Mathematical Essentials of Data Science

If we use a transportation metaphor we might say that statistics and machine learning are the vehicles that take us to both new and familiar places. We could also think of programming and software engineering as the roads and infrastructure necessary to make travel even possible. Linear algebra on the other hand aligns well with the motors and engines that propel our vehicles.

Most of us seldom think about what is under the hood as we hum steadily along a nicely paved road, but success as a data scientist requires at least a fundamental understanding. Here we present the essentials of linear algebra with the goal that you become prepared for an educational experience in data science. You may even come to believe that viewing math through the lens of matrices and vectors makes things easier.

Important

The principal focus of this contents is to introduce numeric computing and linear algebra through Python. A portion of the second day will provide a basis for the calculus that you will need as a data scientist.

Day 1:

• Thinking in terms of vectors and matrices
• Matrix operations
• Linear Algebra I

Day 2:

• Linear Algebra Part II
• Matrix Decomposition
• PCA and SVD

Appendices:

• Helpful math
• Calculus
• Symbolic computing
• Python Installation Guide
• NumPy Commands
• Other important NumPy commands
• Works cited