I have a dataframe df
df <- data.frame(id =c(1,2,1,4,1,5,6),
label=c("a","b", "a", "a","a", "e", "a"),
color = c("g","a","g","g","a","a","a"),
threshold = c(12, 10, 12, 12, 12, 35, 40),
value =c(32.1,0,15.0,10,1,50,45),stringsAsFactors = F
)
Threshold value is based on the label
I should get a table below like this by considering each id,with respective label how many times exceeding its threshold by the value
Color is independent in consideration for calculating the exceed values
I tried like this
final_df <- df %>%
mutate(check = if_else(value > threshold, 1, 0)) %>%
group_by(id, label) %>%
summarise(exceed = sum(check))
But instead of getting with respective id i have got the number of total in exceed
With base R only, use aggregate.
aggregate(seq.int(nrow(df)) ~ id + label, df, function(i) sum(df[i, 4] < df[i, 5]))
# id label seq.int(nrow(df))
#1 1 a 2
#2 4 a 0
#3 6 a 1
#4 2 b 0
#5 5 e 1
In order to match the expected output posted in the question, it will take a little extra work.
exceed <- seq.int(nrow(df))
agg <- aggregate(exceed ~ id + label, df, function(i) sum(df[i, 4] < df[i, 5]))
res <- merge(df[1:3], agg)
unique(res)
# id label color exceed
#1 1 a g 2
#3 1 a a 2
#4 2 b a 0
#5 4 a g 0
#6 5 e a 1
#7 6 a a 1
By a small modification of your code:
df %>%
group_by(id, label) %>%
mutate(check = if_else(value > threshold, 1, 0)) %>%
summarise(exceed = sum(check)) %>%
group_by(id, label)
id label exceed
<dbl> <chr> <dbl>
1 1 a 2
2 2 b 0
3 4 a 0
4 5 e 1
5 6 a 1
To match the expected output more closely:
df %>%
group_by(id, label) %>%
mutate(exceed = sum(if_else(value > threshold, 1, 0))) %>%
group_by(id, label, color) %>%
filter(row_number() == 1)
id label color threshold value exceed
<dbl> <chr> <chr> <dbl> <dbl> <dbl>
1 1 a g 12 32.1 2
2 2 b a 10 0 0
3 4 a g 12 10 0
4 1 a a 12 1 2
5 5 e a 35 50 1
6 6 a a 40 45 1
library(dplyr)
df %>%
group_by(id, label) %>%
mutate(exceed = sum(value > threshold)) %>%
slice(1)
id label color threshold value exceed
<dbl> <chr> <chr> <dbl> <dbl> <int>
1 1 a g 12 32.1 2
2 2 b a 10 0 0
3 4 a g 12 10 0
4 5 e a 35 50 1
5 6 a a 40 45 1
If you like the output to contain a separate row for each combination, of ID, label and color, just add a new group_by before the slice function:
df %>%
group_by(id, label) %>%
mutate(exceed = sum(value > threshold)) %>%
group_by(id, label, color) %>%
slice(1)
id label color threshold value exceed
<dbl> <chr> <chr> <dbl> <dbl> <int>
1 1 a a 12 1 2
2 1 a g 12 32.1 2
3 2 b a 10 0 0
4 4 a g 12 10 0
5 5 e a 35 50 1
6 6 a a 40 45 1
A little change in your code
final_df <- df %>% mutate(check = if_else(value > threshold, 1, 0)) %>% group_by(id, label) %>% filter(check==1)
unique(final_df$id)
We could use table and merge :
table_ <- table(subset(df,value>threshold, c("id","label")))
df2 <- merge(unique(df[c("id","label","color")]),table_,all.x=TRUE)
df2$Freq[is.na(df2$Freq)] <- 0
# id label color Freq
# 1 1 a g 2
# 2 1 a a 2
# 3 2 b a 0
# 4 4 a g 0
# 5 5 e a 1
# 6 6 a a 1
Related
I have a dataframe like below, which contains the body lengths and the observed counts of species A and B at each station
> set.seed(10)
> df <- data.frame(
+ species = c(rep("A",4), rep("B",4)),
+ station = rep(1:2, 4),
+ length = round(rnorm(8, 15, 2)),
+ count = round(rnorm(8, 5, 2))
+ )
> df
species station length count
1 A 1 15 2
2 A 2 15 4
3 A 1 12 7
4 A 2 14 7
5 B 1 16 5
6 B 2 16 7
7 B 1 13 6
8 B 2 14 5
What I want to do is to transform this into a table with 2cm bins like this. But how can I get this?
