Call variable from custom function - r

This would seem to be a straightforward problem but I can't find an answer for it...
How do I write a function where one of the calls refers to a specific variable name?
For example, if I have a data frame:
data=structure(list(x = 1:10, treatment = c(1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L)), .Names = c("x", "treatment"), row.names = c(NA,
-10L), class = "data.frame")
I can write a trivial function that adds treatment to the other variable in the data frame but this only works if there is a variable called "treatment" in d.
ff=function(data,treatment){data+treatment)}
ff(data,data$treatment)
This works but I want to set it up so the user doesn't call data$Var in the function.

Is this what you want?
ff <- function(data, colname) {
data + data[[colname]]
}
ff( data, "treatment" )
or
ff <- function(data, column) {
colname <- deparse(substitute(column))
data + data[[colname]]
}
ff( data, treatment )
(the later can lead to hard to find bugs if someone tries something like ff(data, 1:10))

Related

Building a ROC producing function in R

I want to make a function that accepts an xgboost model and the data (test set that I already got, called mydata[[2]]) and returns a ROC curve.
My first try was like this:
evaluate_model_plot = function(model,data) {
plt = roc(data[,1],predict(model, data[,-1]))
plot(plt, main = 'Test Set')
}
I get this error:
> evaluate_model_plot(myxgb, mydata[[2]])
Error in xgb.DMatrix(newdata, missing = missing) :
xgb.DMatrix does not support construction from list
I tried again:
evaluate_model_plot = function(model,data) {
dtest = xgb.DMatrix(data = data.matrix(data[,-1]),label=as.numeric(as.character(data[,1])))
plt = roc(dtest,predict(model, dtest))
plot(plt, main = 'Test Set')
}
Now the error is:
Error in unique.default(x, nmax = nmax) :
unique() applies only to vectors
I'm not sure how to fix this. The first error is not very clear to me since the data I'm providing is a data frame, it's saying that it doesn't accept a list, although the input is not a list..
Here is a sample from my test set:
> dput(data[[2]][1:15,1:5])
structure(list(CR = structure(c(1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L,
1L, 2L, 2L, 1L, 1L, 1L, 1L), levels = c("0", "1"), class = "factor"),
CD4.T.cells = c(0.0410284948786532, -0.0366277340916379,
-0.0349008907108641, -0.062499826731091, -0.206241592996545,
-0.0874700869552125, -0.182120904486964, -0.171941115538424,
-0.101887370292612, -0.0471260521659922, 0.00336508376392719,
-0.0558977705951249, -0.0346269111530533, 0.0405376992753275,
-0.116824556352525), CD8.T.cells = c(-0.0372301980787381,
-0.0550538743643369, -0.157003425700701, -0.280984614146961,
-0.245432535063266, -0.147192190940429, -0.244633652045209,
-0.213892169574032, -0.301036923607255, -0.427604924497491,
-0.371628492024595, -0.0166106304573527, -0.200413064153971,
-0.276715360733834, -0.13198989690999), T.helpers = c(0.186447606591857,
0.0686746776877563, -0.0662055287009653, -0.0969110962088053,
-0.176807066557773, -0.079679981476819, -0.0642576894506894,
-0.0543810984331623, -0.0741755574175595, -0.0131228323048211,
-0.214234307929943, -0.0137492004706794, -0.000982317887326278,
-0.126128005295858, -0.177662982037535), NK.cells = c(-0.0172673823614314,
-0.0518877213975413, -0.129207379606117, -0.174457678991973,
-0.103184559349521, -0.0415572732935339, -0.100644327844509,
-0.124636632740142, -0.131184498665394, -0.181979331198521,
0.0352080568467581, -0.00354359170704435, -0.0820137078499403,
-0.167969284367181, 0.132078267822988)), row.names = c("Pt101",
"Pt18", "Pt2", "Pt3", "Pt48", "Pt59", "Pt67", "Pt82", "Pt98",
"EA595647", "EA632133", "EA632149", "EA632171", "EA639018", "G109543_RCCBMS-00114-T_v1_RNA_OnPrem"
), class = "data.frame")

ggplot r: How to Highlight the Data from a Year [duplicate]

