Merging two df One to Many within List - R - r

To start I will ignore the use of lists and show what I want using two df's.
I have df1
ID v1 Join_ID
1 100 1
2 110 2
3 150 3
And df2
Join_ID Type v2
1 a 80
1 b 90
2 a 70
2 b 60
3 a 50
3 b 40
I want the df.join to be:
ID v1 Join_ID a_v2 b_v2
1 100 1 80 90
2 110 2 70 60
3 150 3 50 40
I have tried:
df.merged <- merge(df1, df2, by="Join_ID")
df.wide <- dcast(melt(df.merged, id.vars=c("ID", "type")), ID~variable+type)
But this repeats all the variables in df1 for each type: v1_a v1_b
On top of this I have two lists
list.1
df1_a
df1_b
df1_c
list.2
df2_a
df2_b
df2_c
And I want the df1_a in list 1 to join with the df2_a in list 2

We can do this with maping through the list elements and then do the join
library(tidyverse)
map2(list.1, list.2, ~
.y %>%
mutate(Type = paste0(Type, "_v2")) %>%
spread(Type, v2) %>%
inner_join(.x, by = 'Join_ID'))
data
df1 <- structure(list(ID = 1:3, v1 = c(100L, 110L, 150L), Join_ID = 1:3),
.Names = c("ID",
"v1", "Join_ID"), class = "data.frame", row.names = c(NA, -3L
))
df2 <- structure(list(Join_ID = c(1L, 1L, 2L, 2L, 3L, 3L), Type = c("a",
"b", "a", "b", "a", "b"), v2 = c(80L, 90L, 70L, 60L, 50L, 40L
)), .Names = c("Join_ID", "Type", "v2"), class = "data.frame", row.names = c(NA,
-6L))
list.1 <- list(df1_a = df1, df1_b = df1, df1_c = df1)
list.2 <- list(df2_a = df2, df2_b = df2, df2_c = df2)

Some replies to your request :
1. the reshaping of df2
2. the join with different column names
library(reshape2)
df1=data.frame(id=c(1,2,3), v1=c(100,110,150))
df2=data.frame(Join_ID=c(1,1,2,2,3,3),Type=c("a","b","a","b","a","b"),v2=c(80,90,70,60,50,40))
cast_df2=dcast(df2, Join_ID ~ Type)
mergedData <- full_join(df1,cast_df2, by=c("id"="Join_ID"),suffixes=c("_df1","_df2") )

Related

How to collapse rows by identical values in a column

Good evening,
I have a two columns tab separated .txt file, as the following:
number letter
1 a
1 b
2 a
2 b
3 b
I would like to collapse rows where the column "number" has identical value, by creating a comma separated value in the corresponding column "letter".
In other words, this should be the output:
number letter
1 a,b
2 a,b
3 b
I have looked up the web but I did not find an actual solution.
Thank you in advance,
Giuseppe
We can use aggregate in base R
aggregate(letter ~ number, df1, FUN = paste, collapse=",")
-output
# number letter
#1 1 a,b
#2 2 a,b
#3 3 b
Or with tidyverse
library(dplyr)
library(stringr)
df1 %>%
group_by(number) %>%
summarise(letter = str_c(letter, collapse=","))
data
df1 <- structure(list(number = c(1L, 1L, 2L, 2L, 3L), letter = c("a",
"b", "a", "b", "b")), class = "data.frame", row.names = c(NA,
-5L))
We can also combine aggregate() with toString:
#Code
newdf <- aggregate(letter~.,df,toString)
Output:
number letter
1 1 a, b
2 2 a, b
3 3 b
Some data:
#Data
df <- structure(list(number = c(1L, 1L, 2L, 2L, 3L), letter = c("a",
"b", "a", "b", "b")), class = "data.frame", row.names = c(NA,
-5L))

