feat: add ci, versioning (#1)

* feat: add version

* fix tests

* feat: add ci

* refactor: rewrite tests

* refactor: rewrite tests

* feat: add pylint config

* fix ci

* fix ci

.github/workflows/ci.yml

@@ -30,7 +30,7 @@ jobs:
           auto-activate-base: false
 
       - name: Update scrnasim env with dev packages
-        run: mamba env update -n scrnasim -f environment.dev.yml
+        run: mamba env update -n scrnasim -f environment-dev.yml
 
       - name: display environment info
         run: |
@@ -67,7 +67,7 @@ jobs:
           auto-activate-base: false
 
       - name: update scrnasim env with dev packages
-        run: mamba env update -n scrnasim -f environment.dev.yml
+        run: mamba env update -n scrnasim -f environment-dev.yml
 
       - name: display environment info
         run: |
@@ -85,4 +85,4 @@ jobs:
           token: ${{ secrets.CODECOV_TOKEN }}
           files: ./coverage.xml
           verbose: true
-          fail_ci_if_error: false
+          fail_ci_if_error: false

environment.yml

@@ -11,5 +11,6 @@ dependencies:
   - pandas>=1.4.4
   - pip>=20.2.3
   - python>=3.6, <=3.10
+  - pyarrow
   - pip:
     - -e .

pylint.cfg

@@ -0,0 +1,2 @@
+[MESSAGES CONTROL]
+disable=C0103,E1101,I1101,R0801

requirements.txt

@@ -1,7 +1,7 @@
-argparse
-biopython
+biopython>=1.78
 numpy>=1.23.3
 pandas>=1.4.4
 polars==0.16.17
 gtfparse
 setuptools
+cli_test_helpers

scRNAsim_toolz/cdna_generator/cli.py

@@ -1,7 +1,7 @@
 """Receive command line arguments."""
-
 import argparse
 import logging
+from scRNAsim_toolz.version import __version__
 
 logging.basicConfig(
     format='[%(asctime)s: %(levelname)s] %(message)s \
@@ -41,6 +41,10 @@ def main():
     parser.add_argument(
         "-ocsv", "--output_csv", help="output fasta file", required=True
     )
+    parser.add_argument(
+        '-v', '--version', action='version',
+        version=f'scRNAsim version: {__version__}'
+    )
     args = parser.parse_args()
 
     LOG.info("Running cDNA generator...")

scRNAsim_toolz/fragment_selector/cli.py

@@ -5,7 +5,7 @@
 from Bio import SeqIO  # type: ignore
 import numpy as np  # type: ignore
 import pandas as pd  # type: ignore
-
+from scRNAsim_toolz.version import __version__
 
 from .fragmentation import fragmentation
 from .utils import check_positive
@@ -124,6 +124,10 @@ def parse_arguments() -> argparse.Namespace:
                         help="Chunk size for batch processing")
     parser.add_argument('--sep', required=False, default=",",
                         help="Sequence counts file separator.")
+    parser.add_argument(
+        '-v', '--version', action='version',
+        version=f'scRNAsim version: {__version__}'
+    )
     args = parser.parse_args()
 
     return args

scRNAsim_toolz/priming_site_predictor/cli.py

@@ -1,6 +1,7 @@
 """Receive command line arguments."""
 import argparse
 import logging
+from scRNAsim_toolz.version import __version__
 from .psp import CreatePrimer
 from .psp import PrimingSitePredictor
 
@@ -65,6 +66,10 @@ def parse_args():
         "-o", "--output-filename",
         help="Path where the output gtf should be written"
         )
+    parser.add_argument(
+        '-v', '--version', action='version',
+        version=f'scRNAsim version: {__version__}'
+    )
     args = parser.parse_args()
 
     return args

scRNAsim_toolz/read_sequencer/cli.py

@@ -1,6 +1,7 @@
 """Receive command line arguments."""
 import argparse
 import logging
+from scRNAsim_toolz.version import __version__
 from .read_sequencer import ReadSequencer
 
