justifying labels and label transparency in ggplot

2
votes

I have the following data:

new_pairs
     x    y Freq start.latittude start.longitude              start.station end.latitude
1  359  519  929        40.75188       -73.97770         Pershing\nSquare N     40.75510
2  477  465 5032        40.75514       -73.98658        Broadway &\nW 41 St     40.75641
3  484  519 1246        40.75188       -73.97770         Pershing\nSquare N     40.75500
4  484  318 2654        40.75320       -73.97799 E 43 St &\nVanderbilt\nAve     40.75500
5  492  267 1828        40.75098       -73.98765        Broadway &\nW 36 St     40.75020
6  492  498  957        40.74855       -73.98808        Broadway &\nW 32 St     40.75020
7  492  362 1405        40.75173       -73.98754        Broadway &\nW 37 St     40.75020
8  493  477 1582        40.75641       -73.99003           W 41 St &\n8 Ave     40.75680
9  493  529  728        40.75757       -73.99099           W 42 St &\n8 Ave     40.75680
10 529 2021 1748        40.75929       -73.98860           W 45 St &\n8 Ave     40.75757
   end.longitude        end.station                             interaction
1      -73.97499 E 47 St &\nPark Av     E 47 St &Park Av > PershingSquare N
2      -73.99003   W 41 St &\n8 Ave      W 41 St &8 Ave > Broadway &W 41 St
3      -73.98014   W 44 St &\n5 Ave       W 44 St &5 Ave > PershingSquare N
4      -73.98014   W 44 St &\n5 Ave W 44 St &5 Ave > E 43 St &VanderbiltAve
5      -73.99093   W 33 St &\n7 Ave      W 33 St &7 Ave > Broadway &W 36 St
6      -73.99093   W 33 St &\n7 Ave      W 33 St &7 Ave > Broadway &W 32 St
7      -73.99093   W 33 St &\n7 Ave      W 33 St &7 Ave > Broadway &W 37 St
8      -73.98291   W 45 St &\n6 Ave         W 45 St &6 Ave > W 41 St &8 Ave
9      -73.98291   W 45 St &\n6 Ave         W 45 St &6 Ave > W 42 St &8 Ave
10     -73.99099   W 42 St &\n8 Ave         W 42 St &8 Ave > W 45 St &8 Ave

I would like to change the plot so that the labels are all justified to the center and change transparency based on their Freq so that the lower Freq are more transparent and the higher Freq are less transparent

ggplot(data= new_pairs, aes(x= reorder(interaction, -Freq), y=Freq))+ geom_bar(stat="identity", aes(fill = Freq, alpha = .7)) + ylab("Bikes received")+ xlab("Station")+ geom_text(aes(x = interaction, label = interaction), vjust="inward",hjust = "inward", size = 4, nudge_y = 1, fontface ="bold")+theme(axis.text.y=element_blank())+ggtitle("Bikes received viarebalancing")+coord_flip()+theme(legend.position = "none")


