summaryrefslogtreecommitdiff
path: root/examples
diff options
context:
space:
mode:
authorDaniel Friesel <daniel.friesel@uos.de>2022-09-29 14:57:00 +0200
committerDaniel Friesel <daniel.friesel@uos.de>2022-09-29 14:57:00 +0200
commite3e247fcb6b8bf89af36cb149c670d40e47a01d9 (patch)
treed73b69d3c74cb679b4955a2fcca87c7a8c266b37 /examples
parent2a9e7be2dcaa2f19ce520eb149f7ee53f9f3d7b3 (diff)
examples/busybox: Add model generation instructions
Diffstat (limited to 'examples')
-rwxr-xr-xexamples/busybox.sh8
1 files changed, 8 insertions, 0 deletions
diff --git a/examples/busybox.sh b/examples/busybox.sh
index 22a7561..f1baff1 100755
--- a/examples/busybox.sh
+++ b/examples/busybox.sh
@@ -101,4 +101,12 @@ Alternatively, you can run multiple build processes in parallel.
> cd data
> for i in {1..10}; do ../dfatool/bin/explore-kconfig.py --random 1000 ../busybox-build-\${i} & done
+Once everything is done, you have various options for generating a kconfig-webconf performance model.
+To do so, call bin/analyze-kconfig.py from the data directory.
+For example, to generate a CART:
+
+> DFATOOL_DTREE_SKLEARN_CART=1 DFATOOL_PARAM_CATEGORIAL_TO_SCALAR=1 DFATOOL_KCONF_IGNORE_STRING=1 DFATOOL_KCONF_WITH_CHOICE_NODES=0 ~/var/ess/aemr/dfatool/bin/analyze-kconfig.py --force-tree --skip-param-stats --export-webconf /tmp/busybox-cart.json ../busybox-1.35.0/Kconfig .
+
+By adding the option "--cross-validation kfold:10", you can determine the model prediction error.
+
__EOF__