帶有重疊標籤的geom_text（）

Question

因此，我的散點圖的某些標籤重疊。我已經嘗試使用direct.label和「smart.grid」方法，但它不會產生合適的結果。這是我目前的圖形：

產生它的代碼：

ggplot(d, aes(x=ILE2, y=TE,label=d$CA)) + 
    geom_point(mapping=aes(x=ILE2, y=TE, fill=d$CA), size=9, shape=20, color="black") + 
    geom_text(data = d,mapping=aes(x=ILE2, y=TE,label=d$CA), size=4, vjust=3, hjust=0.5,size=6)+ 
    geom_smooth(method=lm,se=F)+ 
    theme(legend.position = "none")+ 
    ggtitle("Tasa de Empleo según Índice de Libertad Económica") + 
    labs(x="Índice de Libertad Económica",y="Tasa de Empleo") + 
    theme(plot.title = element_text(family =windowsFonts(Times=windowsFont("TT Times New Roman")), color="#666666", face="bold", size=22, hjust=0.5)) + 
    theme(axis.title = element_text(family =windowsFonts(Times=windowsFont("TT Times New Roman")), color="#666666", face="bold", size=22)) 

數據：

structure(list(CA = structure(c(1L, 2L, 3L, 4L, 6L, 8L, 9L, 5L, 
7L, 10L, 11L, 12L, 14L, 15L, 16L, 17L, 13L), .Label = c("Andalucía", 
"Aragón", "Asturias", "Balears", "C. La Mancha", "C. Valenciana", 
"C. y León", "Canarias", "Cantabria", "Cataluña", "Extremadura", 
"Galicia", "La Rioja", "Madrid", "Murcia", "Navarra", "País Vasco" 
), class = "factor"), CA.excel = structure(c(1L, 2L, 3L, 4L, 
10L, 5L, 6L, 7L, 8L, 9L, 11L, 12L, 13L, 14L, 15L, 16L, 17L), .Label = c("Andalucía", 
"Aragón", "Asturias, Principado de", "Balears, Illes", "Canarias", 
"Cantabria", "Castilla - La Mancha", "Castilla y León", "Cataluña", 
"Comunitat Valenciana", "Extremadura", "Galicia", "Madrid, Comunidad de", 
"Murcia, Región de", "Navarra, Comunidad Foral de", "País Vasco", 
"Rioja, La"), class = "factor"), ILE = c(0.64, 0.45, 0.61, 0.36, 
0.4, 0.4, 0.48, 0.54, 0.5, 0.5, 0.72, 0.53, 0.19, 0.49, 0.43, 
0.46, 0.39), ILE2 = c(0.36, 0.55, 0.39, 0.64, 0.6, 0.6, 0.52, 
0.46, 0.5, 0.5, 0.28, 0.48, 0.81, 0.51, 0.58, 0.54, 0.61), TE = c(39.04, 
47.6, 40.61, 48.82, 44.65, 43.06, 45.77, 41.85, 43.49, 49.76, 
38.38, 41.82, 53.08, 43.4, 49.49, 47.98, 48.83), migdest = c(21774L, 
5511L, 3147L, 9333L, 17187L, 7568L, 2689L, 12547L, 8701L, 19727L, 
3878L, 6147L, 38182L, 6678L, 3024L, 7363L, 1736L), Poblacion = c(8399618L, 
1326403L, 1049875L, 1124972L, 4939674L, 2126144L, 585359L, 2062767L, 
2478079L, 7396991L, 1091623L, 2734656L, 6385298L, 1463773L, 636402L, 
2165100L, 313569L), MigraPob = c(0.002592261, 0.004154845, 0.002997501, 
0.008296203, 0.003479379, 0.003559496, 0.004593765, 0.006082607, 
0.003511188, 0.002666895, 0.003552507, 0.002247815, 0.005979674, 
0.004562182, 0.004751713, 0.003400767, 0.005536262), Ocupados = structure(c(3L, 
12L, 9L, 10L, 1L, 14L, 5L, 13L, 16L, 7L, 8L, 17L, 4L, 11L, 6L, 
15L, 2L), .Label = c("1.836.300", "126.900", "2.683.700", "2.786.600", 
"226.300", "258.200", "3.023.200", "350.100", "371.800", "455.900", 
"513.400", "524.500", "707.000", "771.500", "870.300", "913.300", 
"987.500"), class = "factor"), Activos = structure(c(11L, 15L, 
12L, 14L, 6L, 2L, 7L, 17L, 3L, 9L, 13L, 4L, 8L, 16L, 10L, 1L, 
5L), .Label = c("1.041.500,00", "1.115.000,00", "1.147.000,00", 
"1.263.200,00", "153.900,00", "2.425.100,00", "277.900,00", "3.389.400,00", 
"3.781.300,00", "306.100,00", "4.042.900,00", "458.900,00", "501.800,00", 
"586.600,00", "644.300,00", "700.300,00", "991.500,00"), class = "factor"), 
    Tocup = c(0.664, 0.814, 0.81, 0.777, 0.757, 0.692, 0.814, 
    0.713, 0.796, 0.8, 0.698, 0.782, 0.822, 0.733, 0.844, 0.836, 
    0.825), Paro = c(0.336, 0.186, 0.19, 0.223, 0.243, 0.308, 
    0.186, 0.287, 0.204, 0.2, 0.302, 0.218, 0.178, 0.267, 0.156, 
    0.164, 0.175), X..Emp.disueltas14 = structure(c(9L, 16L, 
    12L, 15L, 17L, 8L, 14L, 1L, 7L, 4L, 11L, 2L, 13L, 10L, 5L, 
    3L, 6L), .Label = c("1.102", "1.529", "1.544", "1.953", "160", 
    "196", "2.465", "260", "3.172", "349", "362", "467", "5.147", 
    "552", "833", "846", "915"), class = "factor"), EmpD1000h = c(0.3776, 
    0.6378, 0.4448, 0.7405, 0.1852, 0.1223, 0.943, 0.5342, 0.9947, 
    0.264, 0.3316, 0.5591, 0.8061, 0.2384, 0.2514, 0.7131, 0.6251 
    ), EmpCreadas = c(15541L, 1933L, 1364L, 2887L, 11206L, 3486L, 
    819L, 2812L, 3000L, 17664L, 1186L, 4266L, 20268L, 2732L, 
    905L, 3447L, 448L), TasaEmpC = c(1.850203188, 1.45732481, 
    1.299202286, 2.566286094, 2.26857076, 1.639587911, 1.399141382, 
    1.363217465, 1.210615158, 2.387998039, 1.086455672, 1.559976831, 
    3.174166656, 1.866409614, 1.422057127, 1.592074269, 1.42871266 
    ), RentaMediaHogar = c(21332L, 29120L, 25623L, 26923L, 22392L, 
    21539L, 23905L, 22271L, 24587L, 30407L, 19364L, 26001L, 31587L, 
    21269L, 33047L, 34240L, 26666L), GananciaMediaTrab = c(20782.03, 
    22054.85, 21994.99, 20776.29, 19167.93, 20052.12, 20440.56, 
    20630.07, 24253.73, 20878.02, 19129.72, 19824.66, 26215.36, 
    20449.83, 23836.93, 26915.07, 20628.81)), .Names = c("CA", 
"CA.excel", "ILE", "ILE2", "TE", "migdest", "Poblacion", "MigraPob", 
"Ocupados", "Activos", "Tocup", "Paro", "X..Emp.disueltas14", 
"EmpD1000h", "EmpCreadas", "TasaEmpC", "RentaMediaHogar", "GananciaMediaTrab" 
), class = "data.frame", row.names = c(NA, -17L)) 

