Related
I want to calculate the mean of column and and also concatenate the texts in second column output.
for example in below i want to calculate the mean of C1 and then concatenate all texts in C1T in next column if there is more than one text in C1T.
df <- data.frame(A1 = c("class","type","class","type","class","class","class","class","class"),
B1 = c("b2","b3","b3","b1","b3","b3","b3","b2","b1"),
C1=c(6, NA, 1, 6, NA, 1, 6, 6, 2),
C1T=c(NA, "Part of other business", NA, NA, NA, NA, NA, NA, NA),
C2=c(NA, 4, 1, 2, 4, 4, 3, 3, NA),
C2T=c(NA, NA, NA, NA, NA, NA, NA, NA, NA),
C3=c(3, 4, 3, 3, 6, NA, 2, 4, 1),
C3T=c(NA, NA, NA, NA, "two part are available but not in source", NA, NA, NA, NA),
C4=c(5, 5, 2, NA, NA, 6, 4, 1, 2),
C5T=c(NA, NA, NA, NA, NA, NA, NA, "Critical Expert", NA),
C5=c(6, 2, 6, 4, 2, 2, 5, 4, 1),
C5T=c(NA, NA, NA, NA, NA, "most of things are stuck", "weather responsible", NA, NA))
var <- "C1"
var1 <- "C1T"
var <- rlang::parse_expr(var)
var1 <- rlang::parse_expr(var1)
df1 <- df%>%filter(A1 == "class")
T1<- df1 %>%group_by(B1)%>%summarise(mean=round(mean(!!var,na.rm = TRUE),1))
Comments <- df1 %>% group_by(B1) %>% summarise_at(vars(var1), paste0, collapse = " ") %>%
select(var1) %>% unlist() %>% gsub("NA","",.) %>% stringi::stri_trim_both()
cbind(T1,Comments)
Edited Answer:
var <- "C1"
var1 <- "C1T"
filtercol <- "A1"
filterval <- "class"
groupingvar <- "B1"
var <- rlang::parse_expr(var)
var1 <- rlang::parse_expr(var1)
filtercol <- rlang::parse_expr(filtercol)
groupingvar <- rlang::parse_expr(groupingvar)
library(dplyr)
df1 <- df %>% filter(!!filtercol == filterval)
T1 <- df1 %>% group_by(!!groupingvar) %>% summarise(mean=round(mean(as.numeric(!!var),na.rm = TRUE),1))
Comments <- df1 %>% select(!!groupingvar, !!var1) %>%
group_by(!!groupingvar) %>%
summarise_at(vars(!!var1), paste0, collapse = " ") %>%
select(!!var1) %>% unlist() %>% gsub("NA", "", .) %>%
stringi::stri_trim_both()
T1 <- cbind(T1,Comments)
Update on OP's request (see comments):
library(dplyr)
# helper function to coalesce by column
coalesce_by_column <- function(df) {
return(coalesce(df[1], df[2]))
}
df %>%
pivot_longer(
cols = contains("T"),
names_to = "names",
values_to = "values"
) %>%
filter(names == "C1T") %>%
group_by(names) %>%
summarise(Mean = mean(c_across(C1:C5 & where(is.numeric)), na.rm = TRUE),
Comments = coalesce_by_column(values))
Output:
names Mean Comments
<chr> <dbl> <chr>
1 C1T 3.47 Part of other business
First answer
coalesce to construct Comments column
rowwise with c_across to calculate the mean rowwise.
In case you need to group, you can use ``group_by`
library(dplyr)
df %>%
mutate(Comments = coalesce(C1T, C2T, C3T, C4T, C5T),.keep="unused") %>%
rowwise() %>%
mutate(Mean = mean(c_across(C1:C5 & where(is.numeric)), na.rm = TRUE)) %>%
select(A1, B1, Mean, Comments)
Output:
A1 B1 Mean Comments
<chr> <chr> <dbl> <chr>
1 class b2 5 NA
2 type b3 3.75 Part of other business
3 class b3 2.6 NA
4 type b1 3.75 NA
5 class b3 4 two part are available but not in source
6 class b3 3.25 most of things are stuck
7 class b3 4 weather responsible
8 class b2 3.6 Critical Expert
9 class b1 1.5 NA
So I guess this is possible to achieve by just making a veeery long line code using mutate() and ifelse() but I want to know if there is a way of doing it without writing a tone of code.
