Pivot longer with mutliple data points in a single column - r

I have a data frame containing a varying number of data points in the same column:
library(tidyverse)
df <- tribble(~id, ~data,
"A", "a;b;c",
"B", "e;f")
I want to obtain one row per data point, separating the content of column data and distributing it on rows. This code gives the expected result, but is clumsy:
df %>%
separate(data,
into = paste0("dat_",1:5),
sep = ";",
fill = "right") %>%
pivot_longer(starts_with("dat_"),
names_to = "data_number",
names_pattern = "dat_(\\d+)") %>%
filter(!is.na(value))
#> # A tibble: 5 x 3
#> id data_number value
#> <chr> <chr> <chr>
#> 1 A 1 a
#> 2 A 2 b
#> 3 A 3 c
#> 4 B 1 e
#> 5 B 2 f
Tidyverse solutions preferred.

Here is one way
library(dplyr)
library(tidyr)
library(data.table)
df %>%
separate_rows(data) %>%
mutate(data_number = rowid(id), .before = 2)
-output
# A tibble: 5 x 3
id data_number data
<chr> <int> <chr>
1 A 1 a
2 A 2 b
3 A 3 c
4 B 1 e
5 B 2 f

library(dplyr)
library(tidyr)
df %>%
separate_rows(data)
output:
# A tibble: 5 x 2
id data
<chr> <chr>
1 A a
2 A b
3 A c
4 B e
5 B f

Using str_split and unnest -
library(tidyverse)
df %>%
mutate(data = str_split(data, ';'),
data_number = map(data, seq_along)) %>%
unnest(c(data, data_number))
# id data data_number
# <chr> <chr> <int>
#1 A a 1
#2 A b 2
#3 A c 3
#4 B e 1
#5 B f 2

Related

Count co-occurrences of two words but the order is not important in r

WHAT I WANT: I want to count co-occurrence of two words. But I don't care the order they appear in the string.
MY PROBLEM: I don't know how to deal When two given words appear in different order.
SO FAR: I use unnest_token function to split the string by words using the "skip_ngrams" option for the token argument. Then I filtered the combination of exactly two words. I use separate to create word1 and word2 columns. Finally, I count the occurrence.
The output that I get is like this:
# A tibble: 3 × 3
word1 word2 n
<chr> <chr> <dbl>
1 a c 3
2 b a 1
3 c a 5
But words "a" and "c" occur in a different order so they are counted as a different element. What I want is this:
# A tibble: 2 × 3
word1 word2 n
<chr> <chr> <dbl>
1 a c 8
2 b a 1
MY DATA: My data looks like this and this is the whole process with different data but the same problem. In this case "a b" and "c a" should take a value of n = 2.
library(tidyverse)
library(tidytext)
enframe(c("a b c a d e")) %>%
unnest_tokens(skipgram, value, token = "skip_ngrams", n = 5) %>%
mutate(n_words = str_count(skipgram, pattern = "\\S+")) %>%
filter(n_words == 2) %>%
separate(col = skipgram, into = c("word1", "word2"), sep = "\\s+") %>%
count(word1, word2)
#> # A tibble: 9 × 3
#> word1 word2 n
#> <chr> <chr> <int>
#> 1 a b 1
#> 2 a c 1
#> 3 a d 1
#> 4 a e 1
#> 5 b a 1
#> 6 b c 1
#> 7 c a 1
#> 8 c d 1
#> 9 d e 1
Created on 2022-02-09 by the reprex package (v2.0.1)
We may use pmin/pmax to sort the columns by row before applying the count
library(tidytext)
library(dplyr)
library(stringr)
library(tidyr)
enframe(c("a b c a d e")) %>%
unnest_tokens(skipgram, value, token = "skip_ngrams", n = 5) %>%
mutate(n_words = str_count(skipgram, pattern = "\\S+")) %>%
filter(n_words == 2) %>%
separate(col = skipgram, into = c("word1", "word2"),
sep = "\\s+") %>%
transmute(word11 = pmin(word1, word2), word22 = pmax(word1, word2)) %>%
count(word11, word22)
-output
# A tibble: 7 × 3
word11 word22 n
<chr> <chr> <int>
1 a b 2
2 a c 2
3 a d 1
4 a e 1
5 b c 1
6 c d 1
7 d e 1
The pmin/pmax approach by #akrun is super efficient. Here is another option with igraph
library(tidytext)
library(dplyr)
library(stringr)
library(tidyr)
library(igraph)
enframe(c("a b c a d e")) %>%
unnest_tokens(skipgram, value, token = "skip_ngrams", n = 5) %>%
mutate(n_words = str_count(skipgram, pattern = "\\S+")) %>%
filter(n_words == 2) %>%
separate(col = skipgram, into = c("word1", "word2"), sep = "\\s+") %>%
count(word1, word2) %>%
graph_from_data_frame(directed = FALSE) %>%
simplify(edge.attr.comb = "sum") %>%
get.data.frame()
which gives
from to n
1 a b 2
2 a c 2
3 a d 1
4 a e 1
5 b c 1
6 c d 1
7 d e 1

