Related
I have My Data stored in p, which can be found below.
I have four specific categories for a group of tumor patients. Three of the groups correspond to the tumor stage and is stored as p$WHO.Grade=1,2,3. The last group is All tumor patients combined.
I am producing a specific plot consisting of multiple boxplots demonstrating the distribution of a continuous covariate (p$ki67pro) in the four groups described as above and in relation to the event of recurrence (p$recurrence==0 for no and p$recurrence==1 for yes).
As it turns out, there are no events for p$WHO.Grade==3, which means that I want my blot to look exactly like this (manipulated in photoshop):
However, I get the picture below when I use the following script:
library(ggplot2)
library(dplyr)
p %>%
bind_rows(p %>% mutate(WHO.Grade = 4)) %>%
mutate(WHO.Grade = factor(WHO.Grade),
recurrence = factor(recurrence)) %>%
ggplot(aes(WHO.Grade, ki67pro,
fill = recurrence, colour = recurrence)) +
geom_boxplot(outlier.alpha = 0,
position = position_dodge(width = 0.78, preserve = "single")) +
geom_point(size = 3, shape = 21,
position = position_jitterdodge()) +
scale_x_discrete(name = "",
label = c("WHO-I","WHO-II","WHO-III","All")) +
scale_y_continuous(name = "x", breaks=seq(0,30,5), limits=c(0,30)) +
scale_fill_manual(values = c("#edf1f9", "#fcebeb"), name = "",
labels = c("", "")) +
scale_colour_manual(values = c("#1C73C2", "red"), name = "",
labels = c("","")) +
theme(legend.position="none",
panel.background = element_blank(),
axis.line = element_line(colour = "black"))
It seems like p$WHO.Grade==All automatically is inserted at the p$WHO.Grade==3 space, which should be leaved blank.
Therefore, my question is: how can I graphically insert a blank space at p$WHO.Grade==3 given my
script above?
p <- structure(list(WHO.Grade = c(1L, 2L, 1L, 1L, 1L, 1L, 2L, 1L,
1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L), ki67pro = c(1L, 12L, 3L, 3L, 5L, 3L,
25L, 7L, 4L, 5L, 12L, 3L, 15L, 4L, 5L, 7L, 8L, 3L, 12L, 10L,
4L, 10L, 7L, 3L, 2L, 3L, 7L, 4L, 7L, 10L, 4L, 5L, 5L, 3L, 5L,
2L, 5L, 3L, 3L, 3L, 4L, 4L, 3L, 2L, 5L, 1L, 5L, 2L, 3L, 1L, 2L,
3L, 3L, 5L, 4L, 20L, 5L, 0L, 4L, 3L, 0L, 3L, 4L, 1L, 2L, 20L,
2L, 3L, 5L, 4L, 8L, 1L, 4L, 5L, 4L, 3L, 6L, 12L, 3L, 4L, 4L,
2L, 5L, 3L, 3L, 3L, 2L, 5L, 4L, 2L, 3L, 4L, 3L, 3L, 2L, 2L, 4L,
7L, 4L, 3L, 4L, 2L, 3L, 6L, 2L, 3L, 10L, 5L, 10L, 3L, 10L, 3L,
4L, 5L, 2L, 4L, 3L, 4L, 4L, 4L, 5L, 3L, 12L, 5L, 4L, 3L, 2L,
4L, 3L, 4L, 2L, 1L, 6L, 1L, 4L, 12L, 3L, 4L, 3L, 2L, 6L, 5L,
4L, 3L, 4L, 4L, 4L, 3L, 5L, 4L, 5L, 4L, 1L, 3L, 3L, 4L, 0L, 3L
), recurrence = c(0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 0L,
0L, 1L, 0L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 0L, 0L,
1L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
1L, 1L, 0L, 0L, 0L, 1L, 0L, 0L, 0L, 1L, 1L, 0L, 1L, 0L, 0L, 1L,
1L, 1L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 1L, 1L, 0L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 0L,
0L, 0L, 0L)), class = "data.frame", row.names = c(1L, 2L, 3L,
9L, 10L, 11L, 13L, 14L, 15L, 16L, 18L, 19L, 20L, 21L, 22L, 23L,
24L, 25L, 26L, 27L, 28L, 29L, 30L, 31L, 32L, 33L, 34L, 35L, 36L,
37L, 38L, 39L, 40L, 41L, 44L, 45L, 46L, 47L, 48L, 49L, 50L, 51L,
52L, 53L, 54L, 55L, 57L, 59L, 60L, 61L, 62L, 63L, 64L, 65L, 66L,
