Merge pull request #190 from tleonardi/release_v1.0.4

Release v1.0.4
tleonardi · May 27, 2021 · 20c0b53 · 20c0b53
2 parents 62a8bf4 + 05c1b28
commit 20c0b53
Show file tree

Hide file tree

Showing 8 changed files with 72 additions and 38 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,6 +1,11 @@
 # Changelog
 
 
+## v1.0.4
+
+### Fixed
+- Fixed logging levels and verbosity of log messages
+
 ## v1.0.3
 
 ### Fixed

diff --git a/nanocompore/Eventalign_collapse.py b/nanocompore/Eventalign_collapse.py
@@ -106,12 +106,17 @@ def __call__(self):
             for tb in iter(error_q.get, None):
                 logger.trace("Error caught from error_q")
                 raise NanocomporeError(tb)
+            logger.debug("Caught poison pill in error queue")
 
             # Soft processes and queues stopping
+            logger.debug("Joining all processes")
             for ps in ps_list:
                 ps.join()
+            logger.debug("All processes were joined")
+            logger.debug("Closing all queues")
             for q in (in_q, out_q, error_q):
                 q.close()
+            logger.debug("All queues were closed")
 
         # Catch error, kill all processed and reraise error
         except Exception as E:

diff --git a/nanocompore/SampComp.py b/nanocompore/SampComp.py
@@ -217,14 +217,20 @@ def __call__(self):
 
             # Monitor error queue
             for tb in iter(error_q.get, None):
-                logger.trace("Error caught from error_q")
+                logger.debug("Error caught from error_q")
                 raise NanocomporeError(tb)
+            logger.debug("Error queue was closed")
 
             # Soft processes and queues stopping
+            logger.debug("Waiting for all processes to be joined")
             for ps in ps_list:
                 ps.join()
+            logger.debug("All processes joined successfully")
+
+            logger.debug("Closing all queues")
             for q in (in_q, out_q, error_q):
                 q.close()
+            logger.debug("All queues were closed")
 
             # Return database wrapper object
             return SampCompDB(

diff --git a/nanocompore/Whitelist.py b/nanocompore/Whitelist.py
@@ -173,33 +173,45 @@ def __read_eventalign_index(self,
                     col_names = fp.readline().rstrip().split()
                     c = Counter()
                     for line in fp:
-                        try:
-                            # Transform line to dict and cast str numbers to actual numbers
-                            read = numeric_cast_dict(keys=col_names, values=line.rstrip().split("\t"))
-
-                            # Filter out ref_id if a select_ref_id list or exclude_ref_id list was provided
-                            if select_ref_id and not read["ref_id"] in select_ref_id:
-                                raise NanocomporeError("Ref_id not in select list")
-                            elif exclude_ref_id and read["ref_id"] in exclude_ref_id:
-                                raise NanocomporeError("Ref_id in exclude list")
-
-                            # Filter out reads with high number of invalid kmers if information available
-                            if self.__filter_invalid_kmers:
-                                if max_invalid_kmers_freq:
-                                    invalid_kmers_freq = (read["NNNNN_kmers"]+read["mismatch_kmers"]+read["missing_kmers"])/read["kmers"]
-                                    if invalid_kmers_freq > max_invalid_kmers_freq:
-                                        raise NanocomporeError("High fraction of invalid kmers ({}%) for read {}".format(round(invalid_kmers_freq*100,2), read["read_id"]))
-                                else:
-                                    NNNNN_kmers_freq = read["NNNNN_kmers"]/read["kmers"]
-                                    max_mismatching_freq = read["mismatch_kmers"]/read["kmers"]
-                                    max_missing_freq = read["missing_kmers"]/read["kmers"]
-                                    if NNNNN_kmers_freq > max_NNNNN_freq:
-                                        raise NanocomporeError("High fraction of NNNNN kmers ({}%) for read {}".format(round(NNNNN_kmers_freq*100,2), read["read_id"]))
-                                    elif max_mismatching_freq > max_mismatching_freq:
-                                        raise NanocomporeError("High fraction of mismatching kmers ({}%) for read {}".format(round(max_mismatching_freq*100,2), read["read_id"]))
-                                    elif max_missing_freq > max_missing_freq:
-                                        raise NanocomporeError("High fraction of missing kmers ({}%) for read {}".format(round(max_missing_freq*100,2), read["read_id"]))
-
+                        # Transform line to dict and cast str numbers to actual numbers
+                        read = numeric_cast_dict(keys=col_names, values=line.rstrip().split("\t"))
+                        read_is_valid = True
+                        # Filter out ref_id if a select_ref_id list or exclude_ref_id list was provided
+                        if select_ref_id and not read["ref_id"] in select_ref_id:
+                            read_is_valid = False
+                            c["Ref_id not in select list"]+=1
+                            logger.trace("Ref_id not in select list")
+                        elif exclude_ref_id and read["ref_id"] in exclude_ref_id:
+                            read_is_valid = False
+                            c["Ref_id in exclude list"]+=1
+                            logger.trace("Ref_id in exclude list")
+
+                        # Filter out reads with high number of invalid kmers if information available
+                        if self.__filter_invalid_kmers:
+                            if max_invalid_kmers_freq:
+                                invalid_kmers_freq = (read["NNNNN_kmers"]+read["mismatch_kmers"]+read["missing_kmers"])/read["kmers"]
+                                if invalid_kmers_freq > max_invalid_kmers_freq:
+                                    read_is_valid = False
+                                    c["High fraction of invalid kmers"]+=1
+                                    logger.trace("High fraction of invalid kmers ({}%) for read {}".format(round(invalid_kmers_freq*100,2), read["read_id"]))
+                            else:
+                                NNNNN_kmers_freq = read["NNNNN_kmers"]/read["kmers"]
+                                max_mismatching_freq = read["mismatch_kmers"]/read["kmers"]
+                                max_missing_freq = read["missing_kmers"]/read["kmers"]
+                                if NNNNN_kmers_freq > max_NNNNN_freq:
+                                    read_is_valid = False
+                                    c["High fraction of NNNNN kmers"]+=1
+                                    logger.trace("High fraction of NNNNN kmers ({}%) for read {}".format(round(NNNNN_kmers_freq*100,2), read["read_id"]))
+                                elif max_mismatching_freq > max_mismatching_freq:
+                                    read_is_valid = False
+                                    c["High fraction of mismatching kmers"]
+                                    logger.trace("High fraction of mismatching kmers ({}%) for read {}".format(round(max_mismatching_freq*100,2), read["read_id"]))
+                                elif max_missing_freq > max_missing_freq:
+                                    read_is_valid = False
+                                    c["High fraction of missing kmers"]+=1
+                                    logger.trace("High fraction of missing kmers ({}%) for read {}".format(round(max_missing_freq*100,2), read["read_id"]))
+
+                        if read_is_valid:
                             # Create dict arborescence and save valid reads
                             if not read["ref_id"] in ref_reads:
                                 ref_reads[read["ref_id"]] = OrderedDict()
@@ -212,9 +224,6 @@ def __read_eventalign_index(self,
                             ref_reads[read["ref_id"]][cond_lab][sample_lab].append(read)
                             c ["valid reads"] += 1
 
