I have three csv files which are read into r as dataframes. I want to create a line plot which graphs the "means" columns and uses the "sd" column as an above and below error bar.
This code gives me a multiple lines on a plot but with only one error bar:
ggplot(data=edge_c_summary,aes(x = times,y=means))+
geom_errorbar(aes(ymin=means-sd,ymax=means+sd))+
geom_line(aes(y=means))+
geom_line(data = ridge_c_summary,aes(x=times,y=means))+
geom_errorbar(aes(ymin=means-sd,ymax=means+sd))+
geom_line(data = valley_c_summary,aes(x=times,y=means))+
geom_errorbar(aes(ymin=means-sd,ymax=means+sd))
How can I change this code to make each line have the appropriate error bar for each point?
edge_c_summary
"","times","means","sd"
"1",1,23.6566108007449,0.97897699678658
"12",2,22.7815144766147,1.15800405896118
"19",3,23.3195763580458,1.10152573531062
"20",4,22.3962138084633,1.25626506966065
"21",5,23.0657328322515,1.17624485082946
"22",6,22.1194877505568,1.32888708114411
"23",7,22.9947511929107,1.25304663407105
"24",8,23.121714922049,1.53918225223541
"25",9,25.9304732720463,2.01279986529601
"2",10,27.2791342952275,2.63979959777048
"3",11,28.7510747185261,2.66804271260005
"4",12,29.4782463928968,3.00223132377325
"5",13,29.7261003070624,2.90440605187483
"6",14,30.3099889012209,3.15106156713522
"7",15,29.4545951486163,2.87696770282654
"8",16,29.1991111111111,2.73260690130748
"9",17,27.6885928961749,2.28949704545011
"10",18,26.8358888888889,1.99002819664902
"11",19,25.4207579378628,1.30543445825041
"13",20,24.6197777777778,1.28917282788259
"14",21,24.4374658469945,1.0001400647698
"15",22,23.7050055617353,1.12314557626891
"16",23,23.9770833333333,0.974658804573153
"17",24,23.2177975528365,1.12526920271045
"18",25,23.5250320924262,1.12891528015421
ridge_c_summary
"","times","means","sd"
"1",1,23.681434407626,0.989915240381175
"2",10,26.7027079303675,2.32962251222789
"3",11,27.9654291654292,2.38864888176336
"4",12,28.7457528957529,2.69414439432221
"5",13,28.9534165181224,2.68690267338402
"6",14,29.4438223938224,2.91979342111894
"7",15,28.8215325215325,2.6872152195944
"8",16,28.5877813504823,2.57493709806332
"9",17,27.3870056497175,2.19608259108006
"10",18,26.8308927424534,2.03789359897681
"11",19,25.5481404343945,1.41979111451077
"12",2,23.1454838709677,1.13422699496685
"13",20,24.9886246786632,1.36068090029202
"14",21,24.5601606664683,1.05832239119392
"15",22,24.1409646302251,1.16360525517371
"16",23,24.0566369047619,1.00175077418615
"17",24,23.6077813504823,1.11726702939239
"18",25,23.5780952380952,1.10355334756497
"19",3,23.3004172876304,1.10354221988403
"20",4,22.7314193548387,1.23686119466203
"21",5,23.0191654247392,1.18428611015011
"22",6,22.451935483871,1.29021975136401
"23",7,22.9037125037125,1.26259590667806
"24",8,23.1967741935484,1.48879695691969
"25",9,25.306534006534,1.76717581300979
valley_c_summary
"","times","means","sd"
"1",1,23.6594671201814,1.00814940817697
"2",10,26.0565511411665,2.16929556678063
"3",11,27.7657114295235,2.35397972988285
"4",12,28.3993260320135,2.71926477093656
"5",13,28.8432522492503,2.59319788793986
"6",14,29.1439865433137,2.86403883310426
"7",15,28.7382333333333,2.61080581070595
"8",16,28.488161209068,2.54623846359401
"9",17,27.2384794931644,2.06859192137737
"10",18,26.7695542472666,1.97980925001807
"11",19,25.4289052069426,1.36213237635363
"12",2,23.234375,1.2419107444281
"13",20,25.0288607594937,1.58285604050205
"14",21,24.5043071786311,1.02557712012499
"15",22,24.1491983122363,1.22981051413331
"16",23,24.0402003338898,0.981743823579669
"17",24,23.6662173546757,1.19576801398666
"18",25,23.700081300813,1.0898936548588
"19",3,23.3752591106653,1.08538931168628
"20",4,22.8620981387479,1.32723123739125
"21",5,23.1140421263791,1.16174678633048
"22",6,22.5889264581572,1.39010429942654
"23",7,22.9904,1.22621465254853
"24",8,23.0340371621622,1.48447539690888
"25",9,25.0078692897633,1.60606487763767
Easiest solution is to add an extra column to each data frame for grouping. For example, using dplyr::mutate and dplyr::bind_rows:
library(dplyr)
edge_c_summary %>%
mutate(source = "edge_c") %>%
bind_rows(mutate(ridge_c_summary, source = "ridge_c")) %>%
bind_rows(mutate(valley_c_summary, source = "valley_c")) %>%
ggplot(aes(times, means) +
geom_line(aes(color = source, group = source)) +
geom_errorbar(aes(ymin = means - sd, ymax = means + sd, color = source))
edge_c_summary <- read.csv(file="edge_c_summary.csv",header=TRUE,sep=",")
ridge_c_summary <- read.csv(file="ridge_c_summary.csv",header=TRUE,sep=",")
valley_c_summary <- read.csv(file="valley_c_summary.csv",header=TRUE,sep=",")
I also added different colors so they are somewhat distinguishable, that you can also ignore if you don't like them.
