Software defect prediction method based on two-stage wrapping-type feature selection

Abstract

The invention discloses a software defect prediction method based on two-stage wrapping-type feature selection, and belongs to the field of software quality assurance. The software defect prediction method comprises the following steps: (1) mining the version control system and the defect tracking system of a software project, extracting a program module from the version control system and the defect tracking system, and carrying out type marking and software measurement on the program module to generate a defect prediction data set D; (2) carrying out two-stage wrapping-type feature selection on the defect prediction data set so as to remove redundant features and irrelevant features in the data set D as many as possible, and finally, selecting an optimal feature subset FS' from an original feature set FS; and (3) on the basis of the optimal feature subset FS', preprocessing the data set D, forming a preprocessed data set D', and finally, constructing a defect prediction model in virtue of a decision tree which is a classification method. By use of the software defect prediction method, on one hand, the redundant features and the irrelevant features in the defect prediction data set can be effectively identified and removed, on the other hand, a class imbalance problem in the defect prediction data set can be effectively alleviated, and finally, the performance of the defect prediction model can be effectively improved.

Description

technical field [0001] The invention belongs to the field of software quality assurance, and in particular relates to a software defect prediction method based on two-stage packaged feature selection. Background technique [0002] Software defect prediction can pre-identify potential defect program modules in the project under test by analyzing the software historical warehouse and building a defect prediction model. By allocating more test resources to these program modules, it can optimize the allocation of test resources and improve the quality of the software. The purpose of product quality. However, when collecting defect prediction data sets, if multiple metrics (ie features) are considered, it is easy to cause the disaster of dimensionality in the data set, that is, the data set will contain irrelevant and redundant features. Among them, redundant features refer to a large number or complete repetition of information contained in other single or multiple features, wh...

AI Technical Summary

Problems solved by technology

On the one hand, a feature may have little correlation with the class label, but if the feature has a complementary relationship with other features, it can significantly improve the performance of the classification method. not optimal

On the other hand, although a certain feature has a strong correlation with the class label, if it is put together with other features, it may have certain redundancy, which will cause the performance of the classification method to decline.

(2) Large search space

[0005] In addition, due to the problem of class imbalance in the distribution of software defects within the tested project, most of the defects are concentrated in a few program modules.

Therefore, there is an obvious class imbalance problem in the collected defect prediction data set, that is, the number of defective modules (majority class) is far less than the number of non-defective modules (minority class)

Images