WiDS Datathon Resources
Tutorials, sample code, videos, and event recordings will be posted here throughout the competition. Please see the WiDS Datathon 2023 resources page on Kaggle for additional resources and links.
WiDS Datathon 2023 Climate Change Panel Webinar Recording
|
In this panel discussion, we speak with experts in a wide range of domains and institutions in order to explore the multi-faceted challenges posed by climate change. Not only do we aim to glimpse at how climate change impacts sectors spanning healthcare, energy and environmental protection, we will hear from our panel how data science can help us understand and mitigate the effects of climate change. This webinar is appropriate for audiences of all backgrounds – no prior familiarity with data science is assumed.
Watch the recording |
WiDS Datathon 2023 Welcome Event Recording
|
Learn all about this year's WiDS Datathon 2023 challenge! You will see how to get started on Kaggle, have access to datathon tutorials and resources, and be invited to attend datathon workshops hosted worldwide. We are excited to share new weekly team building activities to connect you with fellow teammates throughout the entire datathon challenge. During this call you will also have a chance to meet and network with other WiDS Datathon participants, and ask any questions you might have about the WiDS Datathon.
Watch the recording and access the slide deck |
Data Drift for Dynamic Forecasts: An Arthur tutorial for the 2023 WiDS Datathon
|
by Rowan Cheung, Teresa Datta, Haley Massa, Sarah Ostermeier
Data Drift occurs when the data used to test a model is different from the data which the model was trained and validated on. A visual figure is provided below. This is particularly relevant for time series forecasting problems, where it is natural to have variations between months, and trends often occur in annual cycles. For the task of weather and temperature forecasting, we must be aware of two potential sources of drift: temporal and geospatial. Read the tutorial |
Deepnote Introduction, Beginner, and Intermediate notebooks for WiDS Datathon 2023
|
by Allan Campopiano
Deepnote is a real-time collaborative notebook used for analytics and data science. You can work together with Python, SQL, and no-code approaches for analyzing data. We've created a beginner- and intermediate-level tutorial that will help you succeed in this competition. If you are new to Deepnote, you will be prompted to sign up when you run code in this project. Read the tutorials |
Weather Forecasting in MATLAB for the WiDS Datathon 2023
|
by Grace Woolson
Today, I’m going to show an example of how you can use MATLAB for the WiDS Datathon 2023. This year’s challenge tasks participants with creating a model that can predict long-term temperature forecasts, which can help communities adapt to extreme weather events often caused by climate change. WiDS participants will submit their forecasts on Kaggle. Read the tutorial |
Deep Learning Tutorial for WiDS Datathon 2023
|
by Usha Rengaraju, Kaggle 2x Grandmaster
The dataset consists of weather and climate information for a number of US locations, for a number of start dates for the two-week observation, as well as the forecasted temperature and precipitation from a number of weather forecast models. Each row in the data corresponds to a single location and a single start date for the two-week period. The task is to predict the arithmetic mean of the maximum and minimum temperature over the next 14 days, for each location and start date. Read the tutorial |
Getting Started with Kaggle - WiDS Datathon Videos
|
by Usha Rengaraju, Kaggle 2x Grandmaster
Video: Getting Started with Kaggle - an introduction on how to get started with Kaggle and how to navigate WiDS Datathon Kaggle competition page Video: Energy Consumption Prediction - a baseline notebook walkthrough of WiDS Datathon |