Housekeeping

env_osx64.yml

@@ -10,5 +10,10 @@ dependencies:
   - wand  # Python bindings for ImageMagick
   - pip
   - pip:
+      - black
       - hatch
+      - mock
       - pytest
+      - pytest-benchmark
+      - pytest-cov
+      - PyYAML

environment.yml

@@ -10,5 +10,10 @@ dependencies:
   - wand  # Python bindings for ImageMagick
   - pip
   - pip:
-      - pytest
+      - black
       - hatch
+      - mock
+      - pytest
+      - pytest-benchmark
+      - pytest-cov
+      - PyYAML

pyproject.toml

@@ -34,6 +34,7 @@ classifiers = [
 
 dependencies = [
     "biopython",
+    "bitarray",
     "boto3",
     "brewer2mpl",
     "CrossMap",
@@ -50,18 +51,34 @@ dependencies = [
     "more-itertools",
     "natsort",
     "networkx",
-    "numpy<2",
+    "numpy",
     "ortools",
     "pybedtools",
     "pyefd",
+    "pyfasta",
+   #"pygraphviz",
+    "pyliftover",
     "pypdf",
+    "pysam",
     "pytesseract",
     "rich",
     "scikit-image",
     "scipy",
     "seaborn",
+    "segment_anything",
     "Wand",
     "webcolors",
+    #"BCBio",
+    #"BeautifulSoup",
+    #"cyvcf2",
+    #"gurobipy",
+    #"hmmlearn",
+    #"holoviews",
+    #"hvplot",
+    #"matplotlib_venn",
+    #"sklearn",
+    #"xlrd",
+    #"xlwt",
 ]
 
 dynamic = ["version"]

src/jcvi/algorithms/lpsolve.py

@@ -420,11 +420,11 @@ def has_ortools() -> bool:
     Returns:
         bool: True if installed
     """
-    try:
-        from ortools.linear_solver import pywraplp
+    import importlib.util
 
+    if importlib.util.find_spec("ortools.linear_solver.pywraplp") is not None:
         return True
-    except ImportError:
+    else:
         return False
 
 

src/jcvi/annotation/pasa.py

@@ -469,7 +469,7 @@ def consolidate(args):
         gene = "gene_{0:0{pad}}".format(i, pad=6) if mode == "coords" else None
 
         for elem in locus:
-            if type(elem) == tuple:
+            if isinstance(elem, tuple):
                 _gene, dbn = elem
                 if gene is None:
                     gene = _gene

src/jcvi/apps/base.py

@@ -26,12 +26,9 @@
 from socket import gethostname
 from subprocess import CalledProcessError, PIPE, call, check_output
 from time import ctime
-from typing import Any, Collection, List, Optional, Tuple, Union
+from typing import Collection, List, Optional, Tuple, Union
 from urllib.parse import urlencode
 
-# from optparse import OptionParser as OptionP, OptionGroup, SUPPRESS_HELP
-
-
 from natsort import natsorted
 from rich.console import Console
 from rich.logging import RichHandler
@@ -122,7 +119,7 @@ def dispatch(self, globals):
 
         action = sys.argv[1]
 
-        if not action in self.valid_actions:
+        if action not in self.valid_actions:
             print("[error] {0} not a valid {1}\n".format(action, meta), file=sys.stderr)
             alt = get_close_matches(action, self.valid_actions)
             print(
@@ -1000,7 +997,7 @@ def set_home(self, prog, default=None):
         if default is None:  # Last attempt at guessing the path
             try:
                 default = op.dirname(which(prog))
-            except:
+            except Exception:
                 default = None
         else:
             default = op.expanduser(default)
@@ -1029,7 +1026,7 @@ def ConfigSectionMap(Config, section):
             cfg[option] = Config.get(section, option)
             if cfg[option] == -1:
                 logger.debug("Skip: %s", option)
-        except:
+        except Exception:
             logger.error("Exception on %s", option)
             cfg[option] = None
     return cfg
@@ -1318,7 +1315,7 @@ def mkdir(dirname, overwrite=False):
     else:
         try:
             os.mkdir(dirname)
-        except:
+        except Exception:
             os.makedirs(dirname)
         logger.debug("`%s` not found. Creating new.", dirname)
 