 logging.basicConfig(
@@ -52,6 +53,10 @@ def main():
         type=int,
         help="chunk_size for batch processing",
     )
+    parser.add_argument(
+        '-v', '--version', action='version',
+        version=f'scRNAsim version: {__version__}'
+    )
     args = parser.parse_args()
     LOG.info("Read sequencer started.")
     if args.input is not None:

scRNAsim_toolz/sequence_extractor/cli.py

@@ -1,6 +1,7 @@
 """CLI to be run on output fasta file from bedtools getfasta."""
 import argparse
 import logging
+from scRNAsim_toolz.version import __version__
 from .pre_bedtools import pre_bedtools_mode
 from .exon_concat import exon_concatenation
 from .poly_a import poly_a_addition_to_fasta_list
@@ -82,7 +83,10 @@ def parse_args():
         dest="output_bed_file",
         help="Bed file with only exons with strandedness"
              "taken into account for 'pre_bedtools' mode.")
-
+    parser.add_argument(
+        '-v', '--version', action='version',
+        version=f'scRNAsim version: {__version__}'
+    )
     args = parser.parse_args()
     return args
 

scRNAsim_toolz/structure_generator/cli.py

@@ -2,7 +2,7 @@
 import argparse
 import logging
 from pathlib import Path
-
+from scRNAsim_toolz.version import __version__
 from .main import sample_transcripts
 
 
@@ -76,7 +76,10 @@ def build_arg_parser() -> argparse.Namespace:
         help='Level of logging. Can be one of \
             ["CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"]',
     )
-
+    parser.add_argument(
+        '-v', '--version', action='version',
+        version=f'scRNAsim version: {__version__}'
+    )
     args = parser.parse_args()
 
     assert args.prob_inclusion >= 0

scRNAsim_toolz/transcript_sampler/cli.py

@@ -2,6 +2,7 @@
 import argparse
 import time
 import logging
+from scRNAsim_toolz.version import __version__
 
 logging.basicConfig(
     format='[%(asctime)s: %(levelname)s] %(message)s \
@@ -45,6 +46,10 @@ def main():
         "-n", "--n_to_sample", required=True, default=None,
         help="Total number of transcripts to sample"
         )
+    parser.add_argument(
+        '-v', '--version', action='version',
+        version=f'scRNAsim version: {__version__}'
+    )
     args = parser.parse_args()
 
     log = logging.getLogger("main")

scRNAsim_toolz/version.py

@@ -0,0 +1,2 @@
+"""Version of scRNAsim_toolz."""
+__version__ = "0.1.0"

setup.py

@@ -1,6 +1,7 @@
 """scRNAsim package definition."""
 from pathlib import Path
 from setuptools import setup, find_packages  # type: ignore
+from scRNAsim_toolz.version import __version__
 
 # Read long description from file
 with open("README.md", "r", encoding="utf-8") as fh:
@@ -14,8 +15,8 @@
     INSTALL_REQUIRES = fh.read().splitlines()
 
 setup(
-    name="scrnasim",
-    version="0.1.0",
+    name="scrnasim_toolz",
+    version=__version__,
     description=(
         "Repository for the tools used by scRNAsim"
     ),

tests/__init__.py

@@ -0,0 +1 @@
+"""Initialise tests."""

tests/cdna_generator/test_cdna.py

@@ -1,6 +1,6 @@
 """Tests for cDNA functions."""
 import pytest  # type: ignore
-from ...scRNAsim_toolz.cdna_generator.cdna import (  # type: ignore
+from scRNAsim_toolz.cdna_generator.cdna import (
     complement, seq_complement
 )
 

tests/fragment_selector/test_cli.py

@@ -1,16 +1,17 @@
 """Test cli.py functions."""
+from pathlib import Path
 import pytest  # type: ignore
-
-from ...scRNAsim_toolz.fragment_selector.cli import (  # type: ignore
+from scRNAsim_toolz.fragment_selector.cli import (
     file_validation, main
 )
 
-FASTA_FILE = "tests/test_files/test.fasta"
-CSV_FILE = "tests/test_files/test.csv"
-TAB_FILE = "tests/test_files/test_tab.csv"
+TEST_FILES_DIR = Path(__file__).resolve().parent / "test_files"
+FASTA_FILE = TEST_FILES_DIR / "test.fasta"
+CSV_FILE = TEST_FILES_DIR / "test.csv"
+TAB_FILE = TEST_FILES_DIR / "test_tab.csv"
 