67L, 68L, 69L, 70L, 71L, 72L, 73L, 74L, 75L, 76L, 77L, 78L, 79L,
80L, 81L, 82L, 83L, 84L, 85L, 87L, 89L, 90L, 91L, 92L, 93L, 94L,
96L, 97L, 98L, 99L, 100L, 101L, 102L, 103L, 104L, 105L, 106L,
107L, 109L, 110L, 111L, 112L, 113L, 114L, 115L, 116L, 117L, 118L,
119L, 120L, 121L, 123L, 124L, 125L, 126L, 127L, 128L, 130L, 131L,
132L, 133L, 134L, 135L, 136L, 137L, 138L, 139L, 140L, 141L, 142L,
143L, 144L, 145L, 146L, 147L, 148L, 149L, 150L, 151L, 152L, 153L,
154L, 155L, 156L, 157L, 158L, 159L, 160L, 161L, 162L, 163L, 164L,
165L, 166L, 167L, 168L, 169L, 170L, 171L, 172L, 173L, 174L, 175L
))
The simplest way is to adjust your WHO.Grade factor to include all 4 levels - c("WHO-I","WHO-II","WHO-III","All")```. Here's the first adjustment on line 3:
p %>%
bind_rows(p %>% mutate(WHO.Grade = 4)) %>%
mutate(WHO.Grade = factor(WHO.Grade, levels = 1:4, labels = c("WHO-I","WHO-II","WHO-III","All")),
recurrence = factor(recurrence))
Now that we've named our factors, we can modify the scale_x_discrete() call to remove the label and add drop = FALSE:
scale_x_discrete(name = "",
# label = c("WHO-I","WHO-II","WHO-III","All"),
drop = FALSE)
Putting everything together we get:
p %>%
bind_rows(p %>% mutate(WHO.Grade = 4)) %>% as_tibble()%>%
mutate(WHO.Grade = factor(WHO.Grade, levels = 1:4, labels = c("WHO-I","WHO-II","WHO-III","All")),
recurrence = factor(recurrence))%>%
ggplot(aes(WHO.Grade, ki67pro,
fill = recurrence, colour = recurrence)) +
geom_boxplot(outlier.alpha = 0,
position = position_dodge(width = 0.78, preserve = "single")) +
geom_point(size = 3, shape = 21,
position = position_jitterdodge()) +
scale_x_discrete(name = "",
# label = c("WHO-I","WHO-II","WHO-III","All"),
drop = FALSE) +
scale_y_continuous(name = "x", breaks=seq(0,30,5), limits=c(0,30)) +
scale_fill_manual(values = c("#edf1f9", "#fcebeb"), name = "",
labels = c("", "")) +
scale_colour_manual(values = c("#1C73C2", "red"), name = "",
labels = c("","")) +
theme(legend.position="none",
panel.background = element_blank(),
axis.line = element_line(colour = "black"))
I could not reach to the result you want as appeared in the Photoshop image, but you could gain the following image:
Which it is what you want, but all the entries of "WHO-III" are zeros
The code that generates it is:
library(ggplot2)
library(dplyr)
p= p %>%
bind_rows(p %>% mutate(WHO.Grade = 3)) %>%
bind_rows(p %>% mutate(WHO.Grade = 4))
p[p$WHO.Grade == 3, 2] = 0
p %>%
mutate(WHO.Grade = factor(WHO.Grade),
recurrence = factor(recurrence)) %>%
ggplot(aes(WHO.Grade, ki67pro,
fill = recurrence, colour = recurrence)) +
geom_boxplot(outlier.alpha = 0,
position = position_dodge(width = 0.78, preserve = "single")) +
geom_point(size = 3, shape = 21,
position = position_jitterdodge()) +
scale_x_discrete(name = "",
label = c("WHO-I","WHO-II","WHO-III","All"), drop = FALSE) +
scale_y_continuous(name = "x", breaks=seq(0,30,5), limits=c(0,30)) +
scale_fill_manual(values = c("#edf1f9", "#fcebeb"), name = "",
labels = c("", "")) +
scale_colour_manual(values = c("#1C73C2", "red"), name = "",
labels = c("","")) +
theme(legend.position="none",
panel.background = element_blank(),
axis.line = element_line(colour = "black"))
Hope this helps
In my dataset there are 7 binary (categorical) variables (x1-x7.)
