Merge pull request #22 from ryanjameskennedy/20-pylinting-fix

Fix pylinting errors and add pylinting workflow

.github/workflows/pylint.yml

@@ -0,0 +1,24 @@
+name: Pylint
+
+on: [push]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install pylint pytest
+        pip install -e .
+    - name: Analysing the code with pylint
+      run: |
+        pylint --disable=W1401,R0914,W0718 --fail-under 9 $(git ls-files '*.py')

jasentool/__init__.py

@@ -1,3 +1,5 @@
+"""Information regarding jasentool for setup.py"""
+
 __author__ = 'Ryan James Kennedy'
 __author_email__ = '[email protected]'
 __copyright__ = 'Copyright 2023'
@@ -6,7 +8,7 @@
 __license__ = 'GPL3'
 __maintainer__ = 'Ryan James Kennedy'
 __maintainer_email__ = '[email protected]'
-__name__ = 'jasentool'
+__software_name__ = 'jasentool'
 __python_requires__ = '>=3.11'
 __status__ = 'Production'
 __title__ = 'jasentool'

jasentool/__main__.py

@@ -1,15 +1,17 @@
+"""__main__ file that handles help and cli execution"""
+
 import sys
-import os
 
 from jasentool import __author__, __copyright__, __version__
 from jasentool.cli import get_main_parser
 from jasentool.main import OptionsParser
 
 def print_help():
-    print('''
+    """Print help string for jasentool software"""
+    print(f'''
 
-                    ...::: Jasentool v%s :::...
-Author(s): %s
+                    ...::: Jasentool v{__version__} :::...
+Author(s): {__author__}
 
 Description:
     This software is a mongodb tool that fetches, inserts and 
@@ -32,9 +34,10 @@ def print_help():
     fix                 Fix output files from bjorn.
     converge            Converge tuberculosis mutation catlogues.
     qc                  Extract QC values after alignment.
-''' % (__version__, __author__))
+''')
 
 def main():
+    """Main function that handles cli"""
     args = None
     if len(sys.argv) == 1:
         print_help()
@@ -57,14 +60,14 @@ def main():
     except KeyboardInterrupt:
         print('Controlled exit resulting from interrupt signal.')
         sys.exit(1)
-    except Exception as e:
+    except Exception as error_code:
         error_message = 'Uncontrolled exit resulting from an unexpected error.\n\n'
         error_message += '-' * 80 + '\n'
-        error_message += 'EXCEPTION: {}\n'.format(type(e).__name__)
-        error_message += 'MESSAGE: {}\n'.format(e)
+        error_message += f'EXCEPTION: {type(error_code).__name__}\n'
+        error_message += f'MESSAGE: {error_code}\n'
         error_message += '-' * 80 + '\n\n'
         print(error_message)
         sys.exit(1)
 
 if __name__ == "__main__":
-    main()
+    main()

jasentool/cli.py

@@ -1,117 +1,184 @@
-import os
+"""Command line interface module"""
+
 import argparse
 from contextlib import contextmanager
 
 @contextmanager
 def subparser(parser, name, desc):
-    yield parser.add_parser(name, conflict_handler='resolve', help=desc, formatter_class=argparse.RawDescriptionHelpFormatter)
+    """Yield subparser"""
+    yield parser.add_parser(name, conflict_handler='resolve', help=desc,
+                            formatter_class=argparse.RawDescriptionHelpFormatter)
 
 @contextmanager
 def mutex_group(parser, required):
-    group = parser.add_argument_group(f'mutually exclusive {"required" if required else "optional"} arguments')
+    """Yield mutually exclusive group"""
+    arg_type = "required" if required else "optional"
+    group = parser.add_argument_group(f'mutually exclusive {arg_type} arguments')
     yield group.add_mutually_exclusive_group(required=required)
 
