Book Review: Python Data Analysis

Recently, I have been diving more into data analysis and data science. For the past few months, I have been really into it. Why? This is due to a variety of reasons, from Salesforce and Microsoft becoming more AI data driven, to the fact I think in 5 years, Marketing CRM Architects will not just need to know how to set up a CRM but help build the wheel of analysis, invest, and growth within a company’s CRM. This is why I have been doing data analysis since September, so let us do a review.

What I Took From It

Data is the information you collect and with so much data nowadays from not just basic information, but location data, email opens, website clicks, all of it is so much. But with data analysis it allows us to understand our data and understand what our goals are and how to achieve them. That is what this book dives into by helping to understand pattern analysis and outputting into different graphs and charts to see where the data is leading to.

When I started with this book, I had no idea about the power of Jupyter notebooks, but I did know python. I did not know numpy, or matplot but in the end I was taking data and starting to run it through various solutions such as matrix inverse, Davies boudin index, as well as building out heat maps, diagrams and developing charts. These are just some of the things that I learned along the way. What I was not prepared for with data analysis is all the math. I had to start diving into Khan Academy and whipping out a notepad on my iPad to polish off those old high school math skills dealing with linear algebra and calculus.

Getting started with this book, I was using visual studio code for Jupyter notebooks but then I switched over to JetBrains Dataspell. Why did I switch over? Well, a few reasons, you don’t have to do this because Dataspell costs money, but as I was going into it and seeing what books I had planned to jump into next I decided to buy the Jetbrains program for a year.

This book dives into some heavy stuff, from different data pipelines to statistical analysis, now I did find it quite informative on data cleaning cause working within Marketing Cloud, there is a lot of excessive uncleaned data. The key things that I could use within my own career is the KDD process or Knowledge Discovery of Data for data mining cause in my own world, data cleaning, data integration is what I have to use within Marketing Cloud with getting data, making sure it’s the correct one, and making sure it’s the right data that is being sampled and collected while looking for oblivious patterns. Now even though this book is quite advanced and had my brain knocking against the desk at times, it was a lot that I could carry into my own career.

Who Is This Book For:

This book and this area of focus is not for the faint of heart in the tech world. It combines a lot of knowledge that I haven’t used in so long, however with my career being that within dealing with mass amounts of data I felt that is a needed. If your career touches mass amounts of data, then I would highly suggest jumping into understanding some data analysis. If you are planning to jump into data analysis in anyway then this might be a second book to jump into after learning some python.

In Closing:

The reason this book took so long to get reviewed was because of just how advanced the skills and learning that was needed in addition to what was done in the book. However, I do feel that where the of world of marketing and data and AI, there will be a massive need for Marketing CRM admins to understand data analysis and recycling and redoing campaigns and spending more time growing campaigns and growth.