Another vars are scale and we won't use it.
mydat(part of)
structure(list(city = structure(c(2L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L), .Label = c("New-York", "Washington"), class = "factor"),
x1 = c(0L, 0L, 1L, 1L, 0L, 0L, 0L, 1L, 1L, 0L), x2 = c(0L,
0L, 1L, 1L, 0L, 0L, 0L, 1L, 1L, 0L), x3 = c(0L, 0L, 1L, 1L,
0L, 0L, 0L, 1L, 1L, 0L), x4 = c(0L, 0L, 1L, 1L, 0L, 0L, 0L,
1L, 1L, 0L), x5 = c(0L, 0L, 1L, 1L, 0L, 0L, 0L, 1L, 1L, 0L
), x6 = c(0L, 0L, 1L, 1L, 0L, 0L, 0L, 1L, 1L, 0L), x7 = c(0L,
0L, 1L, 1L, 0L, 0L, 0L, 1L, 1L, 0L), var1 = c(10L, 71L, 49L,
70L, 79L, 46L, 87L, 57L, 81L, 68L), var2 = c(34L, 17L, 28L,
63L, 95L, 99L, 40L, 63L, 24L, 90L), var3 = c(21L, 89L, 81L,
26L, 59L, 87L, 84L, 24L, 27L, 83L), var4 = c(86L, 70L, 45L,
40L, 95L, 94L, 39L, 97L, 89L, 30L)), .Names = c("city", "x1",
"x2", "x3", "x4", "x5", "x6", "x7", "var1", "var2", "var3", "var4"
), class = "data.frame", row.names = c(NA, -10L))
I created the function which perform cross-tabs between all binary variables.
Perhaps maybe it will be useful for anybody.
It works.
mydat=read.csv(mydat)
library("gmodels")
mult_crosstab <- function (data = cross) {
for (j in 1:(ncol(data)-1)) {
for (i in (j+1):(ncol(data))) {
x <- names(data)[j]
y <- names(data)[i]
call <- call("CrossTable", as.name(x), as.name(y), chisq = TRUE)
eval(call, data)
}
}
}
mult_crosstab()
But in dataset - mydat there is variable city (Washington and New-York).
How to use my fuction to calculcate the cross-tabs for two cities separately?
Split your data by city, then iterate over each split and run your function
lapply(split(cross, cross$city), mult_crosstab)
It seems that CrossTable is a nasty little function that prints to the console instead of returning an object. You can capture your output as text with capture.output(code_above) if that is what you desire.
This question already has answers here:
How to combine scales for colour and size into one legend?
(2 answers)
Closed 7 years ago.
What is the code to make the two legends into one: A circles legend with color?
I think, a single legend with circles colored according to "size" and "# total number of crimes" is the best way to show the legend.
