Merge pull request #328 from pbashyal-nmdp/upgrade-pandas-222

Support for Python 3.12

Author: mmaiers-nmdp

.github/workflows/python-tests.yml

@@ -16,10 +16,10 @@ jobs:
 
     steps:
     - uses: actions/checkout@v3
-    - name: Set up Python 3.8
+    - name: Set up Python 3.9
       uses: actions/setup-python@v3
       with:
-        python-version: 3.8
+        python-version: 3.9
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip

.github/workflows/pythonpublish.yml

@@ -17,7 +17,7 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v3
       with:
-        python-version: 3.8
+        python-version: 3.9
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip

Dockerfile

@@ -1,10 +1,10 @@
-FROM python:3.11-slim-buster
+FROM python:3.12-slim-bullseye
 
 LABEL MAINTAINER="Pradeep Bashyal"
 
 WORKDIR /app
 
-ARG PY_ARD_VERSION=1.2.1
+ARG PY_ARD_VERSION=1.5.0
 
 COPY requirements.txt /app
 RUN pip install --no-cache-dir --upgrade pip && \

Dockerfile-local

@@ -1,4 +1,4 @@
-FROM python:3.10-slim-buster
+FROM python:3.12-slim-bullseye
 
 LABEL MAINTAINER="Pradeep Bashyal"
 

README.md

@@ -8,6 +8,8 @@ Swiss army knife of **HLA** Nomenclature
 
 **Note:**
 
+- Python Version 3.8 is no longer supported with the latest `py-ard` versions due to latest Pandas library not supporting 3.8. Please use `py-ard==1.2.1` if using Python 3.8
+
 - `ping` mode is default. When in `ping` mode, alleles that do not have a G group, their corresponding P group is used.
 
 - Release `1.1.1` has extensive Serolgy related updates and affects Serology related data. Please rebuild the cache database if there's a missing Serology error.

api-spec.yaml

@@ -2,7 +2,7 @@ openapi: 3.0.3
 info:
   title: ARD Reduction
   description: Reduce to ARD Level
-  version: "1.2.1"
+  version: "1.5.0"
 servers:
   - url: 'http://localhost:8080'
 tags:
@@ -28,15 +28,22 @@ paths:
       operationId: api.version_controller
       summary: IPD-IMGT/HLA Version
       description: |
-        Get IPD-IMGT/HLA DB Version used for this service
+        Get IPD-IMGT/HLA DB Version and `py-ard` version used for this service
       responses:
         200:
           description: IPD-IMGT/HLA version number
           content:
             application/json:
               schema:
-                type: integer
-                example: 3440
+                properties:
+                 ipd-version:
+                    description: IPD-IMGT/HLA DB Version
+                    type: integer
+                    example: 3560
+                 py-ard-version:
+                    description: py-ard library version
+                    type: string
+                    example: "1.2.1"
   /redux:
     post:
       tags:

api.py

@@ -105,12 +105,15 @@ def drbx_blender_controller():
 
 
 def version_controller():
-    version = ard.get_db_version()
-    return {"version": version}, 200
+    ipd_version = ard.get_db_version()
+    return {
+        "ipd-version": ipd_version,
+        "py-ard-version": pyard.__version__,
+    }, 200
 
 
 def splits_controller(allele: str):
-    mapping = pyard.find_broad_splits(allele)
+    mapping = ard.find_broad_splits(allele)
     if mapping:
         return {"broad": mapping[0], "splits": mapping[1]}, 200
 

pyard/__init__.py

@@ -26,7 +26,7 @@
 from .misc import get_imgt_db_versions as db_versions
 
 __author__ = """NMDP Bioinformatics"""
-__version__ = "1.2.1"
+__version__ = "1.5.0"
 
 
 def init(

pyard/data_repository.py

@@ -98,7 +98,7 @@ def generate_ard_mapping(db_connection: sqlite3.Connection, imgt_version) -> ARS
     # filter out the mg with count > 1, leaving only duplicates
     # take the index from the 2d version the data frame, make that a column
     # and turn that into a list
-    multiple_g_list = mg[mg > 1].reset_index()["index"].to_list()
+    multiple_g_list = mg[mg > 1].index.to_list()
 
     # Keep only the alleles that have more than 1 mapping
     dup_g = (
@@ -111,7 +111,7 @@ def generate_ard_mapping(db_connection: sqlite3.Connection, imgt_version) -> ARS
 
     # multiple lgx
     mlgx = df_g_group.drop_duplicates(["2d", "lgx"])["2d"].value_counts()
-    multiple_lgx_list = mlgx[mlgx > 1].reset_index()["index"].to_list()
+    multiple_lgx_list = mlgx[mlgx > 1].index.to_list()
 
     # Keep only the alleles that have more than 1 mapping
     dup_lgx = (

requirements-dev.txt

@@ -1,6 +1,6 @@
-allure-behave==2.9.45
-flake8==4.0.1
+allure-behave==2.13.5
+flake8==7.0.0
 bump2version==1.0.1
-coverage==6.3.2
-wheel==0.38.1
-pre-commit==2.18.1
+coverage==7.5.3
+wheel==0.43.0
+pre-commit==3.7.1

requirements-tests.txt

@@ -1,3 +1,3 @@
 behave==1.2.6
-PyHamcrest==2.0.2
-pytest==7.1.2
+PyHamcrest==2.1.0
+pytest==8.2.2

requirements.txt

@@ -1,3 +1,2 @@
 toml==0.10.2
-numpy==1.24.3
-pandas==1.5.3
+pandas==2.2.2

setup.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 1.2.1
+current_version = 1.5.0
 commit = True
 tag = True
 

setup.py

@@ -36,7 +36,7 @@
 
 setup(
     name="py-ard",
-    version="1.2.1",
+    version="1.5.0",
     description="ARD reduction for HLA with Python",
     long_description=readme,
     long_description_content_type="text/markdown",
@@ -63,9 +63,10 @@
         "Topic :: Scientific/Engineering :: Bio-Informatics",
         "License :: OSI Approved :: GNU Lesser General Public License v3 (LGPLv3)",
         "Natural Language :: English",
-        "Programming Language :: Python :: 3.8",
         "Programming Language :: Python :: 3.9",
         "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
     ],
     test_suite="tests",
     tests_require=test_requirements,

tests/test_pyard.py

@@ -47,6 +47,9 @@ def setUpClass(cls) -> None:
         cls.db_version = "3440"
         cls.ard = pyard.init(cls.db_version, data_dir="/tmp/py-ard")
 
+    def addDuration(self, test, elapsed):  # Required for Python >= 3.12
+        pass
+
     def test_no_mac(self):
         self.assertEqual(self.ard.redux("A*01:01:01", "G"), "A*01:01:01G")
         self.assertEqual(self.ard.redux("A*01:01:01", "lg"), "A*01:01g")

tests/test_smart_sort.py

@@ -28,6 +28,9 @@ class TestSmartSort(unittest.TestCase):
     def setUp(self) -> None:
         super().setUp()
 
+    def addDuration(self, test, elapsed):  # Required for Python >= 3.12
+        pass
+
     def test_same_comparator(self):
         allele = "HLA-A*01:01"
         self.assertEqual(smart_sort_comparator(allele, allele), 0)