class: title-slide, right, top background-image: url(data:image/png;base64,#img/moon.JPG) background-position: 90% 75%, 75% 75% background-size:cover .left-column[ # GRS Workshop<br>Introduction to ggplot ] .right-column[ ### Getting starting - why ggplot? **Eugene Hickey**<br> March 9th 2022 ] .palegrey[.left[.footnote[Graphic by [Elaine Hickey](https://photos.google.com/photo/AF1QipMjKNoaxyne8nte4HmxA6Th9-4fUfSbl_mx-_1G)]]] ??? Welcome to the workshop on ggplot. Where we'll show you how to create impressive data visualisations. --- name: about-me layout: false class: about-me-slide, inverse, middle, center # About me <img style="border-radius: 50%;" src="data:image/png;base64,#img/eugene.jpg" width="150px"/> ## Eugene Hickey ### lecturer in physics .fade[Technological University<br>Dublin] [<svg viewBox="0 0 512 512" style="height:1em;position:relative;display:inline-block;top:.1em;" xmlns="http://www.w3.org/2000/svg"> <path d="M326.612 185.391c59.747 59.809 58.927 155.698.36 214.59-.11.12-.24.25-.36.37l-67.2 67.2c-59.27 59.27-155.699 59.262-214.96 0-59.27-59.26-59.27-155.7 0-214.96l37.106-37.106c9.84-9.84 26.786-3.3 27.294 10.606.648 17.722 3.826 35.527 9.69 52.721 1.986 5.822.567 12.262-3.783 16.612l-13.087 13.087c-28.026 28.026-28.905 73.66-1.155 101.96 28.024 28.579 74.086 28.749 102.325.51l67.2-67.19c28.191-28.191 28.073-73.757 0-101.83-3.701-3.694-7.429-6.564-10.341-8.569a16.037 16.037 0 0 1-6.947-12.606c-.396-10.567 3.348-21.456 11.698-29.806l21.054-21.055c5.521-5.521 14.182-6.199 20.584-1.731a152.482 152.482 0 0 1 20.522 17.197zM467.547 44.449c-59.261-59.262-155.69-59.27-214.96 0l-67.2 67.2c-.12.12-.25.25-.36.37-58.566 58.892-59.387 154.781.36 214.59a152.454 152.454 0 0 0 20.521 17.196c6.402 4.468 15.064 3.789 20.584-1.731l21.054-21.055c8.35-8.35 12.094-19.239 11.698-29.806a16.037 16.037 0 0 0-6.947-12.606c-2.912-2.005-6.64-4.875-10.341-8.569-28.073-28.073-28.191-73.639 0-101.83l67.2-67.19c28.239-28.239 74.3-28.069 102.325.51 27.75 28.3 26.872 73.934-1.155 101.96l-13.087 13.087c-4.35 4.35-5.769 10.79-3.783 16.612 5.864 17.194 9.042 34.999 9.69 52.721.509 13.906 17.454 20.446 27.294 10.606l37.106-37.106c59.271-59.259 59.271-155.699.001-214.959z"></path></svg> www.fizzics.ie](https://www.fizzics.ie) [<svg viewBox="0 0 512 512" style="height:1em;position:relative;display:inline-block;top:.1em;" xmlns="http://www.w3.org/2000/svg"> <path d="M459.37 151.716c.325 4.548.325 9.097.325 13.645 0 138.72-105.583 298.558-298.558 298.558-59.452 0-114.68-17.219-161.137-47.106 8.447.974 16.568 1.299 25.34 1.299 49.055 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.112-72.772 6.498.974 12.995 1.624 19.818 1.624 9.421 0 18.843-1.3 27.614-3.573-48.081-9.747-84.143-51.98-84.143-102.985v-1.299c13.969 7.797 30.214 12.67 47.431 13.319-28.264-18.843-46.781-51.005-46.781-87.391 0-19.492 5.197-37.36 14.294-52.954 51.655 63.675 129.3 105.258 216.365 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.828 46.782-104.934 104.934-104.934 30.213 0 57.502 12.67 76.67 33.137 23.715-4.548 46.456-13.32 66.599-25.34-7.798 24.366-24.366 44.833-46.132 57.827 21.117-2.273 41.584-8.122 60.426-16.243-14.292 20.791-32.161 39.308-52.628 54.253z"></path></svg> @eugene100hickey](https://twitter.com/eugene100hickey) [<svg viewBox="0 0 496 