ggplot(data=edge_c_summary,aes(x = times,y=means))+
geom_errorbar(data=edge_c_summary,aes(ymin=means-sd,ymax=means+sd))+
geom_line(aes(y=means))+
geom_line(data = ridge_c_summary,aes(x=times,y=means),colour="red")+
geom_errorbar(data=ridge_c_summary,aes(ymin=means-sd,ymax=means+sd),colour="red")+
geom_line(data = valley_c_summary,aes(x=times,y=means),colour="blue")+
geom_errorbar(data=valley_c_summary,aes(ymin=means-sd,ymax=means+sd),colour="blue")
Related
I want to draw the map of a lake with the bathymetries I have taken with the sonar. I have a .sl2 file (Lowrance sonar) that I have converted to .csv (Namely, Sonar_13_07_1.csv). Finally I get 3 columns with 30665 rows, here is an example of the first rows:
latitude,longitude,waterDepthM
39.8197123940846,-3.11133523036904,0
39.8197193169248,-3.11133523036904,0
39.8197193169248,-3.11134424374202,0
39.8197262397644,-3.11134424374202,0
39.8197331626032,-3.11135325711499,0
39.8197400854413,-3.11135325711499,0
39.8197470082787,-3.11135325711499,0
39.8197539311154,-3.11135325711499,0
39.8197608539514,-3.11135325711499,0
39.8197608539514,-3.11134424374202,0
39.8197677767867,-3.11134424374202,0
39.8197677767867,-3.11135325711499,0
39.8197746996213,-3.11135325711499,0
39.8197746996213,-3.11134424374202,0
39.8197816224553,-3.11134424374202,0
39.8197885452885,-3.11134424374202,0
39.8197885452885,-3.11133523036904,0
39.819795468121,-3.11133523036904,0
39.8198023909528,-3.11132621699607,0
39.8198023909528,-3.11133523036904,0
39.819809313784,-3.11132621699607,0
39.8198162366144,-3.11132621699607,0
39.8198231594442,-3.11132621699607,0
39.8198370051015,-3.11132621699607,0
39.8198300822732,-3.11132621699607,0
39.8198439279292,-3.11132621699607,0
39.8198508507561,-3.11133523036904,0
39.8198508507561,-3.11132621699607,0
39.8198577735824,-3.11133523036904,0
39.8198646964079,-3.11133523036904,0
39.8198646964079,-3.11134424374202,0
39.8198716192328,-3.11135325711499,0
39.8198716192328,-3.11134424374202,0
39.8198716192328,-3.11136227048797,0
39.8198785420569,-3.11135325711499,0
39.8198716192328,-3.11136227048797,-0.691144658182553
39.8198785420569,-3.11135325711499,-0.691144658182553
39.8198716192328,-3.11136227048797,-0.72783260768886
39.8198785420569,-3.11135325711499,-0.72783260768886
39.8198716192328,-3.11136227048797,-0.735494858005278
39.8198785420569,-3.11135325711499,-0.735494858005278
39.8198716192328,-3.11136227048797,-0.754367615888273
39.8198785420569,-3.11135325711499,-0.754367615888273
39.8198716192328,-3.11136227048797,-0.762954301055886
39.8198785420569,-3.11135325711499,-0.762954301055886
39.8198785420569,-3.11136227048797,-0.762954301055886
I manage to plot it like this:
library(ggplot2)
ggplot(Sonar_13_07_1, aes(longitude, latitude, colour = waterDepthM)) + geom_point() + coord_equal() + xlim(x_coords) + ylim(y_coords)
On the other hand, I plotted the base map of the lake:
library(osmdata)
library(sf)
> x_coords <- c(-3.109, -3.117)
> y_coords <- c(39.817, 39.832)
> bounding_box <- matrix(nrow = 2, ncol=2, byrow = T,
+ data = c(x_coords, y_coords),
+ dimnames = list(c("x", "y"),
+ c("min", "max")))
> osm_water_sf <- osmdata::opq(bbox = bounding_box) %>% # Limit query to bounding_box
