I have this data frame:
id <- c(0,1,2,3,4)
groupA_sample1_values <- c(10,11,12,13,14)
groupA_sample2_values <- c(20,21,22,23,24)
groupA_sample3_values <- c(30,31,32,33,34)
groupB_sample1_values <- c(40,41,42,43,44)
groupB_sample2_values <- c(50,51,52,53,54)
groupB_sample3_values <- c(60,61,62,63,64)
df <- data.frame(id,
groupA_sample1_values,
groupA_sample2_values,
groupA_sample3_values,
groupB_sample1_values,
groupB_sample2_values,
groupB_sample3_values)
df
and I am trying to obtain another table with these columns:
id, group, sample, value.
I belive I would have to extract the name groupA/groupB with regex, and the same for the sample number, and the melt it to a new data frame, but I'm not sure how to approach it.
Any help?
try
library( tidyverse )
df %>%
pivot_longer( -id,
names_to = c("group", "sample" ),
names_pattern = "group(.)_sample(.)_values",
values_to = "value" )
# # A tibble: 30 x 4
# id group sample value
# <dbl> <chr> <chr> <dbl>
# 1 0 A 1 10
# 2 0 A 2 20
# 3 0 A 3 30
# 4 0 B 1 40
# 5 0 B 2 50
# 6 0 B 3 60
# 7 1 A 1 11
# 8 1 A 2 21
# 9 1 A 3 31
#10 1 B 1 41
Related
I have a very simple case where I want to combine several data frames into one based on a common id elements of a particular data frame.
Example:
id <- c(1, 2, 3)
x <- c(10, 12, 14)
data1 <- data.frame(id, x)
id <- c(2, 3)
x <- c(20, 22)
data2 <- data.frame(id, x)
id <- c(1, 3)
x <- c(30, 32)
data3 <- data.frame(id, x)
Which gives us,
$data1
id x
1 1 10
2 2 12
3 3 14
$data2
id x
1 2 20
2 3 22
$data3
id x
1 1 30
2 3 32
Now, I want to combine all three data frames based on the id's of the data3. The expected output should look like
> comb
id x
1 1 10
2 1 NA
3 1 30
4 3 14
5 3 22
6 3 32
I am trying the following, but not getting the expected output.
library(dplyr)
library(tidyr)
combined <- bind_rows(data1, data2, data3, .id = "id") %>% arrange(id)
Any idea how to get the expected output?
Does this work:
library(dplyr)
library(tidyr)
data1 %>% full_join(data2, by = 'id') %>% full_join(data3, by = 'id') %>% arrange(id) %>% right_join(data3, by = 'id') %>%
pivot_longer(cols = -id) %>% select(-name) %>% distinct()
# A tibble: 6 x 2
id value
<dbl> <dbl>
1 1 10
2 1 NA
3 1 30
4 3 14
5 3 22
6 3 32
Combine the 3 dataframes in one list and use filter to select only the id's in 3rd dataframe.
library(dplyr)
library(tidyr)
bind_rows(data1, data2, data3, .id = "new_id") %>%
filter(id %in% id[new_id == 3]) %>%
complete(new_id, id)
# new_id id x
# <chr> <dbl> <dbl>
#1 1 1 10
#2 1 3 14
#3 2 1 NA
#4 2 3 22
#5 3 1 30
#6 3 3 32
A pure base R solution can also make it
lst <- list(data1, data2, data3)
reshape(
subset(
reshape(
do.call(rbind, Map(cbind, lst, grp = seq_along(lst))),
idvar = "id",
timevar = "grp",
direction = "wide"
),
id %in% lst[[3]]$id
),
idvar = "id",
varying = -1,
direction = "long"
)[c("id", "x")]
which gives
id x
1.1 1 10
3.1 3 14
1.2 1 NA
3.2 3 22
1.3 1 30
3.3 3 32
>
Using base R
do.call(rbind, unname(lapply(mget(ls(pattern = "^data\\d+$")), \(x) {
x1 <- subset(x, id %in% data3$id)
v1 <- setdiff(data3$id, x1$id)
if(length(v1) > 0) rbind(x1, cbind(id = v1, x = NA)) else x1
})))
-output
id x
1 1 10
3 3 14
2 3 22
11 1 NA
12 1 30
21 3 32
bind_rows(data1, data2, data3, .id = 'grp')%>%
complete(id, grp)%>%
select(-grp) %>%
filter(id%in%data3$id)
# A tibble: 6 x 2
id x
<dbl> <dbl>
1 1 10
2 1 NA
3 1 30
4 3 14
5 3 22
6 3 32
I have missing categorical variables in a list. I would like to add all the combinations of these classifications to the data frame using complete. I can do this for a single variable using mutate.