 @contextmanager
 def arg_group(parser, name):
+    """Yield mutually argument group"""
     yield parser.add_argument_group(name)
 
 def __query(group, required):
+    """Add query argument to group"""
     group.add_argument('-q', '--query', required=required, nargs='+', help='sample query')
 
 def __sample_id(group, required):
+    """Add sample_id argument to group"""
     group.add_argument('--sample_id', required=required, type=str, help='sample ID')
 
 def __input_dir(group, required, help):
+    """Add input_dir argument to group"""
     group.add_argument('--input_dir', required=required, help=help)
 
 def __input_file(group, required, help):
-    group.add_argument('-i', '--input_file', nargs='+', help=help)
+    """Add input_file argument to group"""
+    group.add_argument('-i', '--input_file', required=required, nargs='+', help=help)
 
 def __csv_file(group, required, help):
+    """Add csv_file argument to group"""
     group.add_argument('--csv_file', required=required, help=help)
 
 def __sh_file(group, required, help):
+    """Add sh_file argument to group"""
     group.add_argument('--sh_file', required=required, help=help)
 
 def __bam_file(group, required):
+    """Add bam_file argument to group"""
     group.add_argument('--bam_file', required=required, type=str, help='input bam file')
 
 def __bed_file(group, required):
+    """Add bed_file argument to group"""
     group.add_argument('--bed_file', required=required, type=str, help='input bed file')
 
 def __baits_file(group, required):
-    group.add_argument('--baits_file', required=required, type=str, default=None, help='input bam file')
+    """Add baits_file argument to group"""
+    group.add_argument('--baits_file', required=required, type=str, default=None,
+                       help='input baits file')
 
 def __reference(group, required, help):
+    """Add reference argument to group"""
     group.add_argument('--reference', required=required, type=str, help=help)
 
 def __output_file(group, required, help):
+    """Add output_file argument to group"""
     group.add_argument('-o', '--output_file', required=required, type=str, help=help)
 
 def __output_dir(group, required):
-    group.add_argument('--output_dir', required=required, type=str, help='directory to output files')
+    """Add output_dir argument to group"""
+    group.add_argument('--output_dir', required=required, type=str,
+                       help='directory to output files')
 
 def __analysis_dir(group, required):
-    group.add_argument('--analysis_dir', required=required, type=str, help='analysis results dir containing jasen results')
+    """Add analysis_dir argument to group"""
+    group.add_argument('--analysis_dir', required=required, type=str,
+                       help='analysis results dir containing jasen results')
 
 def __restore_dir(group, required):
-    group.add_argument('--restore_dir', required=required, type=str, default='/fs2/seqdata/restored', help='directory user wishes spring files to be restored to')
+    """Add restore_dir argument to group"""
+    group.add_argument('--restore_dir', required=required, type=str,
+                       default='/fs2/seqdata/restored',
+                       help='directory user wishes spring files to be restored to')
 
 def __remote_dir(group, required):
-    group.add_argument('--remote_dir', required=required, type=str, default='/fs1/bjorn/jasen', help='directory user wishes spring files to be restored to')
+    """Add remote_dir argument to group"""
+    group.add_argument('--remote_dir', required=required, type=str,
+                       default='/fs1/bjorn/jasen',
+                       help='directory user wishes spring files to be restored to')
 
 def __restore_file(group, required):
-    group.add_argument('--restore_file', required=required, type=str, help='filepath bash shell script (.sh) to be output')
+    """Add restore_file argument to group"""
+    group.add_argument('--restore_file', required=required, type=str,
+                       help='filepath bash shell script (.sh) to be output')
 
 def __missing_log(group, required):
-    group.add_argument('--missing_log', required=required, type=str, default='missing_samples.log', help='file containing missing files')
+    """Add missing_log argument to group"""
+    group.add_argument('--missing_log', required=required, type=str,
+                       default='missing_samples.log',
+                       help='file containing missing files')
 
 def __assay(group, required):
-    group.add_argument('--assay', required=required, type=str, default='jasen-saureus-dev', help='assay for jasen to run')
+    """Add assay argument to group"""
+    group.add_argument('--assay', required=required, type=str,
+                       default='jasen-saureus-dev',
+                       help='assay for jasen to run')
 
 def __platform(group, required):
-    group.add_argument('--platform', required=required, type=str, default='illumina', help='sequencing platform for jasen to run')
+    """Add platform argument to group"""
+    group.add_argument('--platform', required=required, type=str,
+                       default='illumina',
+                       help='sequencing platform for jasen to run')
 