dput(new_pairs)
structure(list(x = structure(c(146L, 253L, 260L, 260L, 268L, 
268L, 268L, 269L, 269L, 304L), .Label = c("72", "79", "82", "83", 
"116", "119", "120", "127", "128", "137", "143", "144", "146", 
"147", "150", "151", "152", "153", "157", "160", "161", "164", 
"167", "168", "173", "174", "195", "212", "216", "217", "218", 
"223", "224", "225", "228", "229", "232", "233", "236", "237", 
"238", "239", "241", "242", "243", "244", "245", "247", "248", 
"249", "250", "251", "252", "253", "254", "257", "258", "259", 
"260", "261", "262", "263", "264", "265", "266", "267", "268", 
"270", "271", "274", "275", "276", "278", "279", "280", "281", 
"282", "284", "285", "289", "290", "291", "293", "294", "295", 
"296", "297", "298", "300", "301", "302", "303", "304", "305", 
"306", "307", "308", "309", "310", "311", "312", "313", "314", 
"315", "316", "317", "318", "319", "320", "321", "322", "323", 
"324", "325", "326", "327", "328", "329", "330", "331", "332", 
"334", "335", "336", "337", "339", "340", "341", "342", "343", 
"344", "345", "346", "347", "348", "349", "350", "351", "352", 
"353", "354", "355", "356", "357", "358", "359", "360", "361", 
"362", "363", "364", "365", "366", "367", "368", "369", "372", 
"373", "375", "376", "377", "379", "380", "382", "383", "384", 
"385", "386", "387", "388", "389", "390", "391", "392", "393", 
"394", "395", "396", "397", "398", "399", "400", "401", "402", 
"403", "404", "405", "406", "407", "408", "409", "410", "411", 
"412", "414", "415", "416", "417", "418", "419", "420", "421", 
"422", "423", "426", "427", "428", "430", "431", "432", "433", 
"434", "435", "436", "437", "438", "439", "440", "441", "442", 
"443", "444", "445", "446", "447", "448", "449", "450", "453", 
"454", "455", "456", "457", "458", "459", "460", "461", "462", 
"463", "464", "465", "466", "467", "468", "469", "470", "471", 
"472", "473", "474", "475", "476", "477", "478", "479", "480", 
"481", "482", "483", "484", "485", "486", "487", "488", "489", 
"490", "491", "492", "493", "494", "495", "496", "497", "498", 
"499", "500", "501", "502", "503", "504", "505", "507", "508", 
"509", "510", "511", "512", "513", "514", "515", "516", "517", 
"518", "519", "520", "521", "522", "523", "524", "525", "526", 
"527", "528", "529", "530", "531", "532", "533", "534", "536", 
"537", "538", "539", "540", "545", "546", "2000", "2002", "2003", 
"2004", "2005", "2006", "2008", "2009", "2010", "2012", "2017", 
"2021", "2022", "2023", "3002"), class = "factor"), y = structure(c(294L, 
241L, 294L, 107L, 66L, 274L, 149L, 253L, 304L, 327L), .Label = c("72", 
"79", "82", "83", "116", "119", "120", "127", "128", "137", "143", 
"144", "146", "147", "150", "151", "152", "153", "157", "160", 
"161", "164", "167", "168", "173", "174", "195", "212", "216", 
"217", "218", "223", "224", "225", "228", "229", "232", "233", 
"236", "237", "238", "239", "241", "242", "243", "244", "245", 
"247", "248", "249", "250", "251", "252", "253", "254", "257", 
"258", "259", "260", "261", "262", "263", "264", "265", "266", 
"267", "268", "270", "271", "274", "275", "276", "278", "279", 
"280", "281", "282", "284", "285", "289", "290", "291", "293", 
"294", "295", "296", "297", "298", "300", "301", "302", "303", 
"304", "305", "306", "307", "308", "309", "310", "311", "312", 
"313", "314", "315", "316", "317", "318", "319", "320", "321", 
"322", "323", "324", "325", "326", "327", "328", "329", "330", 
"331", "332", "334", "335", "336", "337", "339", "340", "341", 
"342", "343", "344", "345", "346", "347", "348", "349", "350", 
"351", "352", "353", "354", "355", "356", "357", "358", "359", 
"360", "361", "362", "363", "364", "365", "366", "367", "368", 
"369", "372", "373", "375", "376", "377", "379", "380", "382", 
"383", "384", "385", "386", "387", "388", "389", "390", "391", 
"392", "393", "394", "395", "396", "397", "398", "399", "400", 
"401", "402", "403", "404", "405", "406", "407", "408", "409", 
"410", "411", "412", "414", "415", "416", "417", "418", "419", 
"420", "421", "422", "423", "426", "427", "428", "430", "431", 
"432", "433", "434", "435", "436", "437", "438", "439", "440", 
"441", "442", "443", "444", "445", "446", "447", "448", "449", 
"450", "453", "454", "455", "456", "457", "458", "459", "460", 
"461", "462", "463", "464", "465", "466", "467", "468", "469", 
"470", "471", "472", "473", "474", "475", "476", "477", "478", 
"479", "480", "481", "482", "483", "484", "485", "486", "487", 
"488", "489", "490", "491", "492", "493", "494", "495", "496", 
"497", "498", "499", "500", "501", "502", "503", "504", "505", 
"507", "508", "509", "510", "511", "512", "513", "514", "515", 
"516", "517", "518", "519", "520", "521", "522", "523", "524", 
"525", "526", "527", "528", "529", "530", "531", "532", "533", 
"534", "536", "537", "538", "539", "540", "545", "546", "2000", 
"2002", "2003", "2004", "2006", "2008", "2009", "2010", "2012", 
"2017", "2021", "2022", "2023", "3002"), class = "factor"), Freq = c(929L, 
5032L, 1246L, 2654L, 1828L, 957L, 1405L, 1582L, 728L, 1748L), 
    start.latittude = c(40.75188406, 40.75513557, 40.75188406, 
    40.75320159, 40.75097711, 40.74854862, 40.75172632, 40.75640548, 
    40.7575699, 40.75929124), start.longitude = c(-73.97770164, 
    -73.98658032, -73.97770164, -73.9779874, -73.98765428, -73.98808416, 
    -73.98753523, -73.9900262, -73.99098507, -73.98859651), start.station = c("Pershing\nSquare N", 
    "Broadway &\nW 41 St", "Pershing\nSquare N", "E 43 St &\nVanderbilt\nAve", 
    "Broadway &\nW 36 St", "Broadway &\nW 32 St", "Broadway &\nW 37 St", 
    "W 41 St &\n8 Ave", "W 42 St &\n8 Ave", "W 45 St &\n8 Ave"
    ), end.latitude = c(40.75510267, 40.75640548, 40.75500254, 
    40.75500254, 40.75019995, 40.75019995, 40.75019995, 40.7568001, 
    40.7568001, 40.7575699), end.longitude = c(-73.97498696, 
    -73.9900262, -73.98014437, -73.98014437, -73.99093085, -73.99093085, 
    -73.99093085, -73.98291153, -73.98291153, -73.99098507), 
    end.station = c("E 47 St &\nPark Av", "W 41 St &\n8 Ave", 
    "W 44 St &\n5 Ave", "W 44 St &\n5 Ave", "W 33 St &\n7 Ave", 
    "W 33 St &\n7 Ave", "W 33 St &\n7 Ave", "W 45 St &\n6 Ave", 
    "W 45 St &\n6 Ave", "W 42 St &\n8 Ave"), interaction = c("E 47 St &Park Av > PershingSquare N", 
    "W 41 St &8 Ave > Broadway &W 41 St", "W 44 St &5 Ave > PershingSquare N", 
    "W 44 St &5 Ave > E 43 St &VanderbiltAve", "W 33 St &7 Ave > Broadway &W 36 St", 
    "W 33 St &7 Ave > Broadway &W 32 St", "W 33 St &7 Ave > Broadway &W 37 St", 
    "W 45 St &6 Ave > W 41 St &8 Ave", "W 45 St &6 Ave > W 42 St &8 Ave", 
    "W 42 St &8 Ave > W 45 St &8 Ave")), .Names = c("x", "y", 
"Freq", "start.latittude", "start.longitude", "start.station", 
"end.latitude", "end.longitude", "end.station", "interaction"
), row.names = c(NA, -10L), class = "data.frame")`

