_filter.py

@@ -0,0 +1,14 @@
+from typing import Sequence
+from deepdog.direct_monte_carlo.direct_mc import DirectMonteCarloFilter
+import numpy
+
+
+class ComposedDMCFilter(DirectMonteCarloFilter):
+	def __init__(self, filters: Sequence[DirectMonteCarloFilter]):
+		self.filters = filters
+
+	def filter_samples(self, samples: numpy.ndarray) -> numpy.ndarray:
+		current_sample = samples
+		for filter in self.filters:
+			current_sample = filter.filter_samples(current_sample)
+		return current_sample

deepdog/direct_monte_carlo/direct_mc.py

@@ -2,7 +2,7 @@ import pdme.model
 import pdme.measurement
 import pdme.measurement.input_types
 import pdme.subspace_simulation
-from typing import Tuple, Sequence
+from typing import Tuple, Dict, NewType, Any
 from dataclasses import dataclass
 import logging
 import numpy
@@ -30,6 +30,20 @@ class DirectMonteCarloConfig:
 	tag: str = ""
 
 
+# Aliasing dict as a generic data container
+DirectMonteCarloData = NewType("DirectMonteCarloData", Dict[str, Any])
+
+
+class DirectMonteCarloFilter:
+	"""
+	Abstract class for filtering out samples matching some criteria. Initialise with data as needed,
+	then filter out samples as needed.
+	"""
+
+	def filter_samples(self, samples: numpy.ndarray) -> numpy.ndarray:
+		raise NotImplementedError
+
+
 class DirectMonteCarloRun:
 	"""
 	A single model Direct Monte Carlo run, currently implemented only using single threading.
@@ -65,25 +79,26 @@ class DirectMonteCarloRun:
 	def __init__(
 		self,
 		model_name_pair: Tuple[str, pdme.model.DipoleModel],
-		measurements: Sequence[pdme.measurement.DotRangeMeasurement],
+		filter: DirectMonteCarloFilter,
 		config: DirectMonteCarloConfig,
 	):
 		self.model_name, self.model = model_name_pair
 
-		self.measurements = measurements
-		self.dot_inputs = [(measure.r, measure.f) for measure in self.measurements]
+		# self.measurements = measurements
+		# self.dot_inputs = [(measure.r, measure.f) for measure in self.measurements]
 
-		self.dot_inputs_array = pdme.measurement.input_types.dot_inputs_to_array(
-			self.dot_inputs
-		)
+		# self.dot_inputs_array = pdme.measurement.input_types.dot_inputs_to_array(
+		# 	self.dot_inputs
+		# )
 
 		self.config = config
-		(
-			self.lows,
-			self.highs,
-		) = pdme.measurement.input_types.dot_range_measurements_low_high_arrays(
-			self.measurements
-		)
+		self.filter = filter
+		# (
+		# 	self.lows,
+		# 	self.highs,
+		# ) = pdme.measurement.input_types.dot_range_measurements_low_high_arrays(
+		# 	self.measurements
+		# )
 
 	def _single_run(self, seed) -> numpy.ndarray:
 		rng = numpy.random.default_rng(seed)
@@ -93,18 +108,20 @@ class DirectMonteCarloRun:
 		)
 
 		current_sample = sample_dipoles
-		for di, low, high in zip(self.dot_inputs_array, self.lows, self.highs):
 
-			if len(current_sample) < 1:
-				break
-			vals = pdme.util.fast_v_calc.fast_vs_for_dipoleses(
-				numpy.array([di]), current_sample
-			)
+		return self.filter.filter_samples(current_sample)
+		# for di, low, high in zip(self.dot_inputs_array, self.lows, self.highs):
 
-			current_sample = current_sample[
-				numpy.all((vals > low) & (vals < high), axis=1)
-			]
-		return current_sample
+		# 	if len(current_sample) < 1:
+		# 		break
+		# 	vals = pdme.util.fast_v_calc.fast_vs_for_dipoleses(
+		# 		numpy.array([di]), current_sample
+		# 	)
+
+		# 	current_sample = current_sample[
+		# 		numpy.all((vals > low) & (vals < high), axis=1)
+		# 	]
+		# return current_sample
 
