libgunshotmatch 0.11.2__tar.gz → 0.13.0__tar.gz

{libgunshotmatch-0.11.2 → libgunshotmatch-0.13.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: libgunshotmatch
-Version: 0.11.2
+Version: 0.13.0
 Summary: Base library for GunShotMatch.
 Author-email: Dominic Davis-Foster <dominic@davis-foster.co.uk>
 License: MIT
@@ -39,6 +39,7 @@ Requires-Dist: scipy>=1.9.0
 Requires-Dist: sdjson>=0.4.0
 Requires-Dist: tomli>=1.2.3; python_version < "3.11"
 Requires-Dist: tomli-w>=1.0.0
+Requires-Dist: typing-extensions>=4.12.2
 Description-Content-Type: text/x-rst
 
 
@@ -135,7 +136,7 @@ libgunshotmatch
 .. |language| image:: https://img.shields.io/github/languages/top/GunShotMatch/libgunshotmatch
 	:alt: GitHub top language
 
-.. |commits-since| image:: https://img.shields.io/github/commits-since/GunShotMatch/libgunshotmatch/v0.11.2
+.. |commits-since| image:: https://img.shields.io/github/commits-since/GunShotMatch/libgunshotmatch/v0.13.0
 	:target: https://github.com/GunShotMatch/libgunshotmatch/pulse
 	:alt: GitHub commits since tagged version
 

{libgunshotmatch-0.11.2 → libgunshotmatch-0.13.0}/README.rst

@@ -91,7 +91,7 @@ libgunshotmatch
 .. |language| image:: https://img.shields.io/github/languages/top/GunShotMatch/libgunshotmatch
 	:alt: GitHub top language
 
-.. |commits-since| image:: https://img.shields.io/github/commits-since/GunShotMatch/libgunshotmatch/v0.11.2
+.. |commits-since| image:: https://img.shields.io/github/commits-since/GunShotMatch/libgunshotmatch/v0.13.0
 	:target: https://github.com/GunShotMatch/libgunshotmatch/pulse
 	:alt: GitHub commits since tagged version
 

{libgunshotmatch-0.11.2 → libgunshotmatch-0.13.0}/libgunshotmatch/__init__.py

@@ -29,5 +29,5 @@ Base library for GunShotMatch.
 __author__: str = "Dominic Davis-Foster"
 __copyright__: str = "2020-2023 Dominic Davis-Foster"
 __license__: str = "MIT License"
-__version__: str = "0.11.2"
+__version__: str = "0.13.0"
 __email__: str = "dominic@davis-foster.co.uk"

{libgunshotmatch-0.11.2 → libgunshotmatch-0.13.0}/libgunshotmatch/consolidate/__init__.py

@@ -41,6 +41,7 @@ import pyms_nist_search
 from pyms.DPA.Alignment import Alignment
 from pyms.Spectrum import MassSpectrum
 from pyms_nist_search import ReferenceData, SearchResult
+from typing_extensions import Self
 
 # this package
 from libgunshotmatch.consolidate._fields import (
@@ -484,9 +485,12 @@ class ConsolidatedPeak:
 			else:
 				ms_list.append(MassSpectrum.from_dict(msd))
 
+		rt_list = [float("nan") if hn == -65535 else hn for hn in d["rt_list"]]
+		area_list = [float("nan") if hn == -65535 else hn for hn in d["area_list"]]
+
 		return cls(
-				rt_list=d["rt_list"],
-				area_list=d["area_list"],
+				rt_list=rt_list,
+				area_list=area_list,
 				ms_list=ms_list,
 				meta=d["meta"],
 				ms_comparison=d["ms_comparison"],
@@ -712,7 +716,7 @@ class ConsolidatedPeakFilter:
 	verbose: bool = False
 
 	@classmethod
-	def from_method(cls: Type["ConsolidatedPeakFilter"], method: ConsolidateMethod) -> "ConsolidatedPeakFilter":
+	def from_method(cls: Type[Self], method: ConsolidateMethod) -> Self:
 		"""
 		Construct a :class:`~.ConsolidatedPeakFilter` from a :class:`~.ConsolidateMethod`.
 

{libgunshotmatch-0.11.2 → libgunshotmatch-0.13.0}/libgunshotmatch/gzip_util.py

@@ -60,16 +60,21 @@ def read_gzip_json(path: PathLike) -> JSONOutput:
 			return sdjson.load(f)
 
 
-def write_gzip_json(path: PathLike, data: JSONInput, indent: Optional[int] = 2) -> None:
+def write_gzip_json(path: PathLike, data: JSONInput, indent: Optional[int] = 2, mtime: int = 0) -> None:
 	"""
 	Write JSON to a gzip file.
 
