Defuse: A Data Annotator and Model Builder for Software Defect Prediction

We propose a language-agnostic tool for software defect prediction, called DEFUSE. The tool automatically collects and classifies failure data, enables the correction of those classifications, and builds machine learning models to detect defects based on those data. We instantiated the tool in the scope of Infrastructure-as-Code, the DevOps practice enabling management and provisioning of infrastructure through the definition of machine-readable files. We present its architecture and provide examples of its application.Demo video: https://youtu.be/37mmLdCX3jU.