条形图中的当前百分比是根据数据总量计算的。我希望每个堆栈都完全 100%。(解决了)
此外,百分比应四舍五入到最接近的整数。(解决了)
编辑:删除所有小于或等于 1 的百分比。(已解决)
Edit2:确保没有标签重叠。
我已经在谷歌上搜索了一段时间了。似乎没有适当的方法来防止标签重叠。
我发现的可能解决方案:
# Load libraries & packages =================================
library("ggplot2")
library("scales")
library("dplyr")
library("foreign")
library("tidyverse")
library("forcats")
# Data setup =================================
spss_file_path <- "D:\\Programming\\Testing\\2017-03-15_data_import&ggplot2\\Beispieldatensatz(fiktiv).sav"
exampledata <- read.spss(spss_file_path, use.value.labels = TRUE,
to.data.frame = TRUE, reencode = TRUE)
exampledata$V43 <- factor(exampledata$V43,
levels = c(1,2,3,4,5),
labels = c("1 Sehr zufrieden","2","3","4", "5 Sehr unzufrieden"))
exampledata$V43 <- factor(exampledata$V43, levels = rev(unique(levels(exampledata$V43))))
exampledata$A_REF <- factor(exampledata$A_REF, levels = rev(unique(levels(exampledata$A_REF))))
exampledata$V101 <- factor(exampledata$V101, levels = rev(unique(levels(exampledata$V101))))
labels <- exampledata %>%
filter(!is.na(V101), !is.na(V43)) %>%
count(A_REF) %>%
mutate(labels = paste(A_REF,"(n=", n, ")")) %>%
select(A_REF, labels)
plot_data <- exampledata %>%
filter(!is.na(V101), !is.na(V43)) %>%
left_join(labels, by = "A_REF")
plot_data <- plot_data %>%
group_by(labels) %>%
summarize(`5 Sehr unzufrieden` = sum(ifelse(V43 == "5 Sehr unzufrieden", 1, 0)) / n(),
`4` = sum(ifelse(V43 == "4", 1, 0)) / n(),
`3` = sum(ifelse(V43 == "3", 1, 0)) / n(),
`2` = sum(ifelse(V43 == "2", 1, 0)) / n(),
`1 Sehr zufrieden` = sum(ifelse(V43 == "1 Sehr zufrieden", 1, 0)) / n()) %>%
gather(key = Rating, value = prop, -labels)
plot_data$labels <- factor(plot_data$labels)
plot_data$Rating <- factor(plot_data$Rating) %>% fct_rev()
# Plot =================================
ggplot(plot_data, aes(x = labels, y = prop, fill = Rating)) +
geom_col() +
scale_y_continuous(labels = scales::percent, breaks = c(0, 0.2, 0.4, 0.6, 0.8, 1)) +
labs(y=NULL, x=NULL, fill=NULL) +
ggtitle(paste(attr(exampledata, "variable.labels")[77])) +
theme_classic() +
geom_text(aes(label = if_else(prop > 0.02, scales::percent(round(prop, 2)), NULL)), position = position_fill(vjust=0.5)) +
coord_flip()
structure(list(exampledata.V101 = structure(c(2L, NA, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, NA, 2L, 2L, 2L, 1L, 2L, NA,
NA, NA, 1L, 1L, 2L, NA, 2L, 2L, 2L, NA, 2L, 2L, NA, NA, 1L, NA,
2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, NA, NA, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, NA, 1L, NA, 1L, NA,
1L, 2L, NA, NA, 2L, NA, 1L, 2L, 2L, NA, 2L, NA, 2L, 2L, 1L, 2L,
1L, 2L, 1L, 1L, 2L, 1L, NA, 2L, 2L, 2L, 2L, NA, 2L, 1L, 2L, 2L
), .Label = c("Weiblich", "Männlich"), class = "factor"), exampledata.A_REF = structure(c(18L,
18L, 18L, 18L, 18L, 17L, 18L, 18L, 18L, 18L, 18L, 18L, 16L, 18L,
18L, 18L, 18L, 18L, 18L, 18L, 18L, 18L, 16L, 18L, 18L, 16L, 18L,
16L, 18L, 18L, 17L, 18L, 18L, 18L, 18L, 18L, 18L, 18L, 18L, 18L,
16L, 18L, 18L, 17L, 18L, 18L, 18L, 18L, 18L, 18L, 17L, 16L, 18L,
