Merge pull request #45 from cmatKhan/develop

debuggging after full run

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "isocomp"
-version = "0.1.0"
+version = "0.2.1"
 description = ""
 authors = ["Yutong Qiu <[email protected]>", "Chia Sin Liew <[email protected]>", "Rupesh Kesharwani <[email protected]>", 
            "Bida Gu <[email protected]>", "chase mateusiak <[email protected]>", 
@@ -30,6 +30,7 @@ isocomp = "isocomp:__main__.main"
 
 [tool.poetry.group.dev.dependencies]
 matplotlib = "^3.7.1"
+autopep8 = "^2.0.4"
 
 [build-system]
 requires = ["poetry-core>=1.0.0"]

scripts/create_windows.py

@@ -21,7 +21,7 @@
 
 warnings.filterwarnings("ignore")
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
+logger = logging.getLogger(__name__)
 
 __all__ = ['get_all_windows','further_merge','main']
 
@@ -192,11 +192,11 @@ def parse_args(args=None):
 
 def main(args=None):
 
-    logging.debug('cmd ling arguments: {args}')
+    logger.debug('cmd ling arguments: {args}')
     args = parse_args(args)
 
     # Check inputs
-    logging.info('checking input...')
+    logger.info('checking input...')
     input_path_list = [args.gene_window_name]
     for input_path in input_path_list:
         if not os.path.exists(input_path):

scripts/find_unique_isoform.py

@@ -49,13 +49,13 @@
 
 # strict positional/optional arguments checking
 argsDict = vars(parser.parse_args())
-logging.info('Parsing Input Arguements...')
-logging.info('Parsing Input Arguements...')
+logger.info('Parsing Input Arguements...')
+logger.info('Parsing Input Arguements...')
 for key, value in argsDict.items():
-    if key in posList: logging.info('Required Argument - %s: %s' %(key, value))
-    if key in optList: logging.info('Optional Argument - %s: %s' %(key, value))
-    if key in posList: logging.info('Required Argument - %s: %s' %(key, value))
-    if key in optList: logging.info('Optional Argument - %s: %s' %(key, value))
+    if key in posList: logger.info('Required Argument - %s: %s' %(key, value))
+    if key in optList: logger.info('Optional Argument - %s: %s' %(key, value))
+    if key in posList: logger.info('Required Argument - %s: %s' %(key, value))
+    if key in optList: logger.info('Optional Argument - %s: %s' %(key, value))
     vars()[key] = value # assign values of arguments into shorthand global variables
 
 
@@ -388,6 +388,6 @@ def compareFunc(seqDict:dict[tuple[str,str,str], list[isoform]], outPre:str, min
     compareFunc(seqDict, outPre, minPercent)
     compareFunc(seqDict, outPre, minPercent)
 
-logging.info('End of Program\n')
-logging.info('End of Program\n')
+logger.info('End of Program\n')
+logger.info('End of Program\n')
 

scripts/rename_fasta.py

@@ -24,7 +24,7 @@
 import sys
 import os
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
+logger = logging.getLogger(__name__)
 
 
 __all__ = ['rename_fa_desc','main']
@@ -76,11 +76,11 @@ def parse_args(args=None):
 
 def main(args=None):
 
-    logging.debug('cmd ling arguments: {args}')
+    logger.debug('cmd ling arguments: {args}')
     args = parse_args(args)
 
     # Check inputs
-    logging.info('checking input...')
+    logger.info('checking input...')
     input_path_list = [args.input]
     for input_path in input_path_list:
         if not os.path.exists(input_path):

src/isocomp/Compare/IsoformLibrary.py

@@ -9,7 +9,7 @@
 # local imports
 from isocomp.Coordinates import Window
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
+logger = logging.getLogger(__name__)
 
 __all__ = ['IsoformLibrary']
 
@@ -58,7 +58,7 @@ def clustered_gtf_path(self) -> str:
 
     @clustered_gtf_path.setter
     def clustered_gtf_path(self, new_path: str) -> None:
-        logging.debug('trying to set new clustered_gtf_path: {new_path}')
+        logger.debug('trying to set new clustered_gtf_path: {new_path}')
         if not os.path.exists(new_path):
             raise FileNotFoundError(f'{new_path} does not exist')
         # TODO allow gff and check format, not extension
@@ -128,7 +128,7 @@ def fasta_dict(self, new_fasta_dict: dict) -> None:
             index file does not exist
         """
 