+ osmdata::add_osm_feature(key = 'natural', value = 'water') %>% # Limit query to waterbodies
+ osmdata::osmdata_sf() # Convert to simple features
ggplot(data=osm_water_sf$osm_polygons) +
geom_sf(color="blue", fill="lightblue") +
xlim(x_coords) + ylim(y_coords)
But finally I don't manage to merge the two plots into one, superimposing the bathymetric data on the base map. Also, my intention would be to obtain contours from the bathymetric data of the lake, but of course, I'm already stuck with the merging of both plots.
Thanks for the suggestion, I have managed to have a spatial data frame like this:
"","waterDepthM","geometry"
"1",0,c(-3.11133523036904, 39.8197123940846)
"2",0,c(-3.11133523036904, 39.8197193169248)
"3",0,c(-3.11134424374202, 39.8197193169248)
"4",0,c(-3.11134424374202, 39.8197262397644)
"5",0,c(-3.11135325711499, 39.8197331626032)
"6",0,c(-3.11135325711499, 39.8197400854413)
"7",0,c(-3.11135325711499, 39.8197470082787)
"8",0,c(-3.11135325711499, 39.8197539311154)
"9",0,c(-3.11135325711499, 39.8197608539514)
"10",0,c(-3.11134424374202, 39.8197608539514)
but when I try to plot both data frames together, I only get a base map of the lake with the depth legend, but no depth values appear.
ggplot() +
+ geom_sf(data=osm_water_sf$osm_polygons, color="blue", fill="NA") +
+ geom_sf(data=Sonar_13_07_1, aes(col=waterDepthM)) +
+ xlim(x_coords) + ylim(y_coords)
plot output
Use the sf package to convert your sonar data frame to a spatial data frame. Something like:
library(sf)
Sonar_13_07_1 = st_as_sf(Sonar_13_07_1, coords=c("longitude","latitude"), crs=4326)
then you have an object you can put in a ggplot construction via an sf geom alongside your OSM vector data. Something like:
ggplot(data=osm_water_sf$osm_polygons) +
geom_sf(color="blue", fill="lightblue") +
geom_sf(data=Sonar_13_07_1, aes(col=waterDepthM)) +
xlim(x_coords) + ylim(y_coords)
Here is a reproducible example
#load the packages
library(easypackages)
packages("tidyverse","readxl","sf","tmaptools","tmap","lubridate",
"lwgeom","Cairo","nngeo","purrr","scales", "ggthemes","janitor")
polls<-st_as_sf(read.csv(url("https://www.caerphilly.gov.uk/CaerphillyDocs/FOI/Datasets_polling_stations_csv.aspx")),
coords = c("Easting","Northing"),crs = 27700)%>%
mutate(date = sample(seq(as.Date('2020/01/01'), as.Date('2020/05/31'), by="day"), 147))
test_stack<-polls%>%st_join(polls%>%st_buffer(dist=1000),join=st_within)%>%
filter(Ballot.Box.Polling.Station.x!=Ballot.Box.Polling.Station.y)%>%
add_count(Ballot.Box.Polling.Station.x)%>%
rename(number_of_neighbours = n)%>%
mutate(interval_date = date.x-date.y)%>%
subset(select = -c(6:8,10,11,13:18))## removing this comment will summarise the data so that only number of neighbours is returned %>%
distinct(Ballot.Box.Polling.Station.x,number_of_neighbours,date.x)%>%
filter(number_of_neighbours >=2)
polls%>%mutate(id = as.numeric(row_number()))%>% mutate(thing = case_when(id %% 2 == 0 ~ "stuff",
id %% 2 !=0 ~ "type"))->polls
qtm(polls)
tmap_mode("view")
tm_shape(polls) + tm_markers(col = "thing")
tm_shape(polls) + tm_dots(col ="thing", size = 0.75)
what I'd like to do is change the colour and size of tm_markers, because in the thing I want to use it in it would be nice to make use of different colour markers easily.