enter image description here

2
rggplot2label
Can you use dput() to show what your data looks like? – ytk
I've tried to use dput() a dozen times but the code is rejected because it says the formatting is wrong. I don't know how to include it – iskandarblue
For the transparency part, you just need to use alpha = Freq in geom_bar() instead of alpha = 0.7. For centering the text, here is a helpful post: stackoverflow.com/questions/6644997/…. – ytk
I don't need the bar transparency to change but the text transparency to change – iskandarblue
I've added the data with dput() – iskandarblue

2 Answers

7
votes

Here's an option:

ggplot(data= new_pairs, aes(x= reorder(interaction, -Freq), y=Freq))+ 
  geom_bar(stat="identity", aes(fill = Freq, alpha = Freq)) + 
  ylab("Bikes received")+ xlab("Station")+ 
  ylim(0, max(new_pairs$Freq)+50) +
  geom_text(aes(label = interaction,y=(max(new_pairs$Freq)+50)/2,alpha = Freq), vjust="center",hjust = "center", size = 4, nudge_y = 1, fontface ="bold")+
  theme(axis.text.y=element_blank())+ggtitle("Bikes received viarebalancing")+
  coord_flip()+theme(legend.position = "none")

You can set a y value in your geom_text aes to put the labels where you want them to be (you use coord_flip so changing y controls the horizontal placement of the text).

I set ylim manually to be able to max(new_pairs$Freq)+50 to center the text labels.

enter image description here

1
votes

If you want to center the text to each bar, here's a solution (based on the thread I linked above):

library(plyr)
new_pairs <- ddply(new_pairs, .(interaction), transform, pos = cumsum(Freq) - (0.5 * Freq))

ggplot(data= new_pairs, aes(x= reorder(interaction, -Freq), y=Freq))+ 
  geom_bar(stat="identity", aes(fill = Freq, alpha = Freq)) + 
  ylab("Bikes received")+ xlab("Station")+ 
  geom_text(aes(label = interaction, y = pos, alpha = Freq), vjust="center",hjust = "center", size = 4, nudge_y = 1, fontface ="bold")+
  theme(axis.text.y=element_blank())+ggtitle("Bikes received via rebalancing")+
  coord_flip()+theme(legend.position = "none")

enter image description here