=== Run information ===
Scheme: weka.classifiers.trees.J48 -C 0.25 -M 2
Relation: accent-weka.filters.unsupervised.attribute.Remove-R1-4-weka.filters.unsupervised.attribute.Remove-R5-12,21,23,25,27,29,31,34,36,39,41,44,46,49,51,67-70,73-76,79-82,85-88,91-92,94-95,97-98,100,102,104,106,108,110,112-113,116,118-120,124,126,128,130-weka.filters.unsupervised.attribute.Remove-R72-76,78-85-weka.filters.unsupervised.attribute.Remove-R1,3-21,23-39,41-71
Instances: 7833
Attributes: 4
lengthinphonemes
leftneighbour1_CELEXfreq
followingpunct_word
accenttype_complex_noneasmissing
Test mode: 10-fold cross-validation
Evaluation cost matrix:
0 1 1 1 1 1
1 0 0.25 0.5 2 1
1 0.25 0 0.25 1 2
1 0.5 0.25 0 0.5 2
1 2 1 0.5 0 0.25
1 1 2 2 0.25 0
=== Classifier model (full training set) ===
J48 pruned tree
------------------
followingpunct_word = excl
| leftneighbour1_CELEXfreq <= 197: earlypeak (8.0/2.0)
| leftneighbour1_CELEXfreq > 197: midpeak (10.0/4.0)
followingpunct_word = comma
| lengthinphonemes <= 5
| | lengthinphonemes <= 2
| | | leftneighbour1_CELEXfreq <= 201
| | | | leftneighbour1_CELEXfreq <= 127
| | | | | leftneighbour1_CELEXfreq <= -100: midpeak (9.0/2.0)
| | | | | leftneighbour1_CELEXfreq > -100: flat (5.0/3.0)
| | | | leftneighbour1_CELEXfreq > 127
| | | | | leftneighbour1_CELEXfreq <= 139: latepeak (3.0)
| | | | | leftneighbour1_CELEXfreq > 139: midpeak (6.0)
| | | leftneighbour1_CELEXfreq > 201
| | | | leftneighbour1_CELEXfreq <= 2790
| | | | | leftneighbour1_CELEXfreq <= 1244: nonearlyvalley (10.0/5.0)
| | | | | leftneighbour1_CELEXfreq > 1244: midpeak (5.0/2.0)
| | | | leftneighbour1_CELEXfreq > 2790
| | | | | leftneighbour1_CELEXfreq <= 7453: flat (2.0/1.0)
| | | | | leftneighbour1_CELEXfreq > 7453: earlyvalley (3.0)
| | lengthinphonemes > 2: midpeak (77.0/36.0)
| lengthinphonemes > 5: earlyvalley (6.0/2.0)
followingpunct_word = dash: latepeak (2.0/1.0)
followingpunct_word = period: earlypeak (376.0/77.0)
followingpunct_word = colon
| leftneighbour1_CELEXfreq <= 228: earlyvalley (3.0/1.0)
| leftneighbour1_CELEXfreq > 228: flat (4.0/1.0)
followingpunct_word = quest
| leftneighbour1_CELEXfreq <= 1550: nonearlyvalley (62.0/23.0)
| leftneighbour1_CELEXfreq > 1550
| | leftneighbour1_CELEXfreq <= 1940: midpeak (17.0/3.0)
| | leftneighbour1_CELEXfreq > 1940: nonearlyvalley (13.0/6.0)
followingpunct_word = none
| leftneighbour1_CELEXfreq <= -100: latepeak (240.0/73.0)
| leftneighbour1_CELEXfreq > -100
| | lengthinphonemes <= 4
| | | leftneighbour1_CELEXfreq <= 1738
| | | | leftneighbour1_CELEXfreq <= 1550
| | | | | lengthinphonemes <= 2: latepeak (241.0/113.0)
| | | | | lengthinphonemes > 2
| | | | | | leftneighbour1_CELEXfreq <= 96
| | | | | | | leftneighbour1_CELEXfreq <= 12
| | | | | | | | lengthinphonemes <= 3
| | | | | | | | | leftneighbour1_CELEXfreq <= 1: midpeak (26.0/12.0)
| | | | | | | | | leftneighbour1_CELEXfreq > 1: latepeak (13.0/6.0)
| | | | | | | | lengthinphonemes > 3
| | | | | | | | | leftneighbour1_CELEXfreq <= 0: latepeak (13.0/4.0)
| | | | | | | | | leftneighbour1_CELEXfreq > 0
| | | | | | | | | | leftneighbour1_CELEXfreq <= 5: midpeak (17.0/7.0)
| | | | | | | | | | leftneighbour1_CELEXfreq > 5: latepeak (7.0/2.0)
| | | | | | | leftneighbour1_CELEXfreq > 12
| | | | | | | | lengthinphonemes <= 3
| | | | | | | | | leftneighbour1_CELEXfreq <= 59: latepeak (36.0/21.0)
| | | | | | | | | leftneighbour1_CELEXfreq > 59
| | | | | | | | | | leftneighbour1_CELEXfreq <= 87: midpeak (10.0/3.0)
| | | | | | | | | | leftneighbour1_CELEXfreq > 87: latepeak (3.0)
| | | | | | | | lengthinphonemes > 3
| | | | | | | | | leftneighbour1_CELEXfreq <= 16
| | | | | | | | | | leftneighbour1_CELEXfreq <= 14: earlypeak (2.0/1.0)
| | | | | | | | | | leftneighbour1_CELEXfreq > 14: flat (2.0/1.0)
| | | | | | | | | leftneighbour1_CELEXfreq > 16
