#### Pretty ggplots examples library(dslabs) head(murders) ## ----ggplot-example-plot-0, echo=FALSE, message=FALSE, warning=FALSE---------------------- library(tidyverse) library(ggthemes) library(ggrepel) ############# Example 1 r <- murders |> summarize(pop = sum(population), tot = sum(total)) |> mutate(rate = tot/pop*10^6) |> pull(rate) murders |> ggplot(aes(x = population/10^6, y = total, label = abb)) + geom_abline(intercept = log10(r), lty = 2, col = "darkgrey") + geom_point(aes(color = region), size = 3) + geom_text_repel() + scale_x_log10() + scale_y_log10() + xlab("Populations in millions (log scale)") + ylab("Total number of murders (log scale)") + ggtitle("US Gun Murders in 2010") + scale_color_discrete(name = "Region") + theme_economist() ##### Example 2: heatmap the_disease <- "Measles" dat <- us_contagious_diseases |> filter(!state%in%c("Hawaii","Alaska") & disease == the_disease) |> mutate(rate = count / population * 10000 * 52 / weeks_reporting) |> mutate(state = reorder(state, rate)) jet.colors <- colorRampPalette(c("#F0FFFF", "cyan", "#007FFF", "yellow", "#FFBF00", "orange", "red", "#7F0000"), bias = 2.25) dat |> ggplot(aes(year, state, fill = rate)) + geom_tile(color = "white", linewidth = 0.35) + scale_x_continuous(expand = c(0,0)) + scale_fill_gradientn(colors = jet.colors(16), na.value = 'white') + geom_vline(xintercept = 1963, col = "black") + theme_minimal() + theme(panel.grid = element_blank()) + coord_cartesian(clip = 'off') + ggtitle(the_disease) + ylab("") + xlab("") + theme(legend.position = "bottom", text = element_text(size = 8)) + annotate(geom = "text", x = 1963, y = 50.5, label = "Vaccine introduced", size = 3, hjust = 0) ######### Example 3: Barchat nyc_regents_scores$total <- rowSums(nyc_regents_scores[,-1], na.rm = TRUE) nyc_regents_scores |> filter(!is.na(score)) |> ggplot(aes(score, total)) + annotate("rect", xmin = 65, xmax = 99, ymin = 0, ymax = 35000, alpha = .5) + geom_bar(stat = "identity", color = "black", fill = "#C4843C") + annotate("text", x = 66, y = 28000, label = "MINIMUM\nREGENTS DIPLOMA\nSCORE IS 65", hjust = 0, size = 3) + annotate("text", x = 0, y = 12000, label = "2010 Regents scores on\nthe five most common tests", hjust = 0, size = 3) + scale_x_continuous(breaks = seq(5, 95, 5), limits = c(0,99)) + scale_y_continuous(position = "right", labels = scales::comma) + ggtitle("Scraping by") + xlab("") + ylab("Number of tests") + theme_minimal() + theme(panel.grid.major.x = element_blank(), panel.grid.minor.x = element_blank(), axis.ticks.length = unit(-0.2, "cm"), plot.title = element_text(face = "bold")) ################################# ### ggplot from scratch ################################# ## ## Data |> ggplot() + LAYER 1 + LAYER2 + ... + LAYER N ## ----message=FALSE, warning=FALSE--------------------------------------------------------- #| cache: false library(dplyr) library(ggplot2) ## ----ggplot-example-plot, echo=FALSE------------------------------------------------------ library(dslabs) library(ggthemes) library(ggrepel) r <- murders |> summarize(pop = sum(population), tot = sum(total)) |> mutate(rate = tot/pop*10^6) |> pull(rate) murders |> ggplot(aes(x = population/10^6, y = total, label = abb)) + geom_abline(intercept = log10(r), lty = 2, col = "darkgrey") + geom_point(aes(color = region), size = 3) + geom_text_repel() + scale_x_log10() + scale_y_log10() + xlab("Populations in millions (log scale)") + ylab("Total number of murders (log scale)") + ggtitle("US Gun Murders in 2010") + scale_color_discrete(name = "Region") + theme_economist() ## ----echo=FALSE--------------------------------------------------------------------------- theme_set(theme_grey()) ## to imitate what happens with setting theme ## ----------------------------------------------------------------------------------------- #| cache: false library(dslabs) ## ----------------------------------------------------------------------------------------- #| eval: false ## ggplot(data = murders) ## ----ggplot-example-1--------------------------------------------------------------------- murders |> ggplot() ## ----------------------------------------------------------------------------------------- p <- ggplot(data = murders) ## ----------------------------------------------------------------------------------------- #| eval: false ## print(p) ## p ## ----ggplot-example-2--------------------------------------------------------------------- murders |> ggplot() + geom_point(aes(population/10^6, total)) ## ----ggplot-example-3--------------------------------------------------------------------- murders |> ggplot() + geom_point(aes(population/10^6, total)) + geom_text(aes(population/10^6, total, label = abb)) ## ----------------------------------------------------------------------------------------- #| eval: false murders |> ggplot(aes(population/10^6, total)) + geom_point() + geom_text(aes(label = abb)) ## ----ggplot-example-4--------------------------------------------------------------------- murders |> ggplot(aes(population/10^6, total)) + geom_point() + geom_text(aes(x = 10, y = 800, label = "Hello there!")) ## ----ggplot-example-5--------------------------------------------------------------------- murders |> ggplot(aes(population/10^6, total)) + geom_point(size = 3) + geom_text(aes(label = abb), nudge_x = 1.5) ## ----ggplot-example-6--------------------------------------------------------------------- murders |> ggplot(aes(population/10^6, total)) + geom_point(aes(color = region), size = 3) ## ----ggplot-example-7--------------------------------------------------------------------- murders |> ggplot(aes(population/10^6, total)) + geom_point(color = "blue", size = 3) ## ----------------------------------------------------------------------------------------- p0 <- murders |> ggplot(aes(population/10^6, total)) ## ----------------------------------------------------------------------------------------- p1 <- p0 + geom_point(aes(color = region), size = 3) ## ----------------------------------------------------------------------------------------- p2 <- p1 + geom_text(aes(label = abb), nudge_x = 0.3) ## ----ggplot-example-8--------------------------------------------------------------------- p3 <- p2 + scale_x_log10() + scale_y_log10() p3 ## ----ggplot-example-9--------------------------------------------------------------------- p4 <- p3 + labs(title = "US Gun Murders in 2010", x = "Populations in millions (log scale)", y = "Total number of murders (log scale)", color = "Region") p4 ## ----------------------------------------------------------------------------------------- r <- murders |> summarize(rate = sum(total)/sum(population)*10^6) |> pull(rate) ## ----ggplot-example-10-------------------------------------------------------------------- p5 <- p4 + geom_abline(intercept = log10(r), lty = 2, color = "darkgrey") p5 ## ----------------------------------------------------------------------------------------- ds_theme_set() ## ----------------------------------------------------------------------------------------- library(ggthemes) p6 <- p5 + theme_economist() p7<-p5+ theme_fivethirtyeight() ## ----final-ggplot-example----------------------------------------------------------------- library(ggthemes) library(ggrepel) r <- murders |> summarize(rate = sum(total) / sum(population) * 10^6) |> pull(rate) murders |> ggplot(aes(population/10^6, total)) + geom_abline(intercept = log10(r), lty = 2, color = "darkgrey") + geom_point(aes(col = region), size = 3) + geom_text_repel(aes(label = abb)) + scale_x_log10() + scale_y_log10() + labs(title = "US Gun Murders in 2010", x = "Populations in millions (log scale)", y = "Total number of murders (log scale)", color = "Region") + theme_economist() ## ----echo=FALSE--------------------------------------------------------------------------- ds_theme_set() ## ----barplot-geom------------------------------------------------------------------------- #| eval: false murders |> ggplot(aes(region)) + geom_bar() ## ----------------------------------------------------------------------------------------- tab <- murders |> count(region) |> mutate(proportion = n/sum(n)) ## ----region-freq-barplot------------------------------------------------------------------ #| eval: false tab |> ggplot(aes(region, proportion)) + geom_col() ## ----eval=FALSE--------------------------------------------------------------------------- heights |> filter(sex == "Female") |> ggplot(aes(height)) + geom_histogram(binwidth = 1, fill = "blue", col = "black") ## ----eval=FALSE--------------------------------------------------------------------------- heights |> filter(sex == "Female") |> ggplot(aes(height)) + geom_density(fill = "blue") ## ----eval = FALSE------------------------------------------------------------------------- heights |> filter(sex == "Female") |> ggplot(aes(height)) + geom_density(fill="blue", adjust = 2) ## ----female-male-boxplots-geom, eval=FALSE------------------------------------------------ heights |> ggplot(aes(sex, height)) + geom_boxplot() ## ----------------------------------------------------------------------------------------- x <- expand.grid(x = 1:12, y = 1:10) |> mutate(z = 1:120) ## ----eval=FALSE--------------------------------------------------------------------------- x |> ggplot(aes(x, y, fill = z)) + geom_raster() ## ----ggplot2-image-new-colors------------------------------------------------------------- x |> ggplot(aes(x, y, fill = z)) + geom_raster() + scale_fill_gradientn(colors = terrain.colors(10, 1)) ## ----gridExtra-example, warning=FALSE, message=FALSE, fig.height=4, fig.width=12, out.width="100%"---- library(gridExtra) grid.arrange(p5, p6, ncol = 2)