Linked to this, is understanding how the clustering of markers works when the map mode is "view" and an html is generated.
Any help on tm_marker behaviour and tm_marker clustering would be brilliant.
thanks == "MANY!"
In the end it turns out to be much simpler than using markers. I don't like "markers", aesthetically, but I do like "dots" and tm_dots lets you sort out the colours more easily (or in my head it's easier..) . And the thing is. Well. Clustering can be applied to dots, bubbles, and tm_symbols.
It's all in here:
https://cran.r-project.org/web/packages/tmap/tmap.pdf
(p 89/90)
ANYWAY
tm_shape(polls) + tm_dots(col ="thing", size = 0.75,clustering = T)
that's the answer (for me). I can cluster and then colour by a field.
I would like to take the height of my plot reactive because sometimes I have to draw just one graph and sometimes two or three graphs. Here my code :
output$myplot<-renderPlot({
plot_to_draw <- data[data$code==input$code,"River_name"]
plot(plot_to_draw)
number_of_plot <- length(plot_to_draw)
},height = 500*number_of_plot)
But shiny reads the height of the plot just one time so that it's not reactive.
Thank you for your answers !
I finally figuerd out a solution ;
server.R
output$myplot<-renderPlot({
plot_to_draw <- data[data$code==input$code,"River_name"]
plot(plot_to_draw)
number_of_plot <- length(plot_to_draw)
},height = function(){500*number_of_plot})
ui.R
plotOutput(outputId="myplot",height = "auto")
This is the solution that I finally got, after drudging with my app and thanks to all persons in this thread for your kind suggestions. Please don't mind the name of the variables.
In the server part:
#I had to transform my imput into a data.frame, otherwise sqldf didn't work.
country12<- reactive({as.data.frame(matrix(c(input$sel_country121),1,1))})
question12<-reactive({
country121 <- country12()
sqldf("SELECT dp.Year, dp.Type_of_Product COUNT (*) as num_products12 FROM dataPanelV5 dp, country121 p WHERE dp.Country_name = p.V1 GROUP BY dp.Year, dp.Type_of_Product")})
#I use this function to calculate the number of different types of products resulting from the query, using unique() and calculating its length, as that number is the number of facets.
n_facets12<-function(){
question121<- question12()
return (500*length(unique(question121$Type_of_Product)))}
output$barplot12 <- renderPlot({
question121<-question12()
ggplot(question121,aes(x=factor(Year),y=num_products12,fill=Type_of_Product)) + geom_bar(stat="identity") + facet_grid(Type_of_Product ~ .,scales = "free_y") +
geom_text(aes(label=num_products12), vjust=-0.2, colour="black") + scale_x_discrete(breaks=question121$Year,labels=as.character(question121$Year),position = "top") + theme(legend.position="top",axis.title.y=element_blank(),axis.text.y = element_blank(),panel.grid.major.y = element_blank(),panel.grid.minor.y = element_blank()) + labs(fill="Type_of_Product", x="Year")
},height = n_facets12)
#And it works!!
I want to generate a plot of interest over time using GTrendsR and ggplot2
The plot I want (generated with google trends) is this:
Any help will be much appreciated.
Thanks!
This is the best I was able to get:
library(ggplot2)
library(devtools)
library(GTrendsR)
usr = "my.email"
psw = "my.password"
ch = gConnect(usr, psw)
location = "all"
query = "MOOCs"
MOOCs_trends = gTrends(ch, geo = location, query = query)
MOOCs<-MOOCs_trends[[1]]
MOOCs$moocs<-as.numeric(as.character(MOOCs$moocs))
MOOCs$Week <- as.character(MOOCs$Week)
MOOCs$start <- as.Date(MOOCs$Week)
ggplot(MOOCs[MOOCs$moocs!=0,], aes(start, moocs)) +
geom_line(colour = "blue") +
ylab("Trends") + xlab("") + theme_bw()
I think that to match the graph generated by google I would need to aggregate the data to months instead of weeks... not sure how to do that yet
The object returned by gtrendsR is a list, of which the trend element in a data.frame that you would want to plot.
