Motivation This is an exercise in using machine learning to predict the level of harmful bacteria in New York Harbor based on environmental factors like tidal conditions, rainfall and location. Among the reasons this is useful is understanding how to rebuild a marine life ecosystem in the harbor, where oysters ...

These are the packages we will need for this analysis. library(tidyverse) library(data.table) library(dtplyr) library(duckdb) library(duckplyr) library(polars) library(tidypolars) library(arrow) library(tictoc) library(microbenchmark) library(gt) The Tidyverse I love the Tidyverse from Posit.co. The biggest evolution of the R language ecosystem ...

These are the packages we will need for this analysis. library(tidyverse) library(data.table) library(dtplyr) library(duckdb) library(duckplyr) library(polars) library(tidypolars) library(arrow) library(tictoc) library(microbenchmark) library(gt) The Tidyverse I love the Tidyverse from Posit.co. The biggest evolution of the R language ecosystem ...

These are the packages we will need for this analysis. library(tidyverse) library(data.table) library(dtplyr) library(duckdb) library(duckplyr) library(polars) library(tidypolars) library(arrow) library(tictoc) library(microbenchmark) library(gt) The Tidyverse I love the Tidyverse from Posit.co. The biggest evolution of the R language ecosystem ...

Some History The war in Ukraine has spawned yet another disaster, the destruction of the dam across the Dnipro river, upstream from Kherson City. This is an ecologial and humanitarian disaster as vast acres of settlements, farmlands and wetlands have been destroyed. This marks the third time a dam in ...

Wrangle the Data suppressPackageStartupMessages({ library(tidyverse) library(rayshader) library(gt) library(gifski) }) The best part of any analysis are the visualizations. I couldn’t resist taking the results of our earlier sentiment analysis and turning it into some appealing eye candy. You’ll recall we tried several different approaches to ...

Introduction Many of us in the U.S. have been surprised by the indifference many in less developed countries have shown about the Ukraine war. There has been much talk lately about how the “Global South” is feeling slighted by the rich countries ...

Introduction In Part 2 of this series we learned that summing the valence measurement of the words in the Afrisenti data set did not agree well with the sentiments already provided. While the sentiments we calculated made sense in general, they w...

Introduction Sentiment analysis is a common task in natural language processing. Many of the tools available for this are calibrated to the English language. Can Google Translate let us apply this toolset to a broader set of languages? We will us...

Inspired by TidyTuesday Some of the the R data science community participate in a weekly challenge called “Tidy Tuesday,” where an interesting data set is presented for analysis but mostly visualization. There are some tremendous examples of beau...

It all started when I decided to change up my Hugo theme. Up until that point I was happily using the Blogdown add-in for RStudio to initiate new blog posts. At some point the default directory structure for Hugo blogs changed and when I tried to ...