This question already has answers here:
geom_smooth on a subset of data
(3 answers)
Closed 3 years ago.
Data: Height was recorded daily
I want to plot the Height of my Plants (Plant A1 - Z50)
in single Plots, and i want to Highlight the current Year.
So i made a Subset of each Plant and a subset for the current year (2018)
Now i need a Plot with the total record an the highlighted Data from 2018
dput(Plant)
structure(list(Name = structure(c(1L, 1L, 1L, 1L, 2L, 2L, 2L,
3L, 3L, 3L), .Label = c("Plant A1", "Plant B1", "Plant C1"), class = "factor"),
Date = structure(c(1L, 4L, 5L, 7L, 1L, 4L, 6L, 1L, 2L, 3L
), .Label = c(" 2001-01-01", " 2001-01-02", " 2001-01-03",
" 2002-01-01", " 2002-02-01", " 2019-01-01", " 2019-12-31"
), class = "factor"), Height_cm = c(91, 106.1, 107.4, 145.9,
169.1, 192.1, 217.4, 139.8, 140.3, 140.3)), .Names = c("Name",
"Date", "Height_cm"), class = "data.frame", row.names = c(NA,
-10L))
Plant_A1 <- filter(Plant, Name == "Plant A1")
Current_Year <- as.numeric("2018")
Plant_A1_Subset <- filter(Plant_A1, format(Plant_A1$Date, '%Y') == Current_Year)
ggplot(data=Plant_A1,aes(x=Plant_A1$Date, y=Plant_A1$Heigth)) +
geom_point() +
geom_smooth(method="loes", level=0.95, span=1/2, color="red") +
labs(x="Data", y="Height cm")
Now i don't know how to put my new Subset for 2018(Plant_A1_Subset) into this graph.
As noted, this question has a duplicate with an answer in this question.
That said here's likely the most common way of handling your problem.
In ggplot2 future calls inherits any arguments passed into aes of the ggplot(aes(...)) function. Thus the plot will always use these arguments in future ggplot functions, unless one manually overwrites the arguments. However we can solve your problem, by simply adding an extra argument in the aes of geom_point. Below I've illustrated a simple way to achieve what you might be looking for.
Specify the aes argument in individual calls
The first method is likely the most intuitive. aes controls the the plotted parameters. As such if you want to add colour to certain points, one way is to let the aes be individual to the geom_point and geom_smooth argument.
library(ggplot2)
library(lubridate) #for month(), year(), day() functions
current_year <- 2018
ggplot(data = Plant_A1, aes(x = Date, y = Heigth)) +
#Note here, colour set in geom_point
geom_point(aes(col = ifelse(year(Date) == current_year, "Yes", "No"))) +
geom_smooth(method="loess", level=0.95,
span=1/2, color="red") +
labs(x="Data", y="Height cm",
col = "Current year?") #Specify legend title for colour
Note here that i have used the inheritance of the aes argument. Simply put, the aes will check the names within data, and if it can find it, it will use these as variables. So there is no need to specify data$....

