MRG: add --detection-column-name to presence_filter; other minor updates (#83)

* WIP: add `detection-column-name`

* minor fixes

* bump version

* oops

Author: ctb

README.md

@@ -459,14 +459,14 @@ sourmash sig cat sketches/{2,47,48,49,51,52,53,59,60,63}.sig.zip \
     -o 10sketches.sig.zip
 sourmash scripts pairwise 10sketches.sig.zip --write-all -o 10sketches.pairwise.csv
 
-sourmash scripts tree --pairwise 10sketches.pairwise.csv --save-image 10sketches.pairwise-cmp.tree.png
+sourmash scripts tree --pairwise 10sketches.pairwise.csv -o 10sketches.pairwise-cmp.tree.png
 ```
 
 and each will produce this plot:
 
 ![neighbor joining tree](examples/disttree10sketches.pairwise.png)
 
- To output the image to a file, specify the file name with `-o` and use your desired filetype extension (.html, .png, .jpg, .jpeg, .pdf, or .svg). To save the tree in newick format, use `--newick` and specify a file ending with '.nwk'. To open an interactive viewer for the tree file, use `--show`. Note: this requires an X display; do not use it without display capacity, as is will cause the tree command to fail.
+ To output the image to a file, specify the file name with `-o` and use your desired filetype extension (.html, .png, .jpg, .jpeg, .pdf, or .svg). To save the tree in newick format, use `--newick` and specify a file ending with '.nwk'. To open an interactive viewer for the tree file, use `--show`. Note: this requires an X display; do not use it without display capacity, as it will cause the tree command to fail.
 
 ### `treemap` - plot a treemap summary of a taxonomy
 

pyproject.toml

@@ -3,7 +3,7 @@ name = "sourmash_plugin_betterplot"
 description = "sourmash plugin for improved plotting/viz and cluster examination."
 readme = "README.md"
 requires-python = ">=3.11"
-version = "0.5.3"
+version = "0.5.4"
 
 # note: "legacy_cgi" is currently needed for ete3, but may need to be changed on next ete release, see: https://github.com/etetoolkit/ete/issues/780
 dependencies = ["sourmash>=4.9.2,<5", "sourmash_utils>=0.2",

src/sourmash_plugin_betterplot.py

@@ -1670,6 +1670,8 @@ def __init__(self, subparser):
                                help='detection threshold (default: None)')
         subparser.add_argument('--detection', action="store_true",
                                default=True)
+        subparser.add_argument('--detection-column-name',
+                               default='f_match_orig')
         subparser.add_argument('--ani', dest='detection',
                                action="store_false")
         subparser.add_argument('--green-color',
@@ -1701,11 +1703,11 @@ def main(self, args):
             notify(f"filtered down to {len(df)} rows with match_containment_ani >= {args.min_ani} (--min-ani)")
 
         if args.min_fraction:
-            df = df[df['f_match_orig'] >= args.min_fraction]
-            notify(f"filtered down to {len(df)} rows with f_match_orig >= {args.min_fraction} (--min-fraction)")
+            df = df[df[args.detection_column_name] >= args.min_fraction]
+            notify(f"filtered down to {len(df)} rows with {args.detection_column_name} >= {args.min_fraction} (--min-fraction)")
 
         if args.detection:
-            plt.plot(df.f_match_orig, df.average_abund, 'k.')
+            plt.plot(df[args.detection_column_name], df.average_abund, 'k.')
         else:
             plt.plot(df.match_containment_ani, df.average_abund, 'k.')