Data Science
Qualification: National Certificate in Information Technology
(Systems Development)
Typical learning time: Full time: 9 - 12 months; Part time: 18 - 24 months
What does a Data Scientist do?
Data Scientists are big data wranglers, gathering and analysing large sets of structured and unstructured data. A Data Scientist’s role combines computer science, statistics, and mathematics. They analyse, process, and model data then interpret the results to create actionable plans and inform decision making.
Data Scientists are analytical experts who utilise tools from both technology and social science to find trends. They use industry knowledge, contextual understanding, and skepticism of existing assumptions to uncover solutions to business challenges.
On the Umuzi programme you will learn how to work with structured as well as messy, unstructured data. You’ll learn to clean and manipulate data before you analyse it and use it to build models. Finally you’ll learn to visualise your results and interpret them to help non-technical colleagues understand your findings so that your work can inform practical decisions.
Your learning journey with Umuzi:
Data Science
STEP 1
Introduction to Data Science
Foundations
Building blocks of data science
How does data work and how do we use it effectively?
Python for data science
How to set yourself up for success with the no. 1 programming language for data science
Data collection and survey design
Gathering the data you need to generate valuable results
Introduction to Statistics and Probability
Conducting exploratory analysis on data sets
How to approach a data set
Basic statistics
Move from basic principles to linear regression
Typical Data Science workflows
How do data
scientists get work done?
Creating consistent product documentation
Basics of Extract Transform & Load pipelines
Learn what goes into making data usable
STEP 2
Deeper Into Data Science
Data wrangling and database development
Data wrangling with Python
Transform and clean your data to make it usable
Data structuring and access
Structuring & accessing data with relational databases (SQL)
Communicating your data - visualisation and presentation
Use leading data visualisation libraries
Create meaningful outputs and communicate to stakeholders
deep dive into statistics
Using
advanced algorithms
K-means & logistic regression
Advanced statistical thinking
Statistical inference, parameter estimation & hypothesis testing
STEP 3
Advanced Data Science
Advanced techniques - Machine learning and AI
Classification learning
Use decision tree learning for unsupervised classification learning
Build ML workflows
Use Sci-kit learn to build ML workflows
Natural language processing
Use NLTK to process symbolic and statistical natural language in English
Advanced Python tools
Utilise the power of pandas
Use open-source tools to manipulate data and perform computations
Powerful array computations
Learn how to use NumPy to handle complex arrays
Algorithm efficiency
Big O Notation
Learn about Big O and algorithm optimisation