> cnt_table <- data.frame(
+ species = c("A","A","B","B"),
+ station = c(1,2,1,2),
+ L11_12 = c(0,0,0,0),
+ L13_14 = c(7,7,6,5),
+ L15_16 = c(2,4,5,7),
+ L17_18 = c(0,0,0,0),
+ L19_20 = c(0,0,0,0)
+ )
> cnt_table
species station L11_12 L13_14 L15_16 L17_18 L19_20
1 A 1 0 7 2 0 0
2 A 2 0 7 4 0 0
3 B 1 0 6 5 0 0
4 B 2 0 5 7 0 0
First, you need to use cut to bin the lengths. Then you can use complete to fill the missing counts with 0. Then, group_by species, station and bin and use summarize to add the counts per group. Last, use pivot_wider to make the bins column labels.
Note 1: The result differs from your expected output, but I think you have a typo.
Note 2: I don't know if teh grouping and summing is necessary. In your example it's not, but logically I would include it.
library(tidyverse)
set.seed(10)
df <- data.frame(
species = c(rep("A",4), rep("B",4)),
station = rep(1:2, 4),
length = round(rnorm(8, 15, 2)),
count = round(rnorm(8, 5, 2))
)
df
#---------------------
df %>%
mutate(length = cut(length,
breaks = seq(10.5, 20.5, by = 2),
labels = c("L11_12", "L13_14", "L15_16", "L17_18", "L19_20"))) %>%
complete(species, station, length, fill = list(count = 0)) %>%
group_by(species, station, length) %>%
summarize(count = sum(count)) %>%
pivot_wider(names_from = length, values_from = count)
#---------------------
# A tibble: 4 x 7
# Groups: species, station [4]
species station L11_12 L13_14 L15_16 L17_18 L19_20
<chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
1 A 1 7 0 2 0 0
2 A 2 0 7 4 0 0
3 B 1 0 6 5 0 0
4 B 2 0 5 7 0 0
a data.table approach that should scale well
library(data.table)
# create alookup table with categories
lookup <- data.table(
name = paste0("L", seq(11, 19, 2), "_", seq(12,20, 2)),
from = seq(11, 19, 2),
to = seq(12,20, 2)
)
lookup
# join with a non-equi join
setDT(df)[lookup, name := i.name, on = .(length >= from, length <= to)]
# spreak to wide
dcast(df, species + station ~ name, value.var = "count", fun.aggregate = sum)
# species station L11_12 L13_14 L15_16
# 1: A 1 7 0 2
# 2: A 2 0 7 4
# 3: B 1 0 6 5
# 4: B 2 0 5 7
You can do something like:
library(dplyr)
library(tidyr)
# Create the bins
df$bin <- cut(df$length, breaks = seq(from = min(df$length-1), to = max(df$length)+1, by = 2))
# Get the data frame into shape
df |>
mutate(
bin_start = substr(bin, 2,3),
bin_end = as.numeric(substr(bin, 5,6))-1,
bin_name = paste0("L", bin_start, "_", bin_end)) |>
group_by(species, station, bin_name) |>
summarise(n = n()) |>
pivot_wider(
names_from = bin_name,
values_from = n,
values_fill = list(n = 0)
)
# A tibble: 4 x 5
# Groups: species, station [4]
# species station L11_12 L13_14 L15_16
# <chr> <int> <int> <int> <int>
# 1 A 1 1 1 0
# 2 A 2 0 2 0
# 3 B 1 1 0 1
# 4 B 2 0 1 1
Define your desired range r, i.e. 11:20 as shown in OP (length should be even!). Then match df$lengh with a helper-matrix m to get bins, calculate aggregated sums and reshape to wide format, e.g. using reshape2::dcast.
