I couldn’t let this stand unchallenged: The new Rasmussen Poll, one of the most accurate in the 2016 Election, just out with a Trump 50% Approval Rating.That's higher than O's #'s!— Donald J. Trump (@realDonaldTrump) June 18, 2017 Ramussen makes their Presidential polling data available for both ? & O. Why not compare their ...

When knitting an R Markdown document to HTML output, R chunks can produce warnings, errors or messages. Normally these messages look like any other console output: Pretty ugly, and usually something I find myself trying to hide at the earliest opportunity. But if you’re using R Markdown’s default ...

I am pleased to announce that tidytext 0.1.3 is now on CRAN! In this release, my collaborator David Robinson and I have fixed a handful of bugs, added tidiers for LDA models from the mallet package, and updated functions for changes to quanteda’s API. You can check out the NEWS ...

My last entry introduces principal component analysis (PCA), one of many unsupervised learning tools. I concluded the post with a demonstration of principal component regression (PCR), which essentially is a ordinary least squares (OLS) fit using the first principal components (PCs) from the predictors. This brings about many advantages: There ...

Results so far obtained allow us to predict the RainTomorrow Yes/No variable. In the first part, we highlighted that such factor variable can be put in relationship with the Rainfall quantitative one by: all.equal(weather_data$Rainfall __ 1, weather_data$RainToday == "Yes") As a consequence, we are able so ...