Simplified example:
library(tidyverse)
df <- tibble(a1 = 1:6,
b1 = rep(c(1,2),3),
c1 = rep(c(1:3), 2))
missing_cols <- list(d1 = c(7:8),
e1 = c(12:14))
# Use the first classification of d1 for mutate and complete with all classifications
df %>%
mutate(!!names(missing_cols)[1] := missing_cols[[1]][1]) %>%
complete(nesting(a1, b1,c1), d1 = missing_cols[[1]])
Desired output
df %>%
mutate(!!names(missing_cols)[1] := missing_cols[[1]][1]) %>%
mutate(!!names(missing_cols)[2] := missing_cols[[2]][1]) %>%
complete(nesting(a1, b1,c1), d1 = missing_cols[[1]], e1 = missing_cols[[2]])
This will get the correct output for d1. How can I do this for all variables in my list?
We can use crossing with cross_df :
library(tidyr)
crossing(df, cross_df(missing_cols))
# a1 b1 c1 d1 e1
# <int> <dbl> <int> <int> <int>
# 1 1 1 1 7 12
# 2 1 1 1 7 13
# 3 1 1 1 7 14
# 4 1 1 1 8 12
# 5 1 1 1 8 13
# 6 1 1 1 8 14
# 7 2 2 2 7 12
# 8 2 2 2 7 13
# 9 2 2 2 7 14
#10 2 2 2 8 12
# … with 26 more rows
cross_df creates all possible combination of missing_cols while crossing takes that output and creates all possible combination with df.
Using expand.grid
library(tidyr)
crossing(df, expand.grid(missing_cols))
I have two dfs : df1 and df2 where the column names are dates. When I join the two df's I get columns like
date1.x, date1.y, date2.x, date2.y, date3.x, date3.y, date4.x, date4.y...........
I want to create new columns which have values which are multiplication of date1.x and date1.y and similarly for other date pairs as well.
df <- data.frame(id=11:13, date1.x=1:3, date2.x=4:6, date1.y=7:9, date2.y=10:12)
df
# id date1.x date2.x date1.y date2.y
# 1 11 1 4 7 10
# 2 12 2 5 8 11
# 3 13 3 6 9 12
grep("^date.*\\.x$", colnames(df), value = TRUE)
# [1] "date1.x" "date2.x"
datenms <- grep("^date.*\\.x$", colnames(df), value = TRUE)
### make sure all of our 'date#.x' columns have matching 'date#.y' columns
datenms <- datenms[ gsub("x$", "y", datenms) %in% colnames(df) ]
datenms
# [1] "date1.x" "date2.x"
subset(df, select = datenms)
# date1.x date2.x
# 1 1 4
# 2 2 5
# 3 3 6
subset(df, select = gsub("x$", "y", datenms))
# date1.y date2.y
# 1 7 10
# 2 8 11
# 3 9 12
subset(df, select = datenms) * subset(df, select = gsub("x$", "y", datenms))
# date1.x date2.x
# 1 7 40
# 2 16 55
# 3 27 72
There are a number of ways to do this, but I suggest that it is a good practice to get used to transforming your data into a format that is easy to work with. The first answer showed you one way to do what you want without transforming your data. My answer will show you how to transform the data so that calculation (this one and others) are easy, and then how to perform the calculation once the data is tidy.
Making your data tidy helps to perform easier aggregations, to graph results, to perform feature engineering for models, etc.
library(dplyr)
library(tidyr)
df <- data.frame(id=11:13, date1.x=1:3, date2.x=4:6, date1.y=7:9, date2.y=10:12)
df
# id date1.x date2.x date1.y date2.y
# 1 11 1 4 7 10
# 2 12 2 5 8 11
# 3 13 3 6 9 12
# Convert the data to a tidy format that is easier for computers to calculate
tidy_df <- df %>%
pivot_longer(
cols = starts_with("date"), # We are tidying any column starting with date
names_to = c("date_num","date_source"), # creating two columns for names
values_to = c("date_value"), # creating one column for values
names_prefix = "date", # removing the "date" prefix
names_sep = "\\." # splitting the names on the period `.`
)
tidy_df
# id date_num date_source date_value
# <int> <chr> <chr> <int>
# 1 11 1 x 1
# 2 11 2 x 4
# 3 11 1 y 7
# 4 11 2 y 10
# 5 12 1 x 2
# 6 12 2 x 5
# 7 12 1 y 8
# 8 12 2 y 11
# 9 13 1 x 3
# 10 13 2 x 6
# 11 13 1 y 9
# 12 13 2 y 12
# Now that the data is tidy we can do easier dataframe grouping and aggregation
tidy_df %>%
group_by(id,date_num) %>%
summarise(date_value_mult = prod(date_value)) %>%
ungroup()
# id date_num date_value_mult
# <int> <chr> <dbl>
# 1 11 1 7
# 2 11 2 40
# 3 12 1 16
# 4 12 2 55
# 5 13 1 27
# 6 13 2 72
# If/When you eventually want the data in a more human readable format you can
# pivot the data back into a human readable format. This is likely after all
# computer calculations are done and you want to present the data. For storing
# the data (such as in a database) you would not need/want this step.
tidy_df %>%
group_by(id,date_num) %>%
summarise(date_value_mult = prod(date_value)) %>%
ungroup() %>%
pivot_wider(
names_from = date_num,
values_from = date_value_mult,
names_prefix = "date"
)
# id date1 date2
# <int> <dbl> <dbl>
# 1 11 7 40
# 2 12 16 55
# 3 13 27 72
I would like to pivot variables nclaims, npatients, nproviders to show up underneath groups.
