Dataiku Explorer Series
Hands-on Workshop
- Thursday, 15th February
- Wework, 120 Spencer St, Melbourne
- 2:30 PM - 5:00 PM (+ Networking)
This interactive hands-on workshop welcomes participants of all backgrounds, extending its accessibility to a diverse audience—from business users to data analysts—regardless of their proficiency in IT.
The goal is to provide you with first-hand experience of building Data and ML pipelines in Dataiku Data Science Studio (DSS) leveraging no-code, low-code and high-code approaches.
There are only limited spots available – so FIRST IN, BEST DRESSED. In case of a high volume of applicants, early closure may occur.
Save your seat
This interactive hands-on workshop welcomes participants of all backgrounds, extending its accessibility to a diverse audience—from business users to data analysts—regardless of their proficiency in IT.
The goal is to provide you with first-hand experience of building Data and ML pipelines in Dataiku Data Science Studio (DSS) leveraging no-code, low-code and high-code approaches.
There are only limited spots available – so FIRST IN, BEST DRESSED. In case of a high volume of applicants, early closure may occur.
What you will learn
Whether you're a seasoned data scientist or just starting to explore the field, this hands-on workshop is crafted to be inclusive and beneficial for individuals at every stage of their skill development journey.
What you will need
Participation in the event requires a laptop with internet access.
By the end of the session, you will be able to:
- Ingest and wrangle data coming from a flat file and a SQL database
- Build an ML model using Automated Machine Learning
- Orchestrate the pipeline to run in batch mode on a timely basis (hourly/daily/weekly/monthly etc); and
- Evaluate your ML models across drift, prediction and performance metrics
Agenda
Thursday, 15th February
2:30 PM - 5:30 PM
Time
Details
2:30 pm - 2.45pm
Guest Check-in
2:45 pm - 2.50pm
Dataiku: Key Concepts
2:50 pm - 3.45pm
Part 1: From data access to machine learning model creation
- Prepare: Ingest data (text file and SQL-based table) and wrangle data (Append, Join, Apply Business Logic to data).
- Build: Apply Exploratory Data Analysis (EDA) techniques prior to building a Machine Learning model.
3:45 pm - 4.45pm
Part 2: Orchestrate and Monitor the ML pipeline
- Deploy: Operate and deploy data pipelines and models.
- Monitor: Evaluate ML models in production across drift, prediction and performance metrics.
4:45 pm - 5.00pm
Session Wrap-up
5:00 pm - 5.30pm
Socials/Networking
Location
WeWork
120 Spencer St, Melbourne VIC 3000
Room 22, Level 22