 	def execute(self) -> DirectMonteCarloResult:
 		step_count = 0

deepdog/direct_monte_carlo/dmc_filters.py

@@ -0,0 +1,143 @@
+from numpy import ndarray
+from deepdog.direct_monte_carlo.direct_mc import DirectMonteCarloFilter
+from typing import Sequence
+import pdme.measurement
+import pdme.measurement.input_types
+import pdme.util.fast_nonlocal_spectrum
+import pdme.util.fast_v_calc
+import numpy
+
+
+class SingleDotPotentialFilter(DirectMonteCarloFilter):
+	def __init__(self, measurements: Sequence[pdme.measurement.DotRangeMeasurement]):
+		self.measurements = measurements
+		self.dot_inputs = [(measure.r, measure.f) for measure in self.measurements]
+
+		self.dot_inputs_array = pdme.measurement.input_types.dot_inputs_to_array(
+			self.dot_inputs
+		)
+		(
+			self.lows,
+			self.highs,
+		) = pdme.measurement.input_types.dot_range_measurements_low_high_arrays(
+			self.measurements
+		)
+
+	def filter_samples(self, samples: ndarray) -> ndarray:
+		current_sample = samples
+		for di, low, high in zip(self.dot_inputs_array, self.lows, self.highs):
+
+			if len(current_sample) < 1:
+				break
+			vals = pdme.util.fast_v_calc.fast_vs_for_dipoleses(
+				numpy.array([di]), current_sample
+			)
+
+			current_sample = current_sample[
+				numpy.all((vals > low) & (vals < high), axis=1)
+			]
+		return current_sample
+
+
+class DoubleDotSpinQubitFrequencyFilter(DirectMonteCarloFilter):
+	def __init__(
+		self,
+		pair_phase_measurements: Sequence[pdme.measurement.DotPairRangeMeasurement],
+	):
+		self.pair_phase_measurements = pair_phase_measurements
+		self.dot_pair_inputs = [
+			(measure.r1, measure.r2, measure.f)
+			for measure in self.pair_phase_measurements
+		]
+		self.dot_pair_inputs_array = (
+			pdme.measurement.input_types.dot_pair_inputs_to_array(self.dot_pair_inputs)
+		)
+		(
+			self.pair_phase_lows,
+			self.pair_phase_highs,
+		) = pdme.measurement.input_types.dot_range_measurements_low_high_arrays(
+			self.pair_phase_measurements
+		)
+
+	def fast_s_spin_qubit_tarucha_nonlocal_dipoleses(
+		self, dot_pair_inputs: numpy.ndarray, dipoleses: numpy.ndarray
+	) -> numpy.ndarray:
+		"""
+		No error correction here baby.
+		"""
+		ps = dipoleses[:, :, 0:3]
+		ss = dipoleses[:, :, 3:6]
+		ws = dipoleses[:, :, 6]
+
+		r1s = dot_pair_inputs[:, 0, 0:3]
+		r2s = dot_pair_inputs[:, 1, 0:3]
+		f1s = dot_pair_inputs[:, 0, 3]
+		# Don't actually need this
+		# f2s = dot_pair_inputs[:, 1, 3]
+
+		diffses1 = r1s[:, None] - ss[:, None, :]
+		diffses2 = r2s[:, None] - ss[:, None, :]
+
+		norms1 = numpy.linalg.norm(diffses1, axis=3)
+		norms2 = numpy.linalg.norm(diffses2, axis=3)
+
+		alphses1 = (
+			(
+				3
+				* numpy.transpose(
+					numpy.transpose(
+						numpy.einsum("abcd,acd->abc", diffses1, ps) / (norms1**2)
+					)
+					* numpy.transpose(diffses1)
+				)[:, :, :, 0]
+			)
+			- ps[:, :, 0, numpy.newaxis]
+		) / (norms1**3)
+		alphses2 = (
+			(
+				3
+				* numpy.transpose(
+					numpy.transpose(
+						numpy.einsum("abcd,acd->abc", diffses2, ps) / (norms2**2)
+					)
+					* numpy.transpose(diffses2)
+				)[:, :, :, 0]
+			)
+			- ps[:, :, 0, numpy.newaxis]
+		) / (norms2**3)
+
+		bses = (1 / numpy.pi) * (
+			ws[:, None, :] / (f1s[:, None] ** 2 + ws[:, None, :] ** 2)
+		)
+
+		return numpy.einsum("...j->...", alphses1 * alphses2 * bses)
+
+	def filter_samples(self, samples: ndarray) -> ndarray:
+		current_sample = samples
+
+		for pi, plow, phigh in zip(
+			self.dot_pair_inputs_array, self.pair_phase_lows, self.pair_phase_highs
+		):
+			if len(current_sample) < 1:
+				break
+
+			###
+			# This should be  abstracted out, but we're going to dump it here for time pressure's sake
+			###
+			# vals = pdme.util.fast_nonlocal_spectrum.signarg(
+			# 	pdme.util.fast_nonlocal_spectrum.fast_s_nonlocal_dipoleses(
+			# 		numpy.array([pi]), current_sample
+			# 	)
+			#
+			vals = pdme.util.fast_nonlocal_spectrum.signarg(
+				self.fast_s_spin_qubit_tarucha_nonlocal_dipoleses(
+					numpy.array([pi]), current_sample
+				)
+			)
+			current_sample = current_sample[
+				numpy.all(
+					((vals > plow) & (vals < phigh)) | ((vals < plow) & (vals > phigh)),
+					axis=1,
+				)
+			]
+		return current_sample

