Impute NA Values in a matrix using linear model - r

I'm trying to write a function that will take a matrix of any size, find a single NA value, and impute that value based on a LINEAR MODEL of the other values in the matrix. I'm running into the issue that my linear model is not supplying me with a slope and an intercept to calculate the missing value, as I believe it should. If anyone can give me any pointers or help me find a more efficient way of achieving this, I would appreciate it.
Here's what I have so far:
rawVector <- c(1, 2, 3, 4, 5, NA, 7, 8, 9)
testMatrix <- matrix(rawVector, nrow = 3, ncol = 3, byrow = T)
imputeMissingValuesHARD <- function(inputMatrix) {
dimnames(inputMatrix) <- list(rownames(inputMatrix, do.NULL = FALSE, prefix = "row"), colnames(inputMatrix, do.NULL = FALSE, prefix = "col"))
dependent <- ""
colNumber <- -1
for(row in 1:nrow(inputMatrix)) {
for(col in 1:ncol(inputMatrix)) {
if(is.na(inputMatrix[row, col]))
{
dependent <- colnames(inputMatrix)[col]
colNumber <- col
}
}
}
otherCols <- colnames(inputMatrix)[-(colNumber)]
myModel <- as.formula(paste(dependent, paste(otherCols, collapse="+"), sep="~"))
fit <- lm(myModel, as.data.frame(inputMatrix))
print(fit)
return("OK")
}
imputeMissingValuesHARD(testMatrix)

Related

R bootstrapping for the two dataframe individual column wise

Want to do Bootstrapping while comparing two dataframe column wise with the different number of rows.
I have two dataframe in which row represent values from experiments and column with the dataset names (data1, data2, data3, data4)
emp.data1 <- data.frame(
data1 = c(234,0,34,0,46,0,0,0,2.26,0, 5,8,93,56),
data2 = c(1.40,1.21,0.83,1.379,2.60,9.06,0.88,1.16,0.64,8.28, 5,8,93,56),
data3 =c(0,34,43,0,0,56,0,0,0,45,5,8,93,56),
data4 =c(45,0,545,34,0,35,0,35,0,534, 5,8,93,56),
stringsAsFactors = FALSE
)
emp.data2 <- data.frame(
data1 = c(45, 0, 0, 45, 45, 53),
data2 = c(23, 0, 45, 12, 90, 78),
data3 = c(72, 45, 756, 78, 763, 98),
data4 = c(1, 3, 65, 78, 9, 45),
stringsAsFactors = FALSE
)
I am trying to do bootstrapping(n=1000). Values are selected at random replacement from emp.data1(14 * 4) without change in the emp.data2(6 * 4). For example from emp.data2 first column (data1) select 6 values colSum and from emp.data1(data1) select 6 random non zero values colSum Divide the values and store in temp repeat the same 1000 times and take a median value et the end. like this i want to do it for each column of the dataframe. sample code I am providing which is working fine but i am not able get the non-zero random values for emp.data1
nboot <- 1e3
boot_temp_emp<- c()
n_data1 <- nrow(emp.data1); n_data2 <- nrow(emp.data2)
for (j in seq_len(nboot)) {
boot <- sample(x = seq_len(n_data1), size = n_data2, replace = TRUE)
value <- colSums(emp.data2)/colSums(emp.data1[boot,])
boot_temp_emp <- rbind(boot_temp_emp, value)
}
boot_data<- apply(boot_temp_emp, 2, median)
From the above script i am able get the output but each column emp.data1[boot,] data has zero values and taken sum. I want indivisual ramdomly selected non-zero values column sum so I tried below script not able remove zero values. Not able get desired output please some one help me to correct my script
nboot <- 1e3
boot_temp_emp<- c()
for (i in colnames(emp.data2)){
for (j in seq_len(nboot)){
data1=emp.data1[i]
data2=emp.data2[i]
n_data1 <- nrow(data1); n_data2 <- nrow(data2)
boot <- sample(x = seq_len(n_data1), size = n_data2, replace = TRUE)
value <- colSums(data2[i])/colSums(data1[boot, ,drop = FALSE])
boot_temp_emp <- rbind(boot_temp_emp, value)
}
}
boot_data<- apply(boot_temp_emp, 2, median)
Thank you
Here is a solution.
Write a function to make the code clearer. This function takes the following arguments.
x the input data.frame emp.data1;
s2 the columns sums of emp.data2;
n = 6 the number of vector elements to sample from emp.data1's columns with a default value of 6.
The create a results matrix, pre-compute the column sums of emp.data2 and call the function in a loop.
boot_fun <- function(x, s2, n = 6){
# the loop makes sure ther is no divide by zero
nrx <- nrow(x)
repeat{
i <- sample(nrx, n, replace = TRUE)
s1 <- colSums(x[i, ])
if(all(s1 != 0)) break
}
s2/s1
}
set.seed(2022)
nboot <- 1e3
sums2 <- colSums(emp.data2)
results <- matrix(nrow = nboot, ncol = ncol(emp.data1))
for(i in seq_len(nboot)){
results[i, ] <- boot_fun(emp.data1, sums2)
}
ratios_medians <- apply(results, 2, median)
old_par <- par(mfrow = c(2, 2))
for(j in 1:4) {
main <- paste0("data", j)
hist(results[, j], main = main, xlab = "ratios", freq = FALSE)
abline(v = ratios_medians[j], col = "blue", lty = "dashed")
}
par(old_par)
Created on 2022-02-24 by the reprex package (v2.0.1)
Edit
Following the comments here is a revised version of the bootstrap function. It makes sure there are no zeros in the sampled vectors, before computing their sums.
boot_fun2 <- function(x, s2, n = 6){
nrx <- nrow(x)
ncx <- ncol(x)
s1 <- numeric(ncx)
for(j in seq.int(ncx)) {
repeat{
i <- sample(nrx, n, replace = TRUE)
if(all(x[i, j] != 0)) {
s1[j] <- sum(x[i, j])
break
}
}
}
s2/s1
}
set.seed(2022)
nboot <- 1e3
sums2 <- colSums(emp.data2)
results2 <- matrix(nrow = nboot, ncol = ncol(emp.data1))
for(i in seq_len(nboot)){
results2[i, ] <- boot_fun2(emp.data1, sums2)
}
ratios_medians2 <- apply(results2, 2, median)
old_par <- par(mfrow = c(2, 2))
for(j in 1:4) {
main <- paste0("data", j)
hist(results2[, j], main = main, xlab = "ratios", freq = FALSE)
abline(v = ratios_medians2[j], col = "blue", lty = "dashed")
}
par(old_par)
Created on 2022-02-27 by the reprex package (v2.0.1)

