Dataframe column to matrix by two other columns - r

I have a dataframe
df<-data.frame(i=rep(1:3,3),j=sort(rep(1:3,3)),v=sample(1:9,9))
df
i j v
1 1 1 3
2 2 1 1
3 3 1 9
4 1 2 8
5 2 2 5
6 3 2 4
7 1 3 7
8 2 3 2
9 3 3 6
that I want to transform to matrix M such that
M[i,j]<-df$v[which(df$i==i & df$j==j)]
is there an easy way to do that?

Based on your description, you can just do,
matrix(df$v, ncol = max(df$j))
# [,1] [,2] [,3]
#[1,] 2 4 7
#[2,] 3 1 5
#[3,] 8 6 9
Data Used:
dput(df)
structure(list(i = c(1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L), j = c(1L,
1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L), v = c(2L, 3L, 8L, 4L, 1L, 6L,
7L, 5L, 9L)), class = "data.frame", row.names = c(NA, -9L))

Related

Subset in R with specific values for specific columns identified by their index number

If I have a data frame like this:
df = data.frame(A = sample(1:5, 10, replace=T), B = sample(1:5, 10, replace=T), C = sample(1:5, 10, replace=T), D = sample(1:5, 10, replace=T), E = sample(1:5, 10, replace=T))
Giving me this:
A B C D E
1 1 5 1 4 3
2 2 3 5 4 3
3 4 2 2 4 4
4 2 1 2 5 2
5 3 3 4 4 5
6 3 2 3 1 5
7 1 5 4 2 3
8 1 3 5 5 1
9 3 1 1 3 5
10 5 3 1 2 4
How do I get a subset that includes all the rows where the values for certain columns (B and D, say) are equal to 1, with the columns identified by their index numbers (2 and 4) rather than their names? In this case:
A B C D E
4 2 1 2 5 2
6 3 2 3 1 5
9 3 1 1 3 5
df[rowSums(df[c(2,4)] == 1) > 0,]
# A B C D E
# 4 2 1 2 5 2
# 6 3 2 3 1 5
# 9 3 1 1 3 5
You said to compare values by column index, so df[c(2,4)] or (or df[,c(2,4)]).
df[c(2,4)] == 1 returns a matrix of logicals, whether the cell's value is equal to 1.
rowSums(.) > 0 finds those rows with at least one 1.
df[rowSums(.)>0,] selects just those rows.
Data
df <- structure(list(A = c(1L, 2L, 4L, 2L, 3L, 3L, 1L, 1L, 3L, 5L), B = c(5L, 3L, 2L, 1L, 3L, 2L, 5L, 3L, 1L, 3L), C = c(1L, 5L, 2L, 2L, 4L, 3L, 4L, 5L, 1L, 1L), D = c(4L, 4L, 4L, 5L, 4L, 1L, 2L, 5L, 3L, 2L), E = c(3L, 3L, 4L, 2L, 5L, 5L, 3L, 1L, 5L, 4L)), class = "data.frame", row.names = c("1", "2", "3", "4", "5", "6", "7", "8", "9", "10"))
tidyverse
df <-
structure(
list(
A = c(1L, 2L, 4L, 2L, 3L, 3L, 1L, 1L, 3L, 5L),
B = c(5L, 3L, 2L, 1L, 3L, 2L, 5L, 3L, 1L, 3L),
C = c(1L, 5L, 2L, 2L, 4L, 3L, 4L, 5L, 1L, 1L),
D = c(4L, 4L, 4L, 5L, 4L, 1L, 2L, 5L, 3L, 2L),
E = c(3L, 3L, 4L, 2L, 5L, 5L, 3L, 1L, 5L, 4L)
),
class = "data.frame",
row.names = c("1", "2", "3", "4", "5", "6", "7", "8", "9", "10")
)
library(tidyverse)
df %>%
filter(B == 1 | D == 1)
#> A B C D E
#> 4 2 1 2 5 2
#> 6 3 2 3 1 5
#> 9 3 1 1 3 5
Created on 2022-01-23 by the reprex package (v2.0.1)
data.table
library(data.table)
setDT(df)[B == 1 | D == 1, ]
#> A B C D E
#> 1: 2 1 2 5 2
#> 2: 3 2 3 1 5
#> 3: 3 1 1 3 5
Created on 2022-01-23 by the reprex package (v2.0.1)