Desired output:
1) There should be one legend: the circles, instead of black should be colored: 0 circle = "yellow" to 800 circle = "red".
My code:
library(maps)
library(ggmap)
Get map from Google Maps
lima <- get_map(location = "lima", zoom = 11, maptype = c("terrain"))
Plot
ggmap(lima) + geom_point(data = limanov2, aes(x = LONGITUD , y = LATITUD, color = TOTALES,
size = TOTALES)) +
scale_size_continuous(name = "Cantidad\ndelitos",range = c(2,12)) +
scale_color_gradient(name = "Cantidad\ndelitos", low = "yellow", high = "red") +
theme(legend.text= element_text(size=14)) +
ggtitle("TOTAL DELITOS - LIMA NOV 2012") +
theme(plot.title = element_text(size = 12, vjust=2, family="Verdana", face="italic"),
legend.position = 'left')
My data:
structure(list(DISTRITO = c("SAN JUAN DE LURIGANCHO", "CALLAO",
"LOS OLIVOS", "ATE", "LIMA", "SAN MARTIN DE PORRES", "SANTIAGO DE SURCO",
"CHORILLOS", "COMAS", "INDEPENDENCIA", "EL AGUSTINO", "LA VICTORIA",
"SAN JUAN DE MIRAFLORES", "VILLA EL SALVADOR", "SAN MIGUEL",
"CARABAYLLO", "MIRAFLORES", "SAN BORJA", "VENTANILLA", "SURQUILLO",
"BREÑA", "ANCON", "PTE. PIEDRA", "RIMAC", "BARRANCO", "LA MOLINA",
"SAN LUIS", "SANTA ANITA", "LURIGANCHO", "P. LIBRE", "MAGDALENA DEL MAR",
"LA PERLA", "CHACLACAYO", "PUENTE PIEDRA", "SAN ISIDRO", "JESUS MARIA",
"BELLAVISTA", "LINCE", "CARMEN DE LA LEGUA REYNOSO", "CIENEGUILLA",
"SANTA ROSA", "LURIN", "PUNTA NEGRA", "PUCUSANA", "LA PUNTA",
"PUNTA HERMOSA", "PACHACAMAC", "SAN BARTOLO", "SANTA MARIA"),
TOTALES = c(861L, 696L, 696L, 642L, 516L, 479L, 442L, 378L,
371L, 368L, 361L, 333L, 325L, 291L, 282L, 251L, 239L, 196L,
193L, 188L, 185L, 174L, 165L, 161L, 138L, 134L, 128L, 119L,
115L, 105L, 67L, 65L, 63L, 58L, 58L, 56L, 45L, 38L, 23L,
23L, 11L, 8L, 6L, 5L, 3L, 3L, 2L, 0L, 0L), HOMICIDIOS = c(1L,
7L, 0L, 1L, 2L, 0L, 0L, 1L, 7L, 4L, 4L, 4L, 0L, 0L, 0L, 2L,
0L, 0L, 7L, 0L, 0L, 0L, 0L, 4L, 0L, 0L, 2L, 0L, 0L, 0L, 0L,
0L, 0L, 1L, 0L, 0L, 0L, 1L, 1L, 0L, 0L, 1L, 0L, 0L, 0L, 0L,
0L, 0L, 0L), LESIONES = c(100L, 72L, 61L, 43L, 44L, 8L, 10L,
15L, 44L, 40L, 50L, 15L, 52L, 28L, 7L, 33L, 15L, 3L, 21L,
7L, 36L, 33L, 15L, 19L, 14L, 1L, 8L, 6L, 16L, 4L, 4L, 9L,
1L, 12L, 2L, 9L, 5L, 2L, 5L, 7L, 1L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L), VIO..DE.LA.LIBERTAD.PERSONAL = c(0L, 7L, 6L,
5L, 6L, 1L, 1L, 0L, 3L, 1L, 2L, 0L, 2L, 0L, 1L, 0L, 1L, 0L,
1L, 1L, 0L, 3L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 1L, 0L, 1L, 0L,
