With the tidyverse and tidymodels at their
Novel readability & lexical dispersion
Chunks of R and slithers of Python; in the caldron boil and bake
Predicting the interest rate for a fixed-rate mortgage using Bayesian regression
Quantile regression, property sales and anything could happen eventually
The grammar of tables, footnotes and occupations consigned to history
Cluster analysis and the characteristics that bind London boroughs
Decades-old residential property bands and inference using a sample of those recently sold
Predicting uncertain species of cetacean strandings recorded by the Natural History Museum
Quantitative textual analysis, word embeddings and analysing shifting trade-talk sentiment?
Simulating stock portfolio returns inspired by bowls of porridge left by three bears
Timeseries comparison and the impact of Covid-19 on the financial markets by sector
R packages & functions that make doing data science a joy based on usage across projects
Animated dimension reduction and East-West historical UN voting patterns
Visualising small multiples when crime data leave you unable to see the wood for the trees
Time series forecasting using cloud services spend data
Exploring colour palettes and small multiples using cloud services spend data
Criminal goings-on in a random forest and predictions with tree-based and glm models
Every story needs a good plot. Which plot types generate the most interest on Wikipedia?
Exploring parliamentary voting patterns with hierarchical clustering
Do we see more planning applications when house sales are depressed?
A little interactive geospatial mapping and an unexpected find
A series of events, such as the Financial Crisis and the 2016 Brexit vote, that damped down residential property sales in London
Visualising the dozens of overlapping sets formed by categories of cloud services
Welcome to the tidyverse with data ingestion, cleaning and tidying. And some visualisations of sales data with a little jittering.