v1.0.1

codecov.yml

@@ -0,0 +1,4 @@
+coverage:
+  patch:
+    target: 78%
+    informational: true

krakenparser/__init__.py

@@ -1,6 +1,6 @@
+from .kpplot.clustermap import clustermap
 from .kpplot.stackedbar import stacked_barplot
 from .kpplot.streamgraph import streamgraph
-from .kpplot.clustermap import clustermap
 
 __all__ = [
     "stacked_barplot",

krakenparser/counts/convert2csv.py

@@ -3,6 +3,7 @@
 import argparse
 import logging
 from pathlib import Path
+
 import pandas as pd
 
 _log = logging.getLogger(__name__)

krakenparser/counts/processing_script.py

@@ -1,17 +1,16 @@
 #!/usr/bin/env python
 
+import argparse
 import os
-import sys
 import tempfile
-import argparse
 from pathlib import Path
 
 
 def modify_taxa_names(line):
     prefixes = ["s__", "g__", "f__", "o__", "c__", "p__"]
     for prefix in prefixes:
         if line.startswith(prefix):
-            parts = line[len(prefix):].split("\t")
+            parts = line[len(prefix) :].split("\t")
             parts[0] = parts[0].replace("_", " ")
             return "\t".join(parts)
     return line

krakenparser/counts/split_mpa.py

@@ -7,28 +7,27 @@
 import argparse
 import logging
 import re
-import sys
 from pathlib import Path
 
 _log = logging.getLogger(__name__)
 
 
 _RANKS = [
     ("species", "s__", []),
-    ("genus",   "g__", ["s__"]),
-    ("family",  "f__", ["s__", "g__"]),
-    ("order",   "o__", ["s__", "g__", "f__"]),
-    ("class",   "c__", ["s__", "g__", "f__", "o__"]),
-    ("phylum",  "p__", ["s__", "g__", "f__", "o__", "c__"]),
+    ("genus", "g__", ["s__"]),
+    ("family", "f__", ["s__", "g__"]),
+    ("order", "o__", ["s__", "g__", "f__"]),
+    ("class", "c__", ["s__", "g__", "f__", "o__"]),
+    ("phylum", "p__", ["s__", "g__", "f__", "o__", "c__"]),
 ]
 
 _HUMAN_TAXA = {
     "species": "s__Homo_sapiens",
-    "genus":   "g__Homo",
-    "family":  "f__Hominidae",
-    "order":   "o__Primates",
-    "class":   "c__Mammalia",
-    "phylum":  "p__Chordata",
+    "genus": "g__Homo",
+    "family": "f__Hominidae",
+    "order": "o__Primates",
+    "class": "c__Mammalia",
+    "phylum": "p__Chordata",
 }
 
 _ACCESSION_RE = re.compile(r"(SRS|SRR|SRX|ERS|ERR|ERX|DRS|DRR|DRX)\d*-")
@@ -41,7 +40,7 @@ def _strip_path_prefix(line: str) -> str:
         return line
     path, rest = line[:tab], line[tab:]
     pipe = path.rfind("|")
-    segment = path[pipe + 1:] if pipe != -1 else path
+    segment = path[pipe + 1 :] if pipe != -1 else path
     return _ACCESSION_RE.sub("", segment + rest)
 
 
@@ -105,7 +104,12 @@ def main() -> None:
         help="Do not filter human-related taxa (default: filtered)",
     )
     args = parser.parse_args()
-    split_mpa(args.input, args.output, viruses_only=args.viruses_only, keep_human=args.keep_human)
+    split_mpa(
+        args.input,
+        args.output,
+        viruses_only=args.viruses_only,
+        keep_human=args.keep_human,
+    )
 
 
 if __name__ == "__main__":

krakenparser/kpplot/base.py

@@ -1,6 +1,7 @@
+from typing import Optional
+
 import matplotlib.pyplot as plt
 import pandas as pd
-from typing import Optional
 
 
 class KpPlotBase:
@@ -44,9 +45,7 @@ def aggregate_by_metadata(
         raise ValueError("metadata must contain 'Sample_id' column")
     if metadata_group not in metadata.columns:
         raise ValueError(f"'{metadata_group}' column not found in metadata")
-    df = df.merge(
-        metadata[["Sample_id", metadata_group]], on="Sample_id", how="left"
-    )
+    df = df.merge(metadata[["Sample_id", metadata_group]], on="Sample_id", how="left")
     df = (
         df.groupby([metadata_group, "taxon"], as_index=False)["rel_abund_perc"]
         .mean()

krakenparser/kpplot/clustermap.py

@@ -1,7 +1,9 @@
-import pandas as pd
+from typing import List, Optional, Tuple
+
 import matplotlib.pyplot as plt
+import pandas as pd
 import seaborn as sns
-from typing import Optional, Tuple, Union, List
+
 from .base import KpPlotBase, aggregate_by_metadata
 