a beautiful solution to decode a table with dplyr and mutate

Dear dplyr/tidyverse companions, I am looking for a nice solution to the following problem. I only get my solutions in base R with a loop. How do you solve this cleanly in tidyverse?
I have a dataset called data, which has not useful column names and not useful values (integer).
data <- tibble(var1 = rep(c(1:3), 2),
var2 = rep(c(1:3), 2))
# A tibble: 6 x 2
var1 var2
<int> <int>
1 1 1
2 2 2
3 3 3
4 1 1
5 2 2
6 3 3
Additional I have a coding table, which has for every column a better name (var1 -> variable1) and a better value (1 -> "a")
coding <- tibble(variable = c(rep("var1", 3),rep("var2", 3)),
name = c(rep("variable1", 3),rep("variable2", 3)),
code = rep(c(1:3), 2),
value = rep(c("a", "b", "c"), 2))
# A tibble: 6 x 4
variable name code value
<chr> <chr> <int> <chr>
1 var1 variable1 1 a
2 var1 variable1 2 b
3 var1 variable1 3 c
4 var2 variable2 1 a
5 var2 variable2 2 b
6 var2 variable2 3 c
I'm looking for a result, which has transformed names of the columns and the real values as factors in the dataset, compare:
result <- tibble(variable1 = factor(rep(c("a", "b", "c"), 2)),
variable2 = factor(rep(c("a", "b", "c"), 2)))
# A tibble: 6 x 2
variable1 variable2
<fct> <fct>
1 a a
2 b b
3 c c
4 a a
5 b b
6 c c
Thank you for your commitment :) :) :) :)
library(dplyr)
library(tidyr)
data %>%
stack() %>%
left_join(coding, by = c(ind = "variable", values = "code")) %>%
group_by(name) %>%
mutate(j = row_number()) %>%
pivot_wider(id_cols = j, values_from = value) %>%
select(-j)
# # A tibble: 6 x 2
# variable1 variable2
# <chr> <chr>
# 1 a a
# 2 b b
# 3 c c
# 4 a a
# 5 b b
# 6 c c
A general solution for any number of columns -
create a row number column to identify each row
get data in long format
join it with coding for each value
keep only unique rows and get it back in wide format.
library(dplyr)
library(tidyr)
data %>%
mutate(row = row_number()) %>%
pivot_longer(cols = -row, values_to = 'code') %>%
left_join(coding, by = 'code') %>%
select(row, name = name.y, value) %>%
distinct() %>%
pivot_wider() %>%
select(-row)
# variable1 variable2
# <chr> <chr>
#1 a a
#2 b b
#3 c c
#4 a a
#5 b b
#6 c c