 def __uri(group):
-    group.add_argument('--address', '--uri', default='mongodb://localhost:27017/', help='Mongodb host address. Use: `sudo lsof -iTCP -sTCP:LISTEN | grep mongo` to get address')
+    """Add mongodb address argument to group"""
+    group.add_argument('--address', '--uri',
+                       default='mongodb://localhost:27017/',
+                       help='Mongodb host address. \
+                        Use: `sudo lsof -iTCP -sTCP:LISTEN | grep mongo` to get address')
 
 def __db_name(group, required):
-    group.add_argument('--db_name', required=required, help='Mongodb database name address. Use: `show dbs` to get db name')
+    """Add db_name argument to group"""
+    group.add_argument('--db_name', required=required,
+                       help='Mongodb database name address. \
+                        Use: `show dbs` to get db name')
 
 def __db_collection(group, required):
-    group.add_argument('--db_collection', required=required, help='Mongodb collection name. Use: `show collections` to get db collection')
+    """Add db_collection argument to group"""
+    group.add_argument('--db_collection', required=required,
+                       help='Mongodb collection name. \
+                        Use: `show collections` to get db collection')
 
 def __out_format(group, required):
-    group.add_argument('-f', '--out_format', required=required, type=str, default="bed", help='output format')
+    """Add out_format argument to group"""
+    group.add_argument('-f', '--out_format', required=required, type=str,
+                       default="bed", help='output format')
 
 def __accession(group, required):
+    """Add accession argument to group"""
     group.add_argument('-a', '--accession', required=required, type=str, help='accession number')
 
 def __remote_hostname(group, required):
-    group.add_argument('--remote_hostname', required=required, type=str, default='rs-fs1.lunarc.lu.se', help='remote hostname')
+    """Add remote_hostname argument to group"""
+    group.add_argument('--remote_hostname', required=required, type=str,
+                       default='rs-fs1.lunarc.lu.se', help='remote hostname')
 
 def __prefix(group):
-    group.add_argument('--prefix', type=str, default='jasentool_results_', help='prefix for all output files')
+    """Add prefix argument to group"""
+    group.add_argument('--prefix', type=str, default='jasentool_results_',
+                       help='prefix for all output files')
 
 def __auto_start(group, required):
-    group.add_argument('--auto_start', required=required, dest='auto_start', action='store_true', default=False, help='automatically start')
+    """Add auto_start argument to group"""
+    group.add_argument('--auto_start', required=required, dest='auto_start', action='store_true',
+                       default=False, help='automatically start')
 
 def __remote(group, required):
-    group.add_argument('--remote', required=required, dest='remote', action='store_true', default=False, help='remote copy')
+    """Add remote argument to group"""
+    group.add_argument('--remote', required=required, dest='remote', action='store_true',
+                       default=False, help='remote copy')
 
 def __combined_output(group):
-    group.add_argument('--combined_output', dest='combined_output', action='store_true', help='combine all of the outputs into one output')
+    """Add combined_output argument to group"""
+    group.add_argument('--combined_output', dest='combined_output', action='store_true',
+                       help='combine all of the outputs into one output')
 
 def __sample_sheet(group, required):
-    group.add_argument('--sample_sheet', required=required, dest='sample_sheet', action='store_true', help='sample sheet input')
+    """Add sample_sheet argument to group"""
+    group.add_argument('--sample_sheet', required=required, dest='sample_sheet',
+                       action='store_true', help='sample sheet input')
 
 def __cpus(group):
+    """Add cpus argument to group"""
     group.add_argument('--cpus', dest='cpus', type=int, default=2, help='input cpus')
 
 def __help(group):
+    """Add help argument to group"""
     group.add_argument('-h', '--help', action='help', help='show help message')
 
 def get_main_parser():
+    """Get/build the main argument parser"""
     main_parser = argparse.ArgumentParser(prog='jasentool', conflict_handler='resolve')
     sub_parsers = main_parser.add_subparsers(help='--', dest='subparser_name')
     with subparser(sub_parsers, 'find', 'Find sample from given mongo db') as parser:
@@ -209,4 +276,4 @@ def get_main_parser():
             __cpus(group)
             __help(group)
 
