tuning.sh [was: bogofilter-0.13.6.3 - new current release]

[Boris 'pi' Piwinger]

David Relson wrote:

>> > The rule of thumb is that $target should be 0.1% to 0.3% of the test set
>> > size.
>>
>>For me that would be more than 70 (using .2%). Or do you
>>only count half the size since the other half is used to
>>build the database? Anyhow this would still be way to big.
> 
> You could try 24 and 36 and see what the results are. 

I guess I should take something smaller (for 24):

 robs   min_dev spam_cutoff  run0 run1 run2 total
0.0320    0.450   0.500000    36   30   41   107
0.0100    0.450   0.500000    34   32   42   108
0.0100    0.425   0.500000    39   38   50   127
0.0320    0.425   0.500000    42   39   51   132
0.1000    0.450   0.500000    48   44   50   142
0.1000    0.425   0.500000    46   45   55   146
0.0100    0.400   0.500000    54   48   60   162
0.3200    0.450   0.500000    54   64   60   178
0.0100    0.375   0.500000    63   58   64   185
0.0320    0.400   0.500000    64   57   64   185

> Alternatively, you could download Greg's new bogotune

That is running now. It suggested 3 if this is comparable.

pi