 

krakenparser/kpplot/stackedbar.py

@@ -1,8 +1,10 @@
-import pandas as pd
+from typing import List, Optional, Tuple, Union
+
 import matplotlib.pyplot as plt
-import seaborn as sns
 import numpy as np
-from typing import Optional, Tuple, Union, List
+import pandas as pd
+import seaborn as sns
+
 from .base import KpPlotBase, aggregate_by_metadata
 
 

krakenparser/kpplot/streamgraph.py

@@ -1,8 +1,10 @@
-import pandas as pd
+from typing import List, Optional, Tuple, Union
+
 import matplotlib.pyplot as plt
-import seaborn as sns
 import numpy as np
-from typing import Optional, Tuple, Union, List
+import pandas as pd
+import seaborn as sns
+
 from .base import KpPlotBase, aggregate_by_metadata
 
 

krakenparser/krakenparser.py

@@ -1,9 +1,11 @@
 import argparse
 import logging
 import subprocess
-from pathlib import Path
 import sys
-from importlib.metadata import version as _pkg_version, PackageNotFoundError as _PNF
+from importlib.metadata import PackageNotFoundError as _PNF
+from importlib.metadata import version as _pkg_version
+from pathlib import Path
+
 try:
     __version__ = _pkg_version("krakenparser")
 except _PNF:
@@ -78,23 +80,28 @@ def main():
 
     # Map flags to (script_path, base_args_to_prepend)
     command_map = {
-        "complete":           (package_dir / "pipeline.py",                      []),
-        "kreport2mpa":        (package_dir / "mpa" / "transform2mpa.py",         []),
-        "combine_mpa":        (package_dir / "mpa" / "mpa_table.py",             []),
-        "deconstruct":        (package_dir / "counts" / "split_mpa.py",          []),
-        "deconstruct_viruses":(package_dir / "counts" / "split_mpa.py",          ["--viruses-only"]),
-        "process":            (package_dir / "counts" / "processing_script.py",  []),
-        "txt2csv":            (package_dir / "counts" / "convert2csv.py",        []),
-        "relabund":           (package_dir / "stats" / "relabund.py",            []),
-        "diversity":          (package_dir / "stats" / "diversity.py",           []),
+        "complete": (package_dir / "pipeline.py", []),
+        "kreport2mpa": (package_dir / "mpa" / "transform2mpa.py", []),
+        "combine_mpa": (package_dir / "mpa" / "mpa_table.py", []),
+        "deconstruct": (package_dir / "counts" / "split_mpa.py", []),
+        "deconstruct_viruses": (
+            package_dir / "counts" / "split_mpa.py",
+            ["--viruses-only"],
+        ),
+        "process": (package_dir / "counts" / "processing_script.py", []),
+        "txt2csv": (package_dir / "counts" / "convert2csv.py", []),
+        "relabund": (package_dir / "stats" / "relabund.py", []),
+        "diversity": (package_dir / "stats" / "diversity.py", []),
     }
 
     if "-h" in sys.argv or "--help" in sys.argv:
         if not any(getattr(args, key) for key in command_map):
             parser.print_help()
             return
 
