Related
In ggplot/facet_wrap(), how to marke axis Y have different format ? Thanks!
library(tidyverse)
test_data <- diamonds
plot_data <- test_data %>% mutate(x_to_price=x/price,
price=price*1000) %>% head(12) %>%
mutate(mseq=1:NROW(.)) %>%
select(price,x_to_price,mseq) %>% gather(key='type',value='amount',- mseq)
plot_data %>% ggplot(aes(x=mseq,y=amount))+geom_line()+geom_point()+
facet_wrap(.~type,scales='free_y')
One option would be the ggh4x package which via facetted_pos_scales allows to set the scales individually for each facet:
library(ggplot2)
library(ggh4x)
ggplot(plot_data, aes(x=mseq,y=amount))+geom_line()+geom_point()+
facet_wrap(.~type,scales='free_y') +
facetted_pos_scales(
y = list(
type == "price" ~ scale_y_continuous(labels = scales::comma_format()),
type == "x_to_price" ~ scale_y_continuous(labels = scales::percent_format())
)
)
I am trying to summarize some statistics in the grid that I made, however something fails when I try to do it.
This is my data
head(catk)
Simple feature collection with 6 features and 40 fields
Geometry type: POINT
Dimension: XY
Bounding box: xmin: 303.22 ymin: -61.43 xmax: 303.95 ymax: -60.78
Geodetic CRS: WGS 84
# A tibble: 6 × 41
X1 day month year c1_id greenweight_caught_kg obs_haul_id
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <lgl>
1 1 4 12 1997 26529 7260 NA
2 2 4 12 1997 26530 7920 NA
3 3 4 12 1997 26531 4692 NA
4 4 4 12 1997 26532 5896 NA
5 5 4 12 1997 26533 88 NA
6 6 5 12 1997 26534 7040 NA
# … with 34 more variables: obs_logbook_id <lgl>, obs_haul_number <lgl>,
# haul_number <dbl>, vessel_name <chr>, vessel_nationality_code <chr>,
# fishing_purpose_code <chr>, season_ccamlr <dbl>,
# target_species <chr>, asd_code <dbl>, trawl_technique <lgl>,
# catchperiod_code <chr>, date_catchperiod_start <date>,
# datetime_set_start <dttm>, datetime_set_end <dttm>,
# datetime_haul_start <dttm>, datetime_haul_end <dttm>, …
and I did this raster
an <- getData("GADM", country = "ATA", level = 0)
an#data$NAME_0
e <- extent(-70,-40,-68,-60)
rc <- crop(an, e)
proj4string(rc) <- CRS("+init=epsg:4326")
rc3 <- st_as_sf(rc)
catk <- st_as_sf(catk, coords = c("Longitude", "Latitude"), crs = 4326) %>%
st_shift_longitude()
Grid <- rc3 %>%
st_make_grid(cellsize = c(1,0.4)) %>% # para que quede cuadrada
st_cast("MULTIPOLYGON") %>%
st_sf() %>%
mutate(cellid = row_number())
result <- Grid %>%
st_join(catk) %>%
group_by(cellid) %>%
summarise(sum_cat = sum(Catcht))
but I can not represent the data in the grid
ggplot() +
geom_sf(data = Grid, color="#d9d9d9", fill=NA) +
geom_sf(data = rc3) +
theme_bw() +
coord_sf() +
scale_alpha(guide="none")+
xlab(expression(paste(Longitude^o,~'O'))) +
ylab(expression(paste(Latitude^o,~'S')))+
guides( colour = guide_legend()) +
theme(panel.background = element_rect(fill = "#f7fbff"),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank())+
theme(legend.position = "right")+
xlim(-69,-45)
fail plot
Please help me to find this solution!!
So I just saw that you shifted the coordinates with st_shift_longitude() and therefore your bounding box is:
Bounding box: xmin: 303.22 ymin: -61.43 xmax: 303.95 ymax: -60.78
Do you really need it? That doesn't match with your defined extent
e <- extent(-70,-40,-68,-60)
And a bbox for WGS84 is suppose to be at max c(-180, -90, 180, 90).
