IN4334 - Machine Learning on Code

Course information

General description

Software repositories archive valuable software engineering data, such as source code, execution traces, historical code changes, mailing lists, and bug reports. This data contains a wealth of information about a project’s status and history. Doing data science on software repositories, researchers can gain empirically based understanding of software development practices, and practitioners can better manage, maintain, and evolve complex software projects.

In the recent years, the advances in Machine Learning and AI technologies, as demonstrated by the successful application of Deep Neural Networks in various domains did not go unoticed in the field of Software Analytics. Researchers have applied DNNs to tackle issues such as automated program repair, code summarization, code structure representation, etc.

IN4334 is a seminar course that aims to give students a deep understanding of and hands-on approach on how deep neural networks and NLP techniques are used by today’s industry leaders to represent knoweledge and solve existing problems in novel ways.

Learning Objectives

This course will enable students to:

• Understand and analyze related work in the area of software analytics
• Apply appropriate research methods to extract data from software repositories
• Evaluate the applicability of results in the software analytics literature on practical problems
• Analyze data from software repositories and extract new insights

Course Organization

• 5 ECTS: This means that you need to devote at least 140 hours of study for this course, per person. Given that the course runs in a period of 7 weeks, the workload is around 20 hours a week.

• Lectures: The course consists of 14 2-hour lectures. You are not required, but you are strongly encouraged, to attend. We will be discussing 2-3 papers (presentations given either by the lecturer or by teams) in terms of techniques, insights and impact.

• Homework: Before each lecture, you must read and prepare questions about the papers that will be discussed during the lecture. You can find the list of the papers to read on the beginning of each week’s lecture.

• Lecturers: The course is supervised by Georgios Gousios and Mauricio Aniche, who are responsible for the content, assignments and exams. Several people will provide extra lectures in topics of their expertise.

• Course work: To finish the course you will need to:

  • Give a 10-min presentation of 1-2 papers
  • Replicate a recent quantitative (2-3 years old) paper with Deep Neural Networks
  • Review and grade each other’s work

• Groups: You will work in groups of 3-4 persons. You are free to choose your group partners.

• Labs: Unsupervised, optional. 4 hours per week, designed to give you a place and time to work together.

The course projects

During the course, you will need to replicate an existing paper with

Replication is a topic much touted but seldom practiced in the mining software repositories and the software analytics communities. It is, however, a core aspect of science, especially empirical.

The purpose of this task is to attempt a replication of a recent paper, either by downloading readily available data sets published together with the paper, requesting the data from the original authors or by applying the same techniques on a different sample. You will select a paper from the list that you studied for your literature survey.

Study material

The following material is a-must-read in the study of software analytics.

Contents

Date	Week	Lecture	Topic	Lecturer
3/9	1	1	Course Introduction, Quantitative methods in Software Engineering	GG
5/9	1	2	Discussion Groups	GG
10/9	2	1	Process Analytics	AR / GG
12/9	2	2	Testing Analytics	students, MB
17/9	3	1	Build Analytics	students, MB
19/9	3	2	Bug Prediction	students, MB
24/9	4	1	Software Ecosystem Analytics	students, JH
26/9	4	2	Release Engineering Analytics	students, AR
1/10	5	1	Results: Survey on Software Analytics	students
3/10	5	2	Code Review	students, GG
8/10	6	1	Runtime and Performance Analytics, Cross-review of surveys	MK
10/10	6	2	App Store Analytics	students, MK
15/10	7	1	Analytics at Work: ING	Hennie Huijgens
17/10	7	2	Results: Replication project results	students

Lecturers

• GG: Georgios Gousios
• MA: Mauricio Aniche

Assessment

The final course grade will be calculated as:

• 80% - Results of replication
• 20% - Presentation

All deliverables will be peer-reviewed by 2 other teams. The peer-review grade is 50% of the final grade per grade item.

Bibliography

[1]

C. Bird, T. Menzies, and T. Zimmermann, The art and science of analyzing software data, 1st ed. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc., 2015.

Copyright

The course contents are copyrighted (c) 2018 - onwards by TU Delft and their respective authors and licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International license.