Filter two tables with crosstalk

I am creating a Flexdashboard in R. I want the dashboard to contains both a table and a series of visualizations, that would be filtered through inputs.
As I need to deliver a dashboard locally (without a server running in the background), I am unable to use Shiny, hence I rely on crosstalk.
I know that the crosstalk package provides limited functionality in the front-end. For instance, the documentation says that you can't aggregate the SharedData object.
Nonetheless, I am not clear if I can use the same inputs to filter two different dataframes.
For example, lets say I have:
Dataframe One: Contains original data
df1 <- structure(list(owner = structure(c(1L, 2L, 2L, 2L, 2L), .Label = c("John",
"Mark"), class = "factor"), hp = c(250, 120, 250, 100, 110),
car = structure(c(2L, 2L, 2L, 1L, 1L), .Label = c("benz",
"bmw"), class = "factor"), id = structure(1:5, .Label = c("car1",
"car2", "car3", "car4", "car5"), class = "factor")), .Names = c("owner",
"hp", "car", "id"), row.names = c(NA, -5L), class = "data.frame")
Dataframe Two: Contains aggregated data
df2 <- structure(list(car = structure(c(1L, 2L, 1L, 2L), .Label = c("benz",
+ "bmw"), class = "factor"), owner = structure(c(1L, 1L, 2L, 2L
+ ), .Label = c("John", "Mark"), class = "factor"), freq = c(0L,
+ 1L, 2L, 2L)), .Names = c("car", "owner", "freq"), row.names = c(NA,
+ -4L), class = "data.frame")
These two dataframes contain columns with identical values - car and owner. As well as, additional columns too.
I could create two different objects:
library(crosstalk)
shared_df1 <- SharedData$new(df1)
shared_df2 <- SharedData$new(df2)
and than:
filter_select("owner", "Car owner:", shared_df1, ~ owner)
filter_select("owner", "Car owner:", shared_df2, ~ owner)
However, that would mean that the user will need to fill inputs that are essentially identical, twice. Also, if the table is large, this would double the size of the memory needed to use the dashboard.
Is it possible to work around this problem in crosstalk?
Ah I recently ran into this too, there is another argument to SharedData$new(..., group = )! The group argument seems to do the trick. I found out by accident when I had two dataframes and used the group =.
If you make a sharedData object, it will include
a dataframe
a key to select rows by - preferably unique, but not necessarily.
a group name
What I think happens is that crosstalk filters the sharedData by the key - for all sharedData objects in the same group! So as long as two dataframes use the same key, you should be able to filter them together in one group.
This should work for your example.
---
title: "blabla"
output:
flexdashboard::flex_dashboard:
orientation: rows
social: menu
source_code: embed
theme: cerulean
---
```{r}
library(plotly)
library(crosstalk)
library(tidyverse)
```
```{r Make dataset}
df1 <- structure(list(owner = structure(c(1L, 2L, 2L, 2L, 2L), .Label = c("John", "Mark"), class = "factor"), hp = c(250, 120, 250, 100, 110), car = structure(c(2L, 2L, 2L, 1L, 1L), .Label = c("benz", "bmw"), class = "factor"), id = structure(1:5, .Label = c("car1", "car2", "car3", "car4", "car5"), class = "factor")), .Names = c("owner", "hp", "car", "id"), row.names = c(NA, -5L), class = "data.frame")
df2 <- structure(list(car = structure(c(1L, 2L, 1L, 2L), .Label = c("benz",
"bmw"), class = "factor"), owner = structure(c(1L, 1L, 2L, 2L
), .Label = c("John", "Mark"), class = "factor"), freq = c(0L,
1L, 2L, 2L)), .Names = c("car", "owner", "freq"), row.names = c(NA,
-4L), class = "data.frame")
```
#
##
### Filters
```{r}
library(crosstalk)
# Notice the 'group = ' argument - this does the trick!
shared_df1 <- SharedData$new(df1, ~owner, group = "Choose owner")
shared_df2 <- SharedData$new(df2, ~owner, group = "Choose owner")
filter_select("owner", "Car owner:", shared_df1, ~owner)
# You don't need this second filter now
# filter_select("owner", "Car owner:", shared_df2, ~ owner)
```
### Plot1 with plotly
```{r}
plot_ly(shared_df1, x = ~id, y = ~hp, color = ~owner) %>% add_markers() %>% highlight("plotly_click")
```
### Plots with plotly
```{r}
plot_ly(shared_df2, x = ~owner, y = ~freq, color = ~car) %>% group_by(owner) %>% add_bars()
```
##
### Dataframe 1
```{r}
DT::datatable(shared_df1)
```
### Dataframe 2
```{r}
DT::datatable(shared_df2)
```
I spent some time on this by trying to extract data from plot_ly() using plotly_data() without luck until I figured out the answer. That's why there's some very simple plots with plotly.
Recently, I've also wanted to use one filter to filter 2 visualizations.
Brief description of my situation
I've wanted to use one filter to filter a boxplot and a table.
Source data has been a data frame. I've wanted to use some of variables for the boxplot and also calculate some statistics (like mean, standard deviation, mode, number of records).
Functions I've needed to use to display results: plotly::plot_ly(), DT::datatable(), crosstalk::bscols().
I've found out that there are 3 key information to solve this situation
Key 1) It's necessary to correctly create shared data.
In my case, I've had to use crosstalk::SharedData$new() twice.
Correct shared data, to be used as source for visualizations, can be used if firstly keys 2 and 3 are fulfilled.
Key 2) When creating shared data, use the same group argument as "Lodewic Van Twillert" explained on 16 Mar 2018.
Key 3) Ensure that all SharedData instances refer conceptually to the same data points, and share the same keys.
Start with ensuring that a data frame has row names even if row names are character vector with numbers (like "1", "2", ...).
Used literature for this key 3: https://rstudio.github.io/crosstalk/using.html. (I suggest to mainly read subtitle "Grouping".)
Summary of steps I've used to fulfill key information from above
Key 3) This one could be tricky in order to fulfill relevant conditions of key 3 above.
The approach I've chosen creates one table containing all data and this table (data frame) will be used to create both shared data.
I've applied data manipulations to original data frame (risk_scores_df) so now this data has a new column.
I've created a new data frame with statistics.
I've joined both data frames using
risk_scores_df <- dplyr::left_join... so now the original data frame contains all prepared data.
I've run print(rownames(risk_scores_df)) to ensure that my updated data frame has row names.
Now, I've had one data frame containing all data (needed for both visualizations) that fulfill conditions of information of key 3 above.
Key 2) I've simply added group = "sd1" in both crosstalk::SharedData$new()
Key 1) This one could be also tricky if a wrong approach is chosen.
Here, the key to create correct shared data instances is to use that one table with all data and choose only rows and columns needed for a relevant shared data.
Example - in my case, I've run codes in Option 1 to create two shared data instances, but also Option 2 is possible.
Option 1 (choosing of only needed rows and columns is in crosstalk::SharedData$new())
rs_df_sd1 <- crosstalk::SharedData$new(
risk_scores_df[, c(1, 2, 5)],
group = "sd1"
)
rs_df_sd1a <- crosstalk::SharedData$new(
risk_scores_df[risk_scores_df$NumRecords > 0 &
is.na(risk_scores_df$NumRecords) == F,
c(1, 6:11)],
group = "sd1"
)
Option 2 (choosing of only needed rows and columns is in additional variables)
sd1 <- risk_scores_df[, c(1, 2, 5)]
sd1a <- risk_scores_df[risk_scores_df$NumRecords > 0 &
is.na(risk_scores_df$NumRecords) == F,
c(1, 6:11)]
rs_df_sd1 <- crosstalk::SharedData$new(sd1, group = "sd1")
rs_df_sd1a <- crosstalk::SharedData$new(sd1a, group = "sd1")
Completing the solution
At this point I've created shared data instances rs_df_sd1 and rs_df_sd1a that can be used as main sources for visualizations that will be filtered using crosstalk::bscols().
Brief example:
box_n_jitter_chart1 <- plotly::plot_ly(rs_df_sd1) %>% add_trace(...
DT_table1 <- DT::datatable(rs_df_sd1a)
crosstalk::bscols(
widths = c(6, 12, NA),
crosstalk::filter_select(
id = "idAvgRisk",
label = "Account",
sharedData = rs_df_sd1,
group = ~Account,
multiple = F
),
box_n_jitter_chart1,
DT_table1
)
Note: DT::datatable() can also use rs_df_sd1a$data() and cells = list(values = base::rbind(... (see that cells = ... is used; see more about using cells e.g. at https://plotly.com/r/reference/table/) but because method data() is used (see more e.g. at https://rdrr.io/cran/crosstalk/man/SharedData.html#method-data) then it will not work with crosstalk::bscols.

