Regards
Prakash
On Tue, Nov 17, 2015 at 2:24 PM, Martin L <martinlion80(a)gmail.com> wrote:
It seams that algorithms 3, 4, 5, 6, 7, 8, 9, 10,
11, 12 have higher
F-measure than first algorithm, while second algorithm its F-measureis is
approximately equal to the first one.
In sum, you could select any of algorithms 3, 4, 5, 6, 7, 8, 9, 10, 11,
12 to be used instead of using first one.
Regards,
Martin
On 17 November 2015 at 22:06, Prakash Poudyal <prakashpoudyal(a)gmail.com>
wrote:
Hi!
Below I am sending the result of statistical test done in experimenter
of weka. Can anybody explain the value it shown are calculated.
In my experiment I do have two class, the value which is shown below
matches with the f-measure of one the class.
Tester: weka.experiment.PairedTTester
Analysing: F_measure
Datasets: 1
Resultsets: 12
Confidence: 0.05 (two tailed)
Sorted by: -
Date: 11/11/15 5:22 PM
Dataset (1) functio | (2) func (3) func (4) func (5)
func (6) func (7) func (8) tree (9) tree (10) tre (11) tre (12) tre
------------------------------------------------------------------------------------------------------------------------------------------
'echr-weka.filters.unsupe (10) 0.88 | 0.88 0.89 v 0.89 v
0.90 v 0.90 v 0.90 v 0.90 v 0.90 v 0.90 v 0.90 v 0.90 v
------------------------------------------------------------------------------------------------------------------------------------------
(v/ /*) | (0/1/0) (1/0/0) (1/0/0)
(1/0/0) (1/0/0) (1/0/0) (1/0/0) (1/0/0) (1/0/0) (1/0/0) (1/0/0)
Key:
(1) functions.SMO '-C 0.001 -L 0.001 -P 1.0E-12 -N 0 -V -1 -W 1 -K
\"functions.supportVector.PolyKernel -E 2.0 -C 250007\"'
-6585883636378691736
(2) functions.SMO '-C 0.01 -L 0.001 -P 1.0E-12 -N 0 -V -1 -W 1 -K
\"functions.supportVector.PolyKernel -E 2.0 -C 250007\"'
-6585883636378691736
(3) functions.SMO '-C 0.1 -L 0.001 -P 1.0E-12 -N 0 -V -1 -W 1 -K
\"functions.supportVector.PolyKernel -E 2.0 -C 250007\"'
-6585883636378691736
(4) functions.SMO '-C 1.0 -L 0.001 -P 1.0E-12 -N 0 -V -1 -W 1 -K
\"functions.supportVector.PolyKernel -E 2.0 -C 250007\"'
-6585883636378691736
(5) functions.SMO '-C 10.0 -L 0.001 -P 1.0E-12 -N 0 -V -1 -W 1 -K
\"functions.supportVector.PolyKernel -E 2.0 -C 250007\"'
-6585883636378691736
(6) functions.SMO '-C 100.0 -L 0.001 -P 1.0E-12 -N 0 -V -1 -W 1 -K
\"functions.supportVector.PolyKernel -E 2.0 -C 250007\"'
-6585883636378691736
(7) functions.SMO '-C 1000.0 -L 0.001 -P 1.0E-12 -N 0 -V -1 -W 1 -K
\"functions.supportVector.PolyKernel -E 2.0 -C 250007\"'
-6585883636378691736
(8) trees.RandomForest '-I 7 -K 0 -S 1 -num-slots 1' 1116839470751428698
(9) trees.RandomForest '-I 10 -K 0 -S 1 -num-slots 1'
1116839470751428698
(10) trees.RandomForest '-I 17 -K 0 -S 1 -num-slots 1'
1116839470751428698
(11) trees.RandomForest '-I 50 -K 0 -S 1 -num-slots 1'
1116839470751428698
(12) trees.RandomForest '-I 100 -K 0 -S 1 -num-slots 1'
1116839470751428698
--
Regards
Prakash Poudyal
_______________________________________________
Wekalist mailing list
Send posts to: Wekalist(a)list.waikato.ac.nz
List info and subscription status:
http://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette:
http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
_______________________________________________
Wekalist mailing list
Send posts to: Wekalist(a)list.waikato.ac.nz
List info and subscription status:
http://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette:
http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html