0L, 1L, 0L, 0L, 0L, 2L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L), VIO..DE.LA.LIBERTAD.SEXUAL = c(56L, 14L, 12L, 15L, 7L,
10L, 2L, 9L, 11L, 13L, 8L, 9L, 7L, 14L, 4L, 15L, 4L, 2L,
17L, 7L, 3L, 4L, 6L, 12L, 2L, 1L, 5L, 3L, 11L, 4L, 1L, 2L,
0L, 6L, 2L, 0L, 3L, 0L, 2L, 2L, 0L, 4L, 0L, 0L, 0L, 0L, 0L,
0L, 0L), HURTO.SIMPLE.Y.AGRAVADO = c(217L, 203L, 296L, 230L,
260L, 167L, 226L, 217L, 130L, 117L, 154L, 133L, 121L, 46L,
163L, 72L, 161L, 119L, 69L, 120L, 64L, 19L, 64L, 21L, 57L,
44L, 39L, 2L, 48L, 60L, 30L, 19L, 48L, 20L, 41L, 25L, 19L,
27L, 7L, 11L, 9L, 0L, 6L, 0L, 2L, 3L, 1L, 0L, 0L), ROBO.SIMPLE.Y.AGRAVADO = c(460L,
289L, 308L, 344L, 186L, 277L, 198L, 130L, 165L, 184L, 137L,
149L, 134L, 188L, 104L, 126L, 58L, 72L, 64L, 51L, 77L, 115L,
79L, 76L, 64L, 88L, 73L, 108L, 40L, 36L, 30L, 32L, 14L, 17L,
12L, 22L, 12L, 8L, 6L, 3L, 1L, 3L, 0L, 2L, 1L, 0L, 1L, 0L,
0L), MICRO.COM.DE.DROGAS = c(26L, 100L, 13L, 3L, 10L, 15L,
5L, 5L, 11L, 8L, 3L, 23L, 9L, 15L, 3L, 3L, 0L, 0L, 8L, 2L,
5L, 0L, 0L, 28L, 0L, 0L, 1L, 0L, 0L, 0L, 2L, 2L, 0L, 2L,
0L, 0L, 6L, 0L, 0L, 0L, 0L, 0L, 0L, 3L, 0L, 0L, 0L, 0L, 0L
), TENENCIA.ILEGAL.DE.ARMAS = c(1L, 4L, 0L, 1L, 1L, 1L, 0L,
1L, 0L, 1L, 3L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 6L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), LONGITUD = c(-77,
-77.12, -77.08, -76.89, -77.04, -77.09, -76.99, -77.01, -77.05,
-77.05, -77, -77.02, -76.97, -76.94, -77.09, -76.99, -77.03,
-77, -77.13, -77.01, -77.05, -77.11, -77.08, -76.7, -77.02,
-76.92, -77, -76.96, -76.86, -77.06, -77.07, -77.12, -76.76,
-77.08, -77.03, -77.05, -77.11, -77.04, -77.09, -76.78, -77.16,
-76.81, -76.73, -76.77, -77.16, -76.76, -76.83, -76.73, -76.77
), LATITUD = c(-11.99, -12.04, -11.95, -12.04, -12.06, -12,
-12.16, -12.2, -11.93, -11.99, -12.04, -12.08, -12.16, -12.23,
-12.08, -11.79, -12.12, -12.1, -11.89, -12.11, -12.06, -11.69,
-11.88, -11.94, -12.15, -12.09, -12.08, -12.04, -11.98, -12.08,
-12.09, -12.07, -11.99, -11.88, -12.1, -12.08, -12.06, -12.09,
-12.04, -12.07, -11.81, -12.24, -12.32, -12.47, -12.07, -12.28,
-12.18, -12.38, -12.42)), class = c("tbl_df", "tbl", "data.frame"
), row.names = c(NA, -49L), .Names = c("DISTRITO", "TOTALES",
"HOMICIDIOS", "LESIONES", "VIO..DE.LA.LIBERTAD.PERSONAL", "VIO..DE.LA.LIBERTAD.SEXUAL",
"HURTO.SIMPLE.Y.AGRAVADO", "ROBO.SIMPLE.Y.AGRAVADO", "MICRO.COM.DE.DROGAS",
"TENENCIA.ILEGAL.DE.ARMAS", "LONGITUD", "LATITUD"))
I've found a solution. Reading the documention for GGPLOT2 V. 0.9
It is the new function: guide_legend() that should be used inside guides().
