Two related fallacies I see in machine learning practice are the shift and balance fallacies (for an earlier simple fallacy, please see here). They involve thinking logistic regression has a bit simpler structure that it actually does, and also thinking logistic regression is a bit less powerful than it actually […]
This note is a little break from our model homotopy series. I have a neat example where one combines two classifiers to get a better classifier using a method I am calling “ROC surgery.” In ROC surgery we look at multiple ROC plots and decide we want to cut out […]
So are model homotopies commonly used? Yes, they are.
Let’s take a stab at our first note on a topic that pre-establishing the definitions of probability model homotopy makes much easier to write. In this note we will discuss tailored probability models. There are models deliberately fit to training data that has an outcome prevalence equal to the expected […]
Nina Zumel just completed an excellent short sequence of articles on picking optimal utility thresholds to convert a continuous model score for a classification problem into a deployable classification rule. Squeezing the Most Utility from Your Models Estimating Uncertainty of Utility Curves This is very compatible with our advice to […]
A common mis-understanding of linear regression and logistic regression is that the intercept is thought to encode the unconditional mean or the training data prevalence. This is easily seen to not be the case. Consider the following example in R. library(wrapr) We set up our example data. # build our […]
We have a new R WVPlots plot: ROCPlotPairList. It is useful for comparing the ROC/AUC of multiple models on the same data set. library(WVPlots) set.seed(34903490) x1 <- rnorm(50) x2 <- rnorm(length(x1)) x3 <- rnorm(length(x1)) y <- 0.2*x2^2 + 0.5*x2 + x1 + rnorm(length(x1)) frm <- data.frame( x1 = x1, x2 […]
R is a powerful data science language because, like Matlab, numpy, and Pandas, it exposes vectorized operations. That is, a user can perform operations on hundreds (or even billions) of cells by merely specifying the operation on the column or vector of values. Of course, sometimes it takes a while […]
I would like to re-share vtreat (R version, Python version) a data preparation documentation for machine learning tasks. vtreat is a system for preparing messy real world data for predictive modeling tasks (classification, regression, and so on). In particular it is very good at re-coding high-cardinality string-valued (or categorical) variables […]
vtreat version 1.5.2 just became available from CRAN. We have a logged a few improvement in the NEWS. The changes are small and incremental, as the package is already in a great stable state for production use.