create multiple train, val, test splits using sample

I want to create train, val, test splits (60:20:20). I repeated the process multiple times.
Test set should contain only 2 observations each time. But why does it sometimes contain 1 or 3 observations.
What is role of replace in sample(). Should I keep it FALSE
library(dplyr)
tbl <- tibble(id = 1:10)
train = list()
val = list()
test = list()
for (run in 1:5)
{
assignment <- sample(1:3, size = nrow(tbl), prob = c(0.6, 0.2, 0.2), replace = TRUE)
# Create a train, validation and test sets
train[[run]] <- tbl[assignment == 1, ]
val[[run]] <- tbl[assignment == 2, ]
test[[run]] <- tbl[assignment == 3, ]
}
If we exactly 6, 2, 2, values for 1, 2, 3 as sample, just replicate the 1, 2, 3 and sample it
v1 <- sample(rep(1:3, c(6, 2, 2)))
Then do a split
split(tbl, v1)
When we use prob, it can change the frequency slightly because it is just a probability. Regarding the use of replace = TRUE, it is needed in the OP's code as the length of 1:3 is just 3, whereas size = nrow(tbl) is 10, thus without replacement, it can't fill those 7 extra elements

Finding index of array of matrices, that is closest to each element of another matrix in R

I have an array Q which has size nquantiles by nfeatures by nfeatures. In this, essentially the slice Q[1,,] would give me the first quantile of my data, across all nfeatures by nfeatures of my data.
What I am interested in, is using another matrix M (again of size nfeatures by nfeatures) which represents some other data, and asking the question to which quantile do each of the elements in M lie in Q.
What would be the quickest way to do this?
I reckon I could do double for loop across all rows and columns of the matrix M and come up with a solution similar to this: Finding the closest index to a value in R
But doing this over all nfeatures x nfeatures values will be very inefficient. I am hoping that there might exist a vectorized way of approaching this problem, but I am at a lost as to how to approach this.
Here is a reproducible way of the slow way I can approach the problem with O(N^2) complexity.
#Generate some data
set.seed(235)
data = rnorm(n = 100, mean = 0, sd = 1)
list_of_matrices = list(matrix(data = data[1:25], ncol = 5, nrow = 5),
matrix(data = data[26:50], ncol = 5, nrow = 5),
matrix(data = data[51:75], ncol = 5, nrow = 5),
matrix(data = data[76:100], ncol = 5, nrow = 5))
#Get the quantiles (5 quantiles here)
Q <- apply(simplify2array(list_of_matrices), 1:2, quantile, prob = c(seq(0,1,length = 5)))
#dim(Q)
#Q should have dims nquantiles by nfeatures by nfeatures
#Generate some other matrix M (true-data)
M = matrix(data = rnorm(n = 25, mean = 0, sd = 1), nrow = 5, ncol = 5)
#Loop through rows and columns in M to find which index of the array matches up closest with element M[i,j]
results = matrix(data = NA, nrow = 5, ncol = 5)
for (i in 1:nrow(M)) {
for (j in 1:ncol(M)) {
true_value = M[i,j]
#Subset Q to the ith and jth element (vector of nqauntiles)
quantiles = Q[,i,j]
results[i,j] = (which.min(abs(quantiles-true_value)))
}
}
'''

Looping a function in R

I have written a cross validation/grid search style code in R that tries to find an optimal threshold value for a given value of mtry (using the random forest algorithm). I have posted my code below using the Sonar data from the library mlbench However, there seems to be some problems with this code.
library(caret)
library(mlbench)
library(randomForest)
res <- matrix(0, nrow = 10, ncol = 6)