I believe I should be using pivot_longer but it doesn't work.
library(tidyr)
ptype <- c(0,1,2,0,1)
groups <- c(rep(1,3), rep(2,2))
nclaims <- c(10,23,32,12,8)
nproviders <- c(2,4,5,1,1)
npatients <- c(8, 20, 29, 9, 6)
dta <- data.frame(ptype=ptype, groups=groups, nclaims=nclaims, nproviders=nproviders, npatients=npatients)
table <- pivot_longer(everything(dta), names_to = "groups", values_to=c("nclaims", "npatients", "nproviders"))
Desired output:
We need to use pivot_longer, then pivot_wider:
dta %>%
pivot_longer(nclaims:npatients) %>%
# values_fill = 0 changes NA values to 0, as in your desired result
pivot_wider(names_from = ptype, values_from = value,
values_fill = 0)
groups name `0` `1` `2`
<dbl> <chr> <dbl> <dbl> <dbl>
1 1 nclaims 10 23 32
2 1 nproviders 2 4 5
3 1 npatients 8 20 29
4 2 nclaims 12 8 0
5 2 nproviders 1 1 0
6 2 npatients 9 6 0
another approach, using reshape2::recast()
library( reshape2 )
recast( dta, groups + variable ~ ptype, id.var = c("ptype", "groups") )
# groups variable 0 1 2
# 1 1 nclaims 10 23 32
# 2 1 nproviders 2 4 5
# 3 1 npatients 8 20 29
# 4 2 nclaims 12 8 NA
# 5 2 nproviders 1 1 NA
# 6 2 npatients 9 6 NA
I am working with gait-cycle data. I have 8 events marked for each id and gait trial. The values "LFCH" and "RFCH" occurs twice in each trial, as these represent the beginning and the end of the gait cycles from left and right leg.
Sample Data Frame:
df <- data.frame(ID = rep(1:5, each = 16),
Gait_nr = rep(1:2, each = 8, times=5),
Frame = rep(c(1,5,7,9,10,15,22,25), times = 10),
Marks = rep(c("LFCH", "LHL", "RFCH", "LTO", "RHL", "LFCH", "RTO", "RFCH"), times =10)
head(df,8)
ID Gait_nr Frame Marks
1 1 1 1 LFCH
2 1 1 5 LHL
3 1 1 7 RFCH
4 1 1 9 LTO
5 1 1 10 RHL
6 1 1 15 LFCH
7 1 1 22 RTO
8 1 1 25 RFCH
I wold like to create something like
Total_gait_left = Frame[The last time Marks == "LFCH"] - Frame[The first time Marks == "LFCH"]
My current code solves the problem, but depends on the position of the Frame values rather than actual values in Marks. Any individual not following the normal gait pattern will have wrong values produced by the code.
library(tidyverse)
l <- df %>% group_by(ID, Gait_nr) %>% filter(grepl("L.+", Marks)) %>%
summarize(Total_gait = Frame[4] - Frame[1],
Side = "left")
r <- df %>% group_by(ID, Gait_nr) %>% filter(grepl("R.+", Marks)) %>%
summarize(Total_gait = Frame[4] - Frame[1],
Side = "right")
val <- union(l,r, by=c("ID", "Gait_nr", "Side")) %>% arrange(ID, Gait_nr, Side)
Can you help me make my code more stable by helping me change e.g. Frame[4] to something like Frame[Marks=="LFCH" the last time ]?
If both LFCH and RFCH happen exactly twice, you can filter and then use diff in summarize:
df %>%
group_by(ID, Gait_nr) %>%
summarise(
left = diff(Frame[Marks == 'LFCH']),
right = diff(Frame[Marks == 'RFCH'])
)
# A tibble: 10 x 4
# Groups: ID [?]
# ID Gait_nr left right
# <int> <int> <dbl> <dbl>
# 1 1 1 14 18
# 2 1 2 14 18
# 3 2 1 14 18
# 4 2 2 14 18
# 5 3 1 14 18
# 6 3 2 14 18
# 7 4 1 14 18
# 8 4 2 14 18
# 9 5 1 14 18
#10 5 2 14 18
We can use first and last from the dplyr package.
library(dplyr)
df2 <- df %>%
filter(Marks %in% "LFCH") %>%
group_by(ID, Gait_nr) %>%
summarise(Total_gait = last(Frame) - first(Frame)) %>%
ungroup()
df2
# # A tibble: 10 x 3
# ID Gait_nr Total_gait
# <int> <int> <dbl>
# 1 1 1 14
# 2 1 2 14
# 3 2 1 14
# 4 2 2 14
# 5 3 1 14
# 6 3 2 14
# 7 4 1 14
# 8 4 2 14
# 9 5 1 14
# 10 5 2 14