Also, on your plot you are not instructed ggplot2 to do anything with the values of catk. Grid and rc3 do not have anything from catk, is the result object.
Anyway, I give a try to your problem even though I don't have access to your dataset. I represent on each cell sum_cat from result
library(raster)
library(sf)
library(dplyr)
library(ggplot2)
# Mock your data
catk <- structure(list(Longitude = c(-59.0860203764828, -50.1352159580643,
-53.7671292009259, -67.9105254106185, -67.5753491797446, -51.7045571975837,
-45.6203830411619, -61.2695183762776, -51.6287384188695, -52.244074640978,
-45.4625770258213, -51.0935832496694, -45.6375681312716, -44.744215508174,
-66.3625310507564), Latitude = c(-62.0038884948778, -65.307178606448,
-65.8980199769778, -60.4475595973147, -67.7543165093134, -60.4616894158005,
-67.9720957068844, -62.2184680275876, -66.2345680342004, -64.1523442367459,
-62.5435163857161, -65.9127866479611, -66.8874734854608, -62.0859917484373,
-66.8762861503705), Catcht = c(18L, 95L, 32L, 40L, 16L, 49L,
22L, 14L, 86L, 45L, 3L, 51L, 45L, 41L, 19L)), row.names = c(NA,
-15L), class = "data.frame")
# Start the analysis
an <- getData("GADM", country = "ATA", level = 0)
e <- extent(-70,-40,-68,-60)
rc <- crop(an, e)
proj4string(rc) <- CRS("+init=epsg:4326")
rc3 <- st_as_sf(rc)
# Don't think you need st_shift_longitude, removed
catk <- st_as_sf(catk, coords = c("Longitude", "Latitude"), crs = 4326)
Grid <- rc3 %>%
st_make_grid(cellsize = c(1,0.4)) %>% # para que quede cuadrada
st_cast("MULTIPOLYGON") %>%
st_sf() %>%
mutate(cellid = row_number())
result <- Grid %>%
st_join(catk) %>%
group_by(cellid) %>%
summarise(sum_cat = sum(Catcht))
ggplot() +
geom_sf(data = Grid, color="#d9d9d9", fill=NA) +
# Add here results with my mock data by grid
geom_sf(data = result %>% filter(!is.na(sum_cat)), aes(fill=sum_cat)) +
geom_sf(data = rc3) +
theme_bw() +
coord_sf() +
scale_alpha(guide="none")+
xlab(expression(paste(Longitude^o,~'O'))) +
ylab(expression(paste(Latitude^o,~'S')))+
guides( colour = guide_legend()) +
theme(panel.background = element_rect(fill = "#f7fbff"),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank())+
theme(legend.position = "right")+
xlim(-69,-45)
Created on 2022-03-23 by the reprex package (v2.0.1)
In R/ggplot2 ,when I use geom_bar(stat='identity',position='fill'),
the 'sales' tip show '0.80000',how to change it to '80.0%' ?
(I know mutate a new variable use scales::percent(sales),can work in geom_point)
library(tidyverse)
library(plotly)
test_data <- data.frame(category=c('A','B','A','B'),
sub_category=c('a1','b1','a2','b2'),
sales=c(1,2,4,5))
p <- test_data %>%
ggplot(aes(x=category,y=sales,
fill=sub_category))+
geom_bar(stat='identity',position='fill')
ggplotly(p)
One option (and perhaps the easiest one) would be to compute your percentages manually instead of making use of position = "fill" and create the tooltip manually via the text aesthetic which makes it easy to style the numbers, ... as you like:
library(plotly)
test_data <- data.frame(
category = c("A", "B", "A", "B"),
sub_category = c("a1", "b1", "a2", "b2"),
sales = c(1, 2, 4, 5)
)
test_data <- test_data %>%
group_by(category) %>%
mutate(pct = sales / sum(sales))
p <- test_data %>%
ggplot(aes(x = category, y = pct, fill = sub_category)) +
geom_col(aes(text = paste0(
"category: ", category, "<br>",
"sub_category: ", sub_category, "<br>",
"sales: ", scales::percent(pct)
)))
ggplotly(p, tooltip = "text")
Using the plotly library, I made the following plot in R:
library(dplyr)
library(ggplot2)
library(plotly)
set.seed(123)
df <- data.frame(var1 = rnorm(1000,10,10),
var2 = rnorm(1000,5,5))
df <- df %>% mutate(var3 = ifelse(var1 <= 5 & var2 <= 5, "a", ifelse(var1 <= 10 & var2 <= 10, "b", "c")))
plot = df %>%
ggplot() + geom_point(aes(x=var1, y= var2, color= var3))
ggplotly(plot)
This is a simple scatter plot - two random variables are generated, and then the colors of the points are decided by some criteria (e.g. if var1 and var2 are between certain ranges).