deepdog/indexify/__init__.py

@@ -0,0 +1,58 @@
+"""
+Probably should just include a way to handle the indexify function I reuse so much.
+
+All about breaking an integer into a tuple of values from lists, which is useful because of how we do CHTC runs.
+"""
+import itertools
+import typing
+import logging
+import math
+
+_logger = logging.getLogger(__name__)
+
+
+# from https://stackoverflow.com/questions/5228158/cartesian-product-of-a-dictionary-of-lists
+def _dict_product(dicts):
+	"""
+	>>> list(dict_product(dict(number=[1,2], character='ab')))
+	[{'character': 'a', 'number': 1},
+	{'character': 'a', 'number': 2},
+	{'character': 'b', 'number': 1},
+	{'character': 'b', 'number': 2}]
+	"""
+	return list(dict(zip(dicts.keys(), x)) for x in itertools.product(*dicts.values()))
+
+
+class Indexifier:
+	"""
+	The order of keys is very important, but collections.OrderedDict is no longer needed in python 3.7.
+	I think it's okay to rely on that.
+	"""
+
+	def __init__(self, list_dict: typing.Dict[str, typing.Sequence]):
+		self.dict = list_dict
+
+	def indexify(self, n: int) -> typing.Dict[str, typing.Any]:
+		product_dict = _dict_product(self.dict)
+		return product_dict[n]
+
+	def _indexify_indices(self, n: int) -> typing.Sequence[int]:
+		"""
+		legacy indexify from old scripts, copypast.
+		could be used like
+		>>> ret = {}
+		>>> for k, i in zip(self.dict.keys(), self._indexify_indices):
+		>>>		ret[k] = self.dict[k][i]
+		>>> return ret
+		"""
+		weights = [len(v) for v in self.dict.values()]
+		N = math.prod(weights)
+		curr_n = n
+		curr_N = N
+		out = []
+		for w in weights[:-1]:
+			# print(f"current: {curr_N}, {curr_n}, {curr_n // w}")
+			curr_N = curr_N // w  # should be int division anyway
+			out.append(curr_n // curr_N)
+			curr_n = curr_n % curr_N
+		return out

deepdog/real_spectrum_run.py

@@ -66,6 +66,139 @@ def get_a_result_fast_filter_pairs(input) -> int:
 	return len(current_sample)
 
 
+def get_a_result_fast_filter_potential_pair_phase_only(input) -> int:
+	(
+		model,
+		pair_inputs,
+		pair_phase_lows,
+		pair_phase_highs,
+		monte_carlo_count,
+		seed,
+	) = input
+
+	rng = numpy.random.default_rng(seed)
+	# TODO: A long term refactor is to pull the frequency stuff out from here. The None stands for max_frequency, which is unneeded in the actually useful models.
+	sample_dipoles = model.get_monte_carlo_dipole_inputs(
+		monte_carlo_count, None, rng_to_use=rng
+	)
+
+	current_sample = sample_dipoles
+
+	for pi, plow, phigh in zip(pair_inputs, pair_phase_lows, pair_phase_highs):
+		if len(current_sample) < 1:
+			break
+		vals = pdme.util.fast_nonlocal_spectrum.signarg(
+			pdme.util.fast_nonlocal_spectrum.fast_s_nonlocal_dipoleses(
+				numpy.array([pi]), current_sample
+			)
+		)
+
+		current_sample = current_sample[
+			numpy.all(
+				((vals > plow) & (vals < phigh)) | ((vals < plow) & (vals > phigh)),
+				axis=1,
+			)
+		]
+	return len(current_sample)
+
+
+def get_a_result_fast_filter_tarucha_spin_qubit_pair_phase_only(input) -> int:
+	(
+		model,
+		pair_inputs,
+		pair_phase_lows,
+		pair_phase_highs,
+		monte_carlo_count,
+		seed,
+	) = input
+
+	def fast_s_spin_qubit_tarucha_nonlocal_dipoleses(
+		dot_pair_inputs: numpy.ndarray, dipoleses: numpy.ndarray
+	) -> numpy.ndarray:
+		"""
+		No error correction here baby.
+		"""
+		ps = dipoleses[:, :, 0:3]
+		ss = dipoleses[:, :, 3:6]
+		ws = dipoleses[:, :, 6]
+
+		r1s = dot_pair_inputs[:, 0, 0:3]
+		r2s = dot_pair_inputs[:, 1, 0:3]
+		f1s = dot_pair_inputs[:, 0, 3]
+		# don't actually need, because we're assuming they're the same frequencies across the pair
+		# f2s = dot_pair_inputs[:, 1, 3]
+
+		diffses1 = r1s[:, None] - ss[:, None, :]
+		diffses2 = r2s[:, None] - ss[:, None, :]
+
+		norms1 = numpy.linalg.norm(diffses1, axis=3)
+		norms2 = numpy.linalg.norm(diffses2, axis=3)
+
+		alphses1 = (
+			(
+				3
+				* numpy.transpose(
+					numpy.transpose(
+						numpy.einsum("abcd,acd->abc", diffses1, ps) / (norms1**2)
+					)
+					* numpy.transpose(diffses1)
+				)[:, :, :, 0]
+			)
+			- ps[:, numpy.newaxis, :, 0]
+		) / (norms1**3)
+		alphses2 = (
+			(
+				3
+				* numpy.transpose(
+					numpy.transpose(
+						numpy.einsum("abcd,acd->abc", diffses2, ps) / (norms2**2)
+					)
+					* numpy.transpose(diffses2)
+				)[:, :, :, 0]
+			)
+			- ps[:, numpy.newaxis, :, 0]
+		) / (norms2**3)
+
+		bses = (1 / numpy.pi) * (
+			ws[:, None, :] / (f1s[:, None] ** 2 + ws[:, None, :] ** 2)
+		)
+
+		return numpy.einsum("...j->...", alphses1 * alphses2 * bses)
+
+	rng = numpy.random.default_rng(seed)
+	# TODO: A long term refactor is to pull the frequency stuff out from here. The None stands for max_frequency, which is unneeded in the actually useful models.
+	sample_dipoles = model.get_monte_carlo_dipole_inputs(
+		monte_carlo_count, None, rng_to_use=rng
+	)
+
+	current_sample = sample_dipoles
+
+	for pi, plow, phigh in zip(pair_inputs, pair_phase_lows, pair_phase_highs):
+		if len(current_sample) < 1:
+			break
+
+		###
+		# This should be  abstracted out, but we're going to dump it here for time pressure's sake
+		###
+		# vals = pdme.util.fast_nonlocal_spectrum.signarg(
+		# 	pdme.util.fast_nonlocal_spectrum.fast_s_nonlocal_dipoleses(
+		# 		numpy.array([pi]), current_sample
+		# 	)
+		#
+		vals = pdme.util.fast_nonlocal_spectrum.signarg(
+			fast_s_spin_qubit_tarucha_nonlocal_dipoleses(
+				numpy.array([pi]), current_sample
+			)
+		)
+		current_sample = current_sample[
+			numpy.all(
+				((vals > plow) & (vals < phigh)) | ((vals < plow) & (vals > phigh)),
+				axis=1,
+			)
+		]
+	return len(current_sample)
+
+
 def get_a_result_fast_filter(input) -> int:
 	model, dot_inputs, lows, highs, monte_carlo_count, seed = input
 