r <- 11:20; m <- matrix(r, ncol=2, byrow=TRUE)
transform(df, bin=factor(sapply(df$length, \(z) which(rowSums(z == m) > 0)),
levels=seq_along(x), labels=apply(m, 1, paste, collapse='_'))) |>
aggregate(count ~ bin + species + station, sum) |>
reshape2::dcast(species + station ~ bin, value.var='count', drop=FALSE, fill=0)
# species station 11_12 13_14 15_16 17_18 19_20
# 1 A 1 7 0 2 0 0
# 2 A 2 0 7 4 0 0
# 3 B 1 0 6 5 0 0
# 4 B 2 0 5 7 0 0
I am trying to filter a data set to only include subjects who have data in all conditions (levels of a factor).
I have tried to filter by calculating the number of levels for each subject, but that does not work.
library(tidyverse)
Data <- data.frame(
Subject = factor(c(rep(1, 3),
rep(2, 3),
rep(3, 1))),
Condition = factor(c("A", "B", "C",
"A", "B", "C",
"A")),
Val = c(1, 0, 1,
0, 0, 1,
1)
)
Data %>%
semi_join(
.,
Data %>%
group_by(Subject) %>%
summarize(Num_Cond = length(levels(Condition))) %>%
filter(Num_Cond == 3),
by = "Subject"
)
This attempt yields:
Subject Condition Val
1 1 A 1
2 1 B 0
3 1 C 1
4 2 A 0
5 2 B 0
6 2 C 1
7 3 A 1
Desired output:
Subject Condition Val
1 1 A 1
2 1 B 0
3 1 C 1
4 2 A 0
5 2 B 0
6 2 C 1
I want to filter subject 3 out because they only have data for one condition.
Is there a dplyr/tidyverse approach for this problem?
We can create a condition with all and levels
library(dplyr)
Data %>%
group_by(Subject) %>%
filter(all(levels(Condition) %in% Condition))
# A tibble: 6 x 3
# Groups: Subject [2]
# Subject Condition Val
# <fct> <fct> <dbl>
#1 1 A 1
#2 1 B 0
#3 1 C 1
#4 2 A 0
#5 2 B 0
#6 2 C 1
Or with n_distinct and nlevels
Data %>%
group_by(Subject) %>%
filter(nlevels(Condition) == n_distinct(Condition))
# A tibble: 6 x 3
# Groups: Subject [2]
# Subject Condition Val
# <fct> <fct> <dbl>
#1 1 A 1
#2 1 B 0
#3 1 C 1
#4 2 A 0
#5 2 B 0
#6 2 C 1
Here is a solution testing wether the number of rows of each groupis equal to the number of levels of Condition.
Data %>%
group_by(Subject) %>%
filter(n() == nlevels(Condition))
## A tibble: 6 x 3
## Groups: Subject [2]
# Subject Condition Val
# <fct> <fct> <dbl>
#1 1 A 1
#2 1 B 0
#3 1 C 1
#4 2 A 0
#5 2 B 0
#6 2 C 1
Edit
Following the comment by user #akrun I tested with a data set having duplicate values for each row and the code above does fail.
bind_rows(Data, Data) %>%
group_by(Subject) %>%
#distinct() %>%
filter(n() == nlevels(Condition))
## A tibble: 0 x 3
## Groups: Subject [0]
## ... with 3 variables: Subject <fct>, Condition <fct>, Val <dbl>
To run the commented out code line would solve the problem.
