Push the `knit` button! ```{r setup, child="exercise-setup.Rmd", eval = file.exists("exercise-setup.Rmd")} ``` ```{r, include = FALSE} knitr::opts_chunk$set( fig.path = "images/part2-exercise-01/", class.source = "solution", message = FALSE, error = FALSE, warning = FALSE, fig.height = 3, fig.width = 10 ) ``` ```{r pkgs, message = FALSE, warning = FALSE} library(tidyverse) # contains ggplot2, dplyr, tidyr, etc ``` ## `tuberculosis` dataset ```{r tb-data} tb <- read_csv(here::here("data/TB_notifications_2020-07-01.csv")) %>% dplyr::select(country, iso3, year, new_sp_m04:new_sp_fu) %>% pivot_longer(cols=new_sp_m04:new_sp_fu, names_to="sexage", values_to="count") %>% mutate(sexage = str_replace(sexage, "new_sp_", "")) %>% mutate(sex=substr(sexage, 1, 1), age=substr(sexage, 2, length(sexage))) %>% dplyr::select(-sexage) %>% filter(!(age %in% c("04", "014", "514", "u"))) %>% filter(year > 1996, year < 2013) %>% mutate(age_group = factor(age, labels = c("15-24", "25-34", "35-44", "45-54", "55-64", "65-"))) %>% dplyr::select(country, year, age_group, sex, count) # Filter Australia tb_oz <- tb %>% filter(country == "Australia") ``` ### Exercise 1.1: Stacked bar chart ```{r part2-exercise-01, echo = T, class = "target"} ggplot(tb_oz, aes(x=year, y=count, fill=sex)) + geom_bar(stat="identity") + facet_wrap(~age_group, ncol=6) + scale_fill_brewer("Sex", palette="Dark2") ``` ### Exercise 1.2: Side-by-side bar chart ```{r part2-exercise-02, echo = T, class = "target"} ggplot(tb_oz, aes(x=year, y=count, fill=sex)) + geom_bar(stat="identity", position="dodge") + facet_wrap(~age_group, ncol=6) + scale_fill_brewer("Sex", palette="Dark2") ``` ### Exercise 1.3: Facetted bar chart ```{r part2-exercise-03, echo = T, class = "target", fig.height = 4} tb_oz %>% ggplot(aes(x=year, y=count, fill=sex)) + geom_bar(stat="identity") + facet_grid(sex~age_group) + scale_fill_brewer("Sex", palette="Dark2") ``` ### Exercise 1.4: Facetted bar chart for 2012 ```{r part2-exercise-04, echo = T, class = "target"} tb_oz %>% filter(year == 2012) %>% ggplot(aes(x=sex, y=count, fill=sex)) + geom_bar(stat="identity") + facet_wrap(~age_group, ncol=6) + scale_fill_brewer("Sex", palette="Dark2") ``` ### Exercise 1.5: Reverse facetted bar chart for 2012 ```{r part2-exercise-05, echo = T, class = "target"} tb_oz %>% filter(year == 2012) %>% ggplot(aes(x=age_group, y=count, fill=age_group)) + geom_bar(stat="identity") + facet_wrap(~sex, ncol=6) + scale_fill_brewer("Age", palette="Dark2") + xlab("Age") ``` ### Exercise 1.6: Facetted pie chart for 2012 ```{r part2-exercise-06, echo = T, class = "target"} tb_oz %>% filter(year == 2012) %>% ggplot(aes(x=1, y=count, fill=sex)) + geom_bar(stat="identity", position="fill") + facet_wrap(~age_group, ncol=6) + scale_fill_brewer("", palette="Dark2") + ggtitle("Angle") + xlab("") + ylab("") + coord_polar(theta = "y") ``` ### Exercise 1.7: Reverse facetted pie chart for 2012 ```{r part2-exercise-07, echo = T, class = "target"} tb_oz %>% filter(year == 2012) %>% ggplot(aes(x=1, y=count, fill=age_group)) + geom_bar(stat="identity", position="fill") + facet_wrap(~sex, ncol=6) + scale_fill_brewer("", palette="Dark2") + ggtitle("Angle") + xlab("") + ylab("") + coord_polar(theta = "y") ``` ### Exercise 1.8: Aggregated count bar chart ```{r part2-exercise-08, echo = T, class = "target"} tb_oz %>% group_by(year) %>% summarise(count = sum(count)) %>% ggplot(aes(x=year, y=count)) + geom_bar(stat="identity") ``` ### Exercise 1.9: Showing proportions ```{r part2-exercise-09, echo = T, class = "target"} tb_oz %>% group_by(year, age_group) %>% summarise(p = count[sex=="m"]/sum(count)) %>% ggplot(aes(x=year, y=p)) + geom_hline(yintercept = 0.50, colour="white", size=2) + geom_point() + facet_wrap(~age_group, ncol=6) + ylab("proportion of males") ``` ### Exercise 1.10: Overlaying a model ```{r part2-exercise-10, echo = T, class = "target"} tb_oz %>% group_by(year, age_group) %>% summarise(p = count[sex=="m"]/sum(count)) %>% ggplot(aes(x=year, y=p)) + geom_hline(yintercept = 0.50, colour="white", size=2) + geom_point() + geom_smooth(se=F) + facet_wrap(~age_group, ncol=6) + ylab("proportion of males") ```