-    def _build_cmd(script: Path, base_args: list[str], user_args: list[str]) -> list[str]:
+    def _build_cmd(
+        script: Path, base_args: list[str], user_args: list[str]
+    ) -> list[str]:
         if script.suffix == ".py":
             # Run as module (-m) so the krakenparser package stays importable.
             # Derive dotted module name from path relative to the package root.
@@ -113,7 +120,9 @@ def _build_cmd(script: Path, base_args: list[str], user_args: list[str]) -> list
     # Default to full pipeline when -i/--input is given without a subcommand
     if "-i" in extra_args or "--input" in extra_args:
         complete_script, complete_base = command_map["complete"]
-        subprocess.run(_build_cmd(complete_script, complete_base, extra_args), check=True)
+        subprocess.run(
+            _build_cmd(complete_script, complete_base, extra_args), check=True
+        )
         return
 
     parser.print_help()

krakenparser/mpa/mpa_table.py

@@ -53,13 +53,18 @@ def main() -> None:
         description="Combine MPA files into a single tab-delimited table."
     )
     parser.add_argument(
-        "-i", "--input",
-        required=True, nargs="+", dest="in_files",
+        "-i",
+        "--input",
+        required=True,
+        nargs="+",
+        dest="in_files",
         help="Input MPA files (one per sample)",
     )
     parser.add_argument(
-        "-o", "--output",
-        required=True, dest="o_file",
+        "-o",
+        "--output",
+        required=True,
+        dest="o_file",
         help="Output merged MPA file",
     )
     args = parser.parse_args()

krakenparser/mpa/transform2mpa.py

@@ -8,8 +8,14 @@
 
 # Maps Kraken2 single-letter rank codes to MPA prefixes
 _RANK_PREFIX = {
-    "D": "d", "K": "k", "P": "p", "C": "c",
-    "O": "o", "F": "f", "G": "g", "S": "s",
+    "D": "d",
+    "K": "k",
+    "P": "p",
+    "C": "c",
+    "O": "o",
+    "F": "f",
+    "G": "g",
+    "S": "s",
 }
 
 
@@ -96,9 +102,7 @@ def kreport_to_mpa(
 
             # Build the full MPA path; omit intermediate (x__) segments when not requested
             path = "|".join(
-                seg
-                for (_, seg, std) in stack
-                if include_intermediate or std
+                seg for (_, seg, std) in stack if include_intermediate or std
             )
 
             value = str(cum_reads) if use_reads else str(pct)
@@ -112,55 +116,71 @@ def main() -> None:
 
     mode = parser.add_mutually_exclusive_group(required=True)
     mode.add_argument(
-        "-r", "--report-file", "--report",
+        "-r",
+        "--report-file",
+        "--report",
         dest="r_file",
         help="Single input Kraken2 report file",
     )
     mode.add_argument(
-        "-i", "--input",
+        "-i",
+        "--input",
         dest="input_dir",
         help="Input directory containing Kraken2 report files (batch mode)",
     )
 
     parser.add_argument(
-        "-o", "--output",
-        required=True, dest="o_file",
+        "-o",
+        "--output",
+        required=True,
+        dest="o_file",
         help="Output MPA file (single mode) or output directory (batch mode)",
     )
     parser.add_argument(
         "--display-header",
-        action="store_true", dest="add_header", default=False,
+        action="store_true",
+        dest="add_header",
+        default=False,
         help="Write a header line with the sample name (filename)",
     )
     parser.add_argument(
         "--read_count",
-        action="store_true", dest="use_reads", default=True,
+        action="store_true",
+        dest="use_reads",
+        default=True,
         help="Output clade read counts [default]",
     )
     parser.add_argument(
         "--percentages",
-        action="store_false", dest="use_reads",
+        action="store_false",
+        dest="use_reads",
         help="Output percentages instead of read counts",
     )
     parser.add_argument(
         "--intermediate-ranks",
-        action="store_true", dest="x_include", default=False,
+        action="store_true",
+        dest="x_include",
+        default=False,
         help="Include non-standard taxonomic ranks in output",
     )
     parser.add_argument(
         "--no-intermediate-ranks",
-        action="store_false", dest="x_include",
+        action="store_false",
+        dest="x_include",
         help="Exclude non-standard taxonomic ranks [default]",
     )
     group = parser.add_mutually_exclusive_group()
     group.add_argument(
         "--remove-spaces",
-        action="store_true", dest="remove_spaces", default=True,
+        action="store_true",
+        dest="remove_spaces",
+        default=True,
         help="Replace spaces with underscores in taxon names [default]",
     )
     group.add_argument(
         "--keep-spaces",
-        action="store_false", dest="remove_spaces",
+        action="store_false",
+        dest="remove_spaces",
         help="Keep spaces in taxon names",
     )
     args = parser.parse_args()