#SummerOfShipping#SOSDay12:
Did some experiments with sklearn and MLflow. Tweaked the Notion page a little. I got a 3-day interview starting tomorrow (thanks to the fortune brought by SOS😆), so will be back on track on Sunday.
#SummerOfShipping#SOSDay9:
Nice talk with @MishaSinitcyn and team in the weekly meeting. Uploaded the first version of our dataset, and made my first PR for this project. Yay!
As for myself, I created the raw data from the GH Archive data David provided and spam data from Misha, for our meeting (tomorrow❎) today✅
(Wish Twitter supports markdown language someday so no more weird syntax like above lol. Wait... can this be turned into a project idea?)
#SOSDay8:
Joined the second general meeting of #SummerOfShipping. Nice presentation on project management by @michaelfromyeg! The demo session with these amazing ideas also inspired me to open my mind to new ideas and put more effort into what I'm currently doing!
#SummerOfShipping#SOSDay6:
Oops, almost forgot my Day6 update: not much progress, but I tried to use BigQuery to get data from GH Archive, and the results are HUGE! So if we are gonna use this, we definitely need to work on the query itself to limit our search range.
#SummerOfShipping#SOSDay5
Investigate the Hugging Face dataset. Wrote a script to discover unique labels in GitHub issues, and how many rows have labels.
#SummerOfShipping#SOSDay4
Thank you for hosting the first team meeting @MishaSinitcyn !
Currently have a lot of trivial ideas but no clear direction, so it's time to roll up my sleeves. Will work on the Hugging Face dataset in the next two days.
#SummerOfShipping#SOSDay4
Had our first team meeting where we went over the dev guidelines, setup instructions, and first steps.
Whole team is now looking for labelled Github issues to begin developing a binary spam classifier (later to be a multiclass classifier).
#SOSDay3: Research how to build a dataset of GitHub issues. Seeking different options (fetch manually or use existing datasets), will do some tests and share my findings with the team!
#SummerOfShipping
#SummerOfShipping#SOSDay2
Had a nice talk with @MishaSinitcyn about his cool idea of Repo Cleanup, and glad to be part of the team! Can't wait for our first official meeting!
Surprisingly (but gladly!), my first post on Twitter is for #SummerOfShipping! Looking forward to building an exciting project this summer!
#SOSDay1: Brainstorming an idea for a data science project. If anyone already has one and is willing to collaborate, please let me know!