GSoC 2021 Project Ideas 9.1-9.4: sktime projects on Software engineering

sktime is a new Python toolbox for machine learning with time series and, to the best of our knowledge, the first unified toolbox for time series. Our ambition is to provide for time series what scikit-learn provides for tabular data. This involves extending scikit-learn to the different time series learning tasks, such as time series classification, clustering, forecasting and anomaly detection. To find out more, check out our paper published at the Workshop on Systems for ML at NeurIPS 2019.

What we are looking for

We’re actively looking for contributors and your help is extremely welcome. Therefore, if

  • you are interested in time series, machine learning (ML), statistics, API design and software architecture,
  • you like coding in Python,
  • you are familiar with the basic data science ecosystem in Python, including numpy, pandas and scikit-learn,
  • you enjoy working with a vibrant team of experienced ML scientists and software engineers,
  • you always wanted to join an open-source community,

then GSoC with sktime is for you! You’ll spend the summer working with our enthusiastic and open-minded team of developers who are creating one of the first comprehensive time series ML toolboxes out there.

9.1 Time series regression
9.2 Time series clustering
9.3 Forecasting
9.4 Develop a new module
(See also projects 9.4 and 9.5, separate posts)

Read more, including closer instructions to students, on the sktime Github GSoc page.

Mentors: Markus Löning, Tony Bagnall, Franz Király, Martina Vilas @martinagvilas

2 Likes

Thank you @malin for posting this here!

@mloning
Hello there! I am Aryan, a 3rd year B.Tech undergraduate from University of Delhi. I am well versed with Python, and have worked on a few Machine Learning Kaggle datasets. I am familiar with numpy, pandas, scikit-learn as well. This summer I would like to improve my ML skills, and would love to work on sktime!

I am not familiar with time series, but I’m sure I will be in a few days. Also, I have worked with teams remotely, use git, and contribute to open source too. Last summer, I successfully completed my GSoC project (based on Python software development) under Python Software Foundation.

I guess I am a beginner in Machine Learning, so I would like to focus on 9,1, 9.2 or 9.3 for now.
I hope I am not too late for working on this project. Do let me know if and how I can start contributing :))

Thank you for your time :))

My name is Aneesh Kumar. I am from India and enrolled in a PG Program.

I found the projects on sktime very interesting and intriguing. I believe the long-term goal of the project will definitely benefit the whole community and it will be a good learning experience.

Although I would love to explore the applied sciences projects, but as a beginner in time series analysis, I am inclined to apply for the software engineering projects under sktime. Kindly let me know what tasks are required to be done from my end as a part of the selection process, so I can be ready well ahead of time.

Mentors for the project @TonyBagnall @martinagvilas

Hi @Aryan and @aneesh!

If you are interested in this project, please follow the application steps outlined here, and let us know if you have any questions.

We are looking forward to reading your application!

2 Likes

Thanks Martina. I will be in touch for any queries.

@mloning @martinagvilas , I have submitted the application form. I’ll start looking into some good first issues to get familiar with the project :))

Thanks @Aryan, we received the application!

1 Like

hey I am interested in this project I want to contribute in Time series regression part…I have gone through repo and tried to understand …please guide me if anything required more…excited to learn new things with you all…:slight_smile:
thanx

Hi @Raghib_Shams, for time series regression the main tasks at the moment are translating time series classifiers to their regressor counterparts - take a look at this issue: Time series regression: refactoring time series classifiers · Issue #212 · alan-turing-institute/sktime · GitHub and the linked draft PR for an example

Hi, I’m Aaditya. I’m a 1st year undergrad student studying in Bangalore.
I’ve worked a couple of ML projects in the past, and through this program I’m looking forward to starting my open source journey. Being someone who has studied and loved computer science and biology in high school, I was instantly excited when I saw the projects here. I hope in the near future, I’ll be proficient and confident enough to contribute in those. For now, I think the sktime projects will be a great place for me to start.
I look forward to contributing :slight_smile: