On Mon, 23 Feb 2015 00:22:31 +0100
Reindl Harald wrote:
> >> in doubt the amout of trained ham and spam should be near 50%,
> >
> > This is myth. What's important is to have enough of each, the actual
> > ratio is not important.
>
> true - but you don't have much to measure the "enough of each"
Am 23.02.2015 um 00:11 schrieb RW:
On Fri, 20 Feb 2015 21:36:38 +0100
Reindl Harald wrote:
And I'd suggest the same for non-spam, train duplicative ham even
if it happens to be similarly addressed to different users. More
data is (nearly) always better for bayesian learning systems
of course
On Fri, 20 Feb 2015 21:36:38 +0100
Reindl Harald wrote:
>
> > And I'd suggest the same for non-spam, train duplicative ham even
> > if it happens to be similarly addressed to different users. More
> > data is (nearly) always better for bayesian learning systems
>
> of course
With the caveat th
Am 22.02.2015 um 22:31 schrieb @lbutlr:
On 22 Feb 2015, at 07:56 , Reindl Harald wrote:
Am 22.02.2015 um 15:49 schrieb @lbutlr:
plugin: eval failed: bayes: (in learn) locker: safe_lock: cannot create
lockfile /home/kreme/.spamassassin/bayes.mutex: Permission denied
(And yes, that is correct
On 22 Feb 2015, at 07:56 , Reindl Harald wrote:
> Am 22.02.2015 um 15:49 schrieb @lbutlr:
>> plugin: eval failed: bayes: (in learn) locker: safe_lock: cannot create
>> lockfile /home/kreme/.spamassassin/bayes.mutex: Permission denied
>>
>> (And yes, that is correct, the spamassassin files in use
Am 22.02.2015 um 15:49 schrieb @lbutlr:
plugin: eval failed: bayes: (in learn) locker: safe_lock: cannot create
lockfile /home/kreme/.spamassassin/bayes.mutex: Permission denied
(And yes, that is correct, the spamassassin files in user’s home are not world
read/writ)
disable autolearning an
plugin: eval failed: bayes: (in learn) locker: safe_lock: cannot create
lockfile /home/kreme/.spamassassin/bayes.mutex: Permission denied
(And yes, that is correct, the spamassassin files in user’s home are not world
read/writ).
--
Train Station: where the train stops. Work Station: ...
Am 22.02.2015 um 15:30 schrieb @lbutlr:
On 21 Feb 2015, at 08:34 , LuKreme wrote:
On Feb 18, 2015, at 6:20 AM, Reindl Harald wrote:
That is a lot cleaner and more obvious, thank you for sharing
I ran this just after log rotation and got div by zero errors, so here is a
(nearly) compl
On 21 Feb 2015, at 08:34 , LuKreme wrote:
> On Feb 18, 2015, at 6:20 AM, Reindl Harald wrote:
>>
>>
>
> That is a lot cleaner and more obvious, thank you for sharing
I ran this just after log rotation and got div by zero errors, so here is a
(nearly) completely pointless ‘fix’:
BAYES_TOTAL=
