Gustavo

Los Angeles has little history with Wagner’s four-opera “Ring” cycle, his epic on how to save the world from conniving gods, power mongers and hoarders of wealth with their ruinous fancies. This global predicament is never out of date. The 2010 L.A. Opera production has been the only full cycle in L.A. since 1930. In this country, San Francisco, New York, Chicago and Seattle have seen several.But after the Los Angeles Philharmonic mounted “Das Rheingold” last weekend — the two-and-a-half-hour prologue to the three main…

Regression models are out there for a long time now, much longer before Machine Learning was a thing. Statisticians have been using these models to understand the relationship between variables even before the 1900s, when Sir Francis Galton (1885) introduced the idea.Fortunately, the theory has developed so much since then, and so have the computers and technology, up to the point that we can say that it is an easy (if not the easiest) model to create these days.However, do not be fooled by its easiness to implement. It…

One thing is true: if you ever coded, you faced an error. Period.Errors are not always a bad thing. I agree that they can drive us mad sometimes, especially if we have looked the code over and over again without finding the bug. However, error messages must be understood as something that is not working as expected in your code.Let’s face it, we can create N test scenarios, but the end user will find the bug N+1. And that’s ok, as long as we can plan for the most common ones.In this article, we will go over known error…

Use R Language to create scores for observations based on many variablesPhoto by Joshua Golde on UnsplashThe more I study about Principal Component Analysis , the more I like that tool. I have already written other posts about this matter, but I keep learning more about what’s “under the hood” of this beautiful math and, of course, I will share that knowledge with you.PCA is a set of mathematical transformations that work based on covariance and correlation of the data. So it basically looks at the data points and finds…

Text everywhere! Since the Internet was spread around the world, the amount of textual data we generate everyday is ginormous. Only textual messages sent everyday, it is estimated that there are around 18 Billion of them circulating on a daily basis*.Now imagine the amount of news generated as well. It’s a so overwhelming amount that there are whole businesses built around news clipping, separating the best information about a given topic to help companies in their marketing strategies.How is AI helping that? Certainly,…

Feature selection is an important step for any data science project. I can imagine you heard it a million times if you’re not new to the field, and I am sure you already heard it if you’re a newbie, but I will say it again: If you feed your model with garbage, you will collect garbage as a result.Ok, now that we took that our of our chest, let’s move on. There are a couple of good ways to select the best features for you model, like running a Random Forest model and then checking the feature_importances_ attribute, using…

When a project involves text analysis, such as sentiment analysis, text mining, or any other task you were entitled to do analyzing textual information will probably require parsing text at some point. This mean that one will have to extract a piece of a text or find a given pattern within a text to be able to extract an insight, for example.If we are dealing with a simple pattern, like a word, or a number, that is easy enough to deal with in R.Imagine you have this following text and you want to find the word random.…

Datasets are made of numbers and/ or text. Thus, we should expect that not all the variables will be just about numbers, which, by the way, count on many techniques to be analyzed, tested and worked.When we are working with numerical variables, there are tools like correlation, PCA, scaling, normalization, and a bunch of tests. On the other hand, if we’re working with text, more specifically, categories, we should go after other techniques to apply to our data analysis.One of these tools is the Correspondence Analysis…

It’s hard to keep up with new tracks every week. With a bevy of songs being released every day, we made a list highlighting some new tracks from Canadian artists.Wynne Badoe f/Bobby Brugal & City Fidelia, “3 Sides”From: TorontoFlanked by two of Ottawa’s finest, Wynne Badoe’s latest throws three confessional-like verses over a hauntingly uplifting instrumental. Each verse offers a personal tale but each rapper never wallows away in their sadness.Gustavo Guaapo, “No Hoes In The Studio”From: TorontoWhile Guaapo’s latest…

When creating a classification model, many algorithms offer the function predict_proba() to give us the probability of that observation being classified under each class. Thus, it is common to see an output like this:In the previous case, the model is 92.5% sure that the observation pertains to class 0, and only 7.5% of chance to be from class 1.If we, therefore, request this same model to give us a binary prediction using the predict() function, we’ll just get a as the result, correct?In this example, it is most likely…