User Tools

Site Tools


data_mining_static_code_attributes_to_learn_defect_predictors

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
data_mining_static_code_attributes_to_learn_defect_predictors [2014/02/15 12:40]
yann
data_mining_static_code_attributes_to_learn_defect_predictors [2017/09/06 01:54] (current)
Line 23: Line 23:
 The authors explain their choice of the measures by explaining that "​accuracy is a poor measure of a learner'​s performance. For example, a learner could score 90 percent accuracy on a data set with 10 percent defective modules, even if it predicts that all defective modules were defect-free"​. They also avoids using self-tests that "can grossly overestimate performance"​. A self-test is a test on part of the object used to build the predictor, typically when doing 10-fold validation. The authors favour using "//​holdout//​ modules not used in the generation of that predictor"​. Finally, the authors apply a logarithmic filter "on all numeric values [to] improve predictor performance"​. ​ The authors explain their choice of the measures by explaining that "​accuracy is a poor measure of a learner'​s performance. For example, a learner could score 90 percent accuracy on a data set with 10 percent defective modules, even if it predicts that all defective modules were defect-free"​. They also avoids using self-tests that "can grossly overestimate performance"​. A self-test is a test on part of the object used to build the predictor, typically when doing 10-fold validation. The authors favour using "//​holdout//​ modules not used in the generation of that predictor"​. Finally, the authors apply a logarithmic filter "on all numeric values [to] improve predictor performance"​. ​
  
-The authors describe in details the procedure for building the predictors and comparing them with one another: the "​[d]ata is filtered and the attributes are ranked using InfoGain. The data is then shuffled into a random order and divided into 10 bins. A learner is then applied to a training set built from nine of the bins. The learned predictor is tested on the remaining bin". They also explain the use of //​performace deltas// to compare the performance of the predictors, according to the chosen measures: "The performance deltas were computed using simple subtraction,​ defined as follows: A positive performance delta for method X means that method X has outperformed some other method in one comparison. Using performance deltas, we say that the best method is the one that generates the largest performance deltas overall comparisons"​. They thus generated almost 800,000 performance deltas!+The authors describe in details the procedure for building the predictors and comparing them with one another: the "​[d]ata is filtered and the attributes are ranked using InfoGain. The data is then shuffled into a random order and divided into 10 bins. A learner is then applied to a training set built from nine of the bins. The learned predictor is tested on the remaining bin". They also explain the use of //​performace deltas// to compare the performance of the predictors, according to the chosen measures: "The performance deltas were computed using simple subtraction,​ defined as follows: A positive performance delta for method X means that method X has outperformed some other method in one comparison. Using performance deltas, we say that the best method is the one that generates the largest performance deltas overall comparisons"​. They thus generated almost 800,000 performance deltas! Finally, the authors use ROC curves to determine the best balance between //pd// and //pf// using a simple Euclidean distance from the "sweet spot"​. 
 + 
 +In conclusion, the authors show that the naïve Bayes-based predictor was the best, i.e., has the best balance between //pd// and //pf// over all other possible combination of attributes and independent variables. But they also show that the different attributes were better for different object systems: 
 +  * For //pc1//, the best code metrics are call_pairs, μ2, and number_of_lines;​ 
 +  * For //mw1//, the best code metrics are B, node_count, μ2; 
 +  * For //kc3//, the best code metrics are loc_executable,​ L, T; 
 +  * For //cm1//, the best code metrics are loc_comments,​ μ1, μ2; 
 +  * For //pc2//, the best code metrics are loc_comments,​ percent_comments;​ 
 +  * For //kc4//, the best code metrics are call_pairs, edge_count, node_count;​ 
 +  * For //pc3//, the best code metrics are loc_blanks, I, number_of_lines;​ 
 +  * For //pc4//, the best code metrics are loc_blanks, loc_code_and_command,​ percent_comments;​ 
 + 
 +The only limitations to the study (in addition to the threats mentioned in the paper) are that one of the authors worked with the NASA on the MDP program, thus there is possibly an experimenter bias. More seriously, the NASA MDP only provide metric values, no source code is available to check the quality of the data, compute different metrics, and apply different analyses!
data_mining_static_code_attributes_to_learn_defect_predictors.1392468006.txt.gz · Last modified: 2017/09/06 01:54 (external edit)