@@ -108,6 +241,11 @@ class RealSpectrumRun:
 
 	run_count: int
 	The number of runs to do.
+
+	If pair_measurements is not None, uses pair measurement method (and single measurements too).
+	If pair_phase_measurements is not None, ignores measurements and uses phase measurements _only_
+	This is lazy design on my part.
+
 	"""
 
 	def __init__(
@@ -125,6 +263,9 @@ class RealSpectrumRun:
 		pair_measurements: Optional[
 			Sequence[pdme.measurement.DotPairRangeMeasurement]
 		] = None,
+		pair_phase_measurements: Optional[
+			Sequence[pdme.measurement.DotPairRangeMeasurement]
+		] = None,
 	) -> None:
 		self.measurements = measurements
 		self.dot_inputs = [(measure.r, measure.f) for measure in self.measurements]
@@ -136,6 +277,8 @@ class RealSpectrumRun:
 		if pair_measurements is not None:
 			self.pair_measurements = pair_measurements
 			self.use_pair_measurements = True
+			self.use_pair_phase_measurements = False
+
 			self.dot_pair_inputs = [
 				(measure.r1, measure.r2, measure.f)
 				for measure in self.pair_measurements
@@ -145,8 +288,22 @@ class RealSpectrumRun:
 					self.dot_pair_inputs
 				)
 			)
+		elif pair_phase_measurements is not None:
+			self.use_pair_measurements = False
+			self.use_pair_phase_measurements = True
+			self.pair_phase_measurements = pair_phase_measurements
+			self.dot_pair_inputs = [
+				(measure.r1, measure.r2, measure.f)
+				for measure in self.pair_phase_measurements
+			]
+			self.dot_pair_inputs_array = (
+				pdme.measurement.input_types.dot_pair_inputs_to_array(
+					self.dot_pair_inputs
+				)
+			)
 		else:
 			self.use_pair_measurements = False
+			self.use_pair_phase_measurements = False
 
 		self.models = [model for (_, model) in models_with_names]
 		self.model_names = [name for (name, _) in models_with_names]
@@ -198,6 +355,16 @@ class RealSpectrumRun:
 				self.pair_measurements
 			)
 
+		pair_phase_lows = None
+		pair_phase_highs = None
+		if self.use_pair_phase_measurements:
+			(
+				pair_phase_lows,
+				pair_phase_highs,
+			) = pdme.measurement.input_types.dot_range_measurements_low_high_arrays(
+				self.pair_phase_measurements
+			)
+
 		# define a new seed sequence for each run
 		seed_sequence = numpy.random.SeedSequence(self.initial_seed)
 
