Welcome to source{d} bi-weekly, a newsletter with the latest news, resources and events related to Code as Data and Machine Learning on Code. Sign up for source{d} bi-weekly newsletter.

Machine Learning for Software Development Analytics Ebook

In this ebook, we first define what is Machine Learning on Code and how source{d} became a leader in this field. We also present the open-source tools and models for Machine Learning on Code. Finally, we describe the solutions available in source{d} Enterprise Edition including a list of past and upcoming research on our roadmap for 2020. Click here to request a copy of the Ebook.

source{d} News

An analysis of the Cloud Foundry project with source{d} EE [Blog]
by Victor Coisne

This blog post includes an updated analysis of the Cloud Foundry GitHub organization. In this analysis, the advanced metrics are related to dependencies, the health index, containers, and compliance metrics. Follow this link to view a read-only dashboard of the entire Cloud Foundry Project analysis. Read the blog post for a summary of our key findings.

Machine Learning on Code [Slides]
by Egor Bulychev

In this talk, Egor explains why applying machine learning to source code is so difficult and why almost none of the tasks can be solved without using methods for processing natural languages. He also talks about code reviews, similar code analysis and developer expertise.

Community News

Towards Neural Decompilation [Resarch Paper]
by Omer Katz, Yuval Olshaker, Yoav Goldberg, Eran Yahav

This paper presents a novel approach to decompilation based on neural machine translation. The main idea is to automatically learn a decompiler from a given compiler. Given a compiler from a source language S to a target language T , the approach automatically trains a decompiler that can translate (decompile) T back to S .

Introducing the CodeSearchNet challenge [Blog]
by Hammel Husein

Searching for code to reuse, call into, or to see how others handle a problem is one of the most common tasks in a software developer’s day. However, search engines for code are often frustrating and never fully understand what we want, unlike regular web search engines. [...] Today we’re announcing the CodeSearchNet Challenge evaluation environment and leaderboard. We’re also releasing a large dataset to help data scientists build models for this task, as well as several baseline models showing the current state of the art.

Measuring Continuous Delivery [Video]
by Steve Smith

In this talk, Steve Smith shows how measuring stability and speed can power a successful adoption of Continuous Delivery in an organisation of any size. This is a deep dive into Continuous Delivery measurement, backed up by long-term case studies in private and public sector organisations.

Getting real about managing up [Video]
by Kellan Elliott-McCrea

Good boss, bad boss, manager, director, VP, CTO, CEO, board member, it doesn't matter, there are days they're going to need help aspiring to competence. In technology we're ambivalent about bosses. We promote the most competent engineer and wonder why they aren't great at management. Meanwhile, our expectations of work as fulfilling and rewarding environment are extremely high. This talk is about what to do when "put your head down and do your work" isn't getting the results you want.

Events

October 4-6th: PyCon ES (Alicante, Spain)

October 4th: source{d} paper reading club (Online)

October 9-11th: DevFest (Nantes, France)

October 18th: source{d} paper reading club (Online)

October 28-31st: Tensorflow World (Santa Clara, USA)

November 9th: DevFest (Moscow, Russia)

Featured Community Member

Omoju Miller is a Data Scientist with over a decade of experience in computational intelligence. She has a Ph.D. from UC Berkeley. In the past, she has co-led the non-profit investment in CS Education for Google and served as a volunteer advisor to the Obama administration’s White House Presidential Innovation Fellows. Make sure to follow @omojumiller on Twitter or visit this page to stay up to date with her latest publications.