Recently I’ve been doing some experiments with the new R package ggfx. Earlier this month I shared an example, using ggfx for good. Since then, new features have been added to ggfx and I’ve found new applications for them. In this post, we’ll take some standard charts and watch them glow up as we add new features from ggfx. Having our charts glow up might not be the best idea, Bob Rudis suggests we’re converging on Excel level graphs.
I have been recently messing around with the new ggfx package. using #rstats ggfx::with_bloom and ggridges::geom_density left with ggfx, right without pic.twitter.com/L8yknjAJVw — 📈 Len Kiefer 📊 (@lenkiefer) March 4, 2021 Most of my applications (see below for a gallery) have maybe not been applying good dataviz guidelines. But I think I have found a good example. We can use the ggfx::with_blend function to layer a recession indicator with a time series and color code the lines.
Yesterday I gave a virtual lecture on data visualization at GMU. Here I’m posting the slides I used for that talk and including my discussion notes for the portion of the talk where I discussed guidelines for data visualization. At the beginning of the talk I spoke a bit about data visualization guidelines. I framed this part of my talk around Jon Schwabish’s five guidelines from his new book Better Data Visualizations see (on Amazon) and here for a blog summary.
Last week the U.S. Commerce Department reported the advance estimate for annual economic growth for 2020. For the full year, US gross domestic product contracted 3.5 percentage points, the largest annual decline since the 11.6 percentage point contraction in 1946. The similarities pretty much end there. In 1946 the US economy was demobilizing after finishing the fight against fascism. Factories were shuttered that had been producing munitions, fighter planes, tanks and liberty ships, while the G.
Earlier today I tweeted out a chart of house prices using my inari color theme. House price growth lifting off pic.twitter.com/TvNJcOZrTF — 📈 Len Kiefer 📊 (@lenkiefer) January 26, 2021 Below is the R code to generate the plot. # load libraries library(tidyquant) library(tidyverse) # list of FRED Tickers tickers<- c("LXXRSA","SPCS20RSA","LVXRSA","SEXRSA", "SFXRSA","NYXRSA","BOXRSA","SDXRSA","CHXRSA", "DNXRSA","PHXRNSA","DAXRNSA","WDXRSA", "ATXRNSA","MIXRNSA","POXRSA","MNXRSA","DEXRNSA","TPXRSA","CRXRSA","CEXRSA") # list of city names cities <- c("Los Angeles","20-city","Las Vegas","Seattle", "San Francisco","New York","Boston","San Diego","Chicago", "Denver","Phoenix","Dallas","Washington DC", "Atlanta","Miami","Portland","Minneapolis","Detroit","Tampa","Charlotte","Cleveland") df.
Seasonally adjusted greetings to you and yours. For you I have an animated chart, a variation on our rate cloud with a wintry theme. R code below. We’ll grab mortgage rate data, make a few new variables and then plot the chart using ggridges::geom_density_ridges2. Using the raincloud option for the poisition argument in ggridges::geom_density_ridges2 places the individual data points below the density plots. Using various shades of white we can turn the rain cloud into a snow cloud.
Today I got to talk #dataviz and shared a bunch of my charts, which always sort of feels like sharing my vacation photos. But it was fun to talk about why I made some of these charts, what they mean, and how different data visualization techniques can bring out new insights in familiar data. The pdf version is below or here. The pptx version has animations, get it here.
VISUAL MEDITATIONS are the analysis of repeated graphs of the same data with variations on a graphical theme. When altering the mapping of data to aesthetics sometimes interesting patterns emerge. I find it a useful practice. I made a series of these a few years ago with different charts. The chart images have been lost to past blog migrations, but the code should still work. In this post, I want to consider several alternative ways to visualize house prices.
For several months now, I’ve been working on a new research paper with Sumit Agarwal, Souphala Chomsisengphet, Hua Kiefer, and Paolina Medina studying refinance activity this year. When we started the project back in the spring we were not sure that the pandemic would allow households to refinance at rates similar to prior periods. It seemed possible that the pandemic would disrupt the mortgage market and make it difficult for households to take advantage of historically low rates.
Recently I’ve been putting my y-axis labels on the right for some time series. I think this idea has been rattling around in my head since it was suggested on Twitter by Maarten Lambrechts: A y-axis on the left is almost always the default, while the most recent and usually most relevant data are on the right. Then shouldn't a y-axis on the right be the default (when there are no data labels), to improve legibility?