r - ggplot疑难解答：错误：美学必须是长度1或与数据相同（24）：x，y，填充

Question

样本数据：

> dput(droplevels(data[1:50, ]))
    structure(list(QtySold = c(3L, -1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 
2L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 6L, 2L, 
1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 
1L, 1L, 2L, 1L, 2L, 2L, 4L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 
2L, -1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 1L, 2L, 
2L, 1L, 1L, 1L, 2L, 3L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 3L, 2L, 1L, 
1L, 1L, 4L, 5L, 1L, 3L, 1L, 2L, 30L, 2L, 10L, 6L, 10L, 8L, 10L, 
20L, 10L, 5L, 1L, 3L, 30L, 20L, 10L, 10L, 90L, 10L, 12L, 10L, 
15L, 10L, 10L, 20L, 10L, 10L, 32L, 10L, 10L, 20L, 1L, 2L, 1L, 
2L, 2L, 5L, 2L, 1L, 3L, 3L, 1L, 1L, 2L, 4L, 2L, 4L, 1L, 1L, 2L, 
2L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 1L, 3L, 
1L, 4L, 2L, 1L, 4L, 4L, 5L, 1L, 3L, 2L, 2L, 4L, 1L, 3L, 3L, 1L, 
3L, 6L, 7L, 1L, 3L, 7L, 2L, 1L, 4L, 2L, 3L, 3L, 5L, 2L, 1L, 1L, 
4L, 6L, 1L, 1L, 1L, 1L, 2L, 1L, 4L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 4L, 1L, 3L, 2L, 1L, 1L, 3L, 1L, 1L, 1L, 1L, 
5L, 1L, 1L, 1L, 1L, 3L, 1L, 2L, 1L, 2L, 2L, 3L, 4L, 1L, 3L, 2L, 
1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 3L, 4L, 2L, 1L, 
4L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 
2L, 1L, 3L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
2L, 2L, 1L, 3L, 1L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 
1L, 1L, 3L, 3L, 1L, 1L, 1L, 1L, 4L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 
1L, 2L, 3L, 1L, -1L, 1L, 1L, 1L, 2L, 2L, 2L, 10L, 1L, 1L, -4L, 
1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
4L, -1L, 2L, 3L, 1L, 1L, 5L, 1L, 10L, 1L, 1L, 4L, 1L, 1L, 1L, 
2L, 30L, 2L, 12L, 20L, 5L, 1L, 5L, 3L, 4L, 12L, 6L, 10L, 8L, 
4L, 6L, 8L, 3L, 6L, 1L, -1L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 3L, 
8L, 6L, 10L, 6L, 15L, 10L, 6L, 8L, 10L, 6L, 20L, 10L, 10L, 10L, 
10L, 1L, 10L, 10L, 5L, 10L, 20L, 4L, 12L, 10L, 10L, 5L, 10L, 
6L, 1L, 1L, 2L, 4L, 1L, 1L, 1L, 3L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 
2L, 3L, 4L, 13L, 4L, 3L, 1L, 12L, 1L, 10L, 1L, 6L, 1L, 1L, 3L, 
10L, 2L, 1L, 1L, 1L, 1L, 1L, -1L, 1L, 1L, 1L, 1L, 8L, 12L, 6L, 
12L, 4L, 2L, 3L, 24L, 10L, 8L, 6L, 1L, 3L, 1L, 1L, 1L, 6L, 1L, 
1L, 1L, -1L, 1L, 2L, 3L, 1L, 1L, 1L, 2L, 1L, 1L, 4L, 1L, 10L, 
-1L), PRODUCT_SUB_LINE_DESCR = structure(c(3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 
1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("Handpieces", 
"PRIVATE LABEL", "SUNDRY"), class = "factor"), MAJOR_CATEGORY_KEY = structure(c(23L, 
23L, 23L, 23L, 21L, 21L, 21L, 23L, 23L, 23L, 11L, 11L, 11L, 11L, 
11L, 11L, 11L, 11L, 11L, 11L, 25L, 19L, 19L, 4L, 4L, 9L, 9L, 
9L, 9L, 9L, 9L, 23L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 
19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 
19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 
19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 
19L, 19L, 19L, 17L, 16L, 4L, 4L, 4L, 4L, 11L, 11L, 4L, 4L, 4L, 
4L, 11L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 21L, 12L, 12L, 12L, 10L, 10L, 10L, 
10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 13L, 13L, 7L, 18L, 7L, 
19L, 19L, 19L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 
21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 
21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 
21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 
21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 
21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 
21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 
21L, 21L, 21L, 21L, 21L, 13L, 13L, 11L, 11L, 6L, 12L, 10L, 10L, 
4L, 4L, 4L, 4L, 4L, 4L, 10L, 19L, 19L, 19L, 19L, 19L, 4L, 4L, 
11L, 11L, 11L, 11L, 11L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 
21L, 21L, 21L, 21L, 21L, 21L, 11L, 16L, 16L, 16L, 16L, 16L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 16L, 16L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 3L, 21L, 4L, 
4L, 4L, 19L, 19L, 19L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 17L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 
19L, 19L, 19L, 12L, 12L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 13L, 
4L, 4L, 4L, 4L, 4L, 4L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 18L, 
21L, 21L, 18L, 18L, 18L, 18L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 
12L, 12L, 12L, 12L, 12L, 12L, 19L, 19L, 18L, 18L, 4L, 11L), .Label = c("AIR ", 
"AML ", "ANS ", "ASE ", "ASP ", "B&D ", "BLE ", "C&P ", "CBL ", 
"CEM ", "CMP ", "CRN ", "END ", "FNP ", "GYP ", "HND ", "IMP ", 
"INS ", "OTH ", "P&P ", "PRE ", "RTC ", "SME ", "UCL ", "XRY "
), class = "factor")), row.names = c(NA, 500L), class = "data.frame")