512" style="position:relative;display:inline-block;top:.1em;height:1em;" xmlns="http://www.w3.org/2000/svg"> <path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6zm-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3zm44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9zM244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8zM97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1zm-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7zm32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1zm-11.4-14.7c-1.6 1-1.6 3.6 0 5.9 1.6 2.3 4.3 3.3 5.6 2.3 1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2z"></path></svg> eugene100hickey](https://github.com/eugene100hickey) --- layout: true <a class="footer-link" href="http://grs-2022.netlify.app">intro-ggplot-grs2022 &mdash; Eugene Hickey</a> <!-- this adds the link footer to all slides, depends on footer-link class in css--> --- class: top # Acknowledgments .pull-left-narrow[.center[<img style="border-radius: 50%;" src="img/rafaella.jpg">]] .pull-right-wide[ [Raffaella Salvante](http://timetables.dit.ie/researchndenterpriseold/graduateresearchschoolold/meettheteam/), co-pilot for this workshop and administrator of the Graduate Research School. ] -- .pull-left-narrow[.center[ <img style="border-radius: 50%;" src="data:image/png;base64,#img/tudublin-logo.jpg" width="125px"/>]] .pull-right-wide[ [Graduate Research School](https://www.tudublin.ie/research/postgraduate-research/graduate-research-school/) for the opportunity to provide this workshop ] -- .pull-left-narrow[.center[ <svg viewBox="0 0 496 512" style="position:relative;display:inline-block;top:.1em;fill:#e5bf00;height:3em;" xmlns="http://www.w3.org/2000/svg"> <path d="M248 8C111 8 0 119 0 256s111 248 248 248 248-111 248-248S385 8 248 8zm0 448c-110.3 0-200-89.7-200-200S137.7 56 248 56s200 89.7 200 200-89.7 200-200 200zm-80-216c17.7 0 32-14.3 32-32s-14.3-32-32-32-32 14.3-32 32 14.3 32 32 32zm160 0c17.7 0 32-14.3 32-32s-14.3-32-32-32-32 14.3-32 32 14.3 32 32 32zm4 72.6c-20.8 25-51.5 39.4-84 39.4s-63.2-14.3-84-39.4c-8.5-10.2-23.7-11.5-33.8-3.1-10.2 8.5-11.5 23.6-3.1 33.8 30 36 74.1 56.6 120.9 56.6s90.9-20.6 120.9-56.6c8.5-10.2 7.1-25.3-3.1-33.8-10.1-8.4-25.3-7.1-33.8 3.1z"></path></svg>]] .pull-right-wide[ - [xaringan 📦](https://github.com/yihui/xaringan#xaringan) developed by Yihui Xie - [flipbookr 📦](https://github.com/EvaMaeRey/flipbookr) developed by Gina Reynolds - [learnr 📦](https://github.com/rstudio/learnr) developed by Garrick Aden-Buie ] --- # Target Audience - graduate students looking for better ways to present their data - people currently using tools like MS Excel for visualisations --- # Why R? - working with a mouse isn't reproducible - difficult to log exactly what you've done - hard to repeat for a series of diagrams - difficult to be inspired by other people's work - good to separate sources of data and the visualisations that disply them - R uses series of commands that input, manipulate, and display data - lots of contributors around the world, diverse fields --- # Why ggplot? - while some plots can be easier to produce using base graphics .pull-left[ ```r hist(LOS_model$Age) ``` <img src="data:image/png;base64,#01-why-ggplot_files/figure-html/base_hist-1.png" width="80%" /> ] .pull-right[ ```r ggplot(data = LOS_model, aes(Age)) + geom_histogram(bins = 10) ``` <img src="data:image/png;base64,#01-why-ggplot_files/figure-html/ggplot_hist-1.png" width="80%" /> ] --- # Why