This is a remote course delivered over two half-day sessions via Zoom, for a small group of approx. 10 people. The course introduces you to time series data analysis using the Python programming language and the PyData ecosystem.

Intended audience: Time Series Analysis with Python is aimed at an audience of software engineers, data scientists, data analysts, business analysts, researchers and students who want to get started with Time Series Analysis with Python, with the purpose of understanding and extracting useful information from their time series data.

The course will focus on practical examples using Python and relevant libraries like pandas and statsmodels. No prior experience with time series analysis, pandas or statsmodels is required, but attendees should have some basic working knowledge of Python to be able to follow the examples and complete the exercises, i.e. you should be familiar with basic Python syntax like lists/dictionaries, for loops or custom functions. This course is not aimed at first-time coders.

Learning Objectives

By attending this course, you will learn about:

• the core concepts and properties of time series like trend, seasonality, or stationarity
• how to represent dates and times in Python and pandas
• how to load time series data in pandas, e.g. from CSV or Excel files
• how to extract summary statistics on time series data
• how to observe changes in your variables over time
• how to compute data aggregation on time windows
• rolling statistics like moving average, why they're important and how to calculate them
• what is time series decomposition and how to perform it to observe trend and seasonality
• how to visualise time series data with pandas, matplotlib and seaborn

Syllabus Overview

1) Time Series Foundations

• Overview on time series and time series analysis
• Loading data in pandas
• Exploratory analysis of time series
• Summary statistics
• Calculate changes over time

2) Working with time index in pandas

• Resampling
• Moving windows
• Comparing two time series with different granularity (e.g. hourly vs daily data points)
• Joining two time series

3) Time Series Decomposition with statsmodels

• Additive and multiplicative models
• Stationarity
• Observing trend, seasonality and noise

4) Visualising Time Series data

• Easy time series plots with pandas
• Custom visualisations using matplotlib and seaborn

5) Final Workshop (small capstone project)

Course schedule, delivery and teaching style

This course is delivered over two half-day sessions on 21-22 June 2021, 2pm-5:30pm UK time (GMT+1). We'll have comfort breaks during the sessions as appropriate.

You'll need your computer/laptop with a recent Anaconda pre-installed with Python 3.8+. I'll check-in with you before the course with set-up and joining instructions to make sure you have everything you need.

This is an online only course via Zoom, you'll need an adequate bandwidth for live video conferencing. You can use Zoom via web, but you'd probably have a better experience with the app.

The course is hands-on and offers plenty of demos/examples/exercises: expect to read Python code and write Python code. Whenever theory is needed, I explain it with a focus on the main intuitions and motivations to keep it practical.

By signing up, you'll receive

• Access to the live sessions on 21-22 June 2021 via Zoom
• Set-up and joining instructions before the course
• Teaching material: code examples, demos and exercises in the form of Jupyter notebooks
• Additional exercises: take-home exercises that you can use after the course to further improve your understanding
• A Certificate of Professional Development after course completion
• An invite for a retrospective group call to discuss progress and problems (1-hour call, circa 2-3 weeks after the training, complimentary)

About the instructor

I'm a Data Science consultant, corporate trainer and author based in London, UK. I specialise in the Python for Data Science (PyData) software stack.

With 20 years of experience in the tech industry, I provide consulting, coaching and training services in the data science space through my company Bonzanini Consulting Ltd.

Backed by a PhD in Information Retrieval, I specialise in text analytics applications, and I’ve enjoyed working on a broad range of information management and data science projects, including flight safety, social media data, behavioural data, biomedical data and recruitment data.

I’m the author of “Mastering Social Media Mining with Python“, “Data Analysis with Python” and “Practical Python Data Science Techniques“, published by Packt Publishing.

I currently serve as chair of the PyData London meetup and conference series (largest Python user group in Europe) and I regularly speak at international tech events.

Refunds and Change Policy

Eventbrite offers you a 100% refund for cancellations up to 7 days before the event. Should you need to cancel I'm happy to talk to you to see if we can figure something out.

I can move a ticket to another colleague if needed, simply get in touch.

In the unlikely event that we have to cancel the course then you will be offered either a 100% refund or the option of moving attendance to another future workshop. Bonzanini Consulting Ltd and Marco Bonzanini are not liable for any other costs incurred.

Questions? Get in touch

If you have questions please contact Marco@BonzaniniConsulting.com.

Check out Marco's blog for a list of past public presentations and workshops. I also curate the newsletter Musings on Data where I share my thoughts and recommendations on Data Science, once every few weeks (it also includes announcements of future trainings, so sign up for early access and discount codes).