I have data where the degree of each individual is written in a non-ordered fashion. The data looks like this:
id <- c(1, 2, 3, 4, 5, 6)
degree1 <- c("masters", "bachelors", "PhD", "bachelors", "bachelors", NA)
degree2 <- c("PhD", "masters", "bachelors", NA, NA, NA)
degree3 <- c("bachelors", NA, "masters", NA, "masters", NA)
Now I want to create a new column containing the string for the highest degree, like this
dat$highest_degree <- c("PhD", "masters", "PhD", "bachelors", "masters", NA)
How can I achieve this?
An option is to loop over the rows for the selected 'degree' column, convert to factor with levels specified in the order, drop the levels to remove the unused levels and select the first level
v1 <- c("PhD", "masters", "bachelors")
dat$highest_degree <- apply(dat[-1], 1, function(x)
levels(droplevels(factor(x, levels = v1)))[1])
dat$highest_degree
#[1] "PhD" "masters" "PhD" "bachelors" "masters" NA
Or using tidyverse, reshape into 'long' format, then slice the first row after arrangeing the long format column by matching with an ordered degree vector and grouping by 'id', then join with the original data
library(dplyr)
library(tidyr)
dat %>%
pivot_longer(cols = starts_with('degree'), values_to = 'highest_degree') %>%
select(-name) %>%
arrange(id, match(highest_degree, v1)) %>%
group_by(id) %>%
slice_head(n = 1) %>%
ungroup %>%
left_join(dat, .)
data
dat <- data.frame(id, degree1, degree2, degree3)
Here is a base R option using pmin + factor
lvs <- c("PhD", "masters", "bachelors")
dat$highest_degree <- lvs[
do.call(
pmin,
c(asplit(matrix(as.integer(factor(as.matrix(dat[-1]), levels = lvs)), nrow(dat)), 2),
na.rm = TRUE
)
)
]
which gives
> dat
id degree1 degree2 degree3 highest_degree
1 1 masters PhD bachelors PhD
2 2 bachelors masters <NA> masters
3 3 PhD bachelors masters PhD
4 4 bachelors <NA> <NA> bachelors
5 5 bachelors <NA> masters masters
6 6 <NA> <NA> <NA> <NA>
Data
> dput(dat)
structure(list(id = c(1, 2, 3, 4, 5, 6), degree1 = c("masters",
"bachelors", "PhD", "bachelors", "bachelors", NA), degree2 = c("PhD",
"masters", "bachelors", NA, NA, NA), degree3 = c("bachelors",
NA, "masters", NA, "masters", NA)), class = "data.frame", row.names = c(NA,
-6L))
I have a dataframe looks like this
df1<-structure(list(person = c("a", "a", "a", "a", "b", "b", "b",
"c"), visitID = c(123, 123, 256, 816, 237, 828, 828, 911), v1 = c(10,
5, 15, 8, 95, 41, 31, 16), v2 = c(8, 72, 29, 12, 70, 23, 28,
66), v3 = c(0, 1, 0, 0, 1, 1, 0, 1)), row.names = c(NA, -8L), class = c("tbl_df",
"tbl", "data.frame"))
Where person is the name/id of the person and visitID is a number generated for each visit. Now each visit may have one or multiple variables (v1, v2, v3). My problem is that I'm trying to transform the structure where cases are aggregated into unique row with wide visits and variables, to look like:
df2<-structure(list(person = c("a", "b", "c"), visit1 = c(123, 237,
911), visit2 = c(256, 828, NA), visit3 = c(816, NA, NA), v1.visit1 = c("10,5",
"95", "16"), v1.visit2 = c("15", "41,31", NA), v1.visit3 = c("8",
NA, NA), v2.visit1 = c("8,72", "70", "66"), v2.visit2 = c("29",
"23,28", NA), v1.visit3 = c("12", NA, NA), v3.visit1 = c("0,1",
"1", "1"), v3.visit2 = c("0", "1,0", NA), v3.visit3 = c("0",
NA, NA)), row.names = c(NA, -3L), class = c("tbl_df", "tbl",
"data.frame"))
Methods I have tried so far:
Method1:
1-aggregate according to "person" with all other variables separated by comma
2-split the variables into multiple columns
The problem with this method is that I would not know then which variable corresponds to which visit, especially that some may have multiple entries and some may not.