From here, I could also summary statistics:
df$var3 = as.factor(df$var3)
summary = df %>%
group_by(var3) %>%
summarize(Mean_var1 = mean(var1), Mean_var2 = mean(var2), count=n())
# A tibble: 3 x 4
var3 Mean_var1 Mean_var2 count
* <fct> <dbl> <dbl> <int>
1 a -1.70 0.946 158
2 b 4.68 4.94 260
3 c 15.8 6.49 582
My question: is it possible to add some buttons to this plot which would allow the user to color the points based on custom choices? E.g. something like this :
Now, the user can type in any range they want - and the color of the points change, and the some summary statistics are generated.
Can someone please show me how to do this in R?
I had this idea - first I would create this massive table that would create all possible range combinations of "var1" and "var2":
vec1 <- c(-20:40,1)
vec2 <- c(-20:40,1)
a <- expand.grid(vec1, vec2)
for (i in seq_along(vec1)) {
for (j in seq_along(vec2)) {
df <- df %>% mutate(var3 = ifelse(var1 <= i & var2 <= i, "a", ifelse(var1 <= j & j <= 10, "b", "c")))
}
}
Then, depending on which ranges the user wants - an SQL style statement isolate the rows from this massive table corresponding to those ranges :
custom_df = df[df$var1 > -20 & df$var1 <10 & df$var1 > -20 & df$var2 <10 , ]
Then, an individual grap would be made for "custom_df" and summary statistics would also be recorded for "custom_df":
summary = custom_df %>%
group_by(var3) %>%
summarize(Mean_var1 = mean(var1), Mean_var2 = mean(var2), count=n())
But I am not sure how to neatly and efficiently do this in R.
Can someone please show me how to do this?
Thanks
I have built a small shiny app to perform most of your requirements. Based on your pre-defined large dataframe df, user can define the following:
Choose the minimum and maximum value for variables var1 and var2.
Choose criteria to define the variable var3, which is used to display different colors of data points. This is a range now.
Save plot as a HTML file.
Summary stats displayed as a table.
You can define further options to provide the user the option to choose color and so on. For that perhaps you should google on how to use scale_color_manual().
Update: Added user option to choose red and green color based on var1 and var2 range values.