18L, 18L, 18L, 18L, 18L, 18L, 18L, 18L, 18L, 18L, 17L, 18L, 18L,
16L, 18L, 16L, 18L, 18L, 16L, 16L, 18L, 18L, 18L, 18L, 18L, 18L,
18L, 17L, 18L, 18L, 18L, 18L, 18L, 18L, 18L, 18L, 18L, 16L, 18L,
16L, 16L, 18L, 18L, 18L, 17L, 16L, 18L), .Label = c("Zertifikat eines Aufbau- oder Ergänzungsstudiums",
"LA Berufliche Schulen", "LA Sonderschule", "LA Gymnasium", "LA Haupt- und Realschule",
"LA Grundschule", "Künstlerischer/musischer Abschluss", "Kirchlicher Abschluss",
"Staatsexamen (ohne Lehramt)", "Diplom Fachhochschule, Diplom I an Gesamthochschulen",
"Diplom Universität, Diplom II an Gesamthochschulen", "Sonstiges",
"Promotion", "Staatsexamen", "Magister", "Diplom", "Master",
"Bachelor"), class = "factor"), exampledata.V43 = structure(c(3L,
5L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 4L, 3L, 3L, 2L, NA, 4L, 5L, 5L,
4L, 4L, 4L, 4L, NA, 2L, 4L, 3L, 5L, 4L, 4L, 4L, NA, 4L, 4L, NA,
NA, 3L, 5L, 2L, 4L, 5L, 4L, 4L, 5L, 5L, 4L, NA, NA, 4L, NA, 3L,
4L, 5L, 5L, 2L, 4L, 4L, 3L, 4L, 4L, 4L, 3L, 5L, 4L, 5L, NA, 4L,
NA, 4L, NA, 4L, 5L, 4L, NA, 5L, NA, 4L, 4L, 4L, NA, 4L, NA, 5L,
4L, 4L, 4L, 4L, 4L, 3L, 3L, 4L, 2L, 4L, 4L, 4L, 3L, 4L, NA, 4L,
5L, 5L, 4L), .Label = c("5 Sehr unzufrieden", "4", "3", "2",
"1 Sehr zufrieden"), class = "factor")), .Names = c("exampledata.V101",
"exampledata.A_REF", "exampledata.V43"), row.names = c(NA, 100L
), class = "data.frame")
通常最好在绘制图表之前将数据处理为汇总数据。我发现尝试ggplot2
为你做总结要么有限,要么很难让它按照你想要的方式展示。
library(tidyverse)
library(forcats)
因为最好在将数据绘制在 中之前对其进行汇总ggplot2
,所以下面的代码计算了每一组label
在比例尺上选择特定答案的比例。在最后一步中,我将数据从宽变为长,以便所有要绘制的比例都在同一个变量中(我称之为prop
)。
plot_data <- plot_data %>% group_by(labels) %>%
summarize(`5 Sehr unzufrieden` = sum(ifelse(V43 == "5 Sehr unzufrieden", 1, 0)) / n(),
`4` = sum(ifelse(V43 == "4", 1, 0)) / n(),
`3` = sum(ifelse(V43 == "3", 1, 0)) / n(),
`2` = sum(ifelse(V43 == "2", 1, 0)) / n(),
`1 Sehr zufrieden` = sum(ifelse(V43 == "1 Sehr zufrieden", 1, 0)) / n()) %>%
gather(key = Rating, value = prop, -labels)
最好将分类变量设置为用于操作的因素,例如顺序和颜色,因此这就是以下内容。最初,我的代码的比例标签(我Rating
在gather
上面的函数中调用)与您拥有的顺序相反,所以我使用fct_rev
从forcats
包中将其反转回来。
plot_data$labels <- factor(plot_data$labels)
plot_data$Rating <- factor(plot_data$Rating) %>% fct_rev()
对于下面的图表,我只是做了一些更改。最值得注意的是我正在使用geom_col
而不是geom_bar
. 在后台,geom_col
与geom_bar(stat = "identity")
- 键入速度相同。我们本质上是在告诉ggplot2
按原样绘制数据图表,而不是将其视为原始数据。但是,我确实需要指定y
美学以指示我想要绘制哪些数据,因此我指定prop
在初始ggplot
调用中使用该变量。
# Plot =================================
ggplot(plot_data, aes(x = labels, y = prop, fill = Rating)) +
geom_col() +
scale_y_continuous(labels = scales::percent, breaks = c(0, 0.2, 0.4, 0.6, 0.8, 1)) +
labs(y=NULL, x=NULL, fill=NULL) +
ggtitle(paste(attr(exampledata, "variable.labels")[77])) +
theme_classic() +
geom_text(aes(label = if_else(prop > 0.01, scales::percent(round(prop, 2)), NULL)), position = position_fill(vjust=0.5)) +
coord_flip()
我更改的唯一另一行是geom_text
上面的调用。我添加了一个if_else
函数,以便它要么显示标签(如果它高于 1%)要么不显示(1% 或更少)。此外,我对百分比进行了四舍五入,以便您使用该round
函数时没有任何小数。请记住,您需要四舍五入到小数点后两位。
本文收集自互联网,转载请注明来源。
如有侵权,请联系[email protected] 删除。
我来说两句