Method2:
1-Count number of each visitID. Take the maximum number of visits per unique person (in the case above is 3)
2-Create 3 columns for each variable.
didn't know how to proceed from here
I found a great answer in the thread Reshape three column data frame to matrix ("long" to "wide" format)
so tried working around with reshape and pivot_wider but couldn't get it to work.
Any ideas are appreciated even if did not lead to the same output.
Thank you
You can try something like this:
df1 %>%
group_by(person, visitID) %>%
summarise(across(matches("v[0-9]+"), list)) %>%
group_by(person) %>%
mutate(visit = seq_len(n()) %>% str_c("visit.", .)) %>%
ungroup() %>%
pivot_wider(
id_cols = person,
names_from = visit,
values_from = c("visitID", matches("v[0-9]+"))
)
replace list with ~str_c(.x, collapse = ",") if you want to have it in character style.
I have the following data in messy format:
structure(list(com_level = c("B", "B", "B", "B", "A", "A"),
hf_com = c(1, 1, 1, 1, 1, 1),
sal_level = c("2", "3", "1", "2", "1", "4"),
exp_sal = c(NA, 1, 1, NA, 1, NA)),
class = c("tbl_df", "tbl", "data.frame"),
row.names = c(NA, -6L))
Column com_level is the factor with 2 levels and column hf_com gives the frequency count for that level.
Column sal_level is the factor with 4 levels and column exp_sal gives the frequency count for that level.
I want to create a contingency table similar to this:
structure(list(`1` = c(1L, 2L),
`2` = c(0L, 1L),
`3` = c(0L, 2L),
`4` = c(1L, 0L)),
row.names = c("A", "B"), class = "data.frame")
I have code that works when I want to compare two columns with the same factor:
# 1 step to create table with frequency counts for exp_sal and curr_sal per category of level
cs_es_table <- df_not_na_num %>%
dplyr::count(sal_level, exp_sal, curr_sal) %>%
tidyr::spread(key = sal_level,value = n) %>% # this code spreads on just one key
select(curr_sal, exp_sal, 1, 2, 3, 4, 5, 6, 7, -8) %>% # reorder columns and omit Column 8 (no answer)
as.data.frame()
# step 2- convert cs_es_table to long format and summarise exp_sal and curr_sal frequencies
cs_es_table <- cs_es_table %>%
gather(key, value, -curr_sal,-exp_sal) %>% # crucial step to make data long
mutate(curr_val = ifelse(curr_sal == 1,value,NA),
exp_val = ifelse(exp_sal == 1,value,NA)) %>% #mutate actually cleans up the data and assigns a value to each new column for 'exp' and 'curr'
group_by(key) %>% #for your summary, because you want to sum up your previous rows which are now assigned a key in a new column
summarise_at( .vars = vars(curr_val, exp_val), .funs = sum, na.rm = TRUE)
This code produces this table but just spreads on one key in step 1:
structure(list(curr_val = c(533L, 448L, 237L, 101L, 56L), exp_val = c(179L,
577L, 725L, 401L, 216L)), row.names = c("< 1000 EUR", "1001-1500 EUR",
"2001-3000 EUR", "3001-4000 EUR", "4001-5000 EUR"), class = "data.frame")
Will I need to use pivot_wider as in this example?
Is it possible to use spread on multiple columns in tidyr similar to dcast?
or
tidyr::spread() with multiple keys and values
Any help would be appreciated to compare the two columns with different factors.
Variables are mistakenly being entered into multiple columns eg: "aaa_1", "aaa_2" and "aaa_3", or "ccc_1, "ccc_2", and "ccc_3"). Need to create single new columns (eg "aaa", or "ccc"). Some variables are currently in a single column though ("hhh_1"), but more columns may be added (hhh_2 etc).