colnames(res) <- c("mtry","Threshhold","Accuracy", "PositivePred", "NegativePred", "F-value")
out <- matrix(0, nrow = 17, ncol = 6)
colnames(out) <- c("mtry","Threshhold","Avg.Accuracy", "Avg.PosPred", "Avg.NegPred", "Avg.F_Value")
rep <- matrix(0, nrow = 10, ncol = 6)
colnames(out) <- c("mtry","Threshhold","Avg_Accuracy", "Avg_PosPred", "Avg_NegPred", "Avg_F_Value")
data(Sonar)
N=Sonar
### creating 10 folds
folds <- cut(seq(1,nrow(N)),breaks=10,labels=FALSE)
for (mtry in 5:14) {
K=mtry-4
for(thresh in seq(1,9,0.5)) {
J = 2*thresh-1
dataset<-N[sample(nrow(N)),] #### mix up the dataset N
for(I in 1:10){
#Segement your data by fold using the which() function
testIndexes <- which(folds==I,arr.ind=TRUE)
N_test <- dataset[testIndexes, ] ### select each fold for test
N_train <- dataset[-testIndexes, ] ### select rest for training
rf = randomForest(Class~., data = N_train, mtry=mtry, ntree=500)
pred = predict(rf, N_test, type="prob")
label = as.factor(ifelse(pred[,2]>=thresh,"M","R"))
confusion = confusionMatrix(N_test$Class, label)
res[I,1]=mtry
res[I,2]=thresh
res[I,3]=confusion$overall[1]
res[I,4]=confusion$byClass[3]
res[I,5]=confusion$byClass[4]
res[I,6]=confusion$byClass[7]
}
print(res)
out[J,1] = mtry
out[J,2] = thresh
out[J,3] = mean(res[,2])
out[J,4] = mean(res[,3])
out[J,5] = mean(res[,4])
out[J,6] = mean(res[,5])
}
print(out)
rep[K,1] = mtry
rep[K,2] = thresh
rep[K,3] = mean(out[,2])
rep[K,4] = mean(out[,3])
rep[K,5] = mean(out[,4])
rep[K,6] = mean(out[,5])
}
print(rep)
Earlier, I wrote a similar code with the "iris" dataset, and I did not seem to have any problems:
library(caret)
library(randomForest)
data(iris)
N <- iris
N$Species = ifelse(N$Species == "setosa", "a", "b")
N$Species = as.factor(N$Species)
res <- matrix(0, nrow = 10, ncol = 5)
colnames(res) <- c("Threshhold","Accuracy", "PositivePred", "NegativePred", "F-value")
out <- matrix(0, nrow = 9, ncol = 5)
colnames(out) <- c("Threshhold","Avg.Accuracy", "Avg.PosPred", "Avg.NegPred", "Avg.F_Value")
### creating 10 folds
folds <- cut(seq(1,nrow(N)),breaks=10,labels=FALSE)
for(J in 1:9) {
thresh = J/10
dataset<-N[sample(nrow(N)),] #### mix up the dataset N
for(I in 1:10){
#Segement your data by fold using the which() function
testIndexes <- which(folds==I,arr.ind=TRUE)
N_test <- dataset[testIndexes, ] ### select each fold for test
N_train <- dataset[-testIndexes, ] ### select rest for training
rf = randomForest(Species~., data = N_train, mtry=3, ntree=10)
pred = predict(rf, N_test, type="prob")
label = as.factor(ifelse(pred[,1]>=thresh,"a","b"))
confusion = confusionMatrix(N_test$Species, label)
res[I,1]=thresh
res[I,2]=confusion$overall[1]
res[I,3]=confusion$byClass[3]
res[I,4]=confusion$byClass[4]
res[I,5]=confusion$byClass[7]
}
print(res)
out[J,1] = thresh
out[J,2] = mean(res[,2])
out[J,3] = mean(res[,3])
out[J,4] = mean(res[,4])
out[J,5] = mean(res[,5])
}
print(out)
Could someone please assist me in debugging the first code?
Thanks
You need to close parenthesis ) in your for loop.
Replace this
for(thresh in seq(1,9,0.5) {
with
for(thresh in seq(1,9,0.5)) {
Update:
Also, it appears that your thresh is always above 1 giving a single value R in the label, as it is never above thresh.
label = as.factor(ifelse(pred[,2]>=thresh,"M","R"))
and that creates a problem in the next statement
confusion = confusionMatrix(N_test$Class, label)
I tested with 0.5, and I get no error.
label = as.factor(ifelse(pred[,2]>=0.5,"M","R"))
If you can define a better thresh - to stay between 0 and 1, you should be fine.

