R 创建以其他列中的值为条件的索引；随时间变化的差异
我正在努力解决以下问题： 下面的dataframe包含各种ID随时间变化的值的开发。我试图得到的是这些值的增加/减少，基于事件发生年份的值。一个id内可能发生多个事件，因此新事件将成为该id的新基准年。 为了让事情更清楚，我也在下面添加了我想要的结果 我拥有的R 创建以其他列中的值为条件的索引；随时间变化的差异,r,plyr,seq,R,Plyr,Seq,我正在努力解决以下问题： 下面的dataframe包含各种ID随时间变化的值的开发。我试图得到的是这些值的增加/减少，基于事件发生年份的值。一个id内可能发生多个事件，因此新事件将成为该id的新基准年。 为了让事情更清楚，我也在下面添加了我想要的结果 我拥有的 id value year event a 100 1950 NA a 101 1951 NA a 102 1952 NA a 103 1953 NA a
id value year event
a 100 1950 NA
a 101 1951 NA
a 102 1952 NA
a 103 1953 NA
a 104 1954 NA
a 105 1955 X
a 106 1956 NA
a 107 1957 NA
a 108 1958 NA
a 107 1959 Y
a 106 1960 NA
a 105 1961 NA
a 104.8 1962 NA
a 104.2 1963 NA
b 70 1970 NA
b 75 1971 NA
b 80 1972 NA
b 85 1973 NA
b 90 1974 NA
b 60 1975 Z
b 59 1976 NA
b 58 1977 NA
b 57 1978 NA
b 56 1979 NA
b 55 1980 W
b 54 1981 NA
b 53 1982 NA
b 52 1983 NA
b 51 1984 NA
id value year event index growth
a 100 1950 NA 0
a 101 1951 NA 0
a 102 1952 NA 0
a 103 1953 NA 0
a 104 1954 NA 0
a 105 1955 X 1 1
a 106 1956 NA 2 1.00952381
a 107 1957 NA 3 1.019047619
a 108 1958 NA 4 1.028571429
a 107 1959 Y 1 1 #new baseline year
a 106 1960 NA 2 0.990654206
a 105 1961 NA 3 0.981308411
a 104.8 1962 NA 4 0.979439252
a 104.2 1963 NA 5 0.973831776
b 70 1970 NA 6
b 75 1971 NA 7
b 80 1972 NA 8
b 85 1973 NA 9
b 90 1974 NA 10
b 60 1975 Z 1 1
b 59 1976 NA 2 0.983333333
b 58 1977 NA 3 0.966666667
b 57 1978 NA 4 0.95
b 56 1979 NA 5 0.933333333
b 55 1980 W 1 1 #new baseline year
b 54 1981 NA 2 0.981818182
b 53 1982 NA 3 0.963636364
b 52 1983 NA 4 0.945454545
b 51 1984 NA 5 0.927272727
x <- ddply(x, .(id), transform, year.min=min(year[!is.na(event)])) #identifies first event year
x1 <- ddply(x[x$year>=x$year.min,], .(id), transform, index=seq_along(id)) #creates counter years following first event; prior years are removed
x1 <- x1[order(x1$id, x1$year),] #sort
x1 <- ddply(x1, .(id), transform, growth=100*(value/value[1])) #calculate difference, however, based on first event year; this is wrong.
library(Interact) #i then merge the df with the years prior to first event which have been removed in the begining
x$id.year <- interaction(x$id,x$year)
x1$id.year <- interaction(x1$id,x1$year)
x$index <- x$growth <- NA
y <- rbind(x[x$year<x$year.min,],x1)
y <- y[order(y$id,y$year),]
x试试：
ddf$index=0
ddf$增长=0
基线=0
r=1；开始=错误
适用于（1:nrow（ddf））{
if（is.na（ddf$event[r]））{
如果（启动）{
ddf$指数[r]=ddf$指数[r-1]+1
ddf$增长率[r]=ddf$价值[r]/基线
}
else{ddf$index[r]=0；
}
}
否则{
开始=T
ddf$索引[r]=1
ddf$增长率[r]=1
基线=ddf$值[r]
}
}
ddf
id值年度事件指数增长
1A 100.0 1950 0.0000000
2 a 101.0 1951 0.0000000
3 a 102.0 1952 0.0000000
4 a 103.0 1953 0.0000000
5 a 104.0 1954 0.0000000
6a 105.01955x110000000
7 a 106.0 1956 2 1.0095238
8 a 107.0 1957 3 1.0190476
9 a 108.0 1958 4 1.0285714
10 a 107.0 1959年Y 11.0000000
11A 106.0 1960 2 0.9906542
12 a 105.0 1961 3 0.9813084
13 a 104.8 1962 4 0.9794393
14 a 104.2 1963 5 0.9738318
15 b 70.0 1970 6 0.6542056
16 b 75.0 1971 7 0.7009346
17 b 80.0 1972 8 0.7476636
18 b 85.0 1973 9 0.7943925
19 b 90.0 1974 10 0.8411215
20 b 60.0 1975 Z 11.0000000
21 b 59.0 1976 2 0.9833333
22 b 58.0 1977 3 0.9666667