How to get all combinations of 2 from a grouped column in a data frame

I could write a loop to do this, but I was wondering how this might be done in R with dplyr. I have a data frame with two columns. Column 1 is the group, Column 2 is the value. I would like a data frame that has every combination of two values from each group in two separate columns. For example:
input = data.frame(col1 = c(1,1,1,2,2), col2 = c("A","B","C","E","F"))
input
#> col1 col2
#> 1 1 A
#> 2 1 B
#> 3 1 C
#> 4 2 E
#> 5 2 F
and have it return
output = data.frame(col1 = c(1,1,1,2), col2 = c("A","B","C","E"), col3 = c("B","C","A","F"))
output
#> col1 col2 col3
#> 1 1 A B
#> 2 1 B C
#> 3 1 C A
#> 4 2 E F
I'd like to be able to include it within dplyr syntax:
input %>%
group_by(col1) %>%
???
I tried writing my own function that produces a data frame of combinations like what I need from a vector and sent it into the group_map function, but didn't have success:
combos = function(x, ...) {
x = t(combn(x, 2))
return(as.data.frame(x))
}
input %>%
group_by(col1) %>%
group_map(.f = combos)
Produced an error.
Any suggestions?
You can do :
library(dplyr)
data <- input %>%
group_by(col1) %>%
summarise(col2 = t(combn(col2, 2)))
cbind(data[1], data.frame(data$col2))
# col1 X1 X2
# <dbl> <chr> <chr>
#1 1 A B
#2 1 A C
#3 1 B C
#4 2 E F
input %>%
group_by(col1) %>%
nest(data=-col1) %>%
mutate(out= map(data, ~ t(combn(unlist(.x), 2)))) %>%
unnest(out) %>% select(-data)
# A tibble: 4 x 2
# Groups: col1 [2]
col1 out[,1] [,2]
<dbl> <chr> <chr>
1 1 A B
2 1 A C
3 1 B C
4 2 E F
Or :
combos = function(x, ...) {
return(tibble(col1=x[[1,1]],col2=t(combn(unlist(x[[2]], use.names=F), 2))))
}
input %>%
group_by(col1) %>%
group_map(.f = combos, .keep=T) %>% invoke(rbind,.) %>% tibble
# A tibble: 4 x 2
col1 col2[,1] [,2]
<dbl> <chr> <chr>
1 1 A B
2 1 A C
3 1 B C
4 2 E F
Thank you! In terms of parsimony, I like both the answer from Ben
input %>%
group_by(col1) %>%
do(data.frame(t(combn(.$col2, 2))))
and Ronak
data <- input %>%
group_by(col1) %>%
summarise(col2 = t(combn(col2, 2)))
cbind(data[1], data.frame(data$col2))

R how to 'spread' data with no key-value pair

I have data:
rowID incidentID participant.type
1 1 A
2 1 B
3 2 A
4 3 A
5 3 B
6 3 C
7 4 B
8 4 C
And I would like to end up with:
rowID incident participant.type participant.type.1 participant.type.2
1 1 A B
2 2 A
3 3 A B C
4 4 B C
I tried the spread but can't achieve one line per incident; I don't think I have a way of creating a key-value pair so I wonder if there is some other method for doing this.
Before using spread(), you need to create a proper key argument.
df %>% select(-rowID) %>%
group_by(incidentID) %>%
mutate(id = 1:n()) %>%
spread(id, participant.type)
# incidentID `1` `2` `3`
# <int> <fct> <fct> <fct>
# 1 1 A B NA
# 2 2 A NA NA
# 3 3 A B C
# 4 4 B C NA
Since your grouping is based on the row order within the icidentID column. The following simple solution will also work.
It is just filtering the dataframe and then merging in the end.
It is probably not the best solution in terms of effective use of computing power, but it is easy to understand.
library(tidyverse)
df <-
tribble(
~rowID, ~incidentID, ~participant.type,
1, 1, "A",
2, 1, "B",
3, 2, "A",
4, 3, "A",
5, 3, "B",
6, 3, "C",
7, 4, "B",
8, 4, "C")
df_1 <- df %>%
select(-rowID) %>%
group_by(incidentID) %>%
filter(row_number()==1)
df_2 <- df %>%
select(-rowID) %>%
group_by(incidentID) %>%
filter(row_number()==2) %>%
rename(participant.type.1 = participant.type)
df_3 <- df %>%
select(-rowID) %>%
group_by(incidentID) %>%
filter(row_number()==3) %>%
rename(participant.type.2 = participant.type)
full_join(df_1, full_join(df_2, df_3))
Result:
Joining, by = "incidentID"
Joining, by = "incidentID"
# A tibble: 4 x 4
# Groups: incidentID [?]
incidentID participant.type participant.type.1 participant.type.2
<dbl> <chr> <chr> <chr>
1 1 A B NA
2 2 A NA NA
3 3 A B C
4 4 B C NA
Here's my solution:
df %>%
select(-rowID) %>%
group_by(incidentID) %>%
nest() %>%
mutate(data = map_chr(data, ~str_c(.x$participant.type, collapse = '_'))) %>%
separate(data, paste0('participant.type.', 0:2)) %>%
mutate_at(2:4, ~replace_na(.x, ''))
We can use reshape2::dcast for this
reshape2::dcast(df, insidentID ~ participant.type)
# insidentID A B C
# 1 1 <NA> B <NA>
# 2 8 <NA> B <NA>
# 3 12 <NA> <NA> C
# 4 16 A <NA> <NA>
# 5 24 <NA> B <NA>
# 6 27 <NA> B C
# 7 29 <NA> <NA> C
with the data
set.seed(123)
df <- data.frame(insidentID = sample(0:30, 8L, replace = TRUE),
participant.type = sample(LETTERS[1:3], 8L, replace = TRUE),
stringsAsFactors = FALSE)
df
# insidentID participant.type
# 1 8 B
# 2 24 B
# 3 12 C
# 4 27 B
# 5 29 C
# 6 1 B
# 7 16 A
# 8 27 C
The 'related question' link provided by #markus shows a variety of other solutions, including what appears to be the most concise in a tidyverse format:
df %>%
group_by(incidentID) %>%
mutate(rn = paste0("newcolumn",row_number())) %>%
spread(rn, participant.type)
gives:
incidentID newcolumn1 newcolumn2 newcolumn3
<int> <fct> <fct> <fct>
1 1 A B NA
2 2 A NA NA
3 3 A B C
4 4 B C NA
A