Finding the maximum square sub-matrix with all equal elements

Does anybody know how it could be possible to subset the maximum K such that K x K is a submatrix with all identical elements, i.e., all the elements in this submatrix must be the same from a given a N x N matrix?
I found many examples in other programming languages except R. I also prefer dplyr if you know.
There is a link to the solution with other languages:
https://www.geeksforgeeks.org/maximum-size-sub-matrix-with-all-1s-in-a-binary-matrix/
But this link provides a special case when all identical elements are next to each other. It retrieves a maximum block of the same elements, not a submatrix in general. I do not want to limit subsetting with this condition.
Here is a base R implementation to make it.
If you want to search the maximum square sub-matrix within a non-square matrix, you can try the code below:
r <- list()
for (w in rev(seq(min(dim(M))))) {
for (rs in seq(nrow(M)-w+1)) {
for (cs in seq(ncol(M)-w+1)) {
mat <- M[rs-1+(1:w),cs-1+(1:w)]
u <- unique(c(mat))
if (all(u!=0) &length(u)==1) r[[length(r)+1]] <- mat
}
}
if (length(r)>0) break
}
such that
> r
[[1]]
[,1] [,2]
[1,] 3 3
[2,] 3 3
[[2]]
[,1] [,2]
[1,] 2 2
[2,] 2 2
[[3]]
[,1] [,2]
[1,] 3 3
[2,] 3 3
[[4]]
[,1] [,2]
[1,] 2 2
[2,] 2 2
[[5]]
[,1] [,2]
[1,] 1 1
[2,] 1 1
[[6]]
[,1] [,2]
[1,] 1 1
[2,] 1 1
[[7]]
[,1] [,2]
[1,] 3 3
[2,] 3 3
[[8]]
[,1] [,2]
[1,] 3 3
[2,] 3 3
DATA
M <- structure(c(1L, 3L, 1L, 2L, 1L, 3L, 3L, 2L, 2L, 3L, 3L, 1L, 1L,
1L, 2L, 2L, 2L, 2L, 3L, 1L, 3L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L,
2L, 2L, 1L, 3L, 1L, 3L, 2L, 2L, 2L, 2L, 3L, 2L, 1L, 3L, 2L, 1L,
1L, 3L, 2L, 2L, 3L, 3L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 1L,
3L, 3L, 2L, 3L, 3L, 2L, 3L, 3L, 1L, 1L, 1L, 1L, 3L, 2L, 3L, 1L,
1L, 2L, 1L, 1L, 1L, 1L, 3L, 2L, 1L, 1L, 3L, 3L, 3L, 2L, 2L, 2L,
3L, 2L, 2L, 3L, 3L, 3L, 1L, 2L, 2L, 1L, 3L, 3L, 2L, 3L, 2L, 1L,
2L, 1L, 3L, 3L, 1L, 2L, 1L, 3L, 2L, 3L, 3L, 1L, 1L, 2L, 2L, 2L,
1L, 1L, 1L, 2L, 1L, 3L, 2L, 3L, 3L, 2L, 3L, 3L, 1L, 1L, 2L, 2L,
1L, 2L, 3L, 3L, 3L, 3L, 3L, 1L, 3L), .Dim = c(15L, 10L))
> M