dplyr join with three data frame

I have 3 data frames as like this
df1 <- structure(list(Vehicle = c("Car1", "Car2", "Car8"), Year = c(20L,
21L, 20L), type = c("A", "A", "A")), class = "data.frame", row.names = c(NA, -3L))
df2 <- structure(list(Vehicle = c("Car1", "Car2", "Car7"), Year = c(20L,
21L, 90L), type = c("M", "M", "M")), class = "data.frame", row.names = c(NA, -3L))
df3 <- structure(list(Vehicle = c("Car1", "Car2", "Car9"), Year = c(20L,
21L, 92L), type = c("I", "I", "I")), class = "data.frame", row.names = c(NA, -3L))
And I need to make a new table as follows
Vehicle Year type
Car1 20 A/M/I
Car2 21 A/M/I
Car7 90 M
Car8 20 A
Car9 92 I
for this purpose I used this code using dplyr as like this, but it is not working with 3 data frames:
dplyr::full_join(df1, df2, df3, by = c('Vehicle', 'Year')) %>%
tidyr::unite(type, type.x, type.y, sep = '/', na.rm = TRUE)
Try this approach. Instead of merging it looks like you want to combine all dataframes and then aggregate. Here the code using dplyr:
library(dplyr)
#Code
newdf <- bind_rows(df1,df2,df3) %>%
group_by(Vehicle,Year) %>%
summarise(type=paste0(type,collapse='|'))
Output:
# A tibble: 5 x 3
# Groups: Vehicle [5]
Vehicle Year type
<chr> <int> <chr>
1 Car1 20 A|M|I
2 Car2 21 A|M|I
3 Car7 90 M
4 Car8 20 A
5 Car9 92 I
Generally, to merge >2 data.frame's/tibble's you'd use either base R's Reduce or purrr::reduce; for example using the latter:
list(df1, df2, df3) %>%
purrr::reduce(dplyr::full_join, by = c("Vehicle", "Year")) %>%
tidyr::unite(type, dplyr::starts_with("type"), sep = "/", na.rm = TRUE)
# Vehicle Year type
#1 Car1 20 A/M/I
#2 Car2 21 A/M/I
#3 Car8 20 A
#4 Car7 90 M
#5 Car9 92 I
Using base R
aggregate(type ~ Vehicle + Year, rbind(df1, df2, df3) ,
FUN = paste, collapse="|")
-output
# Vehicle Year type
#1 Car1 20 A|M|I
#2 Car8 20 A
#3 Car2 21 A|M|I
#4 Car7 90 M
#5 Car9 92 I

Replace a subset of data frame

I have a data frame with some error
T item V1 V2
1 a 2 .1
2 a 5 .8
1 b 1 .7
2 b 2 .2
I have another data frame with corrections for items concerning V1 only
T item V1
1 a 2
2 a 6
How do I get the final data frame? Should I use merge or rbind. Note: actual data frames are big.
An option would be a data.table join on the 'T', 'item' and assigning the 'V1' with the the corresponding 'V1' column (i.V1) from the second dataset
library(data.table)
setDT(df1)[df2, V1 := i.V1, on = .(T, item)]
df1
# T item V1 V2
#1: 1 a 2 0.1
#2: 2 a 6 0.8
#3: 1 b 1 0.7
#4: 2 b 2 0.2
data
df1 <- structure(list(T = c(1L, 2L, 1L, 2L), item = c("a", "a", "b",
"b"), V1 = c(2L, 5L, 1L, 2L), V2 = c(0.1, 0.8, 0.7, 0.2)),
class = "data.frame", row.names = c(NA, -4L))
df2 <- structure(list(T = 1:2, item = c("a", "a"), V1 = c(2L, 6L)),
class = "data.frame", row.names = c(NA,
-2L))
This should work -
library(dplyr)
df1 %>%
left_join(df2, by = c("T", "item")) %>%
mutate(
V1 = coalesce(as.numeric(V1.y), as.numeric(V1.x))
) %>%
select(-V1.x, -V1.y)