This is a function that lets you have more control over legend labels.
This is the end code with the resulting output (See the last line):
ggmap(lima) + geom_point(data = limanov2, aes(x = LONGITUD , y = LATITUD, color = TOTALES,
size = TOTALES)) +
scale_size_continuous(name = "Cantidad\ndelitos",range = c(2,12)) +
scale_color_gradient(name = "Cantidad\ndelitos", low = "yellow", high = "red") +
theme(legend.text= element_text(size=14)) +
ggtitle("TOTAL DELITOS - LIMA NOV 2012") +
theme(plot.title = element_text(size = 12, vjust=2, family="Verdana", face="italic"),
legend.position = 'left') +
guides(colour = guide_legend())
I'm plotting some points over a map with ggmap package.
The problem is that i get the message: "Removed 12 rows containing missing values (geom_point)".
But i don't have any NAs. I've looked the data, and used:
sum(is.na(limanov2)) #Gives 0
to prove it.
This is my code:
library(maps)
library(ggmap)
lima <- get_map(location = "lima", zoom = 11)
ggmap(lima) + geom_point(data = limanov2, aes(x = LONGITUD , y = LATITUD, color = TOTALES,
size = TOTALES)) +
scale_color_gradient(low = "yellow", high = "red")
My data:
structure(list(DISTRITO = c("SAN JUAN DE LURIGANCHO", "CALLAO",
"LOS OLIVOS", "ATE VITARTE", "LIMA CERCADO", "SAN MARTÍN", "SANTIAGO DE SURCO",
"CHORILLOS", "COMAS", "INDEPENDENCIA", "EL AGUSTINO", "LA VICTORIA",
"SAN JUAN DE MIRAFLORES", "VILLA EL SALVADOR", "S. MIGUEL", "CARABAYLLO",
"MIRAFLORES", "PTE. PIEDRA", "SAN BORJA", "VENTANILLA", "SURQUILLO",
"BREÑA", "ANCÓN", "EL RIMAC", "BARRANCO", "LA MOLINA", "SAN LUIS",
"STA. ANITA", "LURIGANCHO", "P. LIBRE", "MAGDALENA", "LA PERLA",
"CHACLACAYO", "SAN ISIDRO", "J. MARÍA", "BELLAVISTA", "LINCE",
"C. DE LA LEGUA", "CIENEGUILLA", "STA.ROSA", "LURÍN", "PTA.NEGRA",
"PUCUSANA", "LA PUNTA", "PTA. HERMOSA", "PACHACAMAC", "SAN BARTOLO",
"SANTA MARÍA"), TOTALES = c(861L, 696L, 696L, 642L, 516L, 479L,
442L, 378L, 371L, 368L, 361L, 333L, 325L, 291L, 282L, 251L, 239L,
223L, 196L, 193L, 188L, 185L, 174L, 161L, 138L, 134L, 128L, 119L,
115L, 105L, 67L, 65L, 63L, 58L, 56L, 45L, 38L, 23L, 23L, 11L,
8L, 6L, 5L, 3L, 3L, 2L, 0L, 0L), HOMICIDIOS = c(1L, 7L, 0L, 1L,
2L, 0L, 0L, 1L, 7L, 4L, 4L, 4L, 0L, 0L, 0L, 2L, 0L, 1L, 0L, 7L,
0L, 0L, 0L, 4L, 0L, 0L, 2L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
