libgunshotmatch 0.11.1__py3-none-any.whl → 0.12.0__py3-none-any.whl

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 = "0.11.1"
+__version__: str = "0.12.0"
 __email__: str = "dominic@davis-foster.co.uk"

libgunshotmatch/comparison/projects.py

@@ -52,15 +52,18 @@ def filter_alignment_to_consolidate(project: Project) -> Alignment:
 
 	# Sort expr_code and peakpos into order from datafile_data
 	desired_order = list(project.datafile_data)[::-1]
-	sort_map = [desired_order.index(code) for code in project.alignment.expr_code]
+	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
 
-	consolidated_peak_retention_times = [cp.rt_list for cp in project.consolidated_peaks]
+	consolidated_peak_retention_times = []
+	for cp in project.consolidated_peaks:
+		consolidated_peak_retention_times.append([None if numpy.isnan(rt) else rt for rt in cp.rt_list])
 
 	aligned_peaks_surviving_consolidate = []
 	for aligned_peaks in zip(*peakpos):
-		aprt = [p.rt for p in reversed(aligned_peaks)]
+		aprt = [None if p is None else p.rt for p in reversed(aligned_peaks)]
 		if aprt in consolidated_peak_retention_times:
 			aligned_peaks_surviving_consolidate.append(aligned_peaks)
 

libgunshotmatch/consolidate/__init__.py

@@ -484,9 +484,12 @@ 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"],

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/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-0.11.1.dist-info → libgunshotmatch-0.12.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: libgunshotmatch
-Version: 0.11.1
+Version: 0.12.0
 Summary: Base library for GunShotMatch.
 Author-email: Dominic Davis-Foster <dominic@davis-foster.co.uk>
 License: MIT
@@ -135,7 +135,7 @@ 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/v0.11.1
+.. |commits-since| image:: https://img.shields.io/github/commits-since/GunShotMatch/libgunshotmatch/v0.12.0
 	:target: https://github.com/GunShotMatch/libgunshotmatch/pulse
 	:alt: GitHub commits since tagged version
 

{libgunshotmatch-0.11.1.dist-info → libgunshotmatch-0.12.0.dist-info}/RECORD

@@ -1,22 +1,22 @@
 libgunshotmatch/comparison/__init__.py,sha256=g-KDfzG-oyRf2aeXlMaJJ3aWfQtQkr5-bGhT70O44XA,3848
 libgunshotmatch/comparison/_utils.py,sha256=aZ6fnFM4M_vTsKq5t79V4tfven1eVdG4EUCuYFuXMVs,1895
-libgunshotmatch/comparison/projects.py,sha256=Dq294cDndmQI2FnIcVXwleCQF0mF2m8U5wWnO5_aD9A,3356
+libgunshotmatch/comparison/projects.py,sha256=fN1-dbD8LNPKcMerKHQwwOVeOwFPcd6E9hZ8QQFJOi4,3505
 libgunshotmatch/comparison/unknowns.py,sha256=kvJJDtfpMp-c3hjCOz7YtvuuDR0YksWmyUuaSBC_5Jg,2710
-libgunshotmatch/consolidate/__init__.py,sha256=qjY5meI2TMCpMGwzLSo4NZ4HbhH8VJoR1t9ev4ObBmA,24706
+libgunshotmatch/consolidate/__init__.py,sha256=LyXgWTYy2YRmavCzzU4u-b-mLi2xDb1_QYk62lqhV9s,24849
 libgunshotmatch/consolidate/_fields.py,sha256=0kfPXJ0EG7GhdFiNzvcmd6W4i1x6Y0s2Y58z3RltPiA,2759
 libgunshotmatch/consolidate/_spectra.py,sha256=24aDoPwGWEyIFCH-fwRa4nifNMPqUyd-qTogk3BMeLY,2319
 libgunshotmatch/method/__init__.py,sha256=TP_3rvv3WEbV6Y5E_QWd2lcORPFnbXV4YRKGwXDa4ds,9423
 libgunshotmatch/method/_fields.py,sha256=HBFl0XmHBaAOHYdABs2NRbjtngGEw7kY0xP6D2Fl7h4,4941
-libgunshotmatch/__init__.py,sha256=RYV-3nDk5ruAuFXDnZuk5LbiFM_503YfSuKwtGTdddk,1434
+libgunshotmatch/__init__.py,sha256=sLe-ceqI8gWFylKLQsa3-o_f9N4Iz7gfvMxWAlZPj2E,1434
 libgunshotmatch/datafile.py,sha256=4C4BiR95PBfIUbiUKQzVfh57tgZu_l6rLS8bIgrgPUs,16246
-libgunshotmatch/gzip_util.py,sha256=PcfT4QC4TM0KI3uCGetRpjChbTXTGmNEJBr7BghO3i8,2414
-libgunshotmatch/peak.py,sha256=jIbuOTj_FWTeb46pZtzSwnGsMK_c71Dd9_T9Gj2DxNk,17616
+libgunshotmatch/gzip_util.py,sha256=bhYUdFmaSNKPV66vTvWkebbLhtMSPiLWBP20JVqgjXw,2562
+libgunshotmatch/peak.py,sha256=w2oWWmMQ9JP2JMK7vaboOTbv83TvgOXuTCxGxGToHGc,21638
 libgunshotmatch/project.py,sha256=498xoKkDSFDsFodwoRwwEfRL-FOX_hnzyDLLgPNxWr0,6987
 libgunshotmatch/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 libgunshotmatch/search.py,sha256=GMP7_DMnXFq3TG8AT1WARIn4ObCfOGfTDakpGeKzJYw,3123
 libgunshotmatch/utils.py,sha256=7WVJPd9wNBFFoAFqh2J6Lsu7BGrGksW32ZqpH7ZIL_I,5776
-libgunshotmatch-0.11.1.dist-info/LICENSE,sha256=bFtJt-lyVJHV-88FeFa_r3BEOsmpna5qG2KOl9JUNfU,1064
-libgunshotmatch-0.11.1.dist-info/METADATA,sha256=X6IRaQ7QLl3ugK51lSmpa205f0Ds1QmbVICEaFucBtw,6394
-libgunshotmatch-0.11.1.dist-info/WHEEL,sha256=pUf8gZsdmDXXTtqZfolZFpfoEwFoEdADIuUvQVl5qAY,83
-libgunshotmatch-0.11.1.dist-info/entry_points.txt,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-libgunshotmatch-0.11.1.dist-info/RECORD,,
+libgunshotmatch-0.12.0.dist-info/LICENSE,sha256=bFtJt-lyVJHV-88FeFa_r3BEOsmpna5qG2KOl9JUNfU,1064
+libgunshotmatch-0.12.0.dist-info/METADATA,sha256=DA8EiUE-EPbsq2MQd-8MAKiaAuuGC50L2GXS54WYpxg,6394
+libgunshotmatch-0.12.0.dist-info/WHEEL,sha256=BKn3NsEitvGOujn9xNlxxTBtBPCGWWsB3u3zHbttCmw,83
+libgunshotmatch-0.12.0.dist-info/entry_points.txt,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+libgunshotmatch-0.12.0.dist-info/RECORD,,

{libgunshotmatch-0.11.1.dist-info → libgunshotmatch-0.12.0.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: whey (0.1.0)
+Generator: whey (0.1.1)
 Root-Is-Purelib: true
 Tag: py3-none-any