@@ -229,6 +396,7 @@ class RealSpectrumRun:
 					seeds = seed_sequence.spawn(self.monte_carlo_cycles)
 
 					if self.use_pair_measurements:
+						_logger.debug("using pair measurements")
 						current_success = sum(
 							pool.imap_unordered(
 								get_a_result_fast_filter_pairs,
@@ -249,6 +417,26 @@ class RealSpectrumRun:
 								self.chunksize,
 							)
 						)
+					elif self.use_pair_phase_measurements:
+						_logger.debug("using pair phase measurements")
+						_logger.debug("specifically using tarucha")
+						current_success = sum(
+							pool.imap_unordered(
+								get_a_result_fast_filter_tarucha_spin_qubit_pair_phase_only,
+								[
+									(
+										model,
+										self.dot_pair_inputs_array,
+										pair_phase_lows,
+										pair_phase_highs,
+										self.monte_carlo_count,
+										seed,
+									)
+									for seed in seeds
+								],
+								self.chunksize,
+							)
+						)
 					else:
 
 						current_success = sum(

deepdog/results/__init__.py

@@ -0,0 +1,169 @@
+import dataclasses
+import re
+import typing
+import logging
+import deepdog.indexify
+import pathlib
+import csv
+
+_logger = logging.getLogger(__name__)
+
+FILENAME_REGEX = r"(?P<timestamp>\d{8}-\d{6})-(?P<filename_slug>.*)\.realdata\.fast_filter\.bayesrun\.csv"
+
+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*)"
+]
+
+FILE_SLUG_REGEXES = [
+	r"mock_tarucha-(?P<job_index>\d+)",
+]
+
+
+@dataclasses.dataclass
+class BayesrunOutputFilename:
+	timestamp: str
+	filename_slug: str
+	path: pathlib.Path
+
+
+@dataclasses.dataclass
+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"
+		}
+
+	def __str__(self):
+		return f"BayesrunColumnParsed[{self.column_field}: {self.model_field_dict}]"
+
+
+@dataclasses.dataclass
+class BayesrunModelResult:
+	parsed_model_keys: typing.Dict[str, str]
+	success: int
+	count: int
+
+
+@dataclasses.dataclass
+class BayesrunOutput:
+	filename: BayesrunOutputFilename
+	data: typing.Dict["str", typing.Any]
+	results: typing.Sequence[BayesrunModelResult]
+
+
+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_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 = re.match(pattern, column)
+		if match:
+			return BayesrunColumnParsed(match.groupdict())
+	else:
+		return None
+
+
+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 = re.match(FILENAME_REGEX, 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
+	)
+
+
+def _parse_file_slug(slug: str) -> typing.Optional[typing.Dict[str, str]]:
+	for pattern in FILE_SLUG_REGEXES:
+		match = re.match(pattern, slug)
+		if match:
+			return match.groupdict()
+	else:
+		return None
+
+
+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

deepdog/subset_simulation/subset_simulation_impl.py

@@ -215,7 +215,7 @@ class SubsetSimulation:
 				for cost, chained in chain:
 					try:
 						filtered_cost = cost[0]
-					except IndexError:
+					except (IndexError, TypeError):
 						filtered_cost = cost
 					all_chains.append((filtered_cost, chained))
 			_logger.debug("finished mcmc")

do.sh

@@ -1,38 +0,0 @@
-#!/usr/bin/env bash
-# Do - The Simplest Build Tool on Earth.
-# Documentation and examples see https://github.com/8gears/do
-
-set -Eeuo pipefail # -e "Automatic exit from bash shell script on error"  -u "Treat unset variables and parameters as errors"
-
-build() {
-   echo "I am ${FUNCNAME[0]}ing"
-   poetry build
-}
-
-test() {
-   echo "I am ${FUNCNAME[0]}ing"
-   poetry run flake8 deepdog tests
-   poetry run mypy deepdog
-   poetry run pytest
-}
-
-fmt() {
-	poetry run black .
-	find . -not \( -path "./.*" -type d -prune \) -type f -name "*.py" -exec sed -i -e 's/    /\t/g' {} \;
-}
-
-release() {
-   ./scripts/release.sh
-}
-
-htmlcov() {
-	poetry run pytest --cov-report=html
-}
-
-all() {
-   build && test
-}
-
-"$@" # <- execute the task
-
-[ "$#" -gt 0 ] || printf "Usage:\n\t./do.sh %s\n" "($(compgen -A function | grep '^[^_]' | paste -sd '|' -))"