1L, 1L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), LESIONES = c(100L,
72L, 61L, 43L, 44L, 8L, 10L, 15L, 44L, 40L, 50L, 15L, 52L, 28L,
7L, 33L, 15L, 27L, 3L, 21L, 7L, 36L, 33L, 19L, 14L, 1L, 8L, 6L,
16L, 4L, 4L, 9L, 1L, 2L, 9L, 5L, 2L, 5L, 7L, 1L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L), VIO..DE.LA.LIBERTAD.PERSONAL = c(0L, 7L,
6L, 5L, 6L, 1L, 1L, 0L, 3L, 1L, 2L, 0L, 2L, 0L, 1L, 0L, 1L, 1L,
0L, 1L, 1L, 0L, 3L, 1L, 1L, 0L, 0L, 0L, 0L, 1L, 0L, 1L, 0L, 1L,
0L, 0L, 0L, 2L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), VIO..DE.LA.LIBERTAD.SEXUAL = c(56L,
14L, 12L, 15L, 7L, 10L, 2L, 9L, 11L, 13L, 8L, 9L, 7L, 14L, 4L,
15L, 4L, 12L, 2L, 17L, 7L, 3L, 4L, 12L, 2L, 1L, 5L, 3L, 11L,
4L, 1L, 2L, 0L, 2L, 0L, 3L, 0L, 2L, 2L, 0L, 4L, 0L, 0L, 0L, 0L,
0L, 0L, 0L), HURTO.SIMPLE.Y.AGRAVADO = c(217L, 203L, 296L, 230L,
260L, 167L, 226L, 217L, 130L, 117L, 154L, 133L, 121L, 46L, 163L,
72L, 161L, 84L, 119L, 69L, 120L, 64L, 19L, 21L, 57L, 44L, 39L,
2L, 48L, 60L, 30L, 19L, 48L, 41L, 25L, 19L, 27L, 7L, 11L, 9L,
0L, 6L, 0L, 2L, 3L, 1L, 0L, 0L), ROBO.SIMPLE.Y.AGRAVADO = c(460L,
289L, 308L, 344L, 186L, 277L, 198L, 130L, 165L, 184L, 137L, 149L,
134L, 188L, 104L, 126L, 58L, 96L, 72L, 64L, 51L, 77L, 115L, 76L,
64L, 88L, 73L, 108L, 40L, 36L, 30L, 32L, 14L, 12L, 22L, 12L,
8L, 6L, 3L, 1L, 3L, 0L, 2L, 1L, 0L, 1L, 0L, 0L), MICRO.COM.DE.DROGAS = c(26L,
100L, 13L, 3L, 10L, 15L, 5L, 5L, 11L, 8L, 3L, 23L, 9L, 15L, 3L,
3L, 0L, 2L, 0L, 8L, 2L, 5L, 0L, 28L, 0L, 0L, 1L, 0L, 0L, 0L,
2L, 2L, 0L, 0L, 0L, 6L, 0L, 0L, 0L, 0L, 0L, 0L, 3L, 0L, 0L, 0L,
0L, 0L), TENENCIA.ILEGAL.DE.ARMAS = c(1L, 4L, 0L, 1L, 1L, 1L,
0L, 1L, 0L, 1L, 3L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 6L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), LONGITUD = c(-77, -77.12,
-77.08, -76.89, -77.04, -77.09, -76.99, -77.01, -77.05, -77.05,
-77, -77.02, -76.97, -76.94, -77.09, -76.99, -77.03, -77.08,
-77, -77.13, -77.01, -77.05, -77.11, -76.7, -77.02, -76.92, -77,
-76.96, -76.86, -77.06, -77.07, -77.12, -76.76, -77.03, -77.05,
-77.11, -77.04, -77.09, -76.78, -77.16, -76.81, -76.73, -76.77,
-77.16, -76.76, -76.83, -76.73, -76.77), LATITUD = c(-11.99,
-12.04, -11.97, -12.04, -12.06, -12, -12.16, -12.2, -11.93, -11.99,
-12.04, -12.08, -12.16, -12.23, -12.08, -11.79, -12.12, -11.88,
-12.1, -11.89, -12.11, -12.06, -11.69, -11.94, -12.15, -12.09,