library(shiny)
library(plotly)
library(dplyr)
library(DT)
### define a large df
set.seed(123)
df <- data.frame(var1 = rnorm(1000,10,10),
var2 = rnorm(1000,15,15))
ui <- fluidPage(
titlePanel(p("My First Test App", style = "color:red")),
sidebarLayout(
sidebarPanel(
p("Choose Variable limits"),
# Horizontal line ----
tags$hr(),
uiOutput("var1a"), uiOutput("var1b"),
uiOutput("var2a"), uiOutput("var2b"),
uiOutput("criteria")
),
mainPanel(
DTOutput("summary"), br(),
plotlyOutput("plot"),
br(), br(), br(),
uiOutput("saveplotbtn")
)
)
)
server <- function(input, output, session){
output$var1a <- renderUI({
tagList(
numericInput("var11", "Variable 1 min",
min = min(df$var1), max = max(df$var1), value = min(df$var1))
)
})
output$var1b <- renderUI({
if (is.null(input$var11)){
low1 <- min(df$var1)
}else low1 <- max(min(df$var1),input$var11) ## cannot be lower than var 1 minimum
tagList(
numericInput("var12", "Variable 1 max", min = low1, max = max(df$var1), value = max(df$var1))
)
})
output$var2a <- renderUI({
tagList(
numericInput("var21", "Variable 2 min",
min = min(df$var2), max = max(df$var2), value = min(df$var2))
)
})
output$var2b <- renderUI({
if (is.null(input$var21)){
low2 <- min(df$var2)
}else low2 <- max(min(df$var2),input$var21) ## cannot be lower than var 2 minimum
tagList(
numericInput("var22", "Variable 2 max", min = low2, max = max(df$var2), value = max(df$var2))
)
})
output$criteria <- renderUI({
req(input$var11,input$var12,input$var21,input$var22)
tagList(
sliderInput("crit11", "Variable 1 red color range:",
min = -10, max = 0, value = c(-10,0)),
sliderInput("crit12", "Variable 2 red color range:",
min = -25, max = 0, value = c(-25,0)),
sliderInput("crit21", "Variable 1 green color range:",
min = 0.1, max = 10, value = c(0.1,10)),
sliderInput("crit22", "Variable 2 green color range:",
min = 0.1, max = 20, value = c(0.1,20))
)
})
dat <- reactive({
req(input$crit11,input$crit12,input$crit21,input$crit22)
df <- df %>% filter(between(var1, input$var11, input$var12)) %>%
filter(between(var2, input$var21, input$var22))
# df1 <- df %>% mutate(var3 = ifelse(var1 <= i & var2 <= i, "a", ifelse(var1 <= j & var2 <= j , "b", "c")))
df1 <- df %>% mutate(var3 = ifelse(between(var1, input$crit11[1], input$crit11[2]) & between(var2, input$crit12[1], input$crit12[2]), "a",
ifelse(between(var1, input$crit21[1], input$crit21[2]) & between(var2, input$crit22[1], input$crit22[2]), "b", "c")))
})
summari <- reactive({
req(dat())
df1 <- dat()
df1$var3 = as.factor(df1$var3)
summary = df1 %>%
group_by(var3) %>%
dplyr::summarize(Mean_var1 = mean(var1), Mean_var2 = mean(var2), count=n())
})
output$summary <- renderDT(summari())
rv <- reactiveValues()
observe({
req(dat())
p <- ggplot(data=dat()) + geom_point(aes(x=var1, y= var2, color= var3))
pp <- ggplotly(p)
rv$plot <- pp
})
output$plot <- renderPlotly({
rv$plot
})
output$saveplotbtn <- renderUI({
div(style="display: block; padding: 5px 350px 5px 50px;",
downloadBttn("saveHTML",
HTML("HTML"),
style = "fill",
color = "default",
size = "lg",
block = TRUE,
no_outline = TRUE
) )
})
output$saveHTML <- downloadHandler(
filename = function() {
paste("myplot", Sys.Date(), ".html", sep = "")
},
content = function(file) {
htmlwidgets::saveWidget(as_widget(rv$plot), file, selfcontained = TRUE) ## self-contained
}
)
}
shinyApp(ui, server)
To a 3 year old post
ggplot2: facet_wrap strip color based on variable in data set
Baptiste has given the following solution:
d <- data.frame(fruit = rep(c("apple", "orange", "plum", "banana", "pear", "grape")),
farm = rep(c(0,1,3,6,9,12), each=6),
weight = rnorm(36, 10000, 2500),
size=rep(c("small", "large")))
p1 = ggplot(data = d, aes(x = farm, y = weight)) +
geom_jitter(position = position_jitter(width = 0.3),
aes(color = factor(farm)), size = 2.5, alpha = 1) +
facet_wrap(~fruit)
dummy <- ggplot(data = d, aes(x = farm, y = weight))+ facet_wrap(~fruit) +
geom_rect(aes(fill=size), xmin=-Inf, xmax=Inf, ymin=-Inf, ymax=Inf) +
theme_minimal()
library(gtable)
g1 <- ggplotGrob(p1)
g2 <- ggplotGrob(dummy)
gtable_select <- function (x, ...)
