What I have:
I have two dataframes to work with. Those are:
> print(myDF_2003)
A_score country B_score
1 200 Germany 11
2 150 Italy 9
3 0 Sweden 0
and:
> print(myDF_2005)
A_score country B_score
1 -300 France 16
2 100 Germany 12
3 200 Italy 15
4 40 Spain 17
They are produced by the following code, which I do not want to change:
#_________2003______________
myDF_2003=data.frame(c(200,150,0),c("Germany", "Italy", "Sweden"), c(11,9,0))
colnames(myDF_2003)=c("A_score","country", "B_score")
myDF_2003$country=as.character(myDF_2003$country)
myDF_2003$country=factor(myDF_2003$country, levels=unique(myDF_2003$country))
myDF_2003$A_score=as.numeric(as.character(myDF_2003$A_score))
myDF_2003$B_score=as.numeric(as.character(myDF_2003$B_score))
#_________2005______________
myDF_2005=data.frame(c(-300,100,200,40),c("France","Germany", "Italy", "Spain"), c(16,12,15,17))
colnames(myDF_2005)=c("A_score","country", "B_score")
myDF_2005$country=as.character(myDF_2005$country)
myDF_2005$country=factor(myDF_2005$country, levels=unique(myDF_2005$country))
myDF_2005$A_score=as.numeric(as.character(myDF_2005$A_score))
myDF_2005$B_score=as.numeric(as.character(myDF_2005$B_score))
What I want:
I want to paste another column to myDF_2005 which has the difference of the B_Scores of countries that exist in both previous dataframes. In other words: I want to produce this output:
> print(myDF_2005_2003_Diff)
A_score country B_score B_score_Diff
1 -300 France 16
2 100 Germany 12 1
3 200 Italy 15 6
4 40 Spain 17
Question:
What is the most elegant code to do this?
# join in a temporary dataframe
temp <- merge(myDF_2005, myDF_2003, by = "country", all.x = T)
# calculate the difference and assign a new column
myDF_2005$B_score_Diff <- temp$B_score.x - temp$B_score.y
A solution using dplyr. The idea is to merge the two data frame and then calculate the difference.
library(dplyr)
myDF_2005_2 <- myDF_2005 %>%
left_join(myDF_2003 %>% select(-A_score), by = "country") %>%
mutate(B_score_Diff = B_score.x - B_score.y) %>%
select(-B_score.y) %>%
rename(B_score = B_score.x)
myDF_2005_2
# A_score country B_score B_score_Diff
# 1 -300 France 16 NA
# 2 100 Germany 12 1
# 3 200 Italy 15 6
# 4 40 Spain 17 NA
Related
I've looked around but I can't find an answer to this!
I've imported a large number of datasets to R.
Each dataset contains information for a single year (ex. df_2012, df_2013, df_2014 etc).
All the datasets have the same variables/columns (ex. varA_2012 in df_2012 corresponds to varA_2013 in df_2013).
I want to create a df with my id variable and varA_2012, varB_2012, varA_2013, varB_2013, varA_2014, varB_2014 etc
I'm trying to create a loop that helps me extract the few columns that I'm interested in (varA_XXXX, varB_XXXX) in each data frame and then do a full join based on my id var.
I haven't used R in a very long time...
So far, I've tried this:
id <- c("France", "Belgium", "Spain")
varA_2012 <- c(1,2,3)
varB_2012 <- c(7,2,9)
varC_2012 <- c(1,56,0)
varD_2012 <- c(13,55,8)
varA_2013 <- c(34,3,56)
varB_2013 <- c(2,53,5)
varC_2013 <- c(24,3,45)
varD_2013 <- c(27,13,8)
varA_2014 <- c(9,10,5)
varB_2014 <- c(95,30,75)
varC_2014 <- c(99,0,51)
varD_2014 <- c(9,40,1)
df_2012 <-data.frame(id, varA_2012, varB_2012, varC_2012, varD_2012)
df_2013 <-data.frame(id, varA_2013, varB_2013, varC_2013, varD_2013)
df_2014 <-data.frame(id, varA_2014, varB_2014, varC_2014, varD_2014)
year = c(2012:2014)
for(i in 1:length(year)) {
df_[i] <- df_[I][df_[i]$id, df_[i]$varA_[i], df_[i]$varB_[i], ]
list2env(df_[i], .GlobalEnv)
}
panel_df <- Reduce(function(x, y) merge(x, y, by="if"), list(df_2012, df_2013, df_2014))
I know that there are probably loads of errors in here.
Here are a couple of options; however, it's unclear what you want the expected output to look like.
