Nowadays, the attraction to the energy-aware software projects has been increasing. The project idea is to mine the Github data (specifically the commit messages), in order to identify the frequent occurring energy terms and based on these terms classify the commits as energy related or not energy related. An energy related commit is the one in which some change is made to the source code with the intention of saving energy. For example, if the source code is related to some mobile app than a change in the source code like: "putting the screen to sleep when the phone is idle", is considered to be an energy related change as this change is made with the intention of saving battery or energy. so the commit related to this change is Energy-aware commit.
Develop a test and train dataset for this project by extracting the data from the Github. To identify top energy-related terms used in energy-aware commits.