chore(release): 1.2.1

CHANGELOG.md

@@ -2,6 +2,16 @@
 
 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.
 
+### [1.2.1](https://gitea.deepak.science:2222/physics/deepdog/compare/1.2.0...1.2.1) (2024-05-12)
+
+## [1.2.0](https://gitea.deepak.science:2222/physics/deepdog/compare/1.1.0...1.2.0) (2024-05-09)
+
+
+### Features
+
+* adds additional matching regexes ([dc1d2d4](https://gitea.deepak.science:2222/physics/deepdog/commit/dc1d2d45a3e631c5efccce80f8a24fa87c6089e0))
+* adds magnitude enabled parsing option ([f0e2fa3](https://gitea.deepak.science:2222/physics/deepdog/commit/f0e2fa3da9f5a5136908d691137a904fda4e3a9a))
+
 ## [1.1.0](https://gitea.deepak.science:2222/physics/deepdog/compare/1.0.1...1.1.0) (2024-05-03)
 
 

deepdog/indexify/__init__.py

@@ -31,10 +31,10 @@ class Indexifier:
 
 	def __init__(self, list_dict: typing.Dict[str, typing.Sequence]):
 		self.dict = list_dict
+		self.product_dict = _dict_product(self.dict)
 
 	def indexify(self, n: int) -> typing.Dict[str, typing.Any]:
-		product_dict = _dict_product(self.dict)
+		return self.product_dict[n]
-		return product_dict[n]
 
 	def _indexify_indices(self, n: int) -> typing.Sequence[int]:
 		"""

deepdog/results/__init__.py

@@ -8,17 +8,30 @@ import csv
 
 _logger = logging.getLogger(__name__)
 
-FILENAME_REGEX = r"(?P<timestamp>\d{8}-\d{6})-(?P<filename_slug>.*)\.realdata\.fast_filter\.bayesrun\.csv"
+FILENAME_REGEX = re.compile(
+	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*)"
+	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*)",
+	]
 ]
 
 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+")
+
 
 @dataclasses.dataclass
 class BayesrunOutputFilename:
@@ -27,7 +40,6 @@ class BayesrunOutputFilename:
 	path: pathlib.Path
 
 
-@dataclasses.dataclass
 class BayesrunColumnParsed:
 	"""
 	class for parsing a bayesrun while pulling certain special fields out
@@ -38,10 +50,21 @@ class BayesrunColumnParsed:
 		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:
@@ -73,7 +96,7 @@ def _parse_bayesrun_column(
 	Returns the groupdict for the first match, or None if no match found.
 	"""
 	for pattern in MODEL_REGEXES:
-		match = re.match(pattern, column)
+		match = pattern.match(column)
 		if match:
 			return BayesrunColumnParsed(match.groupdict())
 	else:
@@ -112,7 +135,7 @@ def _parse_bayesrun_row(
 
 def _parse_output_filename(file: pathlib.Path) -> BayesrunOutputFilename:
 	filename = file.name
-	match = re.match(FILENAME_REGEX, filename)
+	match = FILENAME_REGEX.match(filename)
 	if not match:
 		raise ValueError(f"{filename} was not a valid bayesrun output")
 	groups = match.groupdict()
@@ -123,7 +146,7 @@ def _parse_output_filename(file: pathlib.Path) -> BayesrunOutputFilename:
 
 def _parse_file_slug(slug: str) -> typing.Optional[typing.Dict[str, str]]:
 	for pattern in FILE_SLUG_REGEXES:
-		match = re.match(pattern, slug)
+		match = pattern.match(slug)
 		if match:
 			return match.groupdict()
 	else:

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "deepdog"
-version = "1.1.0"
+version = "1.2.1"
 description = ""
 authors = ["Deepak Mallubhotla <dmallubhotla+github@gmail.com>"]
 

tests/results/test_column_results.py

@@ -7,6 +7,7 @@ def test_parse_groupdict():
 	)
 
 	parsed = deepdog.results._parse_bayesrun_column(example_column_name)
+	assert parsed is not None
 	expected = deepdog.results.BayesrunColumnParsed(
 		{
 			"xmin": "-20",
@@ -23,6 +24,30 @@ def test_parse_groupdict():
 	assert parsed == expected
 
 
+def test_parse_groupdict_with_magnitude():
+	example_column_name = (
+		"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)
+	assert parsed is not None
+	expected = deepdog.results.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