在ggplot和R中的甘特图中创建一致的条形颜色

Question

I reused the same R code with multiple different datasets to produce gantt charts.

require("tidyverse")

task0 <- c('Strategy 1', 'Strategy 1', '2017-04-01', '2020-04-01',0, "Strategy")
task1 <- c('Strategy 1', 'Collect data', '2017-04-01', '2018-04-01',1, "In Progress")
task2 <- c('Strategy 1', 'Clean data', '2018-04-01', '2018-06-01', 1, "Completed")
task3 <- c('Strategy 1', 'Analyse data', '2018-06-01', '2019-04-01',1, "Discontinued")
task4 <- c('Strategy 1', 'Write report', '2019-04-01', '2020-04-01', 1, "Planned")

dataset <- as.data.frame(rbind(task0, task1, task2, task3, task4))
names(dataset) <- c('StrategyName', 'Activity', 'Start', 'End', 'ActivitySort', "Status")


dataset <-  as_tibble(dataset)
dataset <-  dataset  %>% mutate(StartSort = as.Date(Start, "%Y-%m-%d" ))
dataset <-  dataset %>% arrange(StrategyName, desc(ActivitySort), desc(StartSort),Activity,  End)

acts <- c("Planned","Discontinued","In Progress","Completed", "Strategy")
actcols <- c("#000000","#548235", "#2E75B6", "#BF9000", "#7030A0")
els <-unique(dataset$Activity)

g.gantt <- gather(dataset, "state", "date", 3:4) %>% mutate(date = as.Date(date, "%Y-%m-%d" ), Status=factor(Status, acts[length(acts):1]), Activity=factor(Activity, els))

plot <- ggplot(g.gantt, aes(date, Activity, color = Status, group=Activity)) +
  geom_line(size = 5) +
  scale_color_manual(values=actcols, name="Status") +
  labs(x="Project year", y=NULL, title="Activity timeline")

plot + theme(axis.text.y = element_text(hjust = 0))

If the chart data contains all of the status codes, Strategy, In Progress, Completed, Discontinued and Planned then chart colors appear as intended.

However, I the chart data does not contain all 5 status codes, then the manual colors are not set correctly and consistently. For instance, completed status may no longer appear green.

How do I format/set the manual colors so that completed will always appear green regardless of the number of other statuses contained in the dataset?

Answer 1

Thanks to teunbrand's comment for the answer. I did have to tweak sorting.

require("tidyverse")

task0 <- c('Strategy 1', 'Strategy 1', '2017-04-01', '2020-04-01',0, "Strategy")
task1 <- c('Strategy 1', 'Collect data', '2017-04-01', '2018-04-01',1, "In Progress")
task2 <- c('Strategy 1', 'Clean data', '2018-04-01', '2018-06-01', 1, "Completed")
task3 <- c('Strategy 1', 'Analyse data', '2018-06-01', '2019-04-01',1, "Discontinued")
task4 <- c('Strategy 1', 'Write report', '2019-04-01', '2020-04-01', 1, "Planned")

dataset <- as.data.frame(rbind(task0, task1, task2, task3, task4))
names(dataset) <- c('StrategyName', 'Activity', 'Start', 'End', 'ActivitySort', "Status")


dataset <-  as_tibble(dataset)
dataset <-  dataset  %>% mutate(StartSort = as.Date(Start, "%Y-%m-%d" ))
dataset <-  dataset %>% arrange(StrategyName, desc(ActivitySort), desc(StartSort),Activity,  End)

acts <- c("Strategy", "Completed","In Progress", "Discontinued","Planned")
actcols <- c("#000000","#548235", "#2E75B6", "#BF9000", "#7030A0")
els <-unique(dataset$Activity)

g.gantt <- gather(dataset, "state", "date", 3:4) %>% mutate(date = as.Date(date, "%Y-%m-%d" ), Status=factor(Status, acts[length(acts):1]), Activity=factor(Activity, els))

plot <- ggplot(g.gantt, aes(date, Activity, color = Status, group=Activity)) +
  geom_line(size = 5) +
  scale_color_manual(values=actcols, name="Status",  breaks = acts, limits = acts) +
  labs(x="Project year", y=NULL, title="Activity timeline")

plot + theme(axis.text.y = element_text(hjust = 0))