flake.lock

@@ -1,28 +1,33 @@
 {
   "nodes": {
     "flake-utils": {
+      "inputs": {
+        "systems": "systems"
+      },
       "locked": {
-        "lastModified": 1648297722,
-        "narHash": "sha256-W+qlPsiZd8F3XkzXOzAoR+mpFqzm3ekQkJNa+PIh1BQ=",
+        "lastModified": 1710146030,
+        "narHash": "sha256-SZ5L6eA7HJ/nmkzGG7/ISclqe6oZdOZTNoesiInkXPQ=",
         "owner": "numtide",
         "repo": "flake-utils",
-        "rev": "0f8662f1319ad6abf89b3380dd2722369fc51ade",
+        "rev": "b1d9ab70662946ef0850d488da1c9019f3a9752a",
         "type": "github"
       },
       "original": {
         "owner": "numtide",
         "repo": "flake-utils",
-        "rev": "0f8662f1319ad6abf89b3380dd2722369fc51ade",
         "type": "github"
       }
     },
     "flake-utils_2": {
+      "inputs": {
+        "systems": "systems_2"
+      },
       "locked": {
-        "lastModified": 1653893745,
-        "narHash": "sha256-0jntwV3Z8//YwuOjzhV2sgJJPt+HY6KhU7VZUL0fKZQ=",
+        "lastModified": 1705309234,
+        "narHash": "sha256-uNRRNRKmJyCRC/8y1RqBkqWBLM034y4qN7EprSdmgyA=",
         "owner": "numtide",
         "repo": "flake-utils",
-        "rev": "1ed9fb1935d260de5fe1c2f7ee0ebaae17ed2fa1",
+        "rev": "1ef2e671c3b0c19053962c07dbda38332dcebf26",
         "type": "github"
       },
       "original": {
@@ -31,29 +36,34 @@
         "type": "github"
       }
     },
+    "nix-github-actions": {
+      "inputs": {
+        "nixpkgs": [
+          "poetry2nixSrc",
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1703863825,
+        "narHash": "sha256-rXwqjtwiGKJheXB43ybM8NwWB8rO2dSRrEqes0S7F5Y=",
+        "owner": "nix-community",
+        "repo": "nix-github-actions",
+        "rev": "5163432afc817cf8bd1f031418d1869e4c9d5547",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nix-community",
+        "repo": "nix-github-actions",
+        "type": "github"
+      }
+    },
     "nixpkgs": {
       "locked": {
-        "lastModified": 1655087213,
-        "narHash": "sha256-4R5oQ+OwGAAcXWYrxC4gFMTUSstGxaN8kN7e8hkum/8=",
+        "lastModified": 1710703777,
+        "narHash": "sha256-M4CNAgjrtvrxIWIAc98RTYcVFoAgwUhrYekeiMScj18=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "37b6b161e536fddca54424cf80662bce735bdd1e",
-        "type": "github"
-      },
-      "original": {
-        "owner": "NixOS",
-        "repo": "nixpkgs",
-        "rev": "37b6b161e536fddca54424cf80662bce735bdd1e",
-        "type": "github"
-      }
-    },
-    "nixpkgs_2": {
-      "locked": {
-        "lastModified": 1655046959,
-        "narHash": "sha256-gxqHZKq1ReLDe6ZMJSbmSZlLY95DsVq5o6jQihhzvmw=",
-        "owner": "NixOS",
-        "repo": "nixpkgs",
-        "rev": "07bf3d25ce1da3bee6703657e6a787a4c6cdcea9",
+        "rev": "fc7885fbcea4b782142e06ce2d4d08cf92862004",
         "type": "github"
       },
       "original": {
@@ -62,23 +72,27 @@
         "type": "github"
       }
     },
-    "poetry2nix": {
+    "poetry2nixSrc": {
       "inputs": {
         "flake-utils": "flake-utils_2",
-        "nixpkgs": "nixpkgs_2"
+        "nix-github-actions": "nix-github-actions",
+        "nixpkgs": [
+          "nixpkgs"
+        ],
+        "systems": "systems_3",
+        "treefmt-nix": "treefmt-nix"
       },
       "locked": {
-        "lastModified": 1654921554,
-        "narHash": "sha256-hkfMdQAHSwLWlg0sBVvgrQdIiBP45U1/ktmFpY4g2Mo=",
+        "lastModified": 1708589824,
+        "narHash": "sha256-2GOiFTkvs5MtVF65sC78KNVxQSmsxtk0WmV1wJ9V2ck=",
         "owner": "nix-community",
         "repo": "poetry2nix",
-        "rev": "7b71679fa7df00e1678fc3f1d1d4f5f372341b63",
+        "rev": "3c92540611f42d3fb2d0d084a6c694cd6544b609",
         "type": "github"
       },
       "original": {
         "owner": "nix-community",
         "repo": "poetry2nix",
-        "rev": "7b71679fa7df00e1678fc3f1d1d4f5f372341b63",
         "type": "github"
       }
     },
@@ -86,7 +100,72 @@
       "inputs": {
         "flake-utils": "flake-utils",
         "nixpkgs": "nixpkgs",
-        "poetry2nix": "poetry2nix"
+        "poetry2nixSrc": "poetry2nixSrc"
+      }
+    },
+    "systems": {
+      "locked": {
+        "lastModified": 1681028828,
+        "narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
+        "owner": "nix-systems",
+        "repo": "default",
+        "rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nix-systems",
+        "repo": "default",
+        "type": "github"
+      }
+    },
+    "systems_2": {
+      "locked": {
+        "lastModified": 1681028828,
+        "narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
+        "owner": "nix-systems",
+        "repo": "default",
+        "rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nix-systems",
+        "repo": "default",
+        "type": "github"
+      }
+    },
+    "systems_3": {
+      "locked": {
+        "lastModified": 1681028828,
+        "narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
+        "owner": "nix-systems",
+        "repo": "default",
+        "rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
+        "type": "github"
+      },
+      "original": {
+        "id": "systems",
+        "type": "indirect"
+      }
+    },
+    "treefmt-nix": {
+      "inputs": {
+        "nixpkgs": [
+          "poetry2nixSrc",
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1708335038,
+        "narHash": "sha256-ETLZNFBVCabo7lJrpjD6cAbnE11eDOjaQnznmg/6hAE=",
+        "owner": "numtide",
+        "repo": "treefmt-nix",
+        "rev": "e504621290a1fd896631ddbc5e9c16f4366c9f65",
+        "type": "github"
+      },
+      "original": {
+        "owner": "numtide",
+        "repo": "treefmt-nix",
+        "type": "github"
       }
     }
   },

