GROOT (chanGe pROneness Open daTaset)

<p>GROOT (chanGe pROneness Open daTaset)</p> <p>General Information</p> <p>Data Set Characteristics: Multivariate</p> <p>Associated Tasks: Classification</p> <p>Number of Instances: 4183</p> <p>Number of Attributes: 8</p> <p>Missing Values? No</p> <p>Area: Software Engineering</p> <p>Source</p> <p>Cristiano Sousa Melo</p> <p>Matheus Mayron Lima da Cruz</p> <p>Ant&ocirc;nio Diogo Forte Martins</p> <p>Jos&eacute; Maria da Silva Monteiro Filho</p> <p>Javam de Castro Machado</p> <p>Data Set Information</p> <ul> <li>The data set of this work is generated from the backend source code of a WEB application started in 2013, and until 2018 were collected 8 releases to analyze change-prone classes</li> <li>The dependent variable &quot;will change&quot; has obtained according to [1]</li> <li>The dependent variable &quot;will change&quot; is imbalanced, containing 3871 &quot;not change&quot; (0) labels and 312 &quot;will change&quot; (1) label</li> </ul> <p>Attribute Information</p> <p><strong>instanceID</strong>: It is responsible for identifying each instance of the dataset uniquely.</p> <p><strong>classID</strong>: This column indicates the class from which the information of the row was extracted. It is a value obtained by hashing the name of the class.</p> <p><strong>releaseID</strong>: This column indicates the release from which the information of the &nbsp;row was extracted.</p> <p><strong>CBO (Coupling Between Object) [2]:</strong>&nbsp;A class is coupled to another one if it used its member functions and/or instance variables. CBO provides the number of classes to which a given class is coupled. Range: 0 - 162</p> <p><strong>CC (Cyclomatic Complexity) [3]:</strong>&nbsp;It is a software metric used to indicate the complexity of a program. It is a quantitative measure of the number of linearly independent paths through a program&#39;s source code. Range: 0 - 488.0</p> <p><strong>DIT (Depth of Inheritance Tree) [2]:</strong>&nbsp;It is defined as the maximum depth of the inheritance graph of each class. Range: 0 - 7</p> <p><strong>LCOM (Lack of Cohesion on Methods) [2]:</strong>&nbsp;This is the number of pairs of member functions without shared instance variables, minus the number of pairs of members functions with shared instance variables. Range: 0 - 1</p> <p><strong>LOC:</strong>&nbsp;Number of lines of codes. Imports and comments are not included. Range: 0 - 1369</p> <p><strong>NOC (Number Of Children) [2]:</strong>&nbsp;It is the number of direct descendants for each class. Range: 0 - 189</p> <p><strong>RFC (Response For a Class) [2]:</strong>&nbsp;This is the number of methods that can potentially be executed in response to a message received by an object of that class. Range: 0 - 413</p> <p><strong>WMC (Weighted Methods per Class) [2]:</strong>&nbsp;It is the number of methods of a class.Range: 0 - 56</p> <p><strong>class_frequency:</strong>&nbsp;It is the number of appearences that the class has through all the releases. Range: 0 - 8</p> <p><strong>number_of_changes:</strong>&nbsp;It is the number of changes that a class suffered through all the releases. Range: 0 - 7</p> <p><strong>will_change:</strong>&nbsp;It is the dependent variable, the indicator of a class change prone.</p> <p><strong>change_probability:</strong>&nbsp;It is the number of changes divided by the class frequency. Range: 0 - 1</p> <p>References</p> <p>[1] Lu, H., Zhou, Y., Xu, B., Leung, H., and Chen, L. (2012). The ability of object-oriented metrics to predict change-proneness: a meta-analysis. Empirical Software Engineering, 17(3)</p> <p>[2] S. R. Chidamber and C. F. Kemerer, &quot;A metrics suite for object oriented design,&quot; in IEEE Transactions on Software Engineering, vol. 20, no. 6, pp. 476-493, June 1994.</p> <p>[3] T. J. McCabe, &quot;A Complexity Measure,&quot; in IEEE Transactions on Software Engineering, vol. SE-2, no. 4, pp. 308-320, Dec. 1976.</p>