{
matches <- c(...)
x$layout <- x$layout[matches, , drop = FALSE]
x$grobs <- x$grobs[matches]
x
}
panels <- grepl(pattern="panel", g2$layout$name)
strips <- grepl(pattern="strip-t", g2$layout$name)
g2$layout$t[panels] <- g2$layout$t[panels] - 1
g2$layout$b[panels] <- g2$layout$b[panels] - 1
new_strips <- gtable_select(g2, panels | strips)
library(grid)
grid.newpage()
grid.draw(new_strips)
gtable_stack <- function(g1, g2){
g1$grobs <- c(g1$grobs, g2$grobs)
g1$layout <- transform(g1$layout, z= z-max(z), name="g2")
g1$layout <- rbind(g1$layout, g2$layout)
g1
}
## ideally you'd remove the old strips, for now they're just covered
new_plot <- gtable_stack(g1, new_strips)
grid.newpage()
grid.draw(new_plot)
(I have just updated the "strip-t" pattern and opened the grid library as it was suggested in the old post)
I repost this because it's an old brillant stuff and I want to use it myself for a presentation.
I'm a beginner in ggplot and this could also help me for various scripts.
Here are my questions :
- How is it possible to choose the color and not to give the same blue and red please? In my script, I have 3 colors to set, and I hope it can be less agressive. Is it possible to do it ?
- Another question, is it possible to integrate this in the legend, i.e to know what are this colors refering ?
Many thanks
you can change the strip colours with the fill scale in the dummy plot. Combining the legends is a bit tricky, but here's a starting point.
library(ggplot2)
library(gtable)
library(gridExtra)
library(grid)
gtable_stack <- function(g1, g2){
g1$grobs <- c(g1$grobs, g2$grobs)
g1$layout <- transform(g1$layout, z= z-max(z), name="g2")
g1$layout <- rbind(g1$layout, g2$layout)
g1
}
gtable_select <- function (x, ...)
{
matches <- c(...)
x$layout <- x$layout[matches, , drop = FALSE]
x$grobs <- x$grobs[matches]
x
}
d <- data.frame(fruit = rep(c("apple", "orange", "plum", "banana", "pear", "grape")),
farm = rep(c(0,1,3,6,9,12), each=6),
weight = rnorm(36, 10000, 2500),
size=rep(c("small", "large")))
p1 = ggplot(data = d, aes(x = farm, y = weight)) +
geom_jitter(position = position_jitter(width = 0.3),
aes(color = factor(farm)), size = 2.5, alpha = 1) +
facet_wrap(~fruit)
dummy <- ggplot(data = d, aes(x = farm, y = weight))+ facet_wrap(~fruit) +
geom_rect(aes(fill=size), xmin=-Inf, xmax=Inf, ymin=-Inf, ymax=Inf) +
theme_minimal() + scale_fill_brewer(palette = "Pastel2")
g1 <- ggplotGrob(p1)
g2 <- ggplotGrob(dummy)
# extract legends
leg <- g1$grobs[[grep("guide-box", g1$layout$name)]]
dummy_leg <- g2$grobs[[grep("guide-box", g2$layout$name)]]
combined_leg <- rbind.gtable(leg, dummy_leg)
g1$grobs[[grep("guide-box", g1$layout$name)]] <- combined_leg
# move dummy panels one cell up
panels <- grepl(pattern="panel", g2$layout$name)
strips <- grepl(pattern="strip-t", g2$layout$name)
g2$layout$t[panels] <- g2$layout$t[panels] - 1
g2$layout$b[panels] <- g2$layout$b[panels] - 1
new_strips <- gtable_select(g2, panels | strips)
# stack new strips on top of gtable
# ideally you'd remove the old strips, for now they're just covered
new_plot <- gtable_stack(g1, new_strips)
grid.newpage()
grid.draw(new_plot)