Remove Python 2 compat imports

.github/workflows/tests.yml

@@ -0,0 +1,34 @@
+name: Tests
+
+on:
+  push:
+    branches: [ main, master ]
+  pull_request:
+    branches: [ main, master ]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - run: pip install ruff
+      - run: ruff check pepdata/
+
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - run: |
+          pip install pytest pytest-cov
+          pip install -r requirements.txt
+          pip install .
+      - run: pytest tests/

lint.sh

@@ -1,9 +1,6 @@
 #!/bin/bash
 set -o errexit
 
-find pepdata test -name '*.py' \
-  | xargs pylint \
-  --errors-only \
-  --disable=print-statement
+ruff check pepdata/ tests/
 
-echo 'Passes pylint check'
+echo 'Passes ruff check'

pepdata/amino_acid.py

@@ -11,8 +11,6 @@
 # limitations under the License.
 
 
-from __future__ import print_function, division, absolute_import
-
 class AminoAcid(object):
     def __init__(
             self, full_name, short_name, letter, contains=None):

pepdata/amino_acid_alphabet.py

@@ -15,8 +15,6 @@
 Quantify amino acids by their physical/chemical properties
 """
 
-from __future__ import print_function, division, absolute_import
-
 import numpy as np
 
 from .amino_acid import AminoAcid

pepdata/amino_acid_properties.py

@@ -10,8 +10,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from __future__ import print_function, division, absolute_import
-
 from .amino_acid_alphabet import letter_to_index
 
 """

pepdata/blosum.py

@@ -10,8 +10,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from __future__ import print_function, division, absolute_import
-
 from os.path import join
 
 from .static_data import MATRIX_DIR

pepdata/chou_fasman.py

@@ -10,8 +10,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from __future__ import print_function, division, absolute_import
-
 from .amino_acid_alphabet import amino_acid_name_indices
 
 # Chou-Fasman of structural properties from

pepdata/common.py

@@ -13,8 +13,6 @@
 # limitations under the License.
 
 
-from __future__ import print_function, division, absolute_import
-
 import numpy as np
 
 def transform_peptide(peptide, property_dict):

pepdata/iedb/alleles.py

@@ -10,7 +10,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from __future__ import print_function, division, absolute_import
 from collections import namedtuple
 import os
 import xml
@@ -63,7 +62,7 @@ class and source organism.
             continue
         name = name_element.text
 
-        synonyms = set([])
+        synonyms = set()
         for synonym_element in allele.iterfind("Synonyms"):
             for synonym in synonym_element.text.split(","):
                 synonyms.add(synonym.strip())

pepdata/iedb/memoize.py

@@ -10,8 +10,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from __future__ import print_function, division, absolute_import
-
 from functools import wraps
 
 def _prepare_memoization_key(args, kwargs):

pepdata/iedb/mhc.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at
@@ -10,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from __future__ import print_function, division, absolute_import
 import logging
 import os
 

pepdata/iedb/tcell.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at
@@ -11,7 +13,6 @@
 # limitations under the License.
 
 
-from __future__ import print_function, division, absolute_import
 import logging
 import os
 
@@ -24,15 +25,9 @@
 from .common import  bad_amino_acids, cache
 from .columns import (
     get_assay_method,
-    get_assay_num_tested,
-    get_assay_response_measured,
-    get_assay_units,
     get_host_name,
     get_mhc_allele,
-    get_mhc_assay,
     get_mhc_class,
-    get_epitope_source_organism,
-    get_epitope_type,
     get_epitope_name,
 
 )
@@ -119,10 +114,10 @@ def load_dataframe(
             encoding="latin-1")
 
     mhc = get_mhc_allele(df)
-    mhc_class = get_mhc_class(df)
+    mhc_class_series = get_mhc_class(df)
     epitopes = get_epitope_name(df)
     organism = get_host_name(df)
-    assay_method = get_assay_method(df)
+    assay_method_series = get_assay_method(df)
 
 
     # Sometimes the IEDB seems to put in an extra comma in the
@@ -177,23 +172,19 @@ def load_dataframe(
     #  "HLA-Class I,allele undetermined"
     #  or
     #  "Class I,allele undetermined"
-]
-
-    if hla:
-        mask &= df[mhc_allele_column_key].str.contains(hla, na=False)
 
