ect是实现这一点的一种方法。最好的答案是2021年。@EvanRosica,直到他们决定再次更改函数:p这并不能真正回答这个问题,因为它只是与示例的链接。虽然有用,你能把它改成评论吗? Code Country 1950 1951
ect是实现这一点的一种方法。最好的答案是2021年。@EvanRosica,直到他们决定再次更改函数:p这并不能真正回答这个问题,因为它只是与示例的链接。虽然有用,你能把它改成评论吗? Code Country 1950 1951 ,r,dataframe,reshape,r-faq,data.table,tidyr,reshape2,sqldf,R,Dataframe,Reshape,R Faq,Data.table,Tidyr,Reshape2,Sqldf,ect是实现这一点的一种方法。最好的答案是2021年。@EvanRosica,直到他们决定再次更改函数:p这并不能真正回答这个问题,因为它只是与示例的链接。虽然有用,你能把它改成评论吗? Code Country 1950 1951 1952 1953 1954 AFG Afghanistan 20,249 21,352 22,532 23,557 24,555 ALB Albania 8,097 8,986 10,0
ect是实现这一点的一种方法。最好的答案是2021年。@EvanRosica,直到他们决定再次更改函数:p这并不能真正回答这个问题,因为它只是与示例的链接。虽然有用,你能把它改成评论吗?
Code Country 1950 1951 1952 1953 1954
AFG Afghanistan 20,249 21,352 22,532 23,557 24,555
ALB Albania 8,097 8,986 10,058 11,123 12,246
Code Country Year Value
AFG Afghanistan 1950 20,249
AFG Afghanistan 1951 21,352
AFG Afghanistan 1952 22,532
AFG Afghanistan 1953 23,557
AFG Afghanistan 1954 24,555
ALB Albania 1950 8,097
ALB Albania 1951 8,986
ALB Albania 1952 10,058
ALB Albania 1953 11,123
ALB Albania 1954 12,246
#data
x <- read.table(textConnection(
"Code Country 1950 1951 1952 1953 1954
AFG Afghanistan 20,249 21,352 22,532 23,557 24,555
ALB Albania 8,097 8,986 10,058 11,123 12,246"), header=TRUE)
library(reshape)
x2 <- melt(x, id = c("Code", "Country"), variable_name = "Year")
x2[,"Year"] <- as.numeric(gsub("X", "" , x2[,"Year"]))
reshape(d,
direction = "long",
varying = list(names(d)[3:7]),
v.names = "Value",
idvar = c("Code", "Country"),
timevar = "Year",
times = 1950:1954)
library(data.table)
long <- melt(setDT(wide), id.vars = c("Code","Country"), variable.name = "year")
> long
Code Country year value
1: AFG Afghanistan 1950 20,249
2: ALB Albania 1950 8,097
3: AFG Afghanistan 1951 21,352
4: ALB Albania 1951 8,986
5: AFG Afghanistan 1952 22,532
6: ALB Albania 1952 10,058
7: AFG Afghanistan 1953 23,557
8: ALB Albania 1953 11,123
9: AFG Afghanistan 1954 24,555
10: ALB Albania 1954 12,246
melt(setDT(wide), id.vars = 1:2, variable.name = "year")
melt(setDT(wide), measure.vars = 3:7, variable.name = "year")
melt(setDT(wide), measure.vars = as.character(1950:1954), variable.name = "year")
library(tidyr)
long <- wide %>% gather(year, value, -c(Code, Country))
wide %>% gather(year, value, -Code, -Country)
wide %>% gather(year, value, -1:-2)
wide %>% gather(year, value, -(1:2))
wide %>% gather(year, value, -1, -2)
wide %>% gather(year, value, 3:7)
wide %>% gather(year, value, `1950`:`1954`)
library(reshape2)
long <- melt(wide, id.vars = c("Code", "Country"))
# you can also define the id-variables by column number
melt(wide, id.vars = 1:2)
# as an alternative you can also specify the measure-variables
# all other variables will then be used as id-variables
melt(wide, measure.vars = 3:7)
melt(wide, measure.vars = as.character(1950:1954))
long$value <- as.numeric(gsub(",", "", long$value))
# data.table
long <- melt(setDT(wide),
id.vars = c("Code","Country"),
variable.name = "year")[, value := as.numeric(gsub(",", "", value))]
# tidyr and dplyr
long <- wide %>% gather(year, value, -c(Code,Country)) %>%
mutate(value = as.numeric(gsub(",", "", value)))
wide <- read.table(text="Code Country 1950 1951 1952 1953 1954
AFG Afghanistan 20,249 21,352 22,532 23,557 24,555
ALB Albania 8,097 8,986 10,058 11,123 12,246", header=TRUE, check.names=FALSE)
wide %>%
gather(Year, Value, -Code, -Country) %>%
mutate(Year = parse_number(Year)
, Value = parse_number(Value))
Code Country Year Value
1 AFG Afghanistan 1950 20249
2 ALB Albania 1950 8097
3 AFG Afghanistan 1951 21352
4 ALB Albania 1951 8986
5 AFG Afghanistan 1952 22532
6 ALB Albania 1952 10058
7 AFG Afghanistan 1953 23557
8 ALB Albania 1953 11123
9 AFG Afghanistan 1954 24555
10 ALB Albania 1954 12246
cbind(wide[1:2], stack(lapply(wide[-c(1, 2)], as.character)))
## Code Country values ind
## 1 AFG Afghanistan 20,249 1950
## 2 ALB Albania 8,097 1950
## 3 AFG Afghanistan 21,352 1951
## 4 ALB Albania 8,986 1951
## 5 AFG Afghanistan 22,532 1952
## 6 ALB Albania 10,058 1952
## 7 AFG Afghanistan 23,557 1953
## 8 ALB Albania 11,123 1953
## 9 AFG Afghanistan 24,555 1954
## 10 ALB Albania 12,246 1954
sqldf("Select Code, Country, '1950' As Year, `1950` As Value From wide
Union All
Select Code, Country, '1951' As Year, `1951` As Value From wide
Union All
Select Code, Country, '1952' As Year, `1952` As Value From wide
Union All
Select Code, Country, '1953' As Year, `1953` As Value From wide
Union All
Select Code, Country, '1954' As Year, `1954` As Value From wide;")
ValCol <- tail(names(wide), -2)
s <- sprintf("Select Code, Country, '%s' As Year, `%s` As Value from wide", ValCol, ValCol)
mquery <- paste(s, collapse = "\n Union All\n")
cat(mquery) #just to show the query
#> Select Code, Country, '1950' As Year, `1950` As Value from wide
#> Union All
#> Select Code, Country, '1951' As Year, `1951` As Value from wide
#> Union All
#> Select Code, Country, '1952' As Year, `1952` As Value from wide
#> Union All
#> Select Code, Country, '1953' As Year, `1953` As Value from wide
#> Union All
#> Select Code, Country, '1954' As Year, `1954` As Value from wide
sqldf(mquery)
#> Code Country Year Value
#> 1 AFG Afghanistan 1950 20,249
#> 2 ALB Albania 1950 8,097
#> 3 AFG Afghanistan 1951 21,352
#> 4 ALB Albania 1951 8,986
#> 5 AFG Afghanistan 1952 22,532
#> 6 ALB Albania 1952 10,058
#> 7 AFG Afghanistan 1953 23,557
#> 8 ALB Albania 1953 11,123
#> 9 AFG Afghanistan 1954 24,555
#> 10 ALB Albania 1954 12,246
library(tidyr)
pivot_longer(df1, -c(Code, Country), values_to = "Value", names_to = "Year")
# A tibble: 10 x 4
# Code Country Year Value
# <fct> <fct> <chr> <fct>
# 1 AFG Afghanistan 1950 20,249
# 2 AFG Afghanistan 1951 21,352
# 3 AFG Afghanistan 1952 22,532
# 4 AFG Afghanistan 1953 23,557
# 5 AFG Afghanistan 1954 24,555
# 6 ALB Albania 1950 8,097
# 7 ALB Albania 1951 8,986
# 8 ALB Albania 1952 10,058
# 9 ALB Albania 1953 11,123
#10 ALB Albania 1954 12,246
df1 <- structure(list(Code = structure(1:2, .Label = c("AFG", "ALB"), class = "factor"),
Country = structure(1:2, .Label = c("Afghanistan", "Albania"
), class = "factor"), `1950` = structure(1:2, .Label = c("20,249",
"8,097"), class = "factor"), `1951` = structure(1:2, .Label = c("21,352",
"8,986"), class = "factor"), `1952` = structure(2:1, .Label = c("10,058",
"22,532"), class = "factor"), `1953` = structure(2:1, .Label = c("11,123",
"23,557"), class = "factor"), `1954` = structure(2:1, .Label = c("12,246",
"24,555"), class = "factor")), class = "data.frame", row.names = c(NA,
-2L))
# data
wide <- read.table(text="Code Country 1950 1951 1952 1953 1954
AFG Afghanistan 20,249 21,352 22,532 23,557 24,555
ALB Albania 8,097 8,986 10,058 11,123 12,246", header=TRUE, check.names=FALSE)
library(cdata)
# build control table
drec <- data.frame(
Year=as.character(1950:1954),
Value=as.character(1950:1954),
stringsAsFactors=FALSE
)
drec <- cdata::rowrecs_to_blocks_spec(drec, recordKeys=c("Code", "Country"))
# apply control table
cdata::layout_by(drec, wide)
olddata_wide <- read.table(header=TRUE, text='
subject sex control cond1 cond2
1 M 7.9 12.3 10.7
2 F 6.3 10.6 11.1
3 F 9.5 13.1 13.8
4 M 11.5 13.4 12.9
')
# Make sure the subject column is a factor
olddata_wide$subject <- factor(olddata_wide$subject)
olddata_long <- read.table(header=TRUE, text='
subject sex condition measurement
1 M control 7.9
1 M cond1 12.3
1 M cond2 10.7
2 F control 6.3
2 F cond1 10.6
2 F cond2 11.1
3 F control 9.5
3 F cond1 13.1
3 F cond2 13.8
4 M control 11.5
4 M cond1 13.4
4 M cond2 12.9
')
# Make sure the subject column is a factor
olddata_long$subject <- factor(olddata_long$subject)