Patch v0.1.1 (#14)

* add DOI badge to README

* update gitignore

* update lockfile

* add poetry config

* rename Variants module to variants

* add __version__ and logging set up

* fix broken script paths

* convert to src layout

* drop scripts

.gitignore

@@ -164,6 +164,6 @@ cython_debug/
 #  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
+.idea/
 
-.DS_Store
+.DS_Store

README.md

@@ -1,4 +1,7 @@
 # FRAPOSA_PGSC
+
+[![DOI](https://zenodo.org/badge/610312021.svg)](https://zenodo.org/badge/latestdoi/610312021)
+
 FRAPOSA (Fast and Robust Ancestry Prediction by using Online singular value decomposition and Shrinkage Adjustment)
 is a python script to predict the ancestry of study samples by the results of principal component analysis (PCA) on a 
 reference panel. The software originally accompanied 

poetry.toml

@@ -0,0 +1,3 @@
+[virtualenvs]
+create = true
+in-project = true

pyproject.toml

@@ -1,25 +1,18 @@
 [tool.poetry]
 name = "fraposa-pgsc"
-version = "0.1.0"
+version = "0.1.1"
 description = "Tools to perform ancestry projection to a reference dataset within the calculator pipeline (pgsc_calc)"
 homepage = "https://github.com/PGScatalog/fraposa_pgsc"
 authors = ["smlmbrt <sam.a.lambert@gmail.com>"]
 license = "MIT License"
 readme = "README.md"
-packages = [{include = "fraposa_pgsc"}]
+packages = [{include = "fraposa_pgsc", from = "src"}]
 
 [tool.poetry.scripts]
 fraposa = "fraposa_pgsc.fraposa_runner:main"
 fraposa_pred = "fraposa_pgsc.predstupopu:main"
 fraposa_plot = "fraposa_pgsc.plotpcs:main"
 
-# note: poetry currently has half-implemented support for shell scripts
-# https://github.com/python-poetry/poetry/issues/241#issuecomment-1459952704
-# the created package bundles the script correctly in the built wheel file
-# but the script doesn't get added to PATH after poetry build + install
-# the dockerfile takes care of this: splitindiv.sh works as expected
-splitindiv = {reference = "scripts/splitindiv.sh", type = "file"}
-
 [tool.poetry.dependencies]
 python = "^3.10"
 pandas = "^1.5.3"

src/fraposa_pgsc/__init__.py

@@ -0,0 +1,7 @@
+import logging
+import importlib.metadata
+
+log_fmt = "%(name)s: %(asctime)s %(levelname)-8s %(message)s"
+logging.basicConfig(format=log_fmt, datefmt="%Y-%m-%d %H:%M:%S")
+logger = logging.getLogger(__name__)
+__version__ = importlib.metadata.version("fraposa_pgsc")

fraposa_pgsc/fraposa.py → src/fraposa_pgsc/fraposa.py

@@ -8,7 +8,7 @@
 from pyplink import PyPlink
 from sklearn.neighbors import KNeighborsClassifier
 
-from fraposa_pgsc.Variants import MatchType, Variants
+from fraposa_pgsc.variants import MatchType, Variants
 
 matplotlib.use('Agg')
 import matplotlib.pyplot as plt

fraposa_pgsc/plotpcs.py → src/fraposa_pgsc/plotpcs.py

@@ -1,13 +1,15 @@
-#! /usr/bin/env python
+import argparse
+import fraposa_pgsc.fraposa as fp
 
-import fraposa as fp
-import argparse, sys
 
-
-if __name__ == '__main__':
+def main():
     parser = argparse.ArgumentParser()
     parser.add_argument('ref_filepref', help='Prefix of binary PLINK file for the reference data.')
     parser.add_argument('stu_filepref', help='Prefix of binary PLINK file for the study data.')
     args = parser.parse_args()
 
     fp.plot_pcs(args.ref_filepref, args.stu_filepref)
+
+
+if __name__ == '__main__':
+    main()

fraposa_pgsc/predstupopu.py → src/fraposa_pgsc/predstupopu.py

@@ -1,9 +1,8 @@
-#! /usr/bin/env python
-
-import fraposa as fp
+import fraposa_pgsc.fraposa as fp
 import argparse
 
-if __name__ == '__main__':
+
+def main():
     parser=argparse.ArgumentParser()
     parser.add_argument('ref_filepref', help='Prefix of binary PLINK file for the reference data.')
     parser.add_argument('stu_filepref', help='Prefix of binary PLINK file for the study data.')
@@ -19,3 +18,7 @@
         n_neighbors = int(args.nneighbors)
 
     fp.pred_popu_stu(args.ref_filepref, args.stu_filepref, n_neighbors, weights)
+
+
+if __name__ == '__main__':
+    main()