Get started with open source time series processing and prediction
Who is this presentation for?
This presentation is for beginner or intermediate data analysts or for programmers who are interested in understanding more about temporal data analysis. While experienced data analysts will get more out of the course I will make sure that novice data analysts can walk away from this full day training with a complete set of skills, even if the theory aspects of the presentation may not be fully addressed to novice audiences. It is essential that those attending the course have a comfortable working knowledge of Python and some familiarity with R. Finally, those more interested in management may still find this presentation helpful in looking at the range of open source tools available for forecasting and panel data analysis even if they are not able to fully engage with the programming exercises.
Training materials will all be on Katacoda, so attendees need a working computer with the ability to run Katacoda. Attendees should feel comfortable working with Python and also have some understanding of what time series data is and why the analysis of time series data could be useful to their work. Familiarity with R will also be helpful but not essential.
Time-oriented data munging (1.5 hours total) 10 – 11:30)
- Overview of data storage and processing problems in working with timestamps and ordered data
- Working with timestamps
- Rolling windows
- Sampling data at different frequencies
- Aligning temporal data
- Visualizing temporal data
Time series features (1 hour total 11:30 – 12 and 1 – 1:30)
- Overview of typical features created for time series and how features can be used
- Feature traps and how to avoid them
- Hand coding sensible features
- Automating feature generation
Statistical and machine learning models for time series (3.5 hours total)
- Overview of common modeling tasks used for time series data (classification, forecasting, imputation, unsupervised learning)
- Models that use features as compared to models that use raw data
- Example statistical models for forecasting
- Example machine learning models for classification and unsupervised learning
About your instructor
Aileen Nielsen works at an early-stage NYC startup that has something to do with time series data and neural networks, and she’s the author of a Practical Time Series Analysis (2019) and an upcoming book, Practical Fairness, (summer 2020). Previously, Aileen worked at corporate law firms, physics research labs, a variety of NYC tech startups, the mobile health platform One Drop, and on Hillary Clinton’s presidential campaign. Aileen is the chair of the NYC Bar’s Science and Law Committee and a fellow in law and tech at ETH Zurich. Aileen is a frequent speaker at machine learning conferences on both technical and legal subjects.
Get a Training Pass to add this course to your package.
Leave a Comment or Question
Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?
Join the conversation here (requires login)
For conference registration information and customer service
For more information on community discounts and trade opportunities with O’Reilly conferences
For information on exhibiting or sponsoring a conference
For media/analyst press inquires