You are viewing a plain text version of this content. The canonical link for it is here.
Posted to users@spamassassin.apache.org by Roman Gelfand <rg...@gmail.com> on 2015/04/14 16:44:42 UTC
Re-training
I received an email which is based on score ham. I would like to train the
bayes db to consider this email as spam. Is it possible to retrain bayes
db for just that email without having that email available by providing
something like mail id.
Thanks in advance
Re: Re-training
Posted by RW <rw...@googlemail.com>.
On Thu, 16 Apr 2015 12:18:21 -0400
Roman Gelfand wrote:
> Does sa-learn need read write access to emails or read only will do?
Just read access.
> In case of false negative, should I use --forget option to retrain?
There's no need for that, it will work out what to do for itself.
Re: Re-training
Posted by Roman Gelfand <rg...@gmail.com>.
Does sa-learn need read write access to emails or read only will do?
In case of false negative, should I use --forget option to retrain?
On Tue, Apr 14, 2015 at 10:48 AM, Axb <ax...@gmail.com> wrote:
> On 04/14/2015 04:44 PM, Roman Gelfand wrote:
>
>> I received an email which is based on score ham. I would like to train
>> the
>> bayes db to consider this email as spam. Is it possible to retrain bayes
>> db for just that email without having that email available by providing
>> something like mail id.
>>
>
> you need the msg - without it you can't train.
>
> see:
>
> https://spamassassin.apache.org/full/3.4.x/doc/sa-learn.txt
>
>
>
Re: Re-training
Posted by Axb <ax...@gmail.com>.
On 04/14/2015 04:44 PM, Roman Gelfand wrote:
> I received an email which is based on score ham. I would like to train the
> bayes db to consider this email as spam. Is it possible to retrain bayes
> db for just that email without having that email available by providing
> something like mail id.
you need the msg - without it you can't train.
see:
https://spamassassin.apache.org/full/3.4.x/doc/sa-learn.txt