-    return main_parser
+    return main_parser

jasentool/converge.py

@@ -1,11 +1,14 @@
+"""Module to converge mutation catalogues"""
+
 import os
 import pandas as pd
 from jasentool.who import WHO
 from jasentool.genome import Genome
 from jasentool.tbprofiler import Tbprofiler
 from jasentool.utils import Utils
 
-class Converge(object):
+class Converge:
+    """Class that converges mutation catalogues"""
     def __init__(self, download_dir):
         self.download_dir = download_dir
         self.fohm_fpath = os.path.join(os.path.dirname(__file__), "data/dbs/fohm.csv")
@@ -45,6 +48,7 @@ def compare_columns(self, tbdb_df, who_df, column_names):
         return intersection_df, unique_tbdb_df, unique_who_df
 
     def run(self):
+        """Run the retrieval and convergance of mutation catalogues"""
         utils = Utils()
         # Download the genome
         mycobacterium_genome = Genome("NC_000962.3", "AL123456.3", self.download_dir, "h37rv")
@@ -55,14 +59,18 @@ def run(self):
         tbprofiler = Tbprofiler(self.tbdb_filepath)
         #h37rv_gb_filepath = mycobacterium_genome.download_genbank()
         who_df = who._parse(fasta_filepath, gff_filepath, self.download_dir)
-        tbdb_df = tbprofiler._parse(fasta_filepath, gff_filepath, self.download_dir)
-        #tbdb_df, who_df = pd.read_csv("/data/bnf/dev/ryan/pipelines/jasen/converge/tbdb.csv"), pd.read_csv("/data/bnf/dev/ryan/pipelines/jasen/converge/who.csv")
+        tbdb_df = tbprofiler._parse(self.download_dir)
+        #tbdb_df = pd.read_csv("/data/bnf/dev/ryan/pipelines/jasen/converge/tbdb.csv")
+        #who_df = pd.read_csv("/data/bnf/dev/ryan/pipelines/jasen/converge/who.csv")
         fohm_df = pd.read_csv(self.fohm_fpath)
-        intersection_df, unique_tbdb_df, unique_who_df = self.compare_columns(tbdb_df, who_df, ['Drug', 'Gene', 'Mutation'])
-        fohm_tbdb_df = pd.concat([intersection_df, unique_tbdb_df, fohm_df], ignore_index=True).drop_duplicates()
+        column_names = ['Drug', 'Gene', 'Mutation']
+        intersection_df, unique_tbdb_df, unique_who_df = self.compare_columns(tbdb_df, who_df, column_names)
+        dfs_to_concat = [intersection_df, unique_tbdb_df, fohm_df]
+        fohm_tbdb_df = pd.concat(dfs_to_concat, ignore_index=True).drop_duplicates()
         intersection_df.to_csv(self.intersection_outfpath, index=False)
         unique_tbdb_df.to_csv(self.unique_tbdb_outfpath, index=False)
         unique_who_df.to_csv(self.unique_who_outfpath, index=False)
         fohm_tbdb_df.to_csv(self.fohm_tbdb_outfpath, index=False)
-        converged_df = pd.concat([intersection_df, unique_tbdb_df, unique_who_df, fohm_df], ignore_index=True).drop_duplicates()
+        dfs_to_converge = [intersection_df, unique_tbdb_df, unique_who_df, fohm_df]
+        converged_df = pd.concat(dfs_to_converge, ignore_index=True).drop_duplicates()
         converged_df.to_csv(self.convereged_outfpath, index=False)

jasentool/convert.py

@@ -1,8 +1,12 @@
-class Convert(object):
+"""Module that converts file type"""
+
+class Convert:
+    """Convert class for converting files into desired format"""
     @staticmethod
     def targets2bed(target_file, accn):
+        """Convert cgmlst locus targets to bed file format"""
         bed_output = ""
-        with open(target_file, 'r') as fin:
+        with open(target_file, 'r', encoding="utf-8") as fin:
             for line in fin:
                 if line.startswith("Locus"):
                     continue
@@ -11,4 +15,4 @@ def targets2bed(target_file, accn):
                 length = int(line_split[4])
                 end = start + length
                 bed_output += f"{accn}\t{start}\t{end}\n"
-        return bed_output
+        return bed_output