If you want a wide format, then we can use tidyverse to do:
library(tidyverse)
results <-
map(list(df_2012, df_2013, df_2014), function(x)
x %>% dplyr::select(id, starts_with("varA"), starts_with("varB"))) %>%
reduce(., function(x, y)
left_join(x, y, all = TRUE, by = "id"))
Output
id varA_2012 varB_2012 varA_2013 varB_2013 varA_2014 varB_2014
1 Belgium 2 2 3 53 10 30
2 France 1 7 34 2 9 95
3 Spain 3 9 56 5 5 75
However, if you need it in a long format, then we could pivot the data:
results %>%
pivot_longer(-id, names_to = c("variable", "year"), names_sep = "_")
Output
id variable year value
<chr> <chr> <chr> <dbl>
1 France varA 2012 1
2 France varB 2012 7
3 France varA 2013 34
4 France varB 2013 2
5 France varA 2014 9
6 France varB 2014 95
7 Belgium varA 2012 2
8 Belgium varB 2012 2
9 Belgium varA 2013 3
10 Belgium varB 2013 53
11 Belgium varA 2014 10
12 Belgium varB 2014 30
13 Spain varA 2012 3
14 Spain varB 2012 9
15 Spain varA 2013 56
16 Spain varB 2013 5
17 Spain varA 2014 5
18 Spain varB 2014 75
Or if using base R for the wide format, then we can do:
results <-
lapply(list(df_2012, df_2013, df_2014), function(x)
subset(x, select = c("id", names(x)[startsWith(names(x), "varA")], names(x)[startsWith(names(x), "varB")])))
results <-
Reduce(function(x, y)
merge(x, y, all = TRUE, by = "id"), results)
From your initial for loop attempt, it seems the code below may help
> (df <- Reduce(merge, list(df_2012, df_2013, df_2014)))[grepl("^(id|var(A|B))",names(df))]
id varA_2012 varB_2012 varA_2013 varB_2013 varA_2014 varB_2014
1 Belgium 2 2 3 53 10 30
2 France 1 7 34 2 9 95
3 Spain 3 9 56 5 5 75
I have two data sets I would like to join. The income_range data is the master dataset and I would like to join data_occ to the income_range data based on what band the income falls inside. Where there are more than two observations(incomes) that are within the range I would like to take the lower income.
I was attempting to use data.table but was having trouble. I was would also like to keep all columns from both data.frames if possible.
The output dataset should only have 7 observations.
library(data.table)
library(dplyr)
income_range <- data.frame(id = "France"
,inc_lower = c(10, 21, 31, 41,51,61,71)
,inc_high = c(20, 30, 40, 50,60,70,80)
,perct = c(1,2,3,4,5,6,7))
data_occ <- data.frame(id = rep(c("France","Belgium"), each=50)
,income = sample(10:80, 50)
,occ = rep(c("manager","clerk","manual","skilled","office"), each=20))
setDT(income_range)
setDT(data_occ)
First attempt.
df2 <- income_range [data_occ ,
on = .(id, inc_lower <= income, inc_high >= income),
.(id, income, inc_lower,inc_high,perct,occ)]
Thank you in advance.
Since you tagged dplyr, here's one possible solution using that library:
library('fuzzyjoin')
# join dataframes on id == id, inc_lower <= income, inc_high >= income
joined <- income_range %>%
fuzzy_left_join(data_occ,
by = c('id' = 'id', 'inc_lower' = 'income', 'inc_high' = 'income'),
match_fun = list(`==`, `<=`, `>=`)) %>%
rename(id = id.x) %>%
select(-id.y)
# sort by income, and keep only the first row of every unique perct
result <- joined %>%
arrange(income) %>%
group_by(perct) %>%
slice(1)
And the (intermediate) results:
> head(joined)
id inc_lower inc_high perct income occ
1 France 10 20 1 10 manager
2 France 10 20 1 19 manager
3 France 10 20 1 14 manager
4 France 10 20 1 11 manager
5 France 10 20 1 17 manager
6 France 10 20 1 12 manager
> result
# A tibble: 7 x 6
# Groups: perct [7]
id inc_lower inc_high perct income occ
<chr> <dbl> <dbl> <dbl> <int> <chr>
1 France 10 20 1 10 manager
2 France 21 30 2 21 manual
3 France 31 40 3 31 manual
4 France 41 50 4 43 manager
5 France 51 60 5 51 clerk
6 France 61 70 6 61 manager
7 France 71 80 7 71 manager
I've added the intermediate dataframe joined for easy of understanding. You can omit it and just chain the two command chains together with %>%.