-_, csv_counts = file_validation(FASTA_FILE, CSV_FILE, ",")
-_, tab_counts = file_validation(FASTA_FILE, TAB_FILE, "\t")
+_, csv_counts = file_validation(str(FASTA_FILE), str(CSV_FILE), ",")
+_, tab_counts = file_validation(str(FASTA_FILE), str(TAB_FILE), "\t")
 
 
 def test_file():

tests/fragment_selector/test_frag.py

@@ -1,14 +1,15 @@
 """Test utils.py functions."""
+from pathlib import Path
 import pandas as pd  # type: ignore
 import pytest  # type: ignore
 from Bio import SeqIO  # type: ignore
-
-from ...scRNAsim_toolz.fragment_selector.fragmentation import (  # type: ignore
+from scRNAsim_toolz.fragment_selector.fragmentation import (
     fragmentation
 )
 
-FASTA_FILE = "tests/test_files/test.fasta"
-CSV_FILE = "tests/test_files/test.csv"
+TEST_FILES_DIR = Path(__file__).resolve().parent / "test_files"
+FASTA_FILE = TEST_FILES_DIR / "test.fasta"
+CSV_FILE = TEST_FILES_DIR / "test.csv"
 
 fasta_dict = {}
 with open(FASTA_FILE, "r", encoding="utf-8") as handle:

tests/fragment_selector/test_utils.py

@@ -1,8 +1,7 @@
 """Test utils.py functions."""
 import argparse
 import pytest  # type: ignore
-
-from ...scRNAsim_toolz.fragment_selector.utils import (  # type: ignore
+from scRNAsim_toolz.fragment_selector.utils import (
     check_positive
 )
 

tests/priming_site_predictor/test_cli.py

@@ -1,8 +1,8 @@
 """Test functions for cli.py."""
 import unittest
 from unittest.mock import patch
-from ...scRNAsim_toolz.priming_site_predictor import cli  # type: ignore
-from ...scRNAsim_toolz.priming_site_predictor.cli import (  # type: ignore
+from scRNAsim_toolz.priming_site_predictor import cli
+from scRNAsim_toolz.priming_site_predictor.cli import (
     setup_logging
 )
 

tests/priming_site_predictor/test_psp.py

@@ -2,10 +2,11 @@
 import unittest
 from unittest.mock import patch, mock_open
 from unittest import mock
+import os
 import math
 import pandas as pd  # type: ignore
 import pytest  # type: ignore
-from ...scRNAsim_toolz.priming_site_predictor.psp import (  # type: ignore
+from scRNAsim_toolz.priming_site_predictor.psp import (
     CreatePrimer, PrimingSitePredictor
 )
 
@@ -95,6 +96,7 @@ def test_generate_gtf(self):
             print(expected_output)
             # self.assertEqual(self.post_processor.generate_gtf(),
             # expected_output)
+        os.remove("test_output.gtf")
 
     def test_calculate_energy(self):
         """Test the calculate_energy() method."""

tests/read_sequencer/test_cli.py

@@ -1,20 +1,20 @@
 """Test cli.py."""
 import pytest  # type: ignore
 from cli_test_helpers import ArgvContext, shell  # type: ignore
-from ...scRNAsim_toolz.read_sequencer import cli  # type: ignore
+from scRNAsim_toolz.read_sequencer import cli
 
 
 def test_entrypoint():
     """Test if entrypoint script is installed (setup.py)."""
-    result = shell('readsequencer --help')
+    result = shell('read-sequencer --help')
     assert result.exit_code == 0
 
 
 def test_usage_no_args():
     """Test if CLI aborts w/o arguments, displaying usage instructions."""
-    with ArgvContext('readsequencer'), pytest.raises(SystemExit):
+    with ArgvContext('read-sequencer'), pytest.raises(SystemExit):
         cli.main()
 
-    result = shell('readsequencer')
+    result = shell('read-sequencer')
 
     assert 'usage:' in result.stderr