-12.08, -12.04, -11.98, -12.08, -12.09, -12.07, -11.99, -12.1,
-12.08, -12.06, -12.09, -12.04, -12.07, -11.81, -12.24, -12.32,
-12.47, -12.07, -12.28, -12.18, -12.38, -12.42)), class = c("tbl_df",
"tbl", "data.frame"), row.names = c(NA, -48L), .Names = c("DISTRITO",
"TOTALES", "HOMICIDIOS", "LESIONES", "VIO..DE.LA.LIBERTAD.PERSONAL",
"VIO..DE.LA.LIBERTAD.SEXUAL", "HURTO.SIMPLE.Y.AGRAVADO", "ROBO.SIMPLE.Y.AGRAVADO",
"MICRO.COM.DE.DROGAS", "TENENCIA.ILEGAL.DE.ARMAS", "LONGITUD",
"LATITUD"))
You have values outside of the base map zoom range... try changing your zoom parameter.
library(maps)
library(ggmap)
lima <- get_map(location = "lima", zoom = 10)
ggmap(lima) +
geom_point(data = limanov2,
aes(x = LONGITUD , y = LATITUD,
color = TOTALES, size = TOTALES)) +
scale_color_gradient(low = "yellow", high = "red")
When plotting a stacked barplot using {graphics} I get a problem with the x-axis not scaling correctly, the ticks aren't aligned to the bars properly, leaving the axis too short.
# dummy data
mat <- structure(c(0L, 5L, 7L, 10L, 12L, 14L, 16L, 18L, 20L, 22L, 24L,
26L, 28L, 30L, 32L, 34L, 36L, 38L, 40L, 42L, 44L, 46L, 48L, 50L,
52L, 54L, 56L, 58L, 60L, 62L, 63L, 64L, 0L, 0L, 0L, 3L, 0L, 0L,
1L, 0L, 0L, 0L, 5L, 0L, 1L, 4L, 0L, 9L, 0L, 0L, 1L, 0L, 8L, 0L,
7L, 0L, 1L, 1L, 6L, 0L, 1L, 3L, 4L, 0L, 1L, 1L, 5L, 6L, 1L, 6L,
0L, 0L, 5L, 4L, 1L, 8L, 0L, 1L, 1L, 3L, 1L, 3L, 1L, 0L, 1L, 1L,
1L, 1L, 0L, 3L, 3L, 5L, 4L, 1L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 6L, 0L,
11L, 0L, 7L, 0L, 6L, 0L, 0L, 5L, 4L, 0L, 1L, 0L, 1L, 0L, 0L,
1L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 0L, 9L, 0L), .Dim = c(32L, 5L
), .Dimnames = list(NULL, c("Time", "Var1", "Var2", "Var3", "Var4"
)))
# barplot
barplot(t(mat[,2:4]), beside=F, legend=levels(mat), col=c("blue",'red','forestgreen','purple'))
# manually assign x-axis
axis(1,at=c(1:32),labels=mat[,1])
Any pointers on this would be highly appreciated. Im not interested in a ggplot2 solution. Thanks!
For your axis, get the coordinates of the barplots first.
bp <-barplot(t(mat[,2:5]), beside=F,
legend = levels(mat), col = c("blue",'red','forestgreen','purple'))
Now use bp for x-tick labels
axis(1,at=bp,labels=mat[,1])
The resulting plot
Also, if you play with the width of your plot window/device, you can get all the labels.