Here is one data.table approach:
cols = c("inc_lower", "inc_high")
data_occ[, (cols) := income]
result = data_occ[order(income)
][income_range,
on = .(id, inc_lower>=inc_lower, inc_high<=inc_high),
mult="first"]
data_occ[, (cols) := NULL]
# id income occ inc_lower inc_high perct
# 1: France 10 clerk 10 20 1
# 2: France 21 manager 21 30 2
# 3: France 31 clerk 31 40 3
# 4: France 41 clerk 41 50 4
# 5: France 51 clerk 51 60 5
# 6: France 62 manager 61 70 6
# 7: France 71 manager 71 80 7
I have tried to find a solution via similar topics, but haven't found anything suitable. This may be due to the search terms I have used. If I have missed something, please accept my apologies.
Here is a excerpt of my data UN_ (the provided sample should be sufficient):
country year sector UN
AT 1990 1 1.407555
AT 1990 2 1.037137
AT 1990 3 4.769618
AT 1990 4 2.455139
AT 1990 5 2.238618
AT 1990 Total 7.869005
AT 1991 1 1.484667
AT 1991 2 1.001578
AT 1991 3 4.625927
AT 1991 4 2.515453
AT 1991 5 2.702081
AT 1991 Total 8.249567
....
BE 1994 1 3.008115
BE 1994 2 1.550344
BE 1994 3 1.080667
BE 1994 4 1.768645
BE 1994 5 7.208295
BE 1994 Total 1.526016
BE 1995 1 2.958820
BE 1995 2 1.571759
BE 1995 3 1.116049
BE 1995 4 1.888952
BE 1995 5 7.654881
BE 1995 Total 1.547446
....
What I want to do is, to add another row with UN_$sector = Residual. The value of residual will be (UN_$sector = Total) - (the sum of column UN for the sectors c("1", "2", "3", "4", "5")) for a given year AND country.
This is how it should look like:
country year sector UN
AT 1990 1 1.407555
AT 1990 2 1.037137
AT 1990 3 4.769618
AT 1990 4 2.455139
AT 1990 5 2.238618
----> AT 1990 Residual TO BE CALCULATED
AT 1990 Total 7.869005
As I don't want to write many, many lines of code I'm looking for a way to automate this. I was told about loops, but can't really follow the concept at the moment.
Thank you very much for any type of help!!
Best,
Constantin
PS: (for Parfait)
country year sector UN ETS
UK 2012 1 190336512 NA
UK 2012 2 18107910 NA
UK 2012 3 8333564 NA
UK 2012 4 11269017 NA
UK 2012 5 2504751 NA
UK 2012 Total 580957306 NA
UK 2013 1 177882200 NA
UK 2013 2 20353347 NA
UK 2013 3 8838575 NA
UK 2013 4 11051398 NA
UK 2013 5 2684909 NA
UK 2013 Total 566322778 NA
Consider calculating residual first and then stack it with other pieces of data:
# CALCULATE RESIDUALS BY MERGED COLUMNS
agg <- within(merge(aggregate(UN ~ country + year, data = subset(df, sector!='Total'), sum),
aggregate(UN ~ country + year, data = subset(df, sector=='Total'), sum),
by=c("country", "year")),
{UN <- UN.y - UN.x
sector = 'Residual'})
# ROW BIND DIFFERENT PIECES
final_df <- rbind(subset(df, sector!='Total'),
agg[c("country", "year", "sector", "UN")],
subset(df, sector=='Total'))
# ORDER ROWS AND RESET ROWNAMES
final_df <- with(final_df, final_df[order(country, year, as.character(sector)),])
row.names(final_df) <- NULL
Rextester demo
final_df
# country year sector UN
# 1 AT 1990 1 1.407555
# 2 AT 1990 2 1.037137
# 3 AT 1990 3 4.769618
# 4 AT 1990 4 2.455139
# 5 AT 1990 5 2.238618
# 6 AT 1990 Residual -4.039062
# 7 AT 1990 Total 7.869005
# 8 AT 1991 1 1.484667
# 9 AT 1991 2 1.001578
# 10 AT 1991 3 4.625927
# 11 AT 1991 4 2.515453
# 12 AT 1991 5 2.702081
# 13 AT 1991 Residual -4.080139
# 14 AT 1991 Total 8.249567
# 15 BE 1994 1 3.008115
# 16 BE 1994 2 1.550344
# 17 BE 1994 3 1.080667
# 18 BE 1994 4 1.768645
# 19 BE 1994 5 7.208295
# 20 BE 1994 Residual -13.090050
# 21 BE 1994 Total 1.526016
# 22 BE 1995 1 2.958820
# 23 BE 1995 2 1.571759
# 24 BE 1995 3 1.116049
# 25 BE 1995 4 1.888952
# 26 BE 1995 5 7.654881
# 27 BE 1995 Residual -13.643015
# 28 BE 1995 Total 1.547446
I think there are multiple ways you can do this. What I may recommend is to take advantage of the tidyverse suite of packages which includes dplyr.