I found a relatively simple solution by sub-setting on Subject:
Data %>%
semi_join(
.,
Data %>%
group_by(Subject) %>%
droplevels() %>%
summarize(Num_Cond = length(levels(Condition)[Subject])) %>%
filter(Num_Cond == 3),
by = "Subject"
)
This gives the desired output:
Subject Condition Val
1 1 A 1
2 1 B 0
3 1 C 1
4 2 A 0
5 2 B 0
6 2 C 1
I have a dataframe...
df <- tibble(
id = 1:7,
family = c("a","a","b","b","c", "d", "e")
)
Families will only contain 2 members at most (so they're either individuals or pairs).
I need a new column 'random' that assigns the number 1 to families where there is only one member (e.g. c, d and e) and randomly assigns 0 or 1 to families containing 2 members (a and b in the example).
By the end the data should look like the following (depending on the random assignment of 0/1)...
df <- tibble(
id = 1:7,
family = c("a","a","b","b","c", "d", "e"),
random = c(1, 0, 0, 1, 1, 1, 1)
)
I would like to be able to do this with a combination of group_by and mutate since I am mostly using Tidyverse.
I tried the following (but this didn't randomly assign 0/1 within families)...
df %>%
group_by(family) %>%
mutate(
random = if_else(
condition = n() == 1,
true = 1,
false = as.double(sample(0:1,1,replace = T))
)
You could sample along the sequence length of the family group and take the answer modulo 2:
df %>%
group_by(family) %>%
mutate(random = sample(seq(n())) %% 2)
#> # A tibble: 7 x 3
#> # Groups: family [5]
#> id family random
#> <int> <chr> <dbl>
#> 1 1 a 0
#> 2 2 a 1
#> 3 3 b 0
#> 4 4 b 1
#> 5 5 c 1
#> 6 6 d 1
#> 7 7 e 1
We can use if/else
library(dplyr)
df %>%
group_by(family) %>%
mutate(random = if(n() == 1) 1 else sample(rep(0:1, length.out = n())))
# A tibble: 7 x 3
# Groups: family [5]
# id family random
# <int> <chr> <dbl>
#1 1 a 0
#2 2 a 1
#3 3 b 1
#4 4 b 0
#5 5 c 1
#6 6 d 1
#7 7 e 1
Another option
df %>%
group_by(family) %>%
mutate(random = 2 - sample(1:n()))
# A tibble: 7 x 3
# Groups: family [5]
id family random
# <int> <chr> <dbl>
# 1 1 a 1
# 2 2 a 0
# 3 3 b 1
# 4 4 b 0
# 5 5 c 1
# 6 6 d 1
# 7 7 e 1
Hi all I have a got a 2 datasets below. From these 2 datasets(dataset1 is formed from dataset2. I mean the dataset1 is the count of users from dataset2) can we build the the third datasets(expected output)
dataset1
Apps # user Enteries
A 3
B 4
C 6
dataset2
Apps Users
A X
A Y
A Z
B Y
B Y
B Z
B A
C X
C X
C X
C X
C X
C X
Expected output
Apps Entries X Y Z A
A 3 1 1 1
B 4 2 1 1
C 6 6
We can first count first for Apps and Users, get the data in wide format and join with the table for count of Apps.
library(dplyr)
df %>%
count(Apps, Users) %>%
tidyr::pivot_wider(names_from = Users, values_from = n,
values_fill = list(n = 0)) %>%
left_join(df %>% count(Apps), by = 'Apps')
# Apps X Y Z A n
# <chr> <int> <int> <int> <int> <int>
#1 A 1 1 1 0 3
#2 B 0 2 1 1 4
#3 C 6 0 0 0 6
I showing 0 is no problem and having a different column order you can use table and rowSums to produce the expected output.
x <- table(dataset2)
cbind(Entries=rowSums(x), x)
# Entries A X Y Z
#A 3 0 1 1 1
#B 4 1 0 2 1
#C 6 0 6 0 0
A solution where you need not have to calculate Total separately and do joins...