23 b 57.0 1978 4 0.9500000
24 b 56.0 1979 5 0.9333333
25 b 55.0 1980 W 11.0000000
26 b 54.0 1981 2 0.9818182
27 b 53.0 1982 3 0.96364
28 b 52.0 1983 4 0.94545
29 b 51.0 1984 5 0.92727
#创建一个标记，通过id或
#当id更改时
dat$tag这是一个使用dplyr的解决方案
ana <- group_by(mydf, id) %>%
do(na.locf(., na.rm = FALSE)) %>%
mutate(value = as.numeric(value)) %>%
group_by(id, event) %>%
mutate(growth = value/value[1]) %>%
mutate(index = row_number(event))
ana$growth[is.na(ana$event)] <- 0
id value year event growth index
1 a 100.0 1950 NA 0.0000000 1
2 a 101.0 1951 NA 0.0000000 2
3 a 102.0 1952 NA 0.0000000 3
4 a 103.0 1953 NA 0.0000000 4
5 a 104.0 1954 NA 0.0000000 5
6 a 105.0 1955 X 1.0000000 1
7 a 106.0 1956 X 1.0095238 2
8 a 107.0 1957 X 1.0190476 3
9 a 108.0 1958 X 1.0285714 4
10 a 107.0 1959 Y 1.0000000 1
11 a 106.0 1960 Y 0.9906542 2
12 a 105.0 1961 Y 0.9813084 3
13 a 104.8 1962 Y 0.9794393 4
14 a 104.2 1963 Y 0.9738318 5
15 b 70.0 1970 NA 0.0000000 1
16 b 75.0 1971 NA 0.0000000 2
17 b 80.0 1972 NA 0.0000000 3
18 b 85.0 1973 NA 0.0000000 4
19 b 90.0 1974 NA 0.0000000 5
20 b 60.0 1975 Z 1.0000000 1
21 b 59.0 1976 Z 0.9833333 2
22 b 58.0 1977 Z 0.9666667 3
23 b 57.0 1978 Z 0.9500000 4
24 b 56.0 1979 Z 0.9333333 5
25 b 55.0 1980 W 1.0000000 1
26 b 54.0 1981 W 0.9818182 2
27 b 53.0 1982 W 0.9636364 3
28 b 52.0 1983 W 0.9454545 4
ana%
do（na.locf（，na.rm=FALSE））%>%
变异（值=作为数值（值））%>%
分组依据（id，事件）%>%
突变（增长=值/值[1]）%>%
变异（索引=行数（事件））
ana$growth[is.na（ana$event）]很棒。我只加了dat
# Create a tag to indicate the start of each new event by id or
# when id changes
dat$tag <- with(dat, ave(as.character(event), as.character(id),
FUN=function(i) cumsum(!is.na(i))))
# Calculate the growth by id and tag
# this will also produce results for each id before an event has happened
dat$growth <- with(dat, ave(value, tag, id, FUN=function(i) i/i[1] ))
# remove growth prior to an event (this will be when tag equals zero as no
# event have occurred)
dat$growth[dat$tag==0] <- NA
ana <- group_by(mydf, id) %>%
do(na.locf(., na.rm = FALSE)) %>%
mutate(value = as.numeric(value)) %>%
group_by(id, event) %>%
mutate(growth = value/value[1]) %>%
mutate(index = row_number(event))
ana$growth[is.na(ana$event)] <- 0
id value year event growth index
1 a 100.0 1950 NA 0.0000000 1
2 a 101.0 1951 NA 0.0000000 2
3 a 102.0 1952 NA 0.0000000 3
4 a 103.0 1953 NA 0.0000000 4
5 a 104.0 1954 NA 0.0000000 5
6 a 105.0 1955 X 1.0000000 1
7 a 106.0 1956 X 1.0095238 2
8 a 107.0 1957 X 1.0190476 3
9 a 108.0 1958 X 1.0285714 4
10 a 107.0 1959 Y 1.0000000 1
11 a 106.0 1960 Y 0.9906542 2
12 a 105.0 1961 Y 0.9813084 3
13 a 104.8 1962 Y 0.9794393 4
14 a 104.2 1963 Y 0.9738318 5
15 b 70.0 1970 NA 0.0000000 1
16 b 75.0 1971 NA 0.0000000 2
17 b 80.0 1972 NA 0.0000000 3
18 b 85.0 1973 NA 0.0000000 4
19 b 90.0 1974 NA 0.0000000 5
20 b 60.0 1975 Z 1.0000000 1
21 b 59.0 1976 Z 0.9833333 2
22 b 58.0 1977 Z 0.9666667 3
23 b 57.0 1978 Z 0.9500000 4
24 b 56.0 1979 Z 0.9333333 5
25 b 55.0 1980 W 1.0000000 1
26 b 54.0 1981 W 0.9818182 2
27 b 53.0 1982 W 0.9636364 3
28 b 52.0 1983 W 0.9454545 4