 	:param path: The filename to write to.
 	:param data: The JSON-serializable data to output.
 	:param indent: Number of spaces used to indent JSON.
+	:param mtime: Modification time for gzip header
+
+	:rtype:
+
+	.. versionchanged:: 0.12.0  Added ``mtime`` argument.
 	"""
 
 	json_data = sdjson.dumps(data, indent=indent)
 
-	with gzip.open(PathPlus(path), 'w') as f:
+	with gzip.GzipFile(PathPlus(path), 'w', mtime=mtime) as f:
 		f.write(json_data.encode("utf-8"))

{libgunshotmatch-0.11.2 → libgunshotmatch-0.13.0}/libgunshotmatch/peak.py

@@ -27,13 +27,14 @@ Classes representing peaks, and functions for peak filtering.
 #
 
 # stdlib
-from typing import Any, Collection, Dict, List, Mapping, Optional, Sequence, Type, Union
+from typing import TYPE_CHECKING, Any, Collection, Dict, List, Mapping, Optional, Sequence, Type, Union
 
 # 3rd party
 import numpy
 import pandas  # type: ignore[import-untyped]
 import sdjson
 from domdf_python_tools.paths import PathPlus
+from domdf_python_tools.stringlist import StringList
 from domdf_python_tools.typing import PathLike
 from pyms.BillerBiemann import num_ions_threshold
 from pyms.DPA.Alignment import exprl2alignment
@@ -42,10 +43,15 @@ from pyms.Experiment import Experiment
 from pyms.IonChromatogram import IonChromatogram
 from pyms.Noise.Analysis import window_analyzer
 from pyms.Peak.Class import AbstractPeak, ICPeak, Peak
+from pyms.Peak.List import composite_peak
 from pyms.Peak.List.Function import sele_peaks_by_rt
 from pyms.Spectrum import MassSpectrum
 from pyms_nist_search import SearchResult
 
+if TYPE_CHECKING:
+	# this package
+	from libgunshotmatch.project import Project
+
 __all__ = (
 		"PeakList",
 		"QualifiedPeak",
@@ -55,6 +61,7 @@ __all__ = (
 		"filter_peaks",
 		"peak_from_dict",
 		"write_alignment",
+		"write_project_alignment",
 		"base_peak_mass",
 		)
 