Answer 1

您可能會考慮嘗試使用ggrepel將標籤放置在不重疊的位置。

library(ggrepel) 
ggplot(d, aes(x=ILE2, y=TE,label=d$CA)) + 
    geom_point(mapping=aes(x=ILE2, y=TE, fill=d$CA), size=9, shape=20, color="black") + 
    geom_text_repel(
    data = d, 
    mapping=aes(x=ILE2, y=TE,label=d$CA), 
    size=4, size=6, box.padding = unit(0.5, "lines") 
)+ 
    geom_smooth(method=lm,se=F)+ 
    theme(legend.position = "none")+ 
    ggtitle("Tasa de Empleo según Índice de Libertad Económica") + 
    labs(x="Índice de Libertad Económica",y="Tasa de Empleo") 

Answer 2

我覺得有幾個策略，你可以採用，這取決於無論您是需要通用解決方案還是簡單解決此特定圖形。

首先，您可以使用偏移量或抖動（如上面鏈接到的問題I中所述）作爲可能的重複項。 IE-here。這可能提供了最一般的解決方案。

但是，如果你只需要這個了這個特定的圖，你可以使用重疊（在你的數據只有幾個）標籤，在這裏我們使用不同的偏移量（hjust，vjust）爲每個標籤設置多個geom_text電話。

# create label-sets 
lab1 <- ifelse(as.character(d$CA) %in% c("Balears", "Aragón", "Murcia", "C. La Mancha","Extremadura"), 
       "", as.character(d$CA)) 
lab2 <- ifelse(!(as.character(d$CA) %in% c("Balears", "Aragón", "Murcia", "C. La Mancha", "Extremadura")), 
       "", as.character(d$CA)) 

# same graph, two sets of labels. 
ggplot(d, aes(x=ILE2, y=TE)) + 
    geom_point(mapping=aes(x=ILE2, y=TE, fill=d$CA), size=9, shape=20, color="black") + 
    geom_text(data = d,mapping=aes(x=ILE2, y=TE,label=lab1), size=4, vjust=1.5, hjust=1,size=6)+ 
    geom_text(data = d,mapping=aes(x=ILE2, y=TE,label=lab2), size=4, vjust=-1.5, hjust=0,size=6)+ 
    geom_smooth(method=lm,se=F)+ 
    theme(legend.position = "none")+ 
    ggtitle("Tasa de Empleo según Índice de Libertad Económica") + 
    labs(x="Índice de Libertad Económica",y="Tasa de Empleo") + 
    theme(plot.title = element_text(family =windowsFonts(Times=windowsFont("TT Times New Roman")), 
            color="#666666", face="bold", size=22, hjust=0.5)) + 
    theme(axis.title = element_text(family =windowsFonts(Times=windowsFont("TT Times New Roman")), 
            color="#666666", face="bold", size=22)) 

很明顯，你可以調整hjust/vjust，你想對你特別的審美喜好，使標籤更清晰。 注意：我收到有關沒有特定字體系列的警告。如果您提供字體庫，我可以更新解決方案。