Divide vector with grouping vector

I have two vectors, which I would like to combine in one dataframe. One of the vectors values needs to be divided into two columns. The second vector nc informs about the number of values for each observation. If nc is 1, only one value is given in values (which goes into val1) and 999 is to be written in the second column (val2).
What is an r-ish way to divide vector value and populate the two columns of df? I suspect I miss something very obvious, but can't proceed at the moment...Many thanks!
set.seed(123)
nc <- sample(1:2, 10, replace = TRUE)
value <- sample(1:6, sum(nc), replace = TRUE)
# result by hand
df <- data.frame(nc = nc,
val1 = c(6, 3, 4, 1, 2, 2, 6, 5, 6, 5),
val2 = c(999, 5, 999, 6, 1, 999, 6, 4, 4, 999))
Here's an approach based on this answer:
set.seed(123)
nc <- sample(1:2, 10, replace = TRUE)
value <- sample(1:6, sum(nc), replace = TRUE)
splitUsing <- function(x, pos) {
unname(split(x, cumsum(seq_along(x) %in% cumsum(replace(pos, 1, pos[1] + 1)))))
}
combineValues <- function(vals, nums) {
mydf <- data.frame(cbind(nums, do.call(rbind, splitUsing(vals, nums))))
mydf$V3[mydf$nums == 1] <- 999
return(mydf)
}
df <- combineValues(value, nc)
I think this is what you are looking for. I'm not sure it is the fastest way, but it should do the trick.
count <- 0
for (i in 1:length(nc)) {
count <- count + nc[i]
if(nc[i]==1) {
df$val1[i] <- value[count]
df$val2[i] <- 999
} else {
df$val1[i] <- value[count-1]
df$val2[i] <- value[count]
}
}

Resources