This solution uses purrr::pmap and dplyr::mutate for dynamically calculating Total.
library(tidyverse) # dplyr, tidyr, purrr
df %>% count(Apps, Users) %>%
pivot_wider(id_cols = Apps, names_from = Users, values_from = n, values_fill = list(n = 0)) %>%
mutate(Total = pmap_int(.l = select_if(., is.numeric),
.f = sum))
which have output what you need
# A tibble: 3 x 6
Apps X Y Z A Total
<chr> <int> <int> <int> <int> <int>
1 A 1 1 1 0 3
2 B 0 2 1 1 4
3 C 6 0 0 0 6
library(tidyverse)
df <- tibble(a = as.factor(1:20), b = c(50, 20, 13, rep(2, 10), rep(1, 7)))
How do I make dplyr look at this data frame df and collapse all these occurences of 2 into a single summed group, and collapse all the occurrences of 1 into a single summed group? And also keep the rest of the data frame.
Turn this:
# A tibble: 20 x 2
a b
<fct> <dbl>
1 1 50
2 2 20
3 3 13
4 4 2
5 5 2
6 6 2
7 7 2
8 8 2
9 9 2
10 10 2
11 11 2
12 12 2
13 13 2
14 14 1
15 15 1
16 16 1
17 17 1
18 18 1
19 19 1
20 20 1
into this:
# A tibble: 5 x 2
a b
<fct> <dbl>
1 1 50
2 2 20
3 3 13
4 grp2 20
5 grp1 7
[Edit] - I fixed the example data. Sorry about that.
We group by a manufactured sortkey to maintain sort order. We used the fact that b is in descending order in the input but if that is not the case in your actual data then replace sortkey = -b with the more general sortkey = data.table::rleid(b) or the longer sortkey = cumsum(coalesce(b != lag(b), FALSE)) .
We also convert b to the group names giving a new a. It wasn't clear which groups are to be converted to grp... form. Hard-coded 1 and 2? Any group with more than one row? Groups at the end with more than one row? At any rate it would be easy enough to change the condition in the if_else once that were clarified.
Finally perform the summation and then remove the sortkey.
df %>%
group_by(sortkey = -b, a = paste0(if_else(b %in% 1:2, "grp", ""), b)) %>%
summarize(b = sum(b)) %>%
ungroup %>%
select(-sortkey)
giving:
# A tibble: 5 x 2
a b
<chr> <int>
1 50 50
2 20 20
3 13 13
4 grp2 20
5 grp1 7
Here's a way. I have converted a from factor to character to make things easier. You can convert it back to factor if you want. Also your test data was a bit wrong.
df <- tibble(a = as.character(1:20), b = c(50, 20, 13, rep(2, 10), rep(1, 7)))
df %>%
mutate(
a = case_when(
b == 1 ~ "grp1",
b == 2 ~ "grp2",
TRUE ~ a
)
) %>%
group_by(a) %>%
summarise(b = sum(b))
# A tibble: 5 x 2
a b
<chr> <dbl>
1 1 50
2 2 20
3 3 13
4 grp1 7
5 grp2 20
This is an approach which gives you the desired names for groups & where you don't need to think in advance how many cases like that you would need (e.g. it would create grp3, grp4, ... depending on the number in b).
library(dplyr)
df %>%
mutate(
grp = as.numeric(lag(df$b) != df$b),
grp = cumsum(ifelse(is.na(grp), 0, grp))
) %>% group_by(grp) %>%
mutate(
a = ifelse(n() > 1, paste0("grp", b), a),
b = sum(b)
) %>% ungroup() %>% distinct(a, b)
Output:
a b
<chr> <dbl>
1 1 50
2 2 20
3 3 13
4 grp2 20
5 grp1 7
Note that the code could be also condensed but that leads to a certain lack of readability in my opinion:
df %>%
group_by(grp = cumsum(ifelse(is.na(as.numeric(lag(df$b) != df$b)), 0, as.numeric(lag(df$b) != df$b)))) %>%
mutate(
a = ifelse(n() > 1, paste0("grp", b), a),
b = sum(b)
) %>% ungroup() %>% distinct(a, b)