Manipulating all split data sets

I'm drawing a blank-- I have 51 sets of split data from a data frame that I had, and I want to take the mean of the height of each set.
print(dataset)
$`1`
ID Species Plant Height
1 A 1 42.7
2 A 1 32.5
$`2`
ID Species Plant Height
3 A 2 43.5
4 A 2 54.3
5 A 2 45.7
...
...
...
$`51`
ID Species Plant Height
134 A 51 52.5
135 A 51 61.2
I know how to run each individually, but with 51 split sections, it would take me ages.
I thought that
mean(dataset[,4])
might work, but it says that I have the wrong number of dimensions. I get now why that is incorrect, but I am no closer to figuring out how to average all of the heights.
The dataset is a list. We could use lapply/sapply/vapply etc to loop through the list elements and get the mean of the 'Height' column. Using vapply, we can specify the class and length of the output (numeric(1)). This will be useful for debugging.
vapply(dataset, function(x) mean(x[,4], na.rm=TRUE), numeric(1))
# 1 2 51
#37.60000 47.83333 56.85000
Or another option (if we have the same columnames/number of columns for the data.frames in the list), would be to use rbindlist from data.table with the optionidcol=TRUEto generate a singledata.table. The '.id' column shows the name of thelistelements. We group by '.id' and get themeanof theHeight`.
library(data.table)
rbindlist(dataset, idcol=TRUE)[, list(Mean=mean(Height, na.rm=TRUE)), by = .id]
# .id Mean
#1: 1 37.60000
#2: 2 47.83333
#3: 51 56.85000
Or a similar option as above is unnest from library(tidyr) to return a single dataset with the '.id' column, grouped by '.id', we summarise to get the mean of 'Height'.
library(tidyr)
library(dplyr)
unnest(dataset, .id) %>%
group_by(.id) %>%
summarise(Mean= mean(Height, na.rm=TRUE))
# .id Mean
#1 1 37.60000
#2 2 47.83333
#3 51 56.85000
The syntax for plyr is
df1 <- unnest(dataset, .id)
ddply(df1, .(.id), summarise, Mean=mean(Height, na.rm=TRUE))
# .id Mean
#1 1 37.60000
#2 2 47.83333
#3 51 56.85000
data
dataset <- structure(list(`1` = structure(list(ID = 1:2, Species = c("A",
"A"), Plant = c(1L, 1L), Height = c(42.7, 32.5)), .Names = c("ID",
"Species", "Plant", "Height"), class = "data.frame", row.names = c(NA,
-2L)), `2` = structure(list(ID = 3:5, Species = c("A", "A", "A"
), Plant = c(2L, 2L, 2L), Height = c(43.5, 54.3, 45.7)), .Names = c("ID",
"Species", "Plant", "Height"), class = "data.frame", row.names = c(NA,
-3L)), `51` = structure(list(ID = 134:135, Species = c("A", "A"
), Plant = c(51L, 51L), Height = c(52.5, 61.2)), .Names = c("ID",
"Species", "Plant", "Height"), class = "data.frame", row.names = c(NA,
-2L))), .Names = c("1", "2", "51"))
This also works, though it uses dplyr.
library(dplyr)
1:length(dataset) %>%
lapply(function(i)
test[[i]] %>%
mutate(section = i ) ) %>%
bind_rows %>%
group_by(section) %>%
summarize(mean_height = mean(height) )