This is what I got:
aaa_1 <- c(43, 23, 65, NA, 45)
aaa_2 <- c(NA, NA, NA, NA, NA)
aaa_3 <- c(NA, NA, 92, NA, 82)
ccc_1 <- c("fra", NA, "spa", NA, NA)
ccc_2 <- c(NA, NA, NA, "wez", NA)
ccc_3 <- c(NA, "ija", NA, "fda", NA)
ccc_4 <- c(NA, NA, NA, NA, NA)
hhh_1 <- c(183, NA, 198, NA, 182)
dataf1 <- data.frame(aaa_1,aaa_2,aaa_3,ccc_1,ccc_2, ccc_3,ccc_4,hhh_1)
This is what I want:
aaa <- c(43, 23, NA, NA, NA)
ccc <- c("fra", "ija", "spa", NA, NA)
hhh <- c(183, NA, 198, NA, 182)
dataf2 <- data.frame(aaa,ccc,hhh)
General solution needed as there are ~100 variables (eg "aaa", "hhh", "ccc", "ttt", "eee", "hhh"etc).
Thanks!
This is a base solution, i.e. no packages.
First define get_only which when given a list converts it to a data.frame and applies get_only to each row. When given a vector it returns the single non-NA in it or NA if there is not only one.
Define root to be the column names without the suffixes.
Convert the data frame to a list of columns, group them by root and apply get_only to each such group.
Finally, convert the resulting list to a data frame.
get_only <- function(x) UseMethod("get_only")
get_only.list <- function(x) apply(data.frame(x), 1, get_only)
get_only.default <- function(x) if (sum(!is.na(x)) == 1) na.omit(x) else NA
root <- sub("_.*", "", names(dataf1))
as.data.frame(lapply(split(as.list(dataf1), root), FUN = get_only))
giving:
age country hight
1 43 fra 183
2 23 ija NA
3 NA spa 198
4 NA <NA> NA
5 NA <NA> 182
We may try with splitstackshape
library(splitstackshape)
nm1 <- sub("_\\d+", "", names(dataf1))
tbl <- table(nm1) > 1
merged.stack(dataf1, var.stubs = names(tbl)[tbl], sep="_")
I'm not sure your example is right. For example in the third row you've got values for both age_1 and age_3, then in the desired output NA for that row.
If I've understood what you're trying to do though, it will be much easier if you transpose columns to rows, fix them and then transpose back again. Try this as a start point using the 'tidyverse' of dplyr and tidyr.
library(tidyverse)
library(stringr)
age_1 <- c(43, 23, 65, NA, 45)
age_2 <- c(NA, NA, NA, NA, NA)
age_3 <- c(NA, NA, 92, NA, 82)
country_1 <- c("fra", NA, "spa", NA, NA)
country_2 <- c(NA, NA, NA, "wez", NA)
country_3 <- c(NA, "ija", NA, "fda", NA)
country_4 <- c(NA, NA, NA, NA, NA)
hight_1 <- c(183, NA, 198, NA, 182)
dataf1 <- data.frame(age_1,age_2,age_3,country_1,country_2, country_3,country_4,hight_1)
data <- dataf1 %>%
mutate(row_num = row_number()) %>% #create a row number to track values
gather(key, value, -row_num) %>% #flatten your data
drop_na() %>% #drop na rows
mutate(key = str_replace(key, "_.", "")) %>% #remove the '_x' part of names
group_by(row_num) %>%
top_n(1) %>%
spread(key, value) #pivot back to columns
For your example you need the group_by() and top_n() lines to make it run because you've got multiple values in the same row. If you only have one value (as I think you should?) then you can remove these two lines. It will be better without them because then it won't run if your data is wrong.
Edit following comment below. This will make any duplicated entries NA.
data <- dataf1 %>%
mutate(row_num = row_number()) %>% #create a row number to track values
gather(key, value, -row_num) %>% #flatten your data
drop_na() %>% #drop na rows
mutate(key = str_replace(key, "_.", "")) %>% #remove the '_x' part of names
group_by(row_num, key) %>%
mutate(count = n()) %>% #count how many entries for each row/key combo
mutate(value = ifelse(count > 1, NA, value)) %>% #set NA for rows with duplicates
drop_na() %>%
spread(key, value) %>% #pivot back to columns
select(-count) #drop the `count` variable