usr = "my.email"
psw = "my.password"
gconnect(usr, psw)
MOOCs_trends = gtrends('MOOCs')
MOOCsDF <- MOOCs_trends$trend
ggplot(data = MOOCsDF) + geom_line(aes(x=start, y=moocs))
This gives:
Now if you want to aggregate by month, I would suggest using the floor_date function from the lubridate package, in combination with dplyr (note that I am using the chain operator %>% which dplyr re-exports from the magrittr package).
usr = "my.email"
psw = "my.password"
gconnect(usr, psw)
MOOCs_trends = gtrends('MOOCs')
MOOCsDF <- MOOCs_trends
MOOCsDF$start <- floor_date(MOOCsDF$start, unit = 'month')
MOOCsDF %>%
group_by(start) %>%
summarise(moocs = sum(moocs)) %>%
ggplot() + geom_line(aes(x=start, y=moocs))
This gives:
Note 1: The query MOOCs was changed to moocs, by gtrendsR, this is reflected in the y variable that you're plotting.
Note 2: some of the cases of functions have changed (e.g. gtrendsR not GTrendsR), I am using current versions.
This will get you most of the way there. The plot doesn't look quite right, but that's more of a function of the data being a bit different. Here's the necessary conversions to numeric and to dates.
MOOCs<-MOOCs_trends[[1]]
library(ggplot2)
library(plyr)
## Convert to string
MOOCs$Week <- as.character(MOOCs$Week)
MOOCs$moocs <- as.numeric(MOOCs$moocs)
# split the string
MOOCs$start <- unlist(llply(strsplit(MOOCs$Week," - "), function(x) return(x[2])))
MOOCs$start <- as.POSIXlt(MOOCs$start)
ggplot(MOOCs,aes(x=start,y=moocs))+geom_point()+geom_path()
Google might do some smoothing, but this will plot the data you have.
I have a table composed by the following data
frame,X,Y
which is the resulting data from several eye tracking analysis.
Now I would like to create a Heatmap using R, like the following
I tried several script found online, none of them gave me that result.
How can I do?
Here some sample data
Ignore the first two columns
task,visualization,frame,X,Y
1,b,1,383,221
1,b,1,632,356
1,b,1,947,663
1,b,1,546,206
1,b,1,488,272
1,b,1,578,752
1,b,1,415,261
1,b,1,693,158
1,b,1,684,528
1,b,1,592,67
1,b,1,393,180
1,b,1,1033,709
1,b,1,1080,739
1,b,1,711,523
1,b,1,1246,49
1,b,1,742,69
1,b,1,601,370
1,b,10,902,684
1,b,10,517,241
1,b,10,583,86
1,b,10,582,754
1,b,10,426,257
1,b,10,575,229
1,b,10,697,150
1,b,10,379,520
1,b,10,390,286
1,b,10,618,396
1,b,10,710,143
1,b,10,383,188
1,b,10,1026,713
1,b,10,1078,625
1,b,10,713,521
You can get this type of plot quite easily using stat_bin2d from ggplot2:
library(ggplot2)
ggplot(dat, aes(x = X, y = Y)) + stat_bin2d(bins = 10)
This does simple binning, as #RomanLustrik suggested you could also perform some kind of kernel smoothing. This can also be done using ggplot2:
ggplot(dat, aes(x = X, y = Y)) +
stat_density2d(geom = "tile", aes(fill = ..density..), contour = FALSE) +
geom_point()
Note that dat is the example data you gave, geting your data into a data.frame:
dat = read.table(textConnection("task,visualization,frame,X,Y
1,b,1,383,221
1,b,1,632,356
1,b,1,947,663
1,b,1,546,206
1,b,1,488,272
1,b,1,578,752
1,b,1,415,261
1,b,1,693,158
1,b,1,684,528
1,b,1,592,67
1,b,1,393,180
1,b,1,1033,709
1,b,1,1080,739
1,b,1,711,523
1,b,1,1246,49
1,b,1,742,69
1,b,1,601,370
1,b,10,902,684
1,b,10,517,241
1,b,10,583,86
1,b,10,582,754
1,b,10,426,257
1,b,10,575,229
1,b,10,697,150
1,b,10,379,520
1,b,10,390,286
1,b,10,618,396
1,b,10,710,143
1,b,10,383,188
1,b,10,1026,713
1,b,10,1078,625
1,b,10,713,521"), header = TRUE, sep = ",")