src/jcvi/apps/phylo.py

@@ -275,7 +275,7 @@ def smart_reroot(treefile, outgroupfile, outfile, format=0):
     try:
         tree.set_outgroup(tree.get_common_ancestor(*outgroup))
     except ValueError:
-        assert type(outgroup) == list
+        assert isinstance(outgroup, list)
         outgroup = outgroup[0]
         tree.set_outgroup(outgroup)
     tree.write(outfile=outfile, format=format)
@@ -481,7 +481,7 @@ def SH_raxml(reftree, querytree, phy_file, shout="SH_out.txt"):
     # hard coded
     try:
         pval = re.search("(Significantly.*:.*)", o).group(0)
-    except:
+    except Exception:
         print("SH test failed.", file=sys.stderr)
     else:
         pval = pval.strip().replace("\t", " ").replace("%", "\%")
@@ -946,7 +946,7 @@ def build(args):
             outfile, phy_file = build_nj_phylip(
                 alignment, outfile=out_file, outgroup=outgroup, work_dir=treedir
             )
-        except:
+        except Exception:
             print("NJ tree cannot be built for {0}".format(dna_file))
 
         if opts.SH:
@@ -964,15 +964,15 @@ def build(args):
                 outfile, phy_file = build_ml_phyml(
                     alignment, outfile=out_file, work_dir=treedir
                 )
-            except:
+            except Exception:
                 print("ML tree cannot be built for {0}".format(dna_file))
 
         elif opts.ml == "raxml":
             try:
                 outfile, phy_file = build_ml_raxml(
                     alignment, outfile=out_file, work_dir=treedir
                 )
-            except:
+            except Exception:
                 print("ML tree cannot be built for {0}".format(dna_file))
 
         if outgroup:

src/jcvi/apps/uclust.py

@@ -599,6 +599,7 @@ def consensus(args):
         RAD = stack(S)
 
         if len(data) == 1:  # No computation needed
+            # TODO: seq is not defined!
             output.append((fname, seq))
             bins.extend(RAD)
             start = end

src/jcvi/apps/wga2ribbon.py

@@ -8,12 +8,7 @@
 
 from collections import namedtuple
 from jcvi.graphics.base import AbstractLayout
-from operator import attrgetter
 import argparse
-import glob
-import os
-import shutil
-import sys
 
 
 def mainArgs():

src/jcvi/assembly/hic.py

@@ -680,7 +680,6 @@ def generate_groups(groupsfile):
     Args:
         groupsfile (str): Path to the groups file
     """
-    data = []
     with open(groupsfile) as fp:
         for row in fp:
             seqids, color = row.split()

src/jcvi/compara/fractionation.py

@@ -381,7 +381,7 @@ def gaps(args):
     not_in_gaps = popen(cmd).read()
     not_in_gaps = int(not_in_gaps)
     in_gaps = total - not_in_gaps
-    print("Ids in gaps: {1}".format(total, percentage(in_gaps, total)), file=sys.stderr)
+    print("Ids in gaps: {0}".format(percentage(in_gaps, total)), file=sys.stderr)
 
 
 def get_tags(idsfile):

src/jcvi/compara/quota.py

@@ -124,7 +124,7 @@ def create_data_model(nodes, constraints_x, qa, constraints_y, qb):
     num_constraints = len(constraints_x)
 
     # non-self
-    if not (constraints_x is constraints_y):
+    if constraints_x is not constraints_y:
         for c in constraints_y:
             constraint_coeffs.append({x: 1 for x in c})
             bounds.append(qb)

src/jcvi/compara/reconstruct.py

@@ -76,6 +76,7 @@ def fuse(args):
 
     Fuse gene orders based on anchors file.
     """
+    # TODO: BiGraph is not used
     from jcvi.algorithms.graph import BiGraph
 
     p = OptionParser(fuse.__doc__)

src/jcvi/compara/synteny.py

@@ -564,7 +564,6 @@ def assemble(args):
     Contents after the 3rd field (end gene) are ignored. Using the example
     above, the final .blocks file will contain 5 columns, one column for each line.
     """
-    import shutil
     from tempfile import mkdtemp, mkstemp
 