[,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] 1 2 2 1 1 3 2 2 1 3
[2,] 3 2 1 3 3 1 2 3 1 3
[3,] 1 2 3 2 3 1 2 2 2 1
[4,] 2 3 1 2 2 2 3 1 2 1
[5,] 1 1 3 3 3 1 2 2 2 2
[6,] 3 3 2 3 3 1 2 1 1 2
[7,] 3 1 2 2 2 1 3 3 1 1
[8,] 2 1 2 2 3 1 3 3 1 2
[9,] 2 1 2 2 3 3 3 1 2 3
[10,] 3 1 3 2 1 2 1 2 1 3
[11,] 3 2 2 1 1 1 2 1 3 3
[12,] 1 1 1 2 1 1 2 3 2 3
[13,] 1 1 3 2 1 3 1 2 3 3
[14,] 1 2 2 2 3 3 3 3 3 1
[15,] 2 2 1 2 2 3 3 3 2 3
EDIT
The approach above is inefficient when with large matrix since all combinations checked. The method below is a R implementation of algorithm stated in https://www.geeksforgeeks.org/maximum-size-sub-matrix-with-all-1s-in-a-binary-matrix/, which is is far more efficient.
M <- unname(as.matrix(read.csv(file = "test2.csv")))
S <- matrix(0,nrow = nrow(M),ncol = ncol(M))
S[,1] <- M[,1]
for (i in 1:nrow(S)) {
for (j in 2:ncol(S)) {
if (M[i,j]==1) {
if (i==1) {
S[i,j] <- M[i,j]
} else {
S[i,j] <- min(c(S[i,j-1],S[i-1,j],S[i-1,j-1]))+1
}
}
}
}
inds <- which(S == max(S),arr.ind = TRUE)
w <- seq(max(S))-1
res <- lapply(seq(nrow(inds)), function(k) M[inds[k,"row"]-w,inds[k,"col"]-w])
I found the following answer to this question using dplyr:
M1 <- M %>% data.frame %>% mutate(sumVar = rowSums(.)) %>%
arrange(desc(sumVar)) %>% dplyr::select(-sumVar)
M2 <- M1 %>% as.matrix %>% t %>% data.frame %>%
mutate(sumVar = rowSums(.)) %>% arrange(desc(sumVar)) %>%
dplyr::select(-sumVar) %>% as.matrix %>% t %>% data.frame %>%
arrange_all(funs(desc(.)))
i <- 1
j <- 1
while(sum(M2[1:i,1:j]) == i*j){
i <- i+1
j <- j+1
M3 <- M2[1:i-1,1:j-1]
}
This is a toy data as #ThomasIsCoding proposed:
M <- structure(c(1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Dim = c(5L,
5L))
and this is the result:
> M
[,1] [,2] [,3] [,4] [,5]
[1,] 1 1 1 0 1
[2,] 1 1 1 1 1
[3,] 1 1 1 1 1
[4,] 1 1 1 1 1
[5,] 0 1 1 1 1
> M1
X1 X2 X3 X4 X5
1 1 1 1 1 1
2 1 1 1 1 1
3 1 1 1 1 1
4 1 1 1 0 1
5 0 1 1 1 1
> M2
X1 X2 X3 X4 X5
1 1 1 1 1 1
2 1 1 1 1 1
3 1 1 1 1 1
4 1 1 1 1 0
5 1 1 1 0 1
> M3
X1 X2 X3 X4
1 1 1 1 1
2 1 1 1 1
3 1 1 1 1
4 1 1 1 1
Note that some more functions should be added to keep the variable names and find them after using arrange!

