moose-classifier 0.14__tar.gz → 1.0__tar.gz

moose_classifier-1.0/.github/workflows/publish-pypi.yml

@@ -0,0 +1,39 @@
+---
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+  workflow_dispatch:
+
+jobs:
+  test:
+    uses: ./.github/workflows/unittests.yml
+
+  publish:
+    needs: test
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+
+    steps:
+      - name: Checkout tag
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.ref }}
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+
+      - name: Install build
+        run: python -m pip install build
+
+      - name: Build package
+        run: python -m build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

moose_classifier-0.14/.github/workflows/unnittests.yml → moose_classifier-1.0/.github/workflows/unittests.yml

@@ -5,8 +5,7 @@ on:
     branches: [ master ]
   pull_request:
     branches: [ master ]
-  schedule:
-    - cron: '0 6 * * 1'  # 6am Monday
+  workflow_call:
 
 jobs:
   build:

{moose_classifier-0.14 → moose_classifier-1.0}/.gitignore

@@ -3,3 +3,4 @@ build/
 dist
 *.egg-info
 test_output
+.venv/

{moose_classifier-0.14/src/moose_classifier.egg-info → moose_classifier-1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: moose_classifier
-Version: 0.14
+Version: 1.0
 Summary: Alignment based taxonomic classifier
 Author: Chris Rosenthal
 Author-email: crosenth@gmail.com

{moose_classifier-0.14 → moose_classifier-1.0}/src/classify.py

@@ -128,6 +128,7 @@ assigned tax_ids of a higher threshold that *could* represent invalid tax_ids
 TODO: generate rank thresholds based on lineages input
 """
 import argparse
+import codecs
 import bz2
 import csv
 import gzip
@@ -178,11 +179,6 @@ ALIGNMENT_DTYPES = {
     'tax_name': str
 }
 
-ALIGNMENT_CONVERT = {
-    'qaccver': 'qseqid',
-    'saccver': 'sseqid'
-}
-
 OUTPUT_COLS = [
     'specimen', 'assignment_id', 'assignment',
     'best_rank', 'max_percent', 'min_percent',
@@ -222,9 +218,8 @@ def action(args):
     details_cols = list(DETAILS_COLS)
     if args.columns:
         header = None
-        sep = csv.Sniffer().sniff(args.columns).delimiter
-        conv = ALIGNMENT_CONVERT
-        names = [conv.get(c, c) for c in args.columns.split(sep)]
+        sep = args.delimiter
+        names = args.columns.split(',')
     elif args.delimiter:
         header = 0
         sep = args.delimiter
@@ -628,7 +623,10 @@ def action(args):
         """sort details for consistency and ease of viewing.
         [no blast results] may have irregular aligns.columns
         """
-        aligns = aligns.sort_values(by=details_cols)
+        aligns = aligns.sort_values(
+            by=['specimen', 'assignment_id', 'weight', 'pident', 'tax_name'],
+            ascending=[True, True, False, False, True]
+            )
 
         aligns.to_csv(
             args.details_out,
@@ -741,20 +739,23 @@ def build_parser():
         title='alignment input format options',
         description='Options for alignment input that is '
                     'header-less or not comma-delimited')
+    align_parser.add_argument(
+        '--delimiter',
+        metavar='',
+        default=',',
+        type=lambda x: codecs.decode(x, 'unicode_escape'),
+        help='specify delimiter')
+
     columns_parser = align_parser.add_mutually_exclusive_group(required=False)
     columns_parser.add_argument(
         '--columns', '--header', '-c',
         dest='columns',
         metavar='',
-        help='specify columns names with delimiter')
-    columns_parser.add_argument(
-        '--delimiter',
-        metavar='',
-        help='specify just delimiter')
+        help='specify comma separated column names')
     columns_parser.add_argument(
         '--blast6', '--std',
         action='store_true',
-        help='standard blast tab-separated format')
+        help='standard blast tab-separated format (ignores delimiter)')
     columns_parser.add_argument(
         '--infer',
         action='store_true',
@@ -768,13 +769,6 @@ def build_parser():
         '--rank-thresholds',
         metavar='',
         help='Columns [tax_id,ranks...] [%(default)s]')
-    selection_parser.add_argument(
-        '--top-n-pct',
-        metavar='',
-        default=25,
-        type=float,
-        help=('top percent hits sorted by pident, evalue '
-              'or bitscore per taxonomy group'))
 
     assignment_parser = parser.add_argument_group('assignment options')
     assignment_parser.add_argument(

{moose_classifier-0.14 → moose_classifier-1.0/src/moose_classifier.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: moose_classifier
-Version: 0.14
+Version: 1.0
 Summary: Alignment based taxonomic classifier
 Author: Chris Rosenthal
 Author-email: crosenth@gmail.com

{moose_classifier-0.14 → moose_classifier-1.0}/src/moose_classifier.egg-info/SOURCES.txt

@@ -2,7 +2,8 @@
 README.md
 pyproject.toml
 requirements.txt
-.github/workflows/unnittests.yml
+.github/workflows/publish-pypi.yml
+.github/workflows/unittests.yml
 sphinx/Makefile
 sphinx/classifier.rst
 sphinx/conf.py