Reduce() in R over similar variable names causing error

I have 19 nested lists generated from a lapply and split operation.
These lists are in the form:
#list1
Var col1 col2 col3
A 2 3 4
B 3 4 5
#list2
Var col1 col2 col3
A 5 6 7
B 5 4 4
......
#list19
Var col1 col2 col3
A 3 6 7
B 7 4 4
I have been able to merge the lists with
merge.all <- function(x, y) merge(x, y, all=TRUE, by="Var")
out <- Reduce(merge.all, DataList)
I am however getting an error due to the similarity in the names of the other columns.
How can I concatenate the name of the list to the variable names so that I get something like this:
Var list1.col1 list1.col2 list1.col3 .......... list19.col3
A 2 3 4 7
B 3 4 5 .......... 4
I'm really sure somebody will come up with a much, much better solution. However, if you're after a quick and dirty solution, this seems to work.
My plan was to simply change the column names prior to merging.
#Sample Data
df1 <- data.frame(Var = c("A","B"), col1 = c(2,3), col2 = c(3,4), col3 = c(4,5))
df2 <- data.frame(Var = c("A","B"), col1 = c(5,5), col2 = c(6,4), col3 = c(7,5))
df19 <- data.frame(Var = c("A","B"), col1 = c(3,7), col2 = c(6,4), col3 = c(7,4))
mylist <- list(df1, df2, df19)
names(mylist) <- c("df1", "df2", "df19") #just manually naming, presumably your list has names
## Change column names by pasting name of dataframe in list with standard column names. - using ugly mix of `lapply` and a `for` loop:
mycolnames <- colnames(df1)
mycolnames1 <- lapply(names(mylist), function(x) paste0(x, mycolnames))
for(i in 1:length(mylist)){
colnames(mylist[[i]]) <- mycolnames1[[i]]
colnames(mylist[[i]])[1] <- "Var" #put Var back in so you can merge
}
## Merge
merge.all <- function(x, y)
merge(x, y, all=TRUE, by="Var")
out <- Reduce(merge.all, mylist)
out
# Var df1col1 df1col2 df1col3 df2col1 df2col2 df2col3 df19col1 df19col2 df19col3
#1 A 2 3 4 5 6 7 3 6 7
#2 B 3 4 5 5 4 5 7 4 4
There you go - it works but is very ugly.
To set the data frame names unique, you could use a function to set all list names that are not the merging variable to unique names.
resetNames <- function(x, byvar = "Var") {
asrl <- as.relistable(lapply(x, names))
allnm <- names(unlist(x, recursive = FALSE))
rpl <- replace(allnm, unlist(asrl) %in% byvar, byvar)
Map(setNames, x, relist(rpl, asrl))
}
Reduce(merge.all, resetNames(dlist))
# Var list1.col1 list1.col2 list1.col3 list2.col1 list2.col2 list2.col4 list3.col1
#1 A 2 3 4 5 6 7 3
#2 B 3 4 5 5 4 4 7
# list3.col2 list3.col3 list4.col1 list4.col2 list4.col3
#1 6 7 3 6 7
#2 4 4 4 5 6
when run your list with an added data frame there are no warnings. And there's always data table. Its merge method does not return a warning for duplicated column names.
library(data.table)
Reduce(merge.all, lapply(dlist, as.data.table))
Another option is to check the names as the data enters the function, change them there, and then you can avoid the warning. This isn't perfect but it works ok here.
merge.all <- function(x, y) {
m <- match(names(y)[-1], gsub("[.](x|y)$", "", names(x)[-1]), 0L)
names(y)[-1][m] <- paste0(names(y)[-1][m], "DUPE")
merge(x, y, all=TRUE, by="Var")
}
rm <- Reduce(merge.all, dlist)
names(rm)
# [1] "Var" "col1" "col2" "col3" "col1DUPE.x"
# [6] "col2DUPE.x" "col4" "col1DUPE.y" "col2DUPE.y" "col3DUPE.x"
# [11] "col1DUPE" "col2DUPE" "col3DUPE.y"
where dlist is
structure(list(list1 = structure(list(Var = structure(1:2, .Label = c("A",
"B"), class = "factor"), col1 = 2:3, col2 = 3:4, col3 = 4:5), .Names = c("Var",
"col1", "col2", "col3"), class = "data.frame", row.names = c(NA,
-2L)), list2 = structure(list(Var = structure(1:2, .Label = c("A",
"B"), class = "factor"), col1 = c(5L, 5L), col2 = c(6L, 4L),
col4 = c(7L, 4L)), .Names = c("Var", "col1", "col2", "col4"
), class = "data.frame", row.names = c(NA, -2L)), list3 = structure(list(
Var = structure(1:2, .Label = c("A", "B"), class = "factor"),
col1 = c(3L, 7L), col2 = c(6L, 4L), col3 = c(7L, 4L)), .Names = c("Var",
"col1", "col2", "col3"), class = "data.frame", row.names = c(NA,
-2L)), list4 = structure(list(Var = structure(1:2, .Label = c("A",
"B"), class = "factor"), col1 = 3:4, col2 = c(6L, 5L), col3 = c(7L,
6L)), .Names = c("Var", "col1", "col2", "col3"), row.names = c(NA,
-2L), class = "data.frame")), .Names = c("list1", "list2", "list3",
"list4"))

Resources