flake.nix

@@ -1,63 +1,46 @@
 {
   description = "Application packaged using poetry2nix";
 
-  inputs.flake-utils.url = "github:numtide/flake-utils?rev=0f8662f1319ad6abf89b3380dd2722369fc51ade";
-  inputs.nixpkgs.url = "github:NixOS/nixpkgs?rev=37b6b161e536fddca54424cf80662bce735bdd1e";
-  inputs.poetry2nix.url = "github:nix-community/poetry2nix?rev=7b71679fa7df00e1678fc3f1d1d4f5f372341b63";
+  inputs.flake-utils.url = "github:numtide/flake-utils";
+  inputs.nixpkgs.url = "github:NixOS/nixpkgs";
+  inputs.poetry2nixSrc = {
+    url = "github:nix-community/poetry2nix";
+    inputs.nixpkgs.follows = "nixpkgs";
+  };
 
-  outputs = { self, nixpkgs, flake-utils, poetry2nix }:
-    {
-      # Nixpkgs overlay providing the application
-      overlay = nixpkgs.lib.composeManyExtensions [
-        poetry2nix.overlay
-        (final: prev: {
-          # The application
-          deepdog = prev.poetry2nix.mkPoetryApplication {
-            overrides = final.poetry2nix.overrides.withDefaults (self: super: {
-              # …
-              # workaround https://github.com/nix-community/poetry2nix/issues/568
-              pdme = super.pdme.overridePythonAttrs (old: {
-                buildInputs = old.buildInputs or [ ] ++ [ final.python39.pkgs.poetry-core ];
-              });
-            });
-            projectDir = ./.;
-          };
-          deepdogEnv = prev.poetry2nix.mkPoetryEnv {
-            overrides = final.poetry2nix.overrides.withDefaults (self: super: {
-              # …
-              # workaround https://github.com/nix-community/poetry2nix/issues/568
-              pdme = super.pdme.overridePythonAttrs (old: {
-                buildInputs = old.buildInputs or [ ] ++ [ final.python39.pkgs.poetry-core ];
-              });
-            });
-            projectDir = ./.;
-          };
-        })
-      ];
-    } // (flake-utils.lib.eachDefaultSystem (system:
+  outputs = { self, nixpkgs, flake-utils, poetry2nixSrc }:
+    flake-utils.lib.eachDefaultSystem (system:
       let
-        pkgs = import nixpkgs {
-          inherit system;
-          overlays = [ self.overlay ];
-        };
-      in
-      {
-        apps = {
-          deepdog = pkgs.deepdog;
-        };
-
-        defaultApp = pkgs.deepdog;
-        devShell = pkgs.mkShell {
-          buildInputs = [
-            pkgs.poetry
-            pkgs.deepdogEnv
-            pkgs.deepdog
-          ];
-          shellHook = ''
-            export DO_NIX_CUSTOM=1
-          '';
-          packages = [ pkgs.nodejs-16_x ];
-        };
-
-      }));
+        pkgs = nixpkgs.legacyPackages.${system};
+	poetry2nix = poetry2nixSrc.lib.mkPoetry2Nix { inherit pkgs; };
+      in {
+        packages = {
+	  deepdogApp = poetry2nix.mkPoetryApplication {
+            projectDir = self;
+	    python = pkgs.python39;
+	    preferWheels = true;
+	  };
+	  deepdogEnv = poetry2nix.mkPoetryEnv {
+	    projectDir = self;
+	    python = pkgs.python39;
+	    preferWheels = true;
+	    overrides = poetry2nix.overrides.withDefaults (self: super: {
+	    });
+	  };
+	  default = self.packages.${system}.deepdogEnv;
+	};
+	devShells.default = pkgs.mkShell {
+	  inputsFrom = [ self.packages.${system}.deepdogEnv ];
+	  buildInputs = [
+	    pkgs.poetry
+	    self.packages.${system}.deepdogEnv
+	    self.packages.${system}.deepdogApp
+	    pkgs.just
+	  ];
+	  shellHook = ''
+	    export DO_NIX_CUSTOM=1
+	  '';
+	};
+      }
+    );
 }