-        logging.debug("new dict: %s", new_fasta_dict)
+        logger.debug("new dict: %s", new_fasta_dict)
 
         # check type
         if not isinstance(new_fasta_dict, dict):

src/isocomp/Compare/align_isoforms.py

@@ -3,7 +3,7 @@
 # external dependencies
 import edlib
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
+logger = logging.getLogger(__name__)
 
 __all__ = ['align_isoforms']
 

src/isocomp/Compare/compare_isoforms_in_cluster.py

@@ -5,7 +5,7 @@
 from .align_isoforms import align_isoforms
 from .IsoformLibrary import IsoformLibrary
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
+logger = logging.getLogger(__name__)
 
 __all__ = ['compare_isoforms_in_cluster']
 
@@ -126,7 +126,8 @@ def compare_isoforms_in_cluster(
     # same strand, overlap threshold, different subjects
     else:
         # group transcripts by coordinates; return unique
-        cluster_gtf_grouped = cluster_gtf.df.groupby(by=['Start', 'End', 'Strand'], as_index=True)
+        cluster_gtf_grouped = cluster_gtf.df\
+            .groupby(by=['Start', 'End', 'Strand'], as_index=True)
 
         for group, cluster_gtf_unique in cluster_gtf_grouped:
             if len(cluster_gtf_unique) > 1:        

src/isocomp/Compare/filter_comparisons.py

@@ -2,7 +2,7 @@
 
 import pandas as pd
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
+logger = logging.getLogger(__name__)
 
 __all__ = ['filter_comparisons']
 

src/isocomp/Compare/find_unique_isoforms.py

@@ -1,12 +1,12 @@
 import logging
-
+import pandas as pd
 from pandas import DataFrame
 
 from .IsoformLibrary import IsoformLibrary
 from .compare_isoforms_in_cluster import compare_isoforms_in_cluster
 from .filter_comparisons import filter_comparisons
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
+logger = logging.getLogger(__name__)
 
 __all__ = ['find_unique_isoforms']
 
@@ -34,11 +34,12 @@ def find_unique_isoforms(clustered_gtf: str,
     # iterate over clusters and compare isoforms
     for cluster in il.cluster_list:
         cluster = str(cluster)
+        logger.debug(cluster)
         # only compare if there are more than 1 isoforms in the window
         if il.get_cluster_coord(cluster).score > 1:
             all_comparisons\
                 .extend(compare_isoforms_in_cluster(il, cluster))
     # filter the result of the comparisons
-    compare_df_fltr = filter_comparisons(all_comparisons)
+    #compare_df_fltr = filter_comparisons(all_comparisons)
 
-    return compare_df_fltr
+    return pd.DataFrame(all_comparisons) #compare_df_fltr

src/isocomp/Compare/vector_crosser.py

@@ -4,7 +4,7 @@
 
 import numpy as np
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
+logger = logging.getLogger(__name__)
 
 __all__ = ['vector_crosser']
 

src/isocomp/Coordinates/Window.py

@@ -2,7 +2,7 @@
 import logging
 import re
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
+logger = logging.getLogger(__name__)
 
 __all__ = ['Window']
 
@@ -48,7 +48,7 @@ def chr(self):
     @chr.setter
     def chr(self, new_chr: str):
         if not isinstance(new_chr, str):
-            logging.debug(new_chr)
+            logger.debug(new_chr)
             raise ValueError('chr must be a string')
         self._chr = new_chr
 
@@ -61,7 +61,7 @@ def start(self):
     @start.setter
     def start(self, new_start: int):
         if not isinstance(new_start, int):
-            logging.debug(new_start)
+            logger.debug(new_start)
             raise ValueError('start must be an integer')
         self._start = new_start
 
@@ -74,7 +74,7 @@ def end(self):
     @end.setter
     def end(self, new_end: int):
         if not isinstance(new_end, int):
-            logging.debug(new_end)
+            logger.debug(new_end)
             raise ValueError('end must be an integer')
         self._end = new_end
 
@@ -87,7 +87,7 @@ def strand(self):
     @strand.setter
     def strand(self, new_strand: str):
         if new_strand not in self._STRAND_VALUES:
-            logging.debug(new_strand)
+            logger.debug(new_strand)
             raise ValueError('strand value: %s is not one of the recognized '
                              'strand values: %s'
                              % (new_strand, ','.join(self._STRAND_VALUES)))
@@ -113,7 +113,7 @@ def score(self):
     @score.setter
     def score(self, new_score: int):
 