以及相关代码

     > newdf = subset(data, select = c(QtySold, PRODUCT_SUB_LINE_DESCR, MAJOR_CATEGORY_KEY))
> sample = newdf %>% 
+   filter(QtySold < 0) %>%
+   group_by(PRODUCT_SUB_LINE_DESCR,MAJOR_CATEGORY_KEY) %>%
+   summarise(returns = sum(QtySold)) %>%
+   spread(PRODUCT_SUB_LINE_DESCR,returns, fill=0) %>%
+   mutate(total_returns = `PRIVATE LABEL` + SUNDRY + Handpieces,
+          PercentageReturn_PL = round(`PRIVATE LABEL`/ total_returns*100,1))
> sample %>%
+               group_by(PRODUCT_SUB_LINE_DESCR) %>%
+               summarise(count=n()) %>%
+               mutate(percent= paste0(round(count/sum(count)*100,1),'%'))
Error in grouped_df_impl(data, unname(vars), drop) : 
  Column `PRODUCT_SUB_LINE_DESCR` is unknown 

我的场景：

• 项目清单
• 我有三个产品的数据集：杂物、手机和自有品牌。
• 我根据（QtySold < 0）类别过滤了数据集，并根据“PRODUCT_SUB_LINE_DESCR”和“MAJOR_CATEGORY_KEY”对新的数据集进行了分组。
• 我想查看属于自有品牌类别的退货商品的百分比。我的代码有一个带有新列“PercentageReturn_PL”的变异命令。
• 最后，当我完成数学运算后，我想用 Y 轴上的 MAJOR_CATEGORY_KEY 绘制整个事情，堆叠的条形图显示一个 MAJOR_CATEGORY_KEY 中三种产品的百分比细分。

我该如何解决这个错误？

> sample %>%
+               group_by(PRODUCT_SUB_LINE_DESCR) %>%
+               summarise(count=n()) %>%
+               mutate(percent= paste0(round(count/sum(count)*100,1),'%'))
Error in grouped_df_impl(data, unname(vars), drop) : 
  Column `PRODUCT_SUB_LINE_DESCR` is unknown 

标签： rggplot2

Answer 1

问题是你spread拿出一列然后试图使用它。图中还有很多额外的东西。

这是一种按主要类别获取 PRIVATE LABEL 回报百分比的方法：

sample_long = 
    newdf %>%
    filter(QtySold < 0) %>%
    group_by(MAJOR_CATEGORY_KEY) %>%
    summarize(returns = sum(QtySold),
                        percent_returns_pl = sum(QtySold[PRODUCT_SUB_LINE_DESCR == "PRIVATE LABEL"]) / returns) 

然后我们可以很容易地绘制：

ggplot(
    sample_long,
    aes(x = MAJOR_CATEGORY_KEY, y = percent_returns_pl)
) +
    geom_col() +
    geom_text(aes(label = scales::percent(percent_returns_pl)), vjust = -0.5) +
    scale_y_continuous(labels = scales::percent)

这是一个带有样本数据的无聊图，使用完整数据应该会更有趣。