Without getting too far into what dplyr and tidyverse can achieve, we can talk about the power of dplyr's inline commands group_by(...), summarise(...), arrange(...) and bind_rows(...) functions. Also, there are tons of great tutorials, cheat sheets, and documentation on all tidyverse packages.
Although it is less and less relevant these days, we generally want to avoid for loops in R. Therefore, we will create a new data frame which contains all of the Residual values then bring it back into your original data frame.
Step 1: Calculating all residual values
We want to calculate the sum of UN values, grouped by country and year. We can achieve this by this value
res_UN = UN_ %>% group_by(country, year) %>% summarise(UN = sum(UN, na.rm = T))
Step 2: Add sector column to res_UN with value 'residual'
This should yield a data frame which contains country, year, and UN, we now need to add a column sector which the value 'Residual' to satisfy your specifications.
res_UN$sector = 'Residual'
Step 3 : Add res_UN back to UN_ and order accordingly
res_UN and UN_ now have the same columns and they can now be added back together.
UN_ = bind_rows(UN_, res_UN) %>% arrange(country, year, sector)
Piecing this all together, should answer your question and can be achieved in a couple lines!
TLDR:
res_UN = UN_ %>% group_by(country, year) %>% summarise(UN = sum(UN, na.rm = T))`
res_UN$sector = 'Residual'
UN_ = bind_rows(UN_, res_UN) %>% arrange(country, year, sector)
I have a table that looks like the following:
Year Country Variable 1 Variable 2
1970 UK 1 3
1970 USA 1 3
1971 UK 2 5
1971 UK 2 3
1971 UK 1 5
1971 USA 2 2
1972 USA 1 1
1972 USA 2 5
I'd be grateful if someone could tell me how I can aggregate the data to group it first by year, then country with the sum of variable 1 and variable 2 coming afterwards so the output would be:
Year Country Sum Variable 1 Sum Variable 2
1970 UK 1 3
1970 USA 1 3
1971 UK 5 13
1971 USA 2 2
1972 USA 3 6
This is the code I've tried to no avail (the real dataframe is 125,000 rows by 30+ columns hence the subset. Please be kind, I'm new to R!)
#making subset from data
GT2 <- subset(GT1, select = c("iyear", "country_txt", "V1", "V2"))
#making sure data types are correct
GT2[,2]=as.character(GT2[,2])
GT2[,3] <- as.numeric(as.character( GT2[,3] ))
GT2[,4] <- as.numeric(as.character( GT2[,4] ))
#removing NA values
GT2Omit <- na.omit(GT2)
#trying to aggregate - i.e. group by year, then country with the sum of Variable 1 and Variable 2 being shown
aggGT2 <-aggregate(GT2Omit, by=list(GT2Omit$iyear, GT2Omit$country_txt), FUN=sum, na.rm=TRUE)
Your aggregate is almost correct:
> aggGT2 <-aggregate(GT2Omit[3:4], by=GT2Omit[c("country_txt", "iyear")], FUN=sum, na.rm=TRUE)
> aggGT2
country_txt iyear V1 V2
1 UK 1970 1 3
2 USA 1970 1 3
3 UK 1971 5 13
4 USA 1971 2 2
5 USA 1972 3 6
dplyr is almost always the answer nowadays.
library(dplyr)
aggGT1 <- GT1 %>% group_by(iyear, country_txt) %>% summarize(sv1=sum(V1), sv2=sum(V2))
Having said that, it is good to learn basic R functions like aggregate and by.
I have this data.frame in R.
> a <- data.frame(year = c(2001,2001,2001,2001), country = c("Japan", "Japan","US","US"), type = c("a","b","a","b"), amount = c(35,67,39,45))
> a
year country type amount
1 2001 Japan a 35
2 2001 Japan b 67
3 2001 US a 39
4 2001 US b 45
How should I transform this into a data.frame that looks like this?
year country type.a type.b
1 2001 Japan 35 67
2 2001 US 39 45
Basically I want the number of rows to be the number of (year x country) pairs, and I want to create additional columns for each type.
base solution, but requires renaming columns and rows
reshape(a, v.names="amount", timevar="type", idvar="country", direction="wide")
year country amount.a amount.b
1 2001 Japan 35 67
3 2001 US 39 45
reshape2 solution
library(reshape2)
dcast(a, year+country ~ paste("type", type, sep="."), value.var="amount")
year country type.a type.b
1 2001 Japan 35 67
2 2001 US 39 45
Another way would be to use spread in the tidyr package and rename in the dplyr package to deliver the expected outcome.
library(dplyr)
library(tidyr)
spread(a,type, amount) %>%
rename(type.a = a, type.b = b)
# year country type.a type.b
#1 2001 Japan 35 67
#2 2001 US 39 45