neleval compare-measures
¶
Calculate statistics of measure distribution over systems
Usage summary¶
$ neleval compare-measures --help
usage: neleval compare-measures [-h] (-g GOLD | -e) [-f {plot,none,json,tab}]
[-o OUT_FMT] [--figsize FIGSIZE] [-m NAME]
[-s {none,name,eigen,mds}] [--cmap CMAP]
[--label-map LABEL_MAP]
FILE [FILE ...]
Calculate statistics of measure distribution over systems
positional arguments:
FILE
optional arguments:
-h, --help show this help message and exit
-g GOLD, --gold GOLD
-e, --evaluation-files
System paths are the tab-formatted outputs of the
evaluate command, rather than system outputs
-f {plot,none,json,tab}, --fmt {plot,none,json,tab}
-o OUT_FMT, --out-fmt OUT_FMT
Path template for saving plots with --fmt=plot
(default: ./{}.pdf))
--figsize FIGSIZE The width,height of a figure in inches (default 8,6)
-m NAME, --measure NAME
Which measures to use: specify a name (or group name)
from the list-measures command. This flag may be
repeated.
-s {none,name,eigen,mds}, --sort-by {none,name,eigen,mds}
For plot, sort by name, eigenvalue, or
multidimensional scaling (requires scikit-learn)
--cmap CMAP
--label-map LABEL_MAP
JSON (or file) mapping internal labels to display
labels