-        logging.debug('new score: %s', new_score)
+        logger.debug('new score: %s', new_score)
 
         if not isinstance(new_score, int):
             raise ValueError('Score must be an integer')

src/isocomp/Coordinates/create_comparison_windows.py

@@ -8,7 +8,7 @@
 
 from .update_source import update_source
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
+logger = logging.getLogger(__name__)
 
 __all__ = ['create_comparison_windows']
 
@@ -39,7 +39,7 @@ def create_comparison_windows(gtf_list: list,
         transcript_id, gene_id, Cluster
     """
     # check input
-    logging.debug(gtf_list)
+    logger.debug(gtf_list)
     if not isinstance(gtf_list, list):
         raise IOError('pyranges_list must be type list')
     for path in gtf_list:
@@ -67,7 +67,7 @@ def create_comparison_windows(gtf_list: list,
     concat_ranges = concat_ranges[concat_ranges.Feature == feature]
     clustered_ranges = concat_ranges.cluster(**kwargs)
 
-    logging.debug('number of merged ranges: %s',
+    logger.debug('number of merged ranges: %s',
                   str(max(clustered_ranges.Cluster)))
 
     return clustered_ranges

src/isocomp/Coordinates/update_source.py

@@ -4,7 +4,7 @@
 # ext dependencies
 import pyranges as pr
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
+logger = logging.getLogger(__name__)
 
 __all__ = ['update_source']
 

src/isocomp/__init__.py

@@ -1,4 +1,2 @@
 from . import Coordinates
-from . import Compare
-
-__version__ = '0.1.0'
+from . import Compare

src/isocomp/__main__.py

@@ -13,7 +13,7 @@
 from .Coordinates import create_comparison_windows
 from .Compare import find_unique_isoforms
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
+logger = logging.getLogger(__name__)
 
 
 def parse_args() -> Callable[[list], argparse.Namespace]:
@@ -222,7 +222,7 @@ def __fasta_to_fastq(args=None) -> None:
         fasta, a path to a fasta format file. Defaults to None.
     """
 
-    logging.debug(args)
+    logger.debug(args)
 
     for seq in SeqIO.parse(args.fasta, "fasta"):
         seq.letter_annotations["solexa_quality"] = [40] * len(seq)
@@ -242,13 +242,13 @@ def __create_windows_gtfs(args=None) -> None:
         FileExistsError: raised if the output path exists and overwrite is 
         False
     """
-    logging.debug(args)
+    logger.debug(args)
 
     # TODO consider stripping extension, if one is passed, from output_prefix
     output_filename = args.output_prefix+'.gtf' \
         if args.output_prefix \
         else 'clustered_regions.gtf'
-    logging.debug(output_filename)
+    logger.debug(output_filename)
 
     if os.path.exists(output_filename) and not args.overwrite:
         raise FileExistsError(f'file with name {output_filename} already '
@@ -277,7 +277,7 @@ def __find_unique_isoforms(args=None) -> None:
         column names
     """
 
-    logging.debug(args)
+    logger.debug(args)
 
     for path in [args.clustered_gtf, args.fasta_map]:
         if not os.path.exists(path):
@@ -287,7 +287,7 @@ def __find_unique_isoforms(args=None) -> None:
     output_filename = args.output_prefix+'.csv' \
         if args.output_prefix \
         else 'unique_isoforms.csv'
-    logging.debug(output_filename)
+    logger.debug(output_filename)
 
     if os.path.exists(output_filename) and not args.overwrite:
         raise FileExistsError(f'file with name {output_filename} already '
@@ -357,8 +357,8 @@ def main(args=None) -> None:
     }
     dictConfig(log_config)
     # log the cmd line arguments at the debug level
-    logging.debug(sys.argv)
-    logging.debug(str(args))
+    logger.debug(sys.argv)
+    logger.debug(str(args))
 
     # note that this works b/c the subparser set_defaults function attribute
     # is set.

src/isocomp/utils/fasta_to_fastq.py

@@ -3,7 +3,7 @@
 # external dependencies
 from Bio import SeqIO
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
+logger = logging.getLogger(__name__)
 
 __all__ = ['fasta_to_fastq']
 
@@ -16,7 +16,7 @@ def fasta_to_fastq(fasta_file: str) -> None:
         fasta_file (str): path to a fasta file
     """
 
-    logging.debug(fasta_file)
+    logger.debug(fasta_file)
 
     for seq in SeqIO.parse(fasta_file, "fasta"):
         seq.letter_annotations["solexa_quality"] = [40] * len(seq)