如何在没有不需要的条纹的情况下对比例进行数据整理和条形图绘制

Question

请在下面的屏幕截图中找到输入数据和预期输出：

但是，当前的情节具有以下代码：

我觉得，我把它搞得太复杂了。但我在整个过程中共享了输入数据和预期数据以及困难重重的代码。你能帮帮我们吗

主要有2个问题。 1. 如果使用 mutate，绘图上会出现不需要的条纹 Summarize used，那就不是加到100% 2.我们如何提取顶级贡献者两者都被我们尝试过但卡在某个地方


# Input data
df <- tibble(
  country = c(rep(c("India","USA","Germany","Africa"), each = 8)),
  type = c("sms","Other","whatsapp","web","online","shiny","whatsapp","whatsapp",
              "sms","sms","sms","web","web","Other","online","whatsapp",
              "sms","Other","whatsapp","shiny","online","shiny","whatsapp","whatsapp",
              "sms","sms","sms","shiny","online","Other","online","Other"
  ),
  cust = rep(c("google","Apple","wallmart","pg"),8),
  quantity = c(10,20,30,40,50,60,70,80,
               90,100,15,25,35,45,55,65,
               75,85,95,105,10,15,20,25,
               30,35,40,45,50,55,60,65)
)

# Without Customer
df %>% 
  group_by(country,type) %>%
  summarise(kpi_wo_cust = sum(quantity)) %>% 
  ungroup() -> df_wo_cust

# With Customer
df %>% 
  group_by(country,type,cust) %>%
  summarise(kpi_cust = sum(quantity)) %>% 
  ungroup() -> df_cust

df_combo <- left_join(df_cust, df_wo_cust, by = c("country","type"))
df_combo %>% glimpse()

# Aggregated data for certain KPIs for final plot
df_aggr <- df_combo %>% 
  group_by(country,type) %>%
  mutate(kpi_cust_total = sum(kpi_cust),
         per_kpi_cust = 100 * (kpi_cust/kpi_cust_total)) %>%
  group_by(country) %>%
  # In order to except from repeated counting, selecting unique()
  mutate(kpi_cust_uniq_total = sum(kpi_cust) %>% unique(),
         per_unq_kpi_cust = 100 * (kpi_cust/kpi_cust_uniq_total) %>% round(4)) 

#
plt = df_aggr %>% ungroup() %>%#glimpse()

# In order to obtain theTop 2 customers (Major contributor) within country and type 
# However, if this code is used, there is an error
# group_by(country, type) %>%
 # nest()  %>%
 # mutate(top_cust = purrr::map_chr(data, function(x){
 #   x %>% arrange(desc(per_kpi_cust)) %>%
 #     top_n(2,per_kpi_cust) %>%
 #     summarise(Cust = paste(cust,round(per_kpi_cust,2), collapse = "<br>")) %>%
 #     pull(cust)
 # })#,data = NULL
 # ) %>%
 # unnest(cols = data) %>%
  group_by(country, type) %>%
# If mutate is used, undesired stripes appear on the plot 
  # Summarize used, then it is not adding to 100% 
  mutate(avg_kpi_cust = per_unq_kpi_cust %>% mean()) %>%
  #summarise(avg_kpi_cust = per_unq_kpi_cust %>% mean()) %>%
  ggplot(aes(x = country, 
             y = avg_kpi_cust, 
             fill = type,  
             text = paste('<br>proportion: ', round(avg_kpi_cust,2), "%",
                          "<br>country:",country
                          ))) +
  geom_bar(stat = "identity"#, position=position_dodge()
  ) +
  coord_flip() +
  theme_bw()


ggplotly(plt)

Answer 1

关键是在 mutate() 之后使用 distinct() 而不是 summarise() 此外， mean() 是之前使用的错误函数而不是 sum() ，这导致条形图不完整。

library(tidyverse)
library(plotly)

# Input data
df <- tibble(
  country = c(rep(c("India","USA","Germany","Africa"), each = 8)),
  type = c("sms","Other","whatsapp","web","online","shiny","whatsapp","whatsapp",
              "sms","sms","sms","web","web","Other","online","whatsapp",
              "sms","Other","whatsapp","shiny","online","shiny","whatsapp","whatsapp",
              "sms","sms","sms","shiny","online","Other","online","Other"
  ),
  cust = rep(c("google","Apple","wallmart","pg"),8),
  quantity = c(10,20,30,40,50,60,70,80,
               90,100,15,25,35,45,55,65,
               75,85,95,105,10,15,20,25,
               30,35,40,45,50,55,60,65)
)

# Without Customer
df %>% 
  group_by(country,type) %>%
  summarise(kpi_wo_cust = sum(quantity)) %>% 
  ungroup() -> df_wo_cust

# With Customer
df %>% 
  group_by(country,type,cust) %>%
  summarise(kpi_cust = sum(quantity)) %>% 
  ungroup() -> df_cust

df_combo <- left_join(df_cust, df_wo_cust, by = c("country","type"))
df_combo %>% glimpse()

# Aggregated data for certain KPIs for final plot
df_aggr <- df_combo %>% 
  group_by(country,type) %>%
  mutate(kpi_cust_total = sum(kpi_cust),
         per_kpi_cust = 100 * (kpi_cust/kpi_cust_total)) %>%
  group_by(country) %>%
  # In order to except from repeated counting, selecting unique()
  mutate(kpi_cust_uniq_total = sum(kpi_cust) %>% unique(),
         per_unq_kpi_cust = 100 * (kpi_cust/kpi_cust_uniq_total) %>% round(4)) 

plt = df_aggr %>% ungroup() %>%
# In order to diplay Top 2 customers (Major contributor) within country and type 
group_by(country, type) %>%
nest()  %>%
mutate(top_cust = purrr::map_chr(data, function(x){
  x %>% arrange(desc(per_kpi_cust)) %>%
    top_n(2,per_kpi_cust) %>%
    summarise(Cust = paste(cust,round(per_kpi_cust,2), collapse = "<br>")) %>%
    pull(Cust)
})) %>%
unnest(cols = data) %>%
  group_by(country, type) %>%
# If mutate is used, undesired stripes appear on the plot 
  # Summarize used, then it is not adding to 100%.
  # So distinct was used
  mutate(avg_kpi_cust = per_unq_kpi_cust %>% sum()) %>%
  ungroup() %>%
  distinct(country, type, .keep_all = T) %>%
  ggplot(aes(x = country, 
             y = avg_kpi_cust, 
             fill = type,  
             text = top_cust
                          )) +
  geom_bar(stat = "identity") +
  coord_flip() +
  theme_bw()

ggplotly(plt, tooltip = "text")

如何在没有不需要的条纹的情况下对比例进行数据整理和条形图绘制

How to data wrangle and barplot the proportion without undesired stripes

grouping

r

bar-chart

dplyr

ggplotly