@@ -401,6 +408,107 @@ def align_peaks(
 	return A1
 
 
+def _format_rt(rt: Optional[float]) -> str:
+	return "NA" if rt is None or numpy.isnan(rt) else f"{rt:.3f}"
+
+
+def _format_area(area: Optional[float]) -> str:
+	return "NA" if area is None else f"{area:.0f}"
+
+
+def _alignment_write_csv(
+		project: "Project",
+		output_dir_p: PathPlus,
+		) -> None:
+
+	# Sort expr_code and peakpos into order from datafile_data
+	desired_order = list(project.datafile_data)
+	sort_map = [project.alignment.expr_code.index(code) for code in desired_order]
+	expr_code = [project.alignment.expr_code[idx] for idx in sort_map]
+	peakpos = [project.alignment.peakpos[idx] for idx in sort_map]
+	assert desired_order == expr_code
+
+	# write headers
+	header = ["UID", "RTavg", *(f'"{item}"' for item in project.datafile_data)]
+
+	rt_stringlist = StringList([','.join(header)])
+	area_stringlist = StringList([','.join(header)])
+
+	# for each alignment position write alignment's peak and area
+	for peak_idx in range(len(peakpos[0])):  # loop through peak lists (rows)
+		rts, areas, new_peak_list = [], [], []
+
+		for row in peakpos:
+			peak = row[peak_idx]
+
+			if peak is None:
+				rts.append(None)
+				areas.append(None)
+			else:
+				rts.append(peak.rt / 60)
+				areas.append(peak.area)
+				new_peak_list.append(peak)
+
+		compo_peak = composite_peak(new_peak_list)
+
+		if compo_peak is None:
+			continue
+
+		uid, mean_rt = compo_peak.UID, f"{float(compo_peak.rt / 60):.3f}"
+		rt_stringlist.append(','.join([uid, mean_rt, *map(_format_rt, rts)]))
+		area_stringlist.append(','.join([uid, mean_rt, *map(_format_area, areas)]))
+
+	(output_dir_p / f"{project.name}_alignment_rt.csv").write_lines(rt_stringlist)
+	(output_dir_p / f"{project.name}_alignment_area.csv").write_lines(area_stringlist)
+
+
+def write_project_alignment(
+		project: "Project",
+		output_dir: PathLike,
+		require_all_datafiles: bool = False,
+		) -> None:
+	"""
+	Write the alignment data (retention times, peak areas, mass spectra) to disk.
+
+	The output files are as follows:
+
+	* :file:`{{project.name}}_alignment_rt.csv`, containing the aligned retention times.
+	* :file:`{{project.name}}_alignment_area.csv`, containing the peak areas for the corresponding aligned retention times.
+	* :file:`{{project.name}}_alignment_rt.json`, containing the aligned retention times.
+	* :file:`{{project.name}}_alignment_area.json`, containing the peak areas for the corresponding aligned retention times.
+	* :file:`{{project.name}}_alignment_ms.json`, containing the mass spectra for the corresponding aligned retention times.
+
+	:param project:
+	:param output_dir: Directory to store the output files in.
+	:param require_all_datafiles: Whether the peak must be present in all experiments to be included in the data frame.
+
+	:rtype:
+
+	.. versionadded:: 0.12.0  Added as an alternative to :func:`~.write_alignment`. This function sorts the columns to match the order of ``project.datafile_data``.
+	"""
+
+	output_dir_p = PathPlus(output_dir)
+
+	_alignment_write_csv(project, output_dir_p)
+
+	rt_alignment = project.alignment.get_peak_alignment(require_all_expr=require_all_datafiles)
+	rt_alignment_filename = output_dir_p / f"{project.name}_alignment_rt.json"
+	rt_alignment_filename.write_clean(rt_alignment.to_json(indent=2))
+
+	area_alignment = project.alignment.get_area_alignment(require_all_expr=require_all_datafiles)
+	area_alignment_filename = output_dir_p / f"{project.name}_alignment_area.json"
+	area_alignment_filename.write_clean(area_alignment.to_json(indent=2))
+
+	ms_alignment = project.alignment.get_ms_alignment(require_all_expr=require_all_datafiles)
+	# ms_alignment.to_json(output_dir_p / 'alignment_ms.json')
+	alignment_ms_filename = (output_dir_p / f"{project.name}_alignment_ms.json")
+	alignment_ms_filename.dump_json(
+			ms_alignment.to_dict(),
+			json_library=sdjson,  # type: ignore[arg-type]
+			indent=2,
+			)
+
+
 def write_alignment(
 		alignment: Alignment,
 		project_name: str,
@@ -434,11 +542,11 @@ def write_alignment(
 
 	rt_alignment = alignment.get_peak_alignment(require_all_expr=require_all_datafiles)
 	rt_alignment_filename = output_dir_p / f"{project_name}_alignment_rt.json"
-	rt_alignment_filename.write_clean(rt_alignment.to_json())
+	rt_alignment_filename.write_clean(rt_alignment.to_json(indent=2))
 
 	area_alignment = alignment.get_area_alignment(require_all_expr=require_all_datafiles)
 	area_alignment_filename = output_dir_p / f"{project_name}_alignment_area.json"
-	area_alignment_filename.write_clean(area_alignment.to_json())
+	area_alignment_filename.write_clean(area_alignment.to_json(indent=2))
 
 	ms_alignment = alignment.get_ms_alignment(require_all_expr=require_all_datafiles)
 	# ms_alignment.to_json(output_dir_p / 'alignment_ms.json')

{libgunshotmatch-0.11.2 → libgunshotmatch-0.13.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "whey"
 
 [project]
 name = "libgunshotmatch"
-version = "0.11.2"
+version = "0.13.0"
 description = "Base library for GunShotMatch."
 readme = "README.rst"
 keywords = []
@@ -23,6 +23,7 @@ dependencies = [
     "sdjson>=0.4.0",
     'tomli>=1.2.3; python_version < "3.11"',
     "tomli-w>=1.0.0",
+    "typing-extensions>=4.12.2",
 ]
 classifiers = [
     "Development Status :: 3 - Alpha",

{libgunshotmatch-0.11.2 → libgunshotmatch-0.13.0}/requirements.txt

@@ -11,3 +11,4 @@ scipy>=1.9.0
 sdjson>=0.4.0
 tomli>=1.2.3; python_version < "3.11"
 tomli-w>=1.0.0
+typing-extensions>=4.12.2