Predicting the areas of the source code having a higher likelihood to change in the future represents an important activity to allow developers to plan preventive maintenance operations. GA and our analysis reveals that cross-project with GA performsīest followed by within-project and then cross-project without Within-project, cross-project without GA and cross-project with (such as decision tree and logistic regression) and ensemble methods in the experimental dataset. In case of cross-projectĬhange-proneness prediction, our analysis reveals that the NDTFĮnsemble method performs higher than other individual classifiers We conclude thatįor with-in project experimental setting, Random Forest (RF) Performance of within project and cross project prediction andĪlso propose a Genetic Algorithm (GA) based approach for identifying the best set of source code metrics. We frame several research questions comparing the Source Eclipse plug-ins and demonstrate the effectiveness of ourĪpproach. We propose a machine learning based approach for cross-projectĬhange-proneness prediction. Cross-project change-proneness prediction is relatively unexplored.
Prediction is an approach which consists of training a model from dataset belonging to one project and testing it on dataset belonging to a different project. Model building such as in the case of a new project.
There are several real word scenario in which suficient training dataset is not available for However, most of the work has focused on within- project training and model building. Several machine learning techniques have been proposed for predicting change-prone classes based on the application of source code metrics as
#Datacrow find and replace software#
Automatic identification of change-prone classes are useful for the software development team as they can focus their testing efforts on areas within the source code which are more likely to change. Change-prone classes or modules are defined as regions of the source code which are more likely to change as a result of a software development of maintenance activity.
0 kommentar(er)
