ggplot直方图在布尔上拆分

如何解决ggplot直方图在布尔上拆分

使用公共数据集（请注意需要花费几分钟的时间）：

library(data.table)
dl <- tempfile()
download.file("http://files.grouplens.org/datasets/movielens/ml-10m.zip",dl)

ratings <- fread(text = gsub("::","\t",readLines(unzip(dl,"ml-10M100K/ratings.dat"))),col.names = c("userId","movieId","rating","timestamp"))

movies <- str_split_fixed(readLines(unzip(dl,"ml-10M100K/movies.dat")),"\\::",3)
colnames(movies) <- c("movieId","title","genres")

if (as.numeric(version$year) < 2020 | (version$year=="2020" & as.numeric(version$month) < 3)){
  # if using R 3.6 or earlier
  movies <- as.data.frame(movies) %>% mutate(movieId = as.numeric(levels(movieId))[movieId],title = as.character(title),genres = as.character(genres))
} else {
  # if using R 4.0 or later
  movies <- as.data.frame(movies) %>% mutate(movieId = as.numeric(movieId),genres = as.character(genres))}

movielens <- left_join(ratings,movies,by = "movieId")

如：

  > head(movielens)
   userId movieId rating timestamp                         title                        genres
1:      1     122      5 838985046              Boomerang (1992)                Comedy|Romance
2:      1     185      5 838983525               Net,The (1995)         Action|Crime|Thriller
3:      1     231      5 838983392          Dumb & Dumber (1994)                        Comedy
4:      1     292      5 838983421               Outbreak (1995)  Action|Drama|Sci-Fi|Thriller
5:      1     316      5 838983392               Stargate (1994)       Action|Adventure|Sci-Fi
6:      1     329      5 838983392 Star Trek: Generations (1994) Action|Adventure|Drama|Sci-Fi
> 

我正尝试用fill分割ggplot直方图，以显示以下总评分与一半评分之间的差异：

movielens %>% 
  mutate(whole = rating == round(rating)) %>% 
  ggplot(mapping=aes(x=rating),fill=whole) +
  geom_histogram()

因为半收视率不常见，但fill由于某些原因无法正常工作...

解决方法

您需要在美学（aka映射）中进行填充，而不是在ggplot()通话中进行填充：

library(data.table)
library(stringr)
library(dplyr)
library(ggplot2)
dl <- tempfile()
download.file("http://files.grouplens.org/datasets/movielens/ml-10m.zip",dl)

ratings <- fread(text = gsub("::","\t",readLines(unzip(dl,"ml-10M100K/ratings.dat"))),col.names = c("userId","movieId","rating","timestamp"))

movies <- str_split_fixed(readLines(unzip(dl,"ml-10M100K/movies.dat")),"\\::",3)
colnames(movies) <- c("movieId","title","genres")

if (as.numeric(version$year) < 2020 | (version$year=="2020" & as.numeric(version$month) < 3)){
  # if using R 3.6 or earlier
  movies <- as.data.frame(movies) %>% mutate(movieId = as.numeric(levels(movieId))[movieId],title = as.character(title),genres = as.character(genres))
} else {
  # if using R 4.0 or later
  movies <- as.data.frame(movies) %>% mutate(movieId = as.numeric(movieId),genres = as.character(genres))}

movielens <- left_join(ratings,movies,by = "movieId")
movielens %>% 
  mutate(whole = rating == round(rating)) %>%
  ggplot(mapping=aes(x=rating,fill=whole)) +
  geom_histogram()