ggplot? - anything moderately complicated is better in ggplot .pull-left[ ```r # David Robinson # http://varianceexplained.org/r/why-I-use-ggplot2/ par(mar = c(1.5, 1.5, 1.5, 1.5)) colors <- 1:6 names(colors) <- unique(top_data$nutrient) # legend approach from http://stackoverflow.com/a/10391001/712603 m <- matrix(c(1:20, 21, 21, 21, 21), nrow = 6, ncol = 4, byrow = TRUE) layout(mat = m, heights = c(.18, .18, .18, .18, .18, .1)) top_data$combined <- paste(top_data$name, top_data$systematic_name) for (gene in unique(top_data$combined)) { sub_data <- filter(top_data, combined == gene) plot(expression ~ rate, sub_data, col = colors[sub_data$nutrient], main = gene) for (n in unique(sub_data$nutrient)) { m <- lm(expression ~ rate, filter(sub_data, nutrient == n)) if (!is.na(m$coefficients[2])) { abline(m, col = colors[n]) } } } # create a new plot for legend plot(1, type = "n", axes = FALSE, xlab = "", ylab = "") legend("top", names(colors), col = colors, horiz = TRUE, lwd = 4) ``` ] .pull-right[ <!-- --> ] --- # Why ggplot? - anything moderately complicated is better in ggplot .pull-left[ ```r ggplot(top_data, aes(rate, expression, color = nutrient)) + geom_point(show.legend = FALSE) + geom_smooth(method = "lm", se = FALSE, show.legend = FALSE) + facet_wrap(~systematic_name, scales = "free_y") ``` ] .pull-right[ <!-- --> ] --- # Lots of addin packages for ggplot gg.gap, ggalignment, ggallin, ggalluvial, ggalt, ggamma, gganimate, ggarchery, ggasym, ggbeeswarm, ggborderline, ggbreak, ggBubbles, ggbuildr, ggbump, ggchangepoint, ggcharts, ggChernoff, ggcleveland, ggconf, ggcorrplot, ggdag, ggdark, ggDCA, ggdemetra, ggdendro, ggdensity, ggdist, ggdmc, gge, ggeasy, ggedit, ggeffects, ggenealogy, ggESDA, ggetho, ggExtra, ggfacto, ggfan, ggfittext, ggfocus, ggforce, ggformula, ggfortify, ggfun, ggfx, gggap, gggenes, ggghost, gggibbous, gggrid, ggh4x, gghalfnorm, gghalves, gghdr, ggheatmap, gghighlight, gghilbertstrings, ggHoriPlot, ggimage, ggimg, gginference, gginnards, ggip, ggiraph, ggiraphExtra, ggjoy, gglasso, gglm, gglogo, ggloop, gglorenz, ggm, ggmap, ggmatplot, ggmcmc, ggmix, ggmosaic, ggmotif, ggmr, ggmuller, ggmulti, ggnetwork, ggnewscale, ggnormalviolin, ggnuplot, ggOceanMaps, ggokabeito, ggpacman, ggpage, ggparallel, ggparliament, ggparty, ggpattern, ggperiodic, ggplot.multistats, ggplot2, ggplot2movies, ggplotAssist, ggplotgui, ggplotify, ggplotlyExtra, ggpmisc, ggPMX, ggpointdensity, ggpol, ggpolar, ggpolypath, ggpp, ggprism, ggpubr, ggpval, ggQC, ggQQunif, ggquickeda, ggquiver, ggraph, ggraptR, ggrasp, ggrastr, ggrepel, ggResidpanel, ggridges, ggrisk, ggROC, ggroups, ggsci, ggseas, ggseg, ggseg3d, ggseqlogo, ggshadow, ggside, ggsignif, ggsn, ggsoccer, ggsolvencyii, ggsom, ggspatial, ggspectra, ggstance, ggstar, ggstatsplot, ggstream, ggstudent, ggswissmaps, ggtea, ggtern, ggtext, ggThemeAssist, ggthemes, ggtikz, ggTimeSeries, ggupset, ggvenn, ggVennDiagram, ggversa, ggvis, ggvoronoi, ggwordcloud, ggx --- # And others, that make ggplots that can then be modified and treated as such .pull-left[ ```r fviz_cluster_example ``` <!-- --> ] .pull-right[ ```r fviz_cluster_example + theme_classic() ``` <!-- --> ] --- # Other reasons - ggplot is easy to make publication-ready - easier to make sequence of visualisations - fits in nicely with the rest of the tidyverse