This repository contains workshop content and resources for the 2018 BC Data Science Workshop hosted by PIMS. Please see below for links relevant to each team.
Approximately fifty workshop participants comprise students affiliated with PIMS institutions or local industry, forming five teams. Each team will have five days to tackle an innovation challenge provided by an industry mentor:
- SSR Mining
- St. Paul's Hospital
- SNC-Lavalin
- Comm100
- CloudPBX
Participants will be given a partition the
bcdata.syzygy.ca Jupyter Hub, courtesy of PIMS (and
thanks to Ian Allison). You will see on this partition a data directory which
houses this repository as well as the workshop data from the industry
mentors. This directory is read only, but the repository [in general] is not:
you can download your own local
copy to ~/ on your partition
and alter content as you please.
Each partition has a 20 GB local disk quota (please do not exceed this). Computational resources are shared amongst participants - if you have a large/expensive computation to perform, the best time to do it is in the morning or at night. Please note that if a job is taking up excessive amounts of computing space then the process may have to be killed to allow all participants fair access to the computing resources.
- Predicting heavy equipment failure
- Connecting genetic mutations to cytokine levels
- Interpolating ship paths in the Port of Metro Vancouver
- Determining intent and automating knowledge base creation from live chat transcripts
- Analyzing user opinion of call quality, and network performance of a VoIP PBX
Please visit the workshop website for information, schedules and resources. The full schedule has updated room assignments.
This repository also contains a resources document for individuals who might need a refresher on GitHub, scikit-learn, pandas, nltk, tidyverse, dplyr or bash. The document also contains some project-specific resources for loading and formatting particular file types (like genetic data); and resources for running specific technical methods that might be useful in solving the projects.
The computing Hub for this workshop is accessible to participants at bcdata.syzygy.ca. Login requires a GitHub handle. Information on how to acquire this handle can be found in the resources document.
- PIMS
- IAM
- CloudPBX
- Comm100
- SSR Mining