     from jcvi.apps.align import last

src/jcvi/formats/bed.py

@@ -1257,9 +1257,9 @@ def fix(args):
         ntotal += 1
 
     if nfixed:
-        logger.debug("Total fixed: %s".format(percentage(nfixed, ntotal)))
+        logger.debug("Total fixed: %s", percentage(nfixed, ntotal))
     if nfiltered:
-        logger.debug("Total filtered: %s".format(percentage(nfiltered, ntotal)))
+        logger.debug("Total filtered: %s", percentage(nfiltered, ntotal))
 
 
 def some(args):
@@ -1307,7 +1307,7 @@ def some(args):
             print(b, file=fw)
 
     fw.close()
-    logger.debug("Stats: %s features kept.".format(percentage(nkeep, ntotal)))
+    logger.debug(f"Stats: {percentage(nkeep, ntotal)} features kept.")
 
 
 def uniq(args):

src/jcvi/formats/fasta.py

@@ -1596,7 +1596,7 @@ def diff(args):
                 printf("[green]Two sequence size match ({})".format(asize))
             else:
                 printf(
-                    "[red]Two sequence size do not match ({}, {}})".format(asize, bsize)
+                    "[red]Two sequence size do not match ({}, {})".format(asize, bsize)
                 )
 
         # print out the first place the two sequences diff

src/jcvi/formats/gff.py

@@ -1037,6 +1037,7 @@ def gb(args):
     <http://www.biostars.org/p/2492/>
     """
     try:
+        # TODO: remove this dependency. Could maybe substitute with BioPython
         from BCBio import GFF
     except ImportError:
         print(

src/jcvi/formats/obo.py

@@ -10,7 +10,7 @@
 
 from collections import deque
 from functools import partial
-from typing import IO, Optional
+from typing import IO, Optional, Tuple
 
 from goatools.obo_parser import GODag
 
@@ -22,7 +22,7 @@
 )
 
 
-def load_GODag(obo_url: str, prt: Optional[IO] = None) -> (GODag, str):
+def load_GODag(obo_url: str, prt: Optional[IO] = None) -> Tuple[GODag, str]:
     """
     Load given obo url and returns GODag object.
 

src/jcvi/graphics/base.py

@@ -322,24 +322,6 @@ def update_figname(figname: str, format: str) -> str:
     return figname + "." + format
 
 
-def update_figname(figname: str, format: str) -> str:
-    """Update the name of a figure to include the format.
-
-    Args:
-        figname (str): Path to the figure
-        format (str): Figure format, must be one of GRAPHIC_FORMATS
-
-    Returns:
-        str: New file path
-    """
-    _, ext = op.splitext(figname)
-    if ext.strip(".") in GRAPHIC_FORMATS:  # User suffix has precedence
-        return figname
-    # When the user has not supplied a format in the filename, use the requested format
-    assert format in GRAPHIC_FORMATS, "Invalid format"
-    return figname + "." + format
-
-
 def savefig(figname, dpi=150, iopts=None, cleanup=True, transparent=False):
     try:
         format = figname.rsplit(".", 1)[-1].lower()
@@ -507,7 +489,7 @@ def asciiplot(x, y, digit=1, width=50, title=None, char="="):
     ay = np.array(y)
 
     if title:
-        print("[bold white]".format(title), file=sys.stderr)
+        print("[bold white]{}".format(title), file=sys.stderr)
 
     az = ay * width // ay.max()
     tx = [asciiaxis(x, digit=digit) for x in ax]

src/jcvi/graphics/tree.py

@@ -492,7 +492,7 @@ def cv(x):
     # Neogene and Cretaceous as these are more relevant for most phylogeny
     if contrast_epochs:
         for era, start, end in Geo:
-            if not era in ("Neogene", "Cretaceous"):
+            if era not in ("Neogene", "Cretaceous"):
                 continue
 
             # Make a beige patch

src/jcvi/utils/cbook.py

@@ -346,7 +346,7 @@ def seqid_parse(seqid, sep=["-"], stdpf=True):
 
     if sep is None:
         sep = [""]
-    elif type(sep) == str:
+    elif isinstance(sep, str):
         sep = [sep]
 
     prefix = seqid[:lastnumi]

src/jcvi/variation/cnv.py

@@ -4,7 +4,6 @@
 """
 Helper functions for Copy Number Variations (CNV).
 """
-import logging
 import os.path as op
 import sys