-    if exclude_hla:
-        mask &= ~(df[mhc_allele_column_key].str.contains(exclude_hla, na=False))
+    if mhc_pattern:
+        mask &= mhc.str.contains(mhc_pattern, na=False)
 
-    if assay_group:
-        mask &= df[assay_group_column_key].str.contains(assay_group)
+    if exclude_mhc:
+        mask &= ~(mhc.str.contains(exclude_mhc, na=False))
 
-    if assay_method:
-        mask &= df[assay_method_column_key].str.contains(assay_method)
+    if assay_method is not None and assay_method_series is not None:
+        mask &= assay_method_series.str.contains(assay_method, na=False)
 
     if peptide_length:
         assert peptide_length > 0
-        mask &= df[epitope_column_key].str.len() == peptide_length
+        mask &= epitopes.str.len() == peptide_length
 
     df = df[mask]
 

pepdata/peptide_vectorizer.py

@@ -13,8 +13,6 @@
 # limitations under the License.
 
 
-from __future__ import print_function, division, absolute_import
-
 import numpy as np
 from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.preprocessing import normalize
@@ -28,7 +26,7 @@ def make_count_vectorizer(reduced_alphabet, max_ngram):
     return CountVectorizer(
         analyzer='char',
         ngram_range=(1, max_ngram),
-        dtype=np.float,
+        dtype=np.float64,
         preprocessor=preprocessor)
 
 class PeptideVectorizer(object):

pepdata/pmbec.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from __future__ import print_function, division, absolute_import
 from os.path import join
 
 from .static_data import MATRIX_DIR

pepdata/reduced_alphabet.py

@@ -18,8 +18,6 @@
 Peterson, Kondev, et al.
 http://www.rpgroup.caltech.edu/publications/Peterson2008.pdf
 """
-from __future__ import print_function, division, absolute_import
-
 def dict_from_list(groups):
     aa_to_group = {}
     for i, group in enumerate(groups):

pepdata/residue_contact_energies.py

@@ -10,8 +10,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from __future__ import print_function, division, absolute_import
-
 from os.path import join
 
 from .amino_acid_alphabet import canonical_amino_acid_letters, dict_to_amino_acid_matrix

pepdata/static_data.py

@@ -11,7 +11,6 @@
 # limitations under the License.
 
 
-from __future__ import print_function, division, absolute_import
 from os.path import dirname, realpath, join
 
 PACKAGE_DIR = dirname(realpath(__file__))

pepdata/version.py

@@ -1,4 +1,4 @@
-__version__ = "1.2.0"
+__version__ = "1.2.2"
 
 
 def print_version():

pyproject.toml

@@ -0,0 +1,39 @@
+[build-system]
+requires = ["setuptools>=64"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "pepdata"
+requires-python = ">=3.9"
+authors = [{name="Alex Rubinsteyn", email="alex.rubinsteyn@mssm.edu"}]
+description = "Immunological peptide datasets and amino acid properties"
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Environment :: Console",
+    "Operating System :: OS Independent",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+]
+readme = "README.md"
+dynamic = ["version", "dependencies"]
+
+[tool.setuptools.dynamic]
+version = {attr = "pepdata.version.__version__"}
+dependencies = {file = ["requirements.txt"]}
+
+[tool.setuptools.packages.find]
+exclude = ["test", "test.*"]
+
+[project.urls]
+"Homepage" = "https://github.com/openvax/pepdata"
+"Bug Tracker" = "https://github.com/openvax/pepdata/issues"
+
+[tool.ruff.lint]
+select = ["E", "F"]
+ignore = ["F821", "E501", "F841", "E731", "E741", "E722", "E721"]
+
+[tool.ruff.lint.per-file-ignores]
+"__init__.py" = ["F401"]
+"test*/*" = ["F401"]

requirements.txt

@@ -1,4 +1,4 @@
-numpy>=1.7
+numpy>=2.0.0,<3.0.0
 scipy>=0.9
 pandas>=0.17
 scikit-learn>=0.14.1