Xpirit joins GoDataFest as a supporter. Thanks to Xpirit, we are able to expand the program of the Microsoft day. Participants of GoDataFest now get access to the skills of the company that employs the most Microsoft MVPs in one single company worldwide!
Check out the Microsoft program, in association with Xpirit!
During GoDataFest (nov. 2- 6), these wonderful ladies will be sharing their experiences with data science, data engineering, and cloud.
Naz Levent shares tricks deploying ML Models to Amazon Sagemaker.
Sara Gerion will be talking monitoring AWS Lambda and Serverless.
Elaine ☁ Versloot talks about ways to take control of your cloud spend.
From Bol.com, Melissa Perotti explains how Bol.com structures ML projects, Mieke Nan dives into the role of the Analytics Translator.
Simone Cammel answers the question why you are not getting your data science models in production.
Data engineer Charlotte van der Scheun demonstrates how Albert Heijn is using Data Build Tool (dbt)
Check out the full program at https://godatafest.com
During this 4-hour workshop on Friday, November 6th from 13:00 – 17:00 CET, you will build your own ‘mini google’.
During this session, host Mark Schep will guide you while building your search engine on COVID-19 related articles (https://aylien.com/blog/free-coronavirus-news-dataset). You will embed your search engine in a simple user interface and publish it as a website. At the end of the day you will have something like this:
You will learn to work with the following tools to get to your end goal:
* The search engine: [Azure Cognitive Search](https://azure.microsoft.com/en-us/services/cognitive-services/)
* Data storage: [Azure Blob Storage](https://azure.microsoft.com/en-us/services/storage/blobs/)
* The User interface: [Docker](https://www.docker.com/) and [Streamlit](https://www.streamlit.io/)
* Deployment: [Azure Container Registry](https://azure.microsoft.com/en-us/services/container-registry/) and [Azure App Services](https://azure.microsoft.com/en-us/services/app-service/).
We will close the day with an open discussion on the implications of our solution & possible use cases
Preparation:
Registration is free of charge. Simply fill in this form to register.
Mark Schep is an entrepreneurial industrial engineer with a passion for data science. His ambition is to build data driven products that add value to organisations. To get there, he leans on his background and experience as a data scientist which he uses to translate business problems into data solutions.
Mark will help you identify valuable data science applications, as well as how to make them work, make them better, and get them to scale.
With Ahmet Erdem, Kaggle Grandmaster at NVIDIA.
RAPIDS is an open-source software that accelerates the whole Data Science Pipeline from Data Preparation/Visualization to Machine Learning on GPU. In this workshop, you can get familiar to RAPIDS which runs on Python with pandas/scikit-learn-like API and experience the speed-up it provides.