This data set contains measurements of code and organisational characteristics (anonymised). It does not contain the source code of the projects studied. Presence (or absence) of a file in a release One measurement for each version of a file in a release Boolean File changes (checksums) One measurement for each version of a file in a release categorical Code churn: line count for each code file One measurement for each version of a code file in a release integer Team composition: presence (or absence) of a team member for each release One measurement for each team member contributing to a release Boolean Edit frequency: count of edits by each team member for each release One measurement for each team member contributing to a release integer Code ownership: count of commits by each team member for each release One measurement for each team member contributing to a release integer