Zeige nur Top 3 Einträge und bleib als "Others" im gestapelten Barplot mit ggplot2

Question

Ich versuche ein Balkendiagramm zu erstellen, das die monatlichen ein- und ausgehenden Anrufe anzeigt. Wenn ich ein gestapeltes Balkendiagramm erstelle, möchte ich in der Lage sein, die Stapel für die Top-3-Kontakte (mit der höchsten Anrufdauer) anzuzeigen und den Rest als andere anzuzeigen. Gibt es eine Möglichkeit, dies in R zu automatisieren?

Mein jetziger Diagramm sieht wie folgt aus:

Meine Datenrahmen (callsummary) heruntergeladen werden kann (3 kb) aus dem unten stehenden Link:

https://dl.dropboxusercontent.com/u/4077057/callsummary.csv 

Mein Code für ggplot ist:

ggplot(callsummary) + 
    aes(x = Bill, y = Duration) + 
    geom_bar(stat = "identity", aes(fill =Contact)) + 
    facet_grid(~Direction) + 
    labs(list(title = "Monthly Call Summary", x = "Month", y = "Total Call duration in Minutes")) + 
    geom_hline(data = subset(monthlysummary, Direction == "In"), aes(yintercept = mean(Duration))) + 
    geom_hline(data = subset(monthlysummary, Direction == "Out"), aes(yintercept = mean(Duration))) 

Beachten Sie, dass ich eine andere Datafra erstellt habe Ich habe monatliche Zusammenfassung nur aufgerufen, um in der Lage zu sein, einen y-Abschnitt hinzuzufügen, der gleich der durchschnittlichen Anrufdauer in beiden "In" - und "Out" -Gittern ist.

Die monthlysummary Datenrahmen wie folgt aussieht:

Direction Bill Duration Amount 
     <fctr> <fctr> <dbl> <dbl> 
1  Out April  9.3 1.40 
2  In April  55.3 0.00 
3  Out May  32.5 4.89 
4  In May  76.9 0.00 
5  Out June  17.4 2.62 
6  In June 114.3 0.00 

Answer 1

# Read the csv file 
callsummary <- read.csv("callsummary.csv", header = T) 
# Remove the first column which are row numbers 
callsummary <- callsummary[,-1]  

library(dplyr) 
library(ggplot2) 


callsummary$Contact <- as.character(callsummary$Contact) 

df <- callsummary %>% 
    group_by(Direction, Bill) %>% 
    arrange(desc(Amount)) %>% 
    mutate(Index = 1:n(), Contact = ifelse(Index > 3, "Other", Contact)) 

df2 <- df %>% group_by(Direction) %>% summarise(Y = mean(Amount)) 


ggplot(df, aes(x = Bill, y = Amount)) + 
    geom_bar(stat = "identity", aes(fill = Contact)) + 
    facet_grid(~ Direction) + 
    labs(list(title = "Monthly Call Summary", x = "Month", y = "Total Call duration in Minutes")) + 
    geom_hline(data = df2, aes(yintercept = Y)) 

Daten (nach dem Entfernen der ersten Spalte)

structure(list(Direction = structure(c(1L, 1L, 2L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 
2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 
2L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("In", 
"Out"), class = "factor"), Contact = c("D28", "D10", "D18", "D3", 
"D10", "D18", "D3", "D18", "D10", "D18", "D21", "D27", "D13", 
"D3", "D10", "D3", "D21", "D22", "D23", "D17", "D13", "D15", 
"D18", "D21", "D2", "D8", "D1", "D15", "D23", "D23", "D18", "D11", 
"D16", "D21", "D24", "D3", "D25", "D15", "D10", "D9", "D22", 
"D19", "D10", "D3", "D8", "D12", "D13", "D15", "D17", "D19", 
"D19", "D20", "D4", "D5", "D6", "D7", "D11", "D13", "D14", "D15", 
"D17", "D19", "D20", "D21", "D22", "D22", "D26", "D27", "DNA" 
), Bill = structure(c(2L, 3L, 3L, 3L, 2L, 1L, 2L, 3L, 1L, 2L, 
2L, 1L, 2L, 1L, 2L, 2L, 3L, 3L, 2L, 3L, 2L, 3L, 1L, 1L, 3L, 3L, 
1L, 1L, 1L, 3L, 2L, 1L, 3L, 3L, 3L, 3L, 1L, 2L, 1L, 1L, 3L, 3L, 
3L, 1L, 3L, 3L, 1L, 2L, 3L, 3L, 2L, 3L, 3L, 3L, 1L, 2L, 2L, 1L, 
3L, 3L, 1L, 1L, 3L, 1L, 1L, 2L, 1L, 3L, 2L), .Label = c("April", 
"June", "May"), class = "factor"), Amount = c(56.3, 20.6, 16.3, 
16, 15.9, 14.3, 11.2, 10.8, 9.1, 8, 7.4, 6.9, 6.4, 5.3, 5.1, 
5, 4.6, 3.9, 3.7, 3.4, 3, 3, 3, 3, 3, 3, 2.8, 2.4, 2.4, 2.4, 
2.3, 2.3, 2, 2, 2, 1.9, 1.5, 1.4, 1.3, 1.3, 1.2, 1.2, 1.1, 1, 
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 
1, 1, 1, 1), NA. = c(0, 0, 2.45, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
0, 0.77, 0.75, 0, 0, 0, 0, 0.45, 0.45, 0.45, 0.45, 0, 0, 0, 0, 
0, 0, 0.35, 0, 0.3, 0.3, 0, 0.29, 0, 0, 0.2, 0, 0.18, 0, 0.17, 
0.15, 0.15, 0.15, 0.15, 0.15, 0.15, 0.15, 0.15, 0.15, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)), .Names = c("Direction", 
"Contact", "Bill", "Amount", "NA."), row.names = c(NA, -69L), class = "data.frame") 

Answer 2

Okay, also Monat spezifische Variablen erstellen, wie ...

callsummary$June <- NA 

callsummary$June[callsummary$Bill %in% sort(
    callsummary$Duration, 
    decreasing = TRUE)[1:3]] <- callsummary$Bill[ 
     callsummary$Bill %in% sort(
      callsummary$Duration, 
      decreasing = TRUE)[1:3]] 

callsummary$June[!callsummary$Bill %in% callsummary$Bill[sort(
    callsummary$Duration, 
    decreasing = TRUE)[1:3]] <- "Others"