Broadcasting is a feature of Python and Numpy. When one is performing array operations, in some cases the shapes of the arguments do not match. The good and bad thing is that Python assumes what you want to happen and does it. In most cases the results are fine, but on occasions Python might do something that you are not expecting. This post discusses to some degree what is broadcasting. The idea is that we will be using it in a future post when doing some regressions for image recognition. Continue reading “Broadcasting in Numpy”
When learning and working with Python on machine learning it is important to make sure that Numpy arrays have the proper dimensions. Using improper dimensions may cause issues / bugs that are hard to track yet it is simple to prevent and we will see in this post. Continue reading “Numpy Vector Notes for Machine Learning”
It is the last Sunday in January 2019 and is relatively cold in the Twin Cities of Minneapolis and St. Paul. The computerized mercury scale indicates -12F not taking into account wind. As usual, get up before 05:00 AM and get in my first 2 hour block of Deep Work. I am in the process of reviewing the last course I took on neural networks and deep learning. Continue reading “Numpy Vectorization – Revisited”
As you may already know, I have been taking several AI / ML related courses. I am a firm believer in always keep on learning. Some time ago I read a report about people in the USA reading books. The statistic that called my attention was: 42% of college graduates never read another book after college. That seems to me quite disturbing. Another statistic is: 57% of new books are not read to completion. To this indicates that a) readers are not committed to learning and / or books are getting worse. Continue reading “Numpy Vectorization”
The past weekend was kind of cold in the Twin Cities area of Minneapolis and St. Paul. Seems like winter a somewhat ahead of time.
In the past few months I have been spending time learning and experimenting with machine learning (ML) and Big Data. Machine learning seems to require a lot of properly cleaned samples. This is one more case when garbage in implies garbage out. That said; the first step is to collect data. Data can come from different sources i.e., databases, files, public repositories, the Internet, etc. Data can be collected from the Internet in different ways. In general one can collect data from the internet using two main approaches: web scraping and via an API. I will cover both of these approaches in the following posts. Continue reading “BeautifulSoup”
Last week I was reading a post on Medium “First Steps in Data Science with Python NumPy” by Kshitij Bajracharya.
What called my attention is his opening statement “I’ve read that the best way to learn something is to blog about it”. I believe Kshitij hit it right on. The reason I agree is that I have been a believer in “If you can’t explain it simply, you don’t understand it well enough”. This quote is attributed to Albert Einstein. Continue reading “Simple Problems in Python”
It is Friday. Many stressful things are happening in different fronts in the past few months. Most of the things are out of my control. It seems like I need to find a way to relax. Hopefully things will turn out well. I fully understand that stress is an internal thing and I am quite good at controlling it. I used to say that stress is the salt of life; but too much salt is not good for you. Continue reading “Crash Course in Python – Part II”
As I have mentioned in previous posts, I like to purchase and read computer related technical books. When I receive the book I write my name and year on the first page. I then locate the date for the last revision and circle it. In 2017 I purchased “Data Science from Scratch” by Joel Grus. I read the first five chapters that I was interested it at the time and moved on to the next book. Continue reading “Crash Course in Python – Part I”
I am constantly reading and experimenting to learn things which I may apply to work projects. A few years ago I decided to spent time on and off learning machine learning (ML). With that purpose in mind, I got a number of books on different subjects (e.g., Deep Learning, Python and Statistics) which seemed to be useful to achieve my goal.
On the platform side, I started experimenting on Windows. Most things work fine but some things do not. For example, I had to wait to use Tensorflow because it ran on Linux but not on Windows. Today it seems to work on both. The same seems to hold true for Docker. Continue reading “Machine Learning – Setup”