-                        except NanocomporeError as E:
-                            c [str(E)] += 1
-
                 logger.debug("\tCondition:{} Sample:{} {}".format(cond_lab, sample_lab, counter_to_str(c)))
         # Fill in missing condition/sample slots in case
         # a ref_id is missing from one of the eventalign files

diff --git a/nanocompore/__init__.py b/nanocompore/__init__.py
@@ -1,10 +1,7 @@
 # -*- coding: utf-8 -*-
 # https://github.com/python-poetry/poetry/pull/2366#issuecomment-652418094
-try:
-    import importlib.metadata as importlib_metadata
-except ModuleNotFoundError:
-    import importlib_metadata
+from nanocompore.common import get_version
 
-__version__ = importlib_metadata.version(__name__)
+__version__ = get_version()
 
 __description__ = 'Software package that identifies raw signal changes between two conditions from https://github.com/jts/nanopolish resquiggled dRNA-Seq data.'
diff --git a/nanocompore/__main__.py b/nanocompore/__main__.py
@@ -153,7 +153,7 @@ def main(args=None):
         sp_output.add_argument("--overwrite", "-w", action='store_true', default=False,
             help="Use --outpath even if it exists already (default: %(default)s)")
         sp_verbosity = sp.add_argument_group("Verbosity options")
-        sp_verbosity.add_argument("--log_level", type=str, default="info", choices=["warning", "info", "debug"],
+        sp_verbosity.add_argument("--log_level", type=str, default="info", choices=["warning", "info", "debug", "trace"],
             help="Set the log level (default: %(default)s)")
         sp_verbosity.add_argument("--progress", default=False, action='store_true',
             help="Display a progress bar during execution (default: %(default)s)")
@@ -213,6 +213,7 @@ def sampcomp_main(args):
     db = s()
 
     # Save all reports
+    logger.info("Saving results")
     if(db):
         db.save_all(pvalue_thr=args.pvalue_thr)
 

diff --git a/nanocompore/common.py b/nanocompore/common.py
@@ -2,6 +2,7 @@
 
 #~~~~~~~~~~~~~~IMPORTS~~~~~~~~~~~~~~#
 # Standard library imports
+import pkg_resources
 import sys
 import os
 from collections import *
@@ -219,3 +220,13 @@ def jhelp (f:"python function or method"):
 
     # Display in Jupyter
     display (Markdown(s))
+
+def get_version():
+    try:
+        distribution = pkg_resources.get_distribution("nanocompore")
+    except pkg_resources.DistributionNotFound:
+        return "dev"  # or "", or None
+        # or try with importib.metadata
+        # or try reading pyproject.toml
+    else:
+        return distribution.version
diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "nanocompore"
-version = "1.0.3"
+version = "1.0.4"
 description = "Software package that identifies raw signal changes between two conditions from https://github.com/jts/nanopolish resquiggled dRNA-Seq data."
 authors = ["Tommaso Leonardi <tom@itm6.xyz>", "Adrien Leger <aleg@ebi.ac.uk>"]
 license = "GPL-3.0"