I have a dataset the following
DT <- data.drame(v1 = c(0,0,0,1,0,0,1))
I want to create a ID cumulatively stopped at a value of 1.
The ID should be
ID<-c(1,2,3,4,1,2,3)
If you are using dplyr, this will do the trick.
DT = data.frame(v1 = c(0,0,0,1,0,0,1))
DT %>%
dplyr::mutate(rno = row_number()) %>%
dplyr::mutate(group = ifelse(v1 == 0, NA, rno)) %>%
tidyr::fill(group, .direction = "up") %>%
dplyr::group_by(group) %>%
dplyr::mutate(ID = row_number()) %>%
dplyr::ungroup() %>%
dplyr::select(v1, ID)
In base R, we can use ave :
with(DT, ave(v1, c(0, cumsum(v1)[-length(v1)]), FUN = seq_along))
#[1] 1 2 3 4 1 2 3
In dplyr , we can use lag to create groups and assign row number in each group.
library(dplyr)
DT %>% group_by(gr = lag(cumsum(v1), default = 0)) %>% mutate(ID = row_number())
and we can use the same logic in data.table :
library(data.table)
setDT(DT)[, ID := seq_len(.N), shift(cumsum(v1), fill = 0)]
Related
I have a df that looks like the following:
ID DATE
12 10-20-20
12 10-22-20
10 10-15-20
9 10-10-20
11 11-01-20
7 11-02-20
I would like to group by month and then create a column for unique id count and repeat id count like below:
MONTH Unique_Count Repeat_Count
10-1-20 2 2
11-1-20 2 0
I am able to get the date down to the first of the month and group by ID but I am not sure how to count unique instances within the months.
df %>%
mutate(month = floor_date(as.Date(DATE), "month")) %>%
group_by(ID) %>%
mutate(count = n())
Are you perhaps looking for:
df %>%
mutate(month = strftime(floor_date(as.Date(DATE, "%m-%d-%y"), "month"),
"%m-%d-%y")) %>%
group_by(month) %>%
summarize(unique_count = length(which(table(ID) == 1)),
repeat_count = sum(table(ID)[(which(table(ID) > 1))]))
#> # A tibble: 2 x 3
#> month unique_count repeat_count
#> <chr> <int> <int>
#> 1 10-01-20 2 2
#> 2 11-01-20 2 0
Here's a shot at it:
library(lubridate)
library(dplyr)
dates <- as.Date(c("2020-10-15", "2020-10-15", "2020-11-16", "2020-11-16", "2020-11-16"))
ids <- c(12, 12, 13, 13, 14)
df <- data.frame(dates, ids)
duplicates <- df %>%
group_by(dates_floored = floor_date(dates, unit = "month"), ids) %>%
mutate(duplicate_count = n()) %>%
filter(duplicate_count > 1) %>%
distinct(ids, .keep_all = TRUE)
uniques <- df %>%
group_by(dates_floored = floor_date(dates, unit = "month"), ids) %>%
mutate(unique_count = n()) %>%
filter(unique_count < 2) %>%
distinct(ids, .keep_all = TRUE)
df_cleaned <- full_join(uniques, duplicates, by = c("ids", "dates", "dates_floored")) %>%
group_by(dates_floored) %>%
summarize(count_duplicates = sum(duplicate_count, na.rm = TRUE),
count_unique = sum(unique_count, na.rm = TRUE))
df_cleaned
I have the following script. Option 1 uses a long format and group_by to identify the first step of many where the status equals 0.
Another option (2) is to use apply to calculate this value for each row, and then transform the data to a long format.
The firs option does not scale well. The second does, but I was unable to get it into a dplyr pipe. I tried to solve this with purrr but did not succeeed.
Questions:
Why does the first option not scale well?
