Hands-on Workshop

Insight Into Python

Introduction:

This Hands-on Workshop is an introduction to Python. Python is an increasingly popular free programming language which has widespread adoption across the scientific community. One of the biggest drivers for the popularity of the language has been its widespread adoption as a tool for data science. Python can supplement existing tools like SAS and R through modules/offerings like RPython and SAS Viya. It can also be used as an analysis tool in its own right, with an extensive set of libraries for common tasks such as data wrangling, data analysis and statistical analysis.

Python has strong representation in the machine learning industry, with industry-standard tooling like TensorFlow, Jupyter and PyTorch. Jupyter Notebooks provide a really easy mechanism for sharing encapsulated data and code in an interactive experience for people looking to pick up the language.


Workshop Overview:

For the session we will focus on a few basics and then put together some relevant examples from the biomedical sciences domain that you can start with. There will be much more than we can cover in the time allotted to take away anything other than a cursory understanding of the Python language – this session will be primarily about sowing the seeds. There will be some pre-course webinar sessions explaining how to get set up so you are ready to go when we start. Attendance at these pre-session courses will be strongly encouraged!


Overview (45minutes):

  • History of Python
  • Overview of the core types
  • Reading and writing files
  • Modules and libraries



Scenario 1 – Machine Learning and Analysis (60 minutes)

  • Take a sample source and load it into Jupyter (Python programming environment) (https://jupyter.org/)
  • Prepare the data for analysis
  • Calculate some aggregate values
  • Prepare a simple plot of the data
  • Take a sample model and train it for entity extract from narrative text
  • Run the model on a sample narrative



Scenario 2 – Using Web APIS (10 minutes)

  • Make a request using the requests library
  • Use the requests library to access the CDISC library
  • Use the Amazon AWS Comprehend Web Services API to extract medically relevant terms from narrative text



Wrap-up and Next Steps (5 minutes)

 

Organisation:

  • Pre-course webinar sessions explaining how to get set up so you are ready to go when we start
  • Attendance at these pre-session courses will be strongly encouraged!


Workshop Lead:

– Geoff Low, Medidata Solutions

 

 

Thinking of joining PhUSE?

Already a member but not sure how you can benefit?

PhUSE is an expanding, global society with a membership of more than 9,500 clinical data scientists. It requires a large pool of resources to help with its running, and so there are many opportunities for members to become involved. Whether it's chairing a conference, presenting at an event, leading a working group or contributing to the quarterly online newsletter, we are always keen to hear from volunteers.

Find Out More