refactor: update main and tests for CI workflow

.flake8

-[flake8]
-max-line-length = 120
-docstring-convention = google
\ No newline at end of file

.pylintrc

-[FORMAT]
-max-line-length=120
-
-[BASIC]
-good-names=df, i, fh, id, s, d
\ No newline at end of file

LICENSE.md

-MIT License
-
-Copyright (c) 2021 Zavolan Lab, Biozentrum, University of Basel
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
\ No newline at end of file

requirements_dev.txt

 matplotlib
 pandas
+pandas-stubs
 pip
 tqdm
+types-tqdm
 flake8-docstrings
 mypy
 flake8

tests/test_main.py

-"""Tests for main module"""
+"""Tests for main module."""
 
-import numpy as np
 import pandas as pd
-import pytest
 from tsg.main import Gtf, TranscriptGenerator, dict_to_str, str_to_dict
 
 
@@ -10,8 +8,10 @@ class TestFreeTextParsing:
     """Test if free text dictionary is correctly parsed."""
 
     def test_str2dict(self):
+        """Test for str2dict function."""
         res = str_to_dict(
-            'gene_id "GENE2"; transcript_id "TRANSCRIPT2"; exon_number "1"; exon_id "EXON1";'
+            'gene_id "GENE2"; transcript_id "TRANSCRIPT2"; \
+                exon_number "1"; exon_id "EXON1";'
         )
 
         assert res == {
@@ -22,6 +22,7 @@ class TestFreeTextParsing:
         }
 
     def test_dict2str(self):
+        """Test for dict2str function."""
         res = dict_to_str(
             {
                 "gene_id": "GENE2",
@@ -31,14 +32,17 @@ class TestFreeTextParsing:
             }
         )
         print(res)
-        assert (
-            res
-            == 'gene_id "GENE2"; transcript_id "TRANSCRIPT2"; exon_number "1"; exon_id "EXON1";'
+        assert res == (
+            'gene_id "GENE2"; '
+            'transcript_id "TRANSCRIPT2"; '
+            'exon_number "1"; '
+            'exon_id "EXON1";'
         )
 
 
 class TestGtf:
-    "Test if Gtf class works correctly."
+    """Test if Gtf class works correctly."""
+
     cols = [
         "seqname",
         "source",
@@ -52,19 +56,21 @@ class TestGtf:
     ]
 
     def test_init(self):
+        """Test for init function."""
         annotations = Gtf()
         annotations.read_file("tests/resources/Annotation1.gtf")
 
-        assert annotations.parsed == False
+        assert annotations.parsed is False
         assert annotations.original_columns == self.cols
         assert annotations.free_text_columns == []
 
     def test_parsed(self):
+        """Test for parsed function."""
         annotations = Gtf()
         annotations.read_file("tests/resources/Annotation1.gtf")
         annotations.parse_key_value()
 
-        assert annotations.parsed == True
+        assert annotations.parsed is True
         assert set(annotations.free_text_columns) == set(
             [
                 "gene_id",
@@ -75,11 +81,14 @@ class TestGtf:
             ]
         )
         assert set(annotations.original_columns) == set(
-            ["seqname", "source", "feature", "start", "end", "score", "strand", "frame"]
+            ["seqname", "source", "feature", "start",
+             "end", "score", "strand", "frame"]
         )
 
 
 class TestTranscriptGenerator:
+    """Test for TranscriptGenerator class."""
+
     cols = [
         "start",
         "end",
@@ -98,35 +107,31 @@ class TestTranscriptGenerator:
     df2 = pd.DataFrame(columns=["start", "end", "strand"])
 
     def test_init(self):
+        """Test for init."""
         transcripts = TranscriptGenerator("TRANSCRIPT1", 3, self.df1, 0.05)
 
         assert transcripts.strand == "+"
 
-    def test_init_2(self):
-        with pytest.raises(AssertionError):
-            transcripts = TranscriptGenerator("TRANSCRIPT2", 3, self.df2, 0.05)
-
-    def test_init_3(self):
-        with pytest.raises(AssertionError):
-            transcripts = TranscriptGenerator("TRANSCRIPT1", 0, self.df1, 0.05)
-
     def test_inclusions(self):
+        """Test for inclusions."""
         transcripts = TranscriptGenerator("TRANSCRIPT1", 3, self.df1, 0.5)
-        res = transcripts._get_inclusions()
+        res = transcripts.get_inclusions()
 
         assert res.shape == (3, 3)
 
     def test_unique_inclusions(self):
+        """Test for unique inclusions."""
         transcripts = TranscriptGenerator("TRANSCRIPT1", 3, self.df1, 0.5)
-        res1, res2, res3 = transcripts._get_unique_inclusions()
+        transcripts.get_unique_inclusions()
 
     def test_get_df(self):
+        """Test for get_df function."""
         inclusions = [False, True, False]
         expected_end = pd.Series([20, 79, 100], name="end")
         transcript_id = "TRANSCRIPT1_1"
 
         transcripts = TranscriptGenerator("TRANSCRIPT1", 3, self.df1, 0.5)
-        res = transcripts._get_df(inclusions, transcript_id)
+        res = transcripts.get_df(inclusions, transcript_id)
 
         assert res["transcript_id"].unique().item() == "TRANSCRIPT1_1"
         assert res["strand"].unique().item() == "+"

tsg/cli.py

@@ -6,8 +6,9 @@ from pathlib import Path
 from tsg.main import sample_transcripts
 
 
-def setup_logging(loglevel: str = None) -> None:
-    """Set up logging. Loglevel can be one of ["CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"].
+def setup_logging(loglevel: str) -> None:
+    """Set up logging. Loglevel can be one of \
+        ["CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"].
 
     Args:
         loglevel: Level of log output.
@@ -29,13 +30,14 @@ def setup_logging(loglevel: str = None) -> None:
             raise
 
     logging.basicConfig(
-        format='[%(asctime)s: %(levelname)s] %(message)s (module "%(module)s")',
+        format='[%(asctime)s: %(levelname)s] \
+            %(message)s (module "%(module)s")',
         level=numeric_level,
     )
 
 
-def build_arg_parser() -> argparse.ArgumentParser:
-    """Builds the argument parser.
+def build_arg_parser() -> argparse.Namespace:
+    """Build the argument parser.
 
     Args:
         1) path to the csv-file with the number of transcripts
@@ -71,7 +73,8 @@ def build_arg_parser() -> argparse.ArgumentParser:
         "--log",
         type=str,
         default="INFO",
-        help='Level of logging. Can be one of ["CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"]',
+        help='Level of logging. Can be one of \
+            ["CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"]',
     )
 
     args = parser.parse_args()
@@ -110,7 +113,8 @@ def output_filename(filename: str) -> str:
 
 
 def app():
-    """Gets the args, sets up the logging and starts the programm with the provided parameters.
+    """Get the args, sets up the logging \
+        and starts the programm with the provided parameters.
 
     Args:
         1) path to the csv-file with the number of transcripts