- Timestamp:
- 05/19/15 11:42:28 (10 years ago)
- Location:
- trunk/CrossPare
- Files:
-
- 5 added
- 1 edited
Legend:
- Unmodified
- Added
- Removed
-
trunk/CrossPare/src/de/ugoe/cs/cpdp/eval/AbstractWekaEvaluation.java
r24 r35 20 20 * For each classifier, the following metrics are calculated: 21 21 * <ul> 22 * <li> Success with recall>0.7, precision>0.5</li>23 * <li> Success with recall>0.7, precision>0.7</li>24 * <li> Success with gscore>0.75</li>25 * <li> Success with gscore>0.6</li>26 * <li>error rate</li>22 * <li>succHe: Success with recall>0.7, precision>0.5</li> 23 * <li>succZi: Success with recall>0.7, precision>0.7</li> 24 * <li>succG75: Success with gscore>0.75</li> 25 * <li>succG60: Success with gscore>0.6</li> 26 * <li>error</li> 27 27 * <li>recall</li> 28 28 * <li>precision</li> … … 31 31 * <li>AUC</li> 32 32 * <li>AUCEC (weighted by LOC, if applicable; 0.0 if LOC not available)</li> 33 * <li>t rue positive rate</li>34 * <li>t rue negative rate</li>35 * <li>t rue positives</li>36 * <li>f alse positives</li>37 * <li>t rue negatives</li>38 * <li>f alse negatives</li>39 * <li> training error</li>40 * <li> training recall</li>41 * <li> training precision</li>42 * <li> training success with recall>0.7 and precision>0.533 * <li>tpr: true positive rate</li> 34 * <li>tnr: true negative rate</li> 35 * <li>tp: true positives</li> 36 * <li>fp: false positives</li> 37 * <li>tn: true negatives</li> 38 * <li>fn: false negatives</li> 39 * <li>errortrain: training error</li> 40 * <li>recalltrain: training recall</li> 41 * <li>precisiontrain: training precision</li> 42 * <li>succHetrain: training success with recall>0.7 and precision>0.5 43 43 * </ul> 44 44 * @author Steffen Herbold
Note: See TracChangeset
for help on using the changeset viewer.