---
name: "popfile-insert"
section: "8"
platform: "linux"
package: "popfile"
version: "0.22.4-1.2"
release: "Debian 6.0 (Squeeze)"
platforms: ["linux"]
url: "https://new.carta.tech/popfile-insert"
---

# popfile-insert(8)

feeds sample emails to a specified bucket to train POPFile

## NAME

popfile-insert - feeds sample emails to a specified bucket to train POPFile

## SYNOPSIS

**popfile-insert** \<*bucketname*\> \<*files*\> ...

## DESCRIPTION

The insert.pl script provides a way to train your corpus by feeding it sample emails for a particular bucket. Those emails are parsed and internally **reclassified** to the bucket you specify.

If you use this script to train POPFile via email samples, be careful about sample size. We do **not** recommend you submit thousands of emails to the script, you will end up with a huge corpus that offers little additional benefit to classification accuracy. Your best approach would be to stick to small representative samples of at most 100 emails per bucket.

## SEE ALSO

[**popfile-bayes**(8)](/popfile-bayes/8.md), [**popfile-pipe**(8)](/popfile-pipe/8.md).\

## AUTHOR

This manual page was written by Lucas Wall \<lwall@debian.org\>, for the Debian project (but may be used by others).