Merge pull request #31 from PennChopMicrobiomeProgram/30-parse_result…

…s-fails-with-nas-in-output

Upgrade parse_results to handle NAs

.github/workflows/test.yml

@@ -13,8 +13,8 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4
 
-      - name: Set up Python 3.10
-        uses: actions/setup-python@v3
+      - name: Set up Python
+        uses: actions/setup-python@v5
         with:
           python-version: '3.x'
 
@@ -90,14 +90,4 @@ jobs:
 
       - name: Lint Code Base
         run: |
-          black --check .
-
-  codacy-analysis-cli:
-    name: Codacy Analysis CLI
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Run Codacy Analysis CLI
-        uses: codacy/codacy-analysis-cli-action@master
+          black --check .

README.md

@@ -2,6 +2,7 @@
 
 <!-- Begin badges -->
 [![Tests](https://github.com/PennChopMicrobiomeProgram/unassigner/actions/workflows/pr.yml/badge.svg)](https://github.com/PennChopMicrobiomeProgram/unassigner/actions/workflows/pr.yml)
+[![Codacy Badge](https://app.codacy.com/project/badge/Grade/9ee8fc7bc3e940bb812b35006e95937d)](https://app.codacy.com/gh/PennChopMicrobiomeProgram/unassigner/dashboard?utm_source=gh&utm_medium=referral&utm_content=&utm_campaign=Badge_grade)
 [![codecov](https://codecov.io/gh/PennChopMicrobiomeProgram/unassigner/graph/badge.svg?token=LAFU84K088)](https://codecov.io/gh/PennChopMicrobiomeProgram/unassigner)
 [![PyPI](https://badge.fury.io/py/unassigner.svg)](https://pypi.org/project/unassigner/)
 [![Bioconda](https://anaconda.org/bioconda/unassigner/badges/downloads.svg)](https://anaconda.org/bioconda/unassigner/)

tests/unit/test_parse.py

@@ -1,7 +1,7 @@
 import tempfile
 import unittest
 
-from unassigner.parse import parse_fasta, parse_desc, load_fasta, write_fasta
+from unassigner.parse import parse_fasta, parse_results, load_fasta, write_fasta
 
 
 class FastaTests(unittest.TestCase):
@@ -40,5 +40,25 @@ def test_write_fasta(self):
         self.assertEqual(f.read(), ">a\nCCGGT\n>b\nTTTTTTTTT\n")
 
 
+class ResultsTests(unittest.TestCase):
+    def test_parse_results(self):
+        results = [
+            "query_id\tspecies\ttypestrain_id\tregion_mismatches\tregion_positions\tprobability_incompatible\n",
+            "Seq1\tA\tB\t1\t2\t0.5\n",
+            "Seq1\tC\tD\t3\t1500\t-2.062794379753541e-12\n",
+            "Seq2\tNA\tNA\tNA\tNA\tNA\n",
+        ]
+
+        with tempfile.NamedTemporaryFile(mode="w+t", encoding="utf-8") as f:
+            f.writelines(results)
+            f.seek(0)
+            content = list(parse_results((l for l in f.readlines())))
+
+        self.assertEqual(content[0]["query_id"], "Seq1")
+        self.assertEqual(content[2]["species"], "NA")
+        self.assertEqual(content[2]["region_mismatches"], None)
+        self.assertEqual(content[2]["probability_incompatible"], None)
+
+
 if __name__ == "__main__":
     unittest.main()

unassigner/parse.py

@@ -98,6 +98,12 @@ def parse_greengenes_accessions(f):
         yield line.split("\t")
 
 
+def cast_num_or_na(val, cast_func):
+    if val == "NA":
+        return None
+    return cast_func(val)
+
+
 def parse_results(f):
     float_fields = ["probability_incompatible"]
     int_fields = ["region_mismatches", "region_positions"]
@@ -110,7 +116,7 @@ def parse_results(f):
         res = dict(zip(fields, vals))
         for field, val in res.items():
             if field in float_fields:
-                res[field] = float(val)
+                res[field] = cast_num_or_na(val, float)
             elif field in int_fields:
-                res[field] = int(val)
+                res[field] = cast_num_or_na(val, int)
         yield res