How can I transform the second option in a dplyr pipe?
require(dplyr)
require(tidyr)
require(ggplot2)
set.seed(314)
# example data
dat <- as.data.frame(matrix(sample(c(0,1),
size = 9000000,
replace = TRUE,
prob = c(5,95)),
ncol = 9))
names(dat) <- paste("step",1:9, sep="_")
steps <- dat %>% select(starts_with("step_")) %>% names()
# option 1 is slow
dat.cum <- dat %>%
mutate(id = row_number()) %>%
gather(step, status,-id) %>%
group_by(id) %>%
mutate(drop = min(if_else(status==0,match(step, steps),99L))) %>%
mutate(status = if_else(match(step, steps)>=drop,0,1))
ggplot(dat.cum, aes(x = step, fill = factor(status))) +
geom_bar()
# option 2 is faster
dat$drop <- apply(dat,1,function(x) min(which(x==0),99))
dat.cum <- dat %>%
gather(step,status,-drop) %>%
mutate(status = if_else(match(step,steps)>=drop,0,1))
ggplot(dat.cum, aes(x = step, fill = factor(status))) +
geom_bar()
If you would like to map along rows you could do:
dat %>%
mutate(drop2 = map_int(seq_len(nrow(dat)), ~ min(which(dat[.x, ] == 0L), 99L)))
It could be that "gathering and grouping" is faster than Looping:
dat %>%
as_tibble() %>%
select(starts_with("step_")) %>%
mutate(row_nr = row_number()) %>%
gather(key = "col", value = "value", -row_nr) %>%
arrange(row_nr, col) %>%
group_by(row_nr) %>%
mutate(col_index = row_number()) %>%
filter(value == 0) %>%
summarise(drop3 = min(col_index)) %>%
ungroup() %>%
right_join(dat %>%
mutate(row_nr = row_number()),
by = "row_nr") %>%
mutate(drop3 = if_else(is.na(drop3), 99, drop3))
I have data similar to below :
df=data.frame(
company=c("McD","McD","McD","KFC","KFC"),
Title=c("Crew Member","Manager","Trainer","Crew Member","Manager"),
Manhours=c(12,NA,5,13,10)
)
df
I would wish to manipulate it and obtain the data frame as below:
df=data.frame(
company=c("KFC", "McD"),
Manager=c(1,1),
Surbodinate=c(1,2),
TotalEmp=c(2,3),
TotalHours=c(23,17)
)
I have managed to manipulate and categorise the employees as well as their count as below:
df<- df %>%
mutate(Role = if_else((Title=="Manager" ),
"Manager","Surbodinate"))%>%
count(company, Role) %>%
spread(Role, n, fill=0)%>%
as.data.frame() %>%
mutate(TotalEmp= select(., Manager:Surbodinate) %>%
apply(1, sum, na.rm=TRUE))
Also, I have summarised the man hours as below:
df <- df %>%group_by(company) %>%
summarize(TotalHours = sum(Manhours, na.rm = TRUE))
How would I combine these two steps at once or is there a cleaner/simpler way of getting the desired output?
dplyr solution:
df %>%
mutate(Title = if_else((Title=="Manager" ),
"Manager","Surbodinate")) %>%
group_by(company) %>%
summarise(Manager = sum(Title == "Manager"), Subordinate = sum(Title == "Surbodinate"), TotalEmp = n(), Manhours = sum(Manhours, na.rm = TRUE))
company Manager Subordinate TotalEmp Manhours
<fct> <int> <int> <int> <dbl>
1 KFC 1 1 2 23
2 McD 1 2 3 17
how about something like this:
df %>%
mutate(Role = ifelse(Title=="Manager" ,
"Manager", "Surbodinate"))%>%
group_by(company) %>%
mutate(TotalEmp = n(),
TotalHours = sum(Manhours, na.rm=TRUE)) %>%
reshape2::dcast(company + TotalEmp + TotalHours ~ Role)
This is not tidyverse nor is it a one step process. But if you use data.table you could do:
library(data.table)
setDT(df, key = "company")
totals <- DT[, .(TotalEmp = .N, TotalHours = sum(Manhours, na.rm = TRUE)), by = company]
dcast(DT, company ~ ifelse(Title == "Manager", "Manager", "Surbodinate"))[totals]
# company Manager Surbodinate TotalEmp TotalHours
# 1 KFC 1 1 2 23
# 2 McD 1 2 3 17
Sorry to bother with a relatively simple question perhaps.
I have this type of dataframe:
A long list of names in the column "NAME" c(a, b, c, d, e ...) , two potential classes in the column "SURNAME" c(A, B) and a third column containing values.
I want to remove all NAMES for which at least in one of the SURNAME classes I have more than 2 "NA" in the VALUE column.