How to use ifelse and paste functions

I am learning the use of the ifelse function from Zuur et al (2009) A Beginners guide to R. In one exercise, there is a data frame called Owls which contains data about about 27 nests and two night of observations.
structure(list(Nest = structure(c(1L, 1L, 1L, 1L), .Label = "AutavauxTV", class = "factor"),
FoodTreatment = structure(c(1L, 2L, 1L, 1L), .Label = c("Deprived",
"Satiated"), class = "factor"), SexParent = structure(c(1L,
1L, 1L, 1L), .Label = "Male", class = "factor"), ArrivalTime = c(22.25,
22.38, 22.53, 22.56), SiblingNegotiation = c(4L, 0L, 2L,
2L), BroodSize = c(5L, 5L, 5L, 5L), NegPerChick = c(0.8,
0, 0.4, 0.4)), .Names = c("Nest", "FoodTreatment", "SexParent",
"ArrivalTime", "SiblingNegotiation", "BroodSize", "NegPerChick"
), row.names = c(NA, 4L), class = "data.frame")
The two nights differed as to the feeding regime (satiated or deprived) and are indicated in the Foodregime variable. The task is to use ifelse and past functions that make a new categorical variable that defines observations from a single night at a particular nest.
In the solutions the following code is suggested:
Owls <- read.table(file = "Owls.txt", header = TRUE, dec = ".")
ifelse(Owls$FoodTreatment == "Satiated", Owls$NestNight <- paste(Owls$Nest, "1",sep = "_"), Owls$NestNight <- paste(Owls$Nest, "2",sep = "_"))
and apparently it creates a new variable with values the endings of which vary ("-1" or "-2")
however when I call the original dataframe, all "-1" endings in the NestNight variable disappears and are turned to "-2."
Why does this happen? Did the authors miss something from the code or it's me who is not getting it?
Many thanks
EDIT: Sorry, I wanted to give a reproducible example by copying my data using dput but it did not work. If you can let me know how I can correct it so that it appears properly, I'd be grateful too!
Solution
If you do the assignment outside the ifelse structure, it works:
Owls$NestNight <- ifelse(Owls$FoodTreatment == "Satiated",
paste(Owls$Nest, "1",sep = ""),
paste(Owls$Nest, "2",sep = ""))
Explanation
What happens in your case is simply if you would execute the following two lines:
Owls$NestNight <- paste(Owls$Nest, "1",sep = "")
Owls$NestNight <- paste(Owls$Nest, "2",sep = "")
You first assign paste(Owls$Nest, "1",sep = "") to Owls$NestNight and then you reassign paste(Owls$Nest, "2",sep = "") to it. The ifelse is not affected by this, but you don't assign it's result to any variable.
Maybe it is more clear if you test this simple code:
c(a <- 1:5, a <- 6:10) #c is your ifelse, a is your Owls$NestNight
a #[1] 6 7 8 9 10

Lattice xyplot() Adding a different mean trend line to each panel?