Sum multiple variables by group and create new column with their sum

I have a data frame with grouped variable and I want to sum them by group. It's easy with dplyr.
library(dplyr)
library(magrittr)
data <- data.frame(group = c("a", "a", "b", "c", "c"), n1 = 1:5, n2 = 2:6)
data %>% group_by(group) %>%
summarise_all(sum)
# A tibble: 3 x 3
group n1 n2
<fctr> <int> <int>
1 a 3 5
2 b 3 4
3 c 9 11
But now I want a new column total with the sum of n1 and n2 by group. Like this:
# A tibble: 3 x 3
group n1 n2 ttl
<fctr> <int> <int> <int>
1 a 3 5 8
2 b 3 4 7
3 c 9 11 20
How can I do that with dplyr?
EDIT:
Actually, it's just an example, I have a lot of variables.
I tried these two codes but it's not in the right dimension...
data %>% group_by(group) %>%
summarise_all(sum) %>%
summarise_if(is.numeric, sum)
data %>% group_by(group) %>%
summarise_all(sum) %>%
mutate_if(is.numeric, .funs = sum)
You can use mutate after summarize:
data %>%
group_by(group) %>%
summarise_all(sum) %>%
mutate(tt1 = n1 + n2)
# A tibble: 3 x 4
# group n1 n2 tt1
# <fctr> <int> <int> <int>
#1 a 3 5 8
#2 b 3 4 7
#3 c 9 11 20
If need to sum all numeric columns, you can use rowSums with select_if (to select numeric columns) to sum columns up:
data %>%
group_by(group) %>%
summarise_all(sum) %>%
mutate(tt1 = rowSums(select_if(., is.numeric)))
# A tibble: 3 x 4
# group n1 n2 tt1
# <fctr> <int> <int> <dbl>
#1 a 3 5 8
#2 b 3 4 7
#3 c 9 11 20
We can use apply together with the dplyr functions.
data <- data.frame(group = c("a", "a", "b", "c", "c"), n1 = 1:5, n2 = 2:6)
data %>% group_by(group) %>%
summarise_all(sum) %>%
mutate(ttl = apply(.[, 2:ncol(.)], 1, sum))
# A tibble: 3 × 4
group n1 n2 ttl
<fctr> <int> <int> <int>
1 a 3 5 8
2 b 3 4 7
3 c 9 11 20
Or rowSums with the same strategy. The key is to use . to specify the data frame and [] with x:ncol(.) to keep the columns you want.
data %>% group_by(group) %>%
summarise_all(sum) %>%
mutate(ttl = rowSums(.[, 2:ncol(.)]))
# A tibble: 3 × 4
group n1 n2 ttl
<fctr> <int> <int> <dbl>
1 a 3 5 8
2 b 3 4 7
3 c 9 11 20
Base R
cbind(aggregate(.~group, data, sum), ttl = sapply(split(data[,-1], data$group), sum))
# group n1 n2 ttl
#a a 3 5 8
#b b 3 4 7
#c c 9 11 20
We can use data.table. Convert the 'data.frame' to 'data.table' (setDT(data)), grouped by 'group', get the sum of each columns in the Subset of data.table, and then with Reduce, get the sum of the rows of the columns of interest
library(data.table)
setDT(data)[, lapply(.SD, sum) , group][, tt1 := Reduce(`+`, .SD),
.SDcols = names(data)[-1]][]
# group n1 n2 tt1
#1: a 3 5 8
#2: b 3 4 7
#3: c 9 11 20
Or with base R
addmargins(as.matrix(rowsum(data[-1], data$group)), 2)
# n1 n2 Sum
#a 3 5 8
#b 3 4 7
#c 9 11 20
Or with dplyr
data %>%
group_by(group) %>%
summarise_all(sum) %>%
mutate(tt = rowSums(.[-1]))

Resources