justfile

@@ -0,0 +1,54 @@
+
+# execute default build
+default: build
+
+# builds the python module using poetry
+build:
+	echo "building..."
+	poetry build
+
+# print a message displaying whether nix is being used
+checknix:
+	#!/usr/bin/env bash
+	set -euxo pipefail
+	if [[ "${DO_NIX_CUSTOM:=0}" -eq 1 ]]; then
+		echo "In an interactive nix env."
+	else
+		echo "Using poetry as runner, no nix detected."
+	fi
+
+# run all tests
+test: fmt
+	#!/usr/bin/env bash
+	set -euxo pipefail
+	
+	if [[ "${DO_NIX_CUSTOM:=0}" -eq 1 ]]; then
+		echo "testing, using nix..."
+		flake8 deepdog tests
+		mypy deepdog
+		pytest
+	else
+		echo "testing..."
+		poetry run flake8 deepdog tests
+		poetry run mypy deepdog
+		poetry run pytest
+	fi
+
+# format code
+fmt:
+	#!/usr/bin/env bash
+	set -euxo pipefail
+	if [[ "${DO_NIX_CUSTOM:=0}" -eq 1 ]]; then
+	      black .
+	else
+		poetry run black .
+	fi
+	find deepdog -type f -name "*.py" -exec sed -i -e 's/    /\t/g' {} \;
+	find tests -type f -name "*.py" -exec sed -i -e 's/    /\t/g' {} \;
+
+# release the app, checking that our working tree is clean and ready for release
+release:
+	./scripts/release.sh
+
+htmlcov:
+	poetry run pytest --cov-report=html

pyproject.toml

@@ -1,24 +1,28 @@
 [tool.poetry]
 name = "deepdog"
-version = "0.7.5"
+version = "0.8.1"
 description = ""
 authors = ["Deepak Mallubhotla <dmallubhotla+github@gmail.com>"]
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<3.10"
-pdme = "^0.9.1"
+pdme = "^0.9.3"
 numpy = "1.22.3"
 scipy = "1.10"
+tqdm = "^4.66.2"
 
 [tool.poetry.dev-dependencies]
 pytest = ">=6"
-flake8 = "^4.0.1"
+flake8 = "^7.0.0"
 pytest-cov = "^4.1.0"
 mypy = "^0.971"
 python-semantic-release = "^7.24.0"
 black = "^22.3.0"
 syrupy = "^4.0.8"
 
+[tool.poetry.scripts]
+probs = "deepdog.cli.probs:wrapped_main"
+
 [build-system]
 requires = ["poetry-core>=1.0.0"]
 build-backend = "poetry.core.masonry.api"
@@ -38,6 +42,13 @@ module = [
 ]
 ignore_missing_imports = true
 
+[[tool.mypy.overrides]]
+module = [
+	"tqdm",
+	"tqdm.*"
+]
+ignore_missing_imports = true
+
 [tool.semantic_release]
 version_toml = "pyproject.toml:tool.poetry.version"
 tag_format = "{version}"

scripts/standard-version/pyproject-updater.js

@@ -1,4 +1,4 @@
-const pattern = /(\[tool\.poetry\]\nname = "deepdog"\nversion = ")(?<vers>\d+\.\d+\.\d)(")/mg;
+const pattern = /(\[tool\.poetry\]\nname = "deepdog"\nversion = ")(?<vers>\d+\.\d+\.\d+)(")/mg;
 
 module.exports.readVersion = function (contents) {
 	const result = pattern.exec(contents);

tests/indexify/test_indexify.py

@@ -0,0 +1,12 @@
+import deepdog.indexify
+import logging
+
+_logger = logging.getLogger(__name__)
+
+
+def test_indexifier():
+	weight_dict = {"key_1": [1, 2, 3], "key_2": ["a", "b", "c"]}
+	indexifier = deepdog.indexify.Indexifier(weight_dict)
+	_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"}

tests/results/test_column_results.py

@@ -0,0 +1,28 @@
+import deepdog.results
+
+
+def test_parse_groupdict():
+	example_column_name = (
+		"geom_-20_20_-10_10_0_5-orientation_free-dipole_count_100_success"
+	)
+
+	parsed = deepdog.results._parse_bayesrun_column(example_column_name)
+	expected = deepdog.results.BayesrunColumnParsed(
+		{
+			"xmin": "-20",
+			"xmax": "20",
+			"ymin": "-10",
+			"ymax": "10",
+			"zmin": "0",
+			"zmax": "5",
+			"orientation": "free",
+			"avg_filled": "100",
+			"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