how to select specific row by a column

I have a data, as an example I show below
a = rep(1:5, each=3)
b = rep(c("a","b","c","a","c"), each = 3)
df = data.frame(a,b)
I want to select all the rows that have the "a"
I tried to do it with
df[df$a %in% a,]
Can someone give me an idea how to get them out?
df2<- structure(list(V1 = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), V2 = structure(c(1L,
2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 1L, 2L, 3L, 4L,
5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L), .Label = c("B02", "B03",
"B04", "B05", "B06", "B07", "C02", "C03", "C04", "C05", "C06",
"C07"), class = "factor")), .Names = c("V1", "V2"), class = "data.frame", row.names = c(NA,
-24L))
I want to select specific rows that start with B but not all of them and just 02, 03, 04, 05
1 B02
1 B03
1 B04
1 B05
2 B02
2 B03
2 B04
2 B05
I also want to have the original data without them too
We need to check the 'b' column
df[df$b %in% 'a',]
For the updated question with 'df2', we can use paste to create the strings 'B02' to 'B05' and use %in% to subset
df2[df2$V2 %in% paste0("B0", 2:5),]
Or another option is grep
df2[grep("^B0[2-5]$", df2$V2),]
> df
a b
1 1 a
2 1 a
3 1 a
4 2 b
5 2 b
6 2 b
7 3 c
8 3 c
9 3 c
10 4 a
11 4 a
12 4 a
13 5 c
14 5 c
15 5 c
This basically says:
For all columns in df choose rows that have value equal to a
> rows_with_a<-df[df$b=='a', ]
> rows_with_a
a b
1 1 a
2 1 a
3 1 a
10 4 a
11 4 a
12 4 a

How to select every 5 other observations in R? [duplicate]

This question already has answers here:
Subset dataframe by multiple logical conditions of rows to remove
(8 answers)
Closed 6 years ago.
I have a dataset that contains 10 "houses" with energy production for every minute of the day. Like so:
HouseID Time KwH
1 1 X
2 1 X
3 1 X
4 1 X
5 1 X
6 1 X
7 1 X
8 1 X
9 1 X
10 1 X
1 2 X
2 2 X
3 2 X
4 2 X
5 2 X
6 2 X
7 2 X
8 2 X
9 2 X
10 2 X
I would like to delete the rows with houseIDs 6 until 10 so that I would be left with only the observations of houseID 1,2,3,4 and 5.
You can try
newdf <- df1[!df1$HouseID %in% 6:10,]
# HouseID Time KwH
#1 1 1 X
#2 2 1 X
#3 3 1 X
#4 4 1 X
#5 5 1 X
#11 1 2 X
#12 2 2 X
#13 3 2 X
#14 4 2 X
#15 5 2 X
data
df1 <- structure(list(HouseID = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L,
10L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L), Time = c(1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L), KwH = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "X",
class = "factor")), .Names = c("HouseID", "Time", "KwH"),
class = "data.frame", row.names = c(NA, -20L))
Assuming df is the name of your data frame then just use the following:
df2 <- subset(df, df$HouseID==1:5)

count frequency based on values in 2 or more columns

I have a pretty simple question but I can't think of a way to do this without using if statements
The data I have looks something like:
df <- structure(list(years = c(1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L,
1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L), id = c(1L, 1L, 1L, 1L, 1L,
1L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L), x = structure(c(2L,
1L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L,
1L), .Label = c("E", "I"), class = "factor")), .Names = c("years",
"id", "x"), class = "data.frame", row.names = c(NA, -18L))
so the table looks like:
years id x
1 1 1 I
2 2 1 E
3 3 1 E
4 1 1 E
5 2 1 I
6 3 1 I
7 1 2 I
8 2 2 E
9 3 2 I
10 1 2 E
11 2 2 E
12 3 2 I
13 1 3 I
14 2 3 E
15 3 3 I
16 1 3 I
17 2 3 I
18 3 3 E
I would like the output to report the fraction of x's that are "I" for each id and each year:
years id xnew
1 1 1 0.5
2 2 1 0.5
3 3 1 0.5
4 1 2 0.5
5 2 2 0.0
6 3 2 1.0
7 1 3 1.0
8 2 3 0.5
9 3 3 0.5
Any help would be greatly appreciated! Thank you!
aggregate(x ~ years + id, data=df, function(y) sum(y=="I")/length(y) )
years id x
1 1 1 0.5
2 2 1 0.5
3 3 1 0.5
4 1 2 0.5
5 2 2 0.0
6 3 2 1.0
7 1 3 1.0
8 2 3 0.5
9 3 3 0.5

Resources