API: changed default k size to 6

HuttleyLab · Aug 25, 2024 · 1335266 · 1335266
1 parent 316d0f9
commit 1335266
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 9 deletions.
diff --git a/src/divergent/cli.py b/src/divergent/cli.py
@@ -86,7 +86,7 @@ def main():
     type=Path,
     help="path to .dvtgseqs file",
 )
-_k = click.option("-k", type=int, default=3, help="k-mer size")
+_k = click.option("-k", type=int, default=6, help="k-mer size")
 
 
 @main.command(**_click_command_opts)

diff --git a/src/divergent/records.py b/src/divergent/records.py
@@ -636,7 +636,7 @@ def __init__(
         stat: str = "stdev",
         moltype: str = "dna",
         include: list[str] | str | None = None,
-        k: int = 4,
+        k: int = 6,
         seed: int | None = None,
     ) -> None:
         """
@@ -651,7 +651,7 @@ def __init__(
         moltype
             molecular type of the sequences
         include
-            sequence names to include
+            sequence names to include in the final result
         k
             k-mer size
         seed
@@ -660,9 +660,8 @@ def __init__(
         Notes
         -----
         If called with an alignment, the ungapped sequences are used.
-        Sequence order of input is randomised. If include is not None, the
-        named sequences are added to the collection before selecting the
-        divergent set.
+        The order of the sequences is randomised. If include is not None, the
+        named sequences are added to the final result.
         """
         self._s2k = seq_to_seqarray(moltype=moltype) + seqarray_to_kmerseq(
             k=k,
@@ -700,7 +699,7 @@ def __init__(
         n: int = 3,
         moltype: str = "dna",
         include: list[str] | str | None = None,
-        k: int = 4,
+        k: int = 6,
         seed: int | None = None,
     ) -> None:
         """
@@ -713,14 +712,15 @@ def __init__(
         k
             k-mer size
         include
-            sequence names to include
+            sequence names to include in the final result
         seed
             random number seed
 
         Notes
         -----
         If called with an alignment, the ungapped sequences are used.
-        Sequence order of input is randomised.
+        The order of the sequences is randomised. If include is not None, the
+        named sequences are added to the final result.
         """
         self._s2k = seq_to_seqarray(moltype=moltype) + seqarray_to_kmerseq(
             k=k,