I have a simple trellis scatterplot. Two panels - male/female. ID is a unique number for each participant. The var1 is a total test time. Mean.values is a vector of two numbers (the means for gender).
No point including a best fit line so what I want is to plot a trend line of the mean in each panel. The two panels have different means, say male = 1 minute, female = 2 minutes.
xyplot(var1 ~ ID|Gender, data=DF,
group = Gender,
panel=function(...) {
panel.xyplot(...)
panel.abline(h=mean.values)
})
At the minute the graph is coming out so that both trendlines appear in each panel. I want only one trendline in each.
Does anyone have the way to do this?
I have tried a number of different ways including the long code for function Addline which just doesn't work for me. I just want to define which panel im looking at and i've looked at ?panel.number but not sure how that works as its coming up that I don't have a current row. (current.row(prefix)).
There must be a simple way of doing this?
[EDIT - Here's the actual data i'm using]
I've tried to simplify the DF
library(lattice)
dput(head(DF))
structure(list(ID = 1:6, Var1 = c(2333858, 4220644,
2941774, 2368496, 3165740, 3630300), mean = c(2412976, 2412976,
2412976, 2412976, 2412976, 2412976), Gender = structure(c(1L,
1L, 1L, 1L, 1L, 1L), .Label = c("1", "2"), class = "factor")), .Names = c("ID",
"Var1", "mean", "Gender"), row.names = c(NA, 6L), class = "data.frame")
dput(tail(DF))
structure(list(ID = 161:166, Var1= c(2825246, 3552170,
3688882, 2487760, 3849108, 3085342), mean = c(3689805, 3689805,
3689805, 3689805, 3689805, 3689805), Gender = structure(c(2L,
2L, 2L, 2L, 2L, 2L), .Label = c("1", "2"), class = "factor")), .Names = c("ID",
"Var1", "mean", "Gender"), row.names = 109:114, class = "data.frame")
plot i'm using:
xyplot((Var1/1000) ~ ID|Gender, data=DF,
group = Gender,scales=list(x=list(at=NULL)),
panel=function(...) {
panel.xyplot(...)
panel.abline(h=mean.values) })
causes 2 lines.
[EDIT - This is the code which includes the function Addline & is everywhere on all the posts and doesn't seem to work for me]
addLine<- function(a=NULL, b=NULL, v = NULL, h = NULL, ..., once=F) { tcL <- trellis.currentLayout() k<-0 for(i in 1:nrow(tcL)) for(j in 1:ncol(tcL)) if (tcL[i,j] > 0) { k<-k+1 trellis.focus("panel", j, i, highlight = FALSE) if (once) panel.abline(a=a[k], b=b[k], v=v[k], h=h[k], ...) else panel.abline(a=a,b=b, v=v, h=h, ...) trellis.unfocus() } }
then writing after the trellis plot (mean.values being a vector of two numbers, mean for female, mean for male)
addLine(v=(mean.values), once=TRUE)
Update - I managed to do it in ggplot2.
Make the ggplot using facet_wrap then -
hline.data <- data.frame(z = c(2413, 3690), Gender = c("Female","Male"))
This creates a DF of the two means and the Gender, 2x2 DF
myplot <- myplot + geom_hline(aes(yintercept = z), hline.data)
This adds the lines to the ggplot.
If you just wanted plot the mean of values you are drawing on the plot aready, you can skip the mean.values variable and just do
xyplot(Var1 ~ ID|Gender, data=DF,
group = Gender,
panel=function(x,y,...) {
panel.xyplot(x,y,...)
panel.abline(h=mean(y))
}
)
With the sample data
DF<-data.frame(
ID=1:10,
Gender=rep(c("M","F"), each=5),
Var1=c(5,6,7,6,5,8,9,10,8,9)
)
this produces
I believe lattice has a specific panel function for this, panel.average().
Try replacing panel.abline(h=mean.values) with panel.average(...).
If that doesn't solve the problem, we might need more information; try using dput() on your data (e.g., dput(DF), or some representative subset).

Resources