I wanted to post an example dataset but I am struggling to format it properly
I was trying to use
df <- df %>%
group_by(NAME) %>%
group_by(SURNAME) %>%
filter(!is.na(VALUE)) %>%
filter(length(VALUE)>=3)
it does not throw an error but I have the impression that something is wrong. Any suggestion? Many thanks
Let's create a dataset to work with:
set.seed(1234)
df <- data.frame(
name = sample(x=letters, size=1e3, replace=TRUE),
surname = sample(x=c("A", "B"), size=1e3, replace=TRUE),
value = sample(x=c(1:10*10,NA), size=1e3, replace=TRUE),
stringsAsFactors = FALSE
)
Here's how to do it with Base R:
# count NAs by name-surname combos (na.action arg is important!)
agg <- aggregate(value ~ name + surname, data=df, FUN=function(x) sum(is.na(x)), na.action=NULL)
# rename is count of NAs column
names(agg)[3] <- "number_of_na"
#add count of NAs back to original data
df <- merge(df, agg, by=c("name", "surname"))
# subset the original data
result <- df[df$number_of_na < 3, ]
Here's how to do it with data.table:
library(data.table)
dt <- as.data.table(df)
dt[ , number_of_na := sum(is.na(value)), by=.(name, surname)]
result <- dt[number_of_na < 3]
Here's how to do it with dplr/tidyverse:
library(dplyr) # or library(tidyverse)
result <- df %>%
group_by(name, surname) %>%
summarize(number_of_na = sum(is.na(value))) %>%
right_join(df, by=c("name", "surname")) %>%
filter(number_of_na < 3)
After grouping by 'NAME', 'SURNAME', create a column with the number of NA elements in that group and then filter out any 'NAME' that have an 'ind' greater than or equal to 3
df %>%
group_by(NAME, SURNAME) %>%
mutate(ind = sum(is.na(VALUE))) %>%
group_by(NAME) %>%
filter(!any(ind >=3)) %>%
select(-ind)
Or do an anti_join after doing the filtering by 'NAME', 'SURNAME' based on the condition
df %>%
group_by(NAME, SURNAME) %>%
filter(sum(is.na(VALUE))>=3) %>%
ungroup %>%
distinct(NAME) %>%
anti_join(df, .)
data
set.seed(24)
df <- data.frame(NAME = rep(letters[1:5], each = 20),
SURNAME = sample(LETTERS[1:4], 5 * 20, replace = TRUE),
VALUE = sample(c(NA, 1:3), 5 *20, replace = TRUE),
stringsAsFactors = FALSE)
My question is a little like this but the problem with the structure of data is different:
Sample data:
df <-data.frame(id = c(1,2,3), stock_1 = c("Google","Microsoft","Yahoo"), stock_2 = c("Yahoo","Google","NA"))
and I would like to convert to this:
df <-data.frame(id = c(1,2,3), Google = c(1,1,0), Microsoft = c(0,1,0), Yahoo= c(1,0,1))
I tried to use sapply() but from the answer to the linked question it is only for one column.
Here is a way to do it with data.table:
library(data.table)
setDT(df)
dcast(melt(df, id = 'id')[value != 'NA'],
id ~ value, fun.aggregate = length)
# id Google Microsoft Yahoo
# 1: 1 1 0 1
# 2: 2 1 1 0
# 3: 3 0 0 1
fill = 0 is unnecessary, and to tolerate duplicates, we can try:
dcast(melt(df, id = 'id')[value != 'NA'],
id ~ value, fun.aggregate = function(x){ 1 * (length(x) != 0)})
2017-01-01
As mentationed by Uwe, we can removed from NAs from the molten data by setting na.rm = TRUE if it is not hard coded as a string ("NA"), the commands finally looks this:
dcast(melt(df, id = 'id', na.rm = TRUE), id ~ value, fun.aggregate = length)
# or
dcast(melt(df, id = 'id', na.rm = TRUE),
id ~ value, fun.aggregate = function(x){ 1 * (length(x) != 0)})
We can also do this with tidyverse
library(tidyverse)
df %>%
gather(key, val, -id) %>%
filter(!is.na(val)) %>%
mutate(ind = 1) %>%
select(-key) %>%
spread(val, ind, fill = 0)
NOTE: It is better to use NA instead of "NA" as we can take care of NA with is.na or na.omit or complete.cases