Programming for Data Analytics - Begins Nov 9 2019, Registration Deposit
A capability boost for anyone that works with data!
We brings together important skills for any analyst. This is what you need to know to carry out a successful machine learning project.
You’ll learn Python which is the most widely taught language in Universities and one of the best for analytics.
You’ll learn about Pandas- an extremely efficient tool for data processing and handling.
We’ll teach you some machine learning theory. You’ll also get practical advice on independent (features) and dependent variable (classes) selection.
We’ll also wade into topics like model testing and bias based on real world experience with models of many different types – traffic, maintenance planning, pipeline safety, financial, energy, economic. (Don’t miss the part on model testing, it alone is worth taking the course and could save your project and your analysis!)
This is not an academic course- it’s a practical one.
Note: this is the registration deposit only. The full cost of this course is $399. There will be an additional payment of $299 due before the start of the second class.
This course runs 6 half days on Saturdays, from 9:30am to 1:30pm. Nov 9, 16, 23, 30, Dec 7 and 14th, 2019. The location is the Callingwood Recreation Centre in Edmonton, also known as the Callingwood Twin Arenas.
Visualization and data description is a foundation of machine learning. Students will learn techniques such as cluster analysis and scatter plots as well as techniques to quickly produce common charts and plots. We will look at network based classifiers (Naive Bayes), clustering and rule based classifiers.
Tools: We will use public domain Python libraries for data preparation, plotting and machine learning. These include Pandas, matplotlib and scikit-learn.
Class outline: 1. Coding fundamentals in Python. 2. Python language features 3. Data transformation, exploration and description, vocabulary. Pandas, matplotlib. 4. Data API’s, machine learning conecpts and vocabulary. scikit-learn 5. Clustering and Rule based Classifiers. Model error and performance. 6. Naive Bayes classifiers, model lift. Testing.
Your Instructor Doug Kaweski has a degree in civil engineering with addition studies in decision analysis, operations research, statistics and machine learning. He has worked as a consultant in: Screening and validation of databases Design of statistical studies
Evaluating reliability of measurement and scoring systems Regression and Bayesian regression Bayesian regression mathematics and software Publication of a Bayesian regression analysis handbook Data visualization and pictograms for embedding in analysis software Optimization techniques, optimization software
He also has experience in machine learning including work with many machine learning techniques, evaluation and real world testing.