| | | | | | | | | | leftneighbour1_CELEXfreq <= 44
| | | | | | | | | | | leftneighbour1_CELEXfreq <= 22: midpeak (6.0/2.0)
| | | | | | | | | | | leftneighbour1_CELEXfreq > 22
| | | | | | | | | | | | leftneighbour1_CELEXfreq <= 31: flat (3.0/1.0)
| | | | | | | | | | | | leftneighbour1_CELEXfreq > 31: latepeak (6.0/2.0)
| | | | | | | | | | leftneighbour1_CELEXfreq > 44: midpeak (8.0/4.0)
| | | | | | leftneighbour1_CELEXfreq > 96
| | | | | | | leftneighbour1_CELEXfreq <= 167: midpeak (23.0/9.0)
| | | | | | | leftneighbour1_CELEXfreq > 167: latepeak (187.0/92.0)
| | | | leftneighbour1_CELEXfreq > 1550: midpeak (54.0/26.0)
| | | leftneighbour1_CELEXfreq > 1738
| | | | leftneighbour1_CELEXfreq <= 12255
| | | | | lengthinphonemes <= 2: latepeak (131.0/54.0)
| | | | | lengthinphonemes > 2
| | | | | | leftneighbour1_CELEXfreq <= 4304: latepeak (117.0/47.0)
| | | | | | leftneighbour1_CELEXfreq > 4304
| | | | | | | leftneighbour1_CELEXfreq <= 7453
| | | | | | | | leftneighbour1_CELEXfreq <= 4693
| | | | | | | | | lengthinphonemes <= 3: latepeak (19.0/9.0)
| | | | | | | | | lengthinphonemes > 3: midpeak (9.0/3.0)
| | | | | | | | leftneighbour1_CELEXfreq > 4693
| | | | | | | | | leftneighbour1_CELEXfreq <= 5912
| | | | | | | | | | leftneighbour1_CELEXfreq <= 5180: latepeak (9.0/4.0)
| | | | | | | | | | leftneighbour1_CELEXfreq > 5180
| | | | | | | | | | | leftneighbour1_CELEXfreq <= 5857: midpeak (56.0/16.0)
| | | | | | | | | | | leftneighbour1_CELEXfreq > 5857: latepeak (2.0)
| | | | | | | | | leftneighbour1_CELEXfreq > 5912: midpeak (3.0/1.0)
| | | | | | | leftneighbour1_CELEXfreq > 7453: latepeak (90.0/34.0)
| | | | leftneighbour1_CELEXfreq > 12255
| | | | | leftneighbour1_CELEXfreq <= 18536: midpeak (30.0/15.0)
| | | | | leftneighbour1_CELEXfreq > 18536
| | | | | | lengthinphonemes <= 2: midpeak (6.0/2.0)
| | | | | | lengthinphonemes > 2: latepeak (32.0/13.0)
| | lengthinphonemes > 4
| | | lengthinphonemes <= 5
| | | | leftneighbour1_CELEXfreq <= 7453
| | | | | leftneighbour1_CELEXfreq <= 5180
| | | | | | leftneighbour1_CELEXfreq <= 3832: midpeak (183.0/72.0)
| | | | | | leftneighbour1_CELEXfreq > 3832: latepeak (4.0/1.0)
| | | | | leftneighbour1_CELEXfreq > 5180: midpeak (20.0/1.0)
| | | | leftneighbour1_CELEXfreq > 7453
| | | | | leftneighbour1_CELEXfreq <= 11474: latepeak (16.0/7.0)
| | | | | leftneighbour1_CELEXfreq > 11474: midpeak (26.0/7.0)
| | | lengthinphonemes > 5
| | | | leftneighbour1_CELEXfreq <= 651
| | | | | lengthinphonemes <= 7: latepeak (35.0/19.0)
| | | | | lengthinphonemes > 7
| | | | | | lengthinphonemes <= 8: midpeak (11.0/5.0)
| | | | | | lengthinphonemes > 8: flat (2.0/1.0)
| | | | leftneighbour1_CELEXfreq > 651: latepeak (69.0/26.0)
Number of Leaves : 59
Size of the tree : 112
Time taken to build model: 0.25 seconds
=== Stratified cross-validation ===
=== Summary ===
Correctly Classified Instances 1388 58.124 %
Incorrectly Classified Instances 1000 41.876 %
Kappa statistic 0.3971
Total Cost 551.75
Average Cost 0.2311
Mean absolute error 0.1837
Root mean squared error 0.3112
Relative absolute error 75.853 %
Root relative squared error 89.4549 %
Total Number of Instances 2388
Ignored Class Unknown Instances 5445
=== Detailed Accuracy By Class ===
TP Rate FP Rate Precision Recall F-Measure Class
0.033 0.007 0.158 0.033 0.054 flat
0.794 0.043 0.778 0.794 0.786 earlypeak
0.436 0.187 0.536 0.436 0.481 midpeak
0.794 0.362 0.555 0.794 0.653 latepeak
0.055 0.007 0.333 0.055 0.094 earlyvalley
0.386 0.014 0.579 0.386 0.463 nonearlyvalley
=== Confusion Matrix ===
a b c d e f <-- classified as
3 7 32 47 1 2 | a = flat
2 301 30 44 1 1 | b = earlypeak
4 75 345 343 7 18 | c = midpeak
6 1 165 687 4 2 | d = latepeak
2 1 46 80 8 9 | e = earlyvalley
2 2 26 37 3 44 | f = nonearlyvalley