August was a bit “light” for summer vacation reasons, but I attacked September with renewed vigor! I look back to when I started this journey in June, and I marvel at how much I’ve learned since thing. And I’ve also been humbled at how much more there is to learn (years’ worth!). However, in the spirit of documenting what’s been accomplished, here’s the record for September 2015:

## Coursera – Exploratory Data Analysis

This is the fourth course in the Coursera Data Science Specialization track and by far, the most enlightening one so far. The initial exploration of a data set is vital to future insights. In addition to learning about the various R graphics packages (especially **ggplot**) an introduction to **clustering** (i.e. k-clusters) provided a taste of things to come.

Data Science requires hard work. It’s not a simple set of skills that can easily be achieved by a set of short tutorials. The last part of this course on clustering gives a taste of that fact. You *will* need an understanding of some higher level mathematics (statistics and linear algebra) in order to make use of the tools and algorithms that have been developed. No pain, no gain, folks. If you’re not willing to sweat for your eigenvalues, then get out of the gym!

## Coursera – Machine Learning

Speaking of mental stretches, this 11-week course on Machine Learning was one of the most challenging I’ve encountered since graduate school It was heavy on the mathematics (especially Linear Algebra) and introduced me to a new mathematics software package called Octave (an open source rendition of MatLab).

This has been the most challenging course I’ve taken so far. The professor recorded 110 lecture videos on a wide variety of topics from basic linear algebra to pattern recognition in photographs to determine numeric digits. You will not be an expert in the subject after this course (after all, are you an expert in Physics after a single class?). But the notes I took and the challenging quizzes and lab exercises this course demanded will provide a wealth of material that I will be referring to for years to come!

Make no mistake – this is an *advanced *course. But this is where modern Data Science is at. You need to know this material if you’re serious about the subject.

The two items above are what were *completed* in September. But for the record, I pursued a number of other tracks throughout the month. I’ll write more about each in the month I completed them, but briefly, this month also contained daily work in:

**Doing Data Science** – What a great book written by two women who developed a course on Data Science at Columbia University! This book feels like a friend or coworker who pulls me aside and says, “Here’s what Data Science is *really* about.”

**Data Smart** – I’m working through this book for a *second* time. I’ve read the book already, but now I’m going back to the beginning and working through every Excel example, taking detailed notes on every step. Chapter 2 on *K-means* *clustering* makes so much more sense now, especially tied in the with Exploratory Data Analysis course as described above.

**SAP HANA Administration** and **Getting Started with SAP Lumira** – I’ve read more than halfway through both of these books in September. HANA as an in-memory, lightening quick database and Lumira as one of the coolest interactive reporting platforms I’ve ever gotten my hands on.

I gave a demonstration this morning to my company’s CEO of a HANA dataset consisting of about a million records that were sliced & diced in no time at all using Lumira’s beautiful & intuitive graph development platform. I’ve been working with data & reporting for 20 years now, and I still am smiling from this leap in technology.

**Coursera – Data Analysis and Statistical Inference **– Finally, I began a new course that reinforced the fundamentals of probability and statistics. So far, basic statistics (mean, variance, normal distribution, Bernoulli distribution) as well as Baye’s Theorem and hypothesis testing were covered in detail in the first three weeks. This foundation of statistics is **essential** to further progress in Data Science. And so far, this has been the highest quality of any Coursera course I’ve worked through.

[…] course on Machine Learning, by Andrew Ng, is famous for launching the Coursera platform and was one of the first courses I took. But there’s these other guys at Stanford who may have one-upped Mr. Ng with their own […]

LikeLike