R 条件相乘向量（货币换算）
我有一个相当大的数据框，其中变量以年度当地货币计价（在下面的示例中为澳大利亚和奥地利货币）： 我想使用以下乘数将此数据框中的值转换为1995美元：R 条件相乘向量（货币换算）,r,vector,conditional,currency,R,Vector,Conditional,Currency,我有一个相当大的数据框，其中变量以年度当地货币计价（在下面的示例中为澳大利亚和奥地利货币）： 我想使用以下乘数将此数据框中的值转换为1995美元： Country _1995 _1996 _1997 _1998 AUS 0,7415 0,78295 0,74406 0,6294 AUT 1,36646 1,30031 1,12904 1,11319 因此，对于表1中包含变量AUS的每一行，每年的值乘以表2中包含AUS的行中相应的$19
Country _1995 _1996 _1997 _1998
AUS 0,7415 0,78295 0,74406 0,6294
AUT 1,36646 1,30031 1,12904 1,11319
Country Var _1995 _1996 _1997 _1998
AUS GO 1014828*0,7415 1059326*0,78295 1119101*0,74406 1194995*0,6294
等等。这可行吗？非常感谢您的帮助 我建议从宽格式改为长格式，这将大大简化操作。整形是最复杂的部分。我在这里使用示例数据和
restrapedplyrrestrape2set.seed（1）
dat类似这样的内容：
（假设您的本地货币数据帧被称为“本地”，带有乘数的数据帧被命名为“conv”。）
#对国家/地区进行分解，否则会得到非常奇怪的结果
local$Country创建一个小助手函数，然后通过管道传输数据可能是最简单的。要使其更清晰，请将转换的行.names
设置为国家/地区并删除该列
df <- read.table(header = TRUE, text = '
Country Var _1995 _1996 _1997 _1998
AUS GO 1014828 1059326 1119101 1194995
AUS L 36873 38895 39502 40425
AUS K 41498 45008 48683 47252
AUT GO 289923 299487 309734 323273
AUT GO 8032 7849 8049 7815
AUT L 1094 1151 1163 1152
AUT K 12032 11760 11743 11611
')
conversions <- read.table(header = TRUE, text='
Country _1995 _1996 _1997 _1998
AUS 0.7415 0.78295 0.74406 0.6294
AUT 1.36646 1.30031 1.12904 1.11319
')
# the primary code to use
# set row.names, makes indexing cleaner below
row.names(conversions) <- conversions$Country
conversions <- conversions[,-1]
# helper function for conversions
myfun <- function(df1, df2) {
df1[,3:6] <- df1[,3:6] * df2[df1$Country,]
df1
}
library(dplyr)
df %>%
group_by(Country) %>%
do(myfun(., conversions))
Source: local data frame [7 x 6]
Groups: Country
Country Var X_1995 X_1996 X_1997 X_1998
1 AUS GO 752494.962 829399.292 832678.290 752129.853
2 AUS L 27341.330 30452.840 29391.858 25443.495
3 AUS K 30770.767 35239.014 36223.073 29740.409
4 AUT GO 396168.183 389425.941 349702.075 359864.271
5 AUT GO 10975.407 10206.133 9087.643 8699.580
6 AUT L 1494.907 1496.657 1313.074 1282.395
7 AUT K 16441.247 15291.646 13258.317 12925.249
df以下是我尝试使用dplyr
。我用各种方法进行了实验，得出了这个结论。我首先将数据（即，mydf
）按国家划分。对于列表中的每个数据帧，我希望应用适当的汇率。因此，我使用国家
对汇率数据（即汇率
）进行了细分，并创建了新数据。（当代码运行时，R计算每个国家的汇率。）我应用我的答案，以便使用mutate\u each（）
计算多个列。最后，我使用bind_rows（）
组合所有数据帧
lapply(split(mydf, mydf$Country), function(i) {
foo <- rate[rate$Country == unique(i$Country),]
mutate_each(i, funs(. * foo$.), y_1995:y_1998)
}) %>%
bind_rows
# Country Var y_1995 y_1996 y_1997 y_1998
#1 AUS GO 752494.962 829399.292 832678.290 752129.853
#2 AUS L 27341.330 30452.840 29391.858 25443.495
#3 AUS K 30770.767 35239.014 36223.073 29740.409
#4 AUT GO 396168.183 389425.941 349702.075 359864.271
#5 AUT GO 10975.407 10206.133 9087.643 8699.580
#6 AUT L 1494.907 1496.657 1313.074 1282.395
#7 AUT K 16441.247 15291.646 13258.317 12925.249
lapply（拆分（mydf，mydf$国家），函数（i）{
富%
绑定行
#国家变量y_1995 y_1996 y_1997 y_1998
#1澳大利亚GO 752494.962 829399.292 832678.290 752129.853
#2澳大利亚法律27341.330 30452.840 29391.858 25443.495
#3澳大利亚K 30770.767 35239.014 36223.073 29740.409
#4 AUT GO 396168.183 389425.941 349702.075 359864.271
#5 AUT GO 10975.407 10206.133 9087.643 8699.580
#6 AUT L 1494.907 1496.657 1313.074 1282.395
#7 AUT K 16441.247 15291.646 13258.317 12925.249
资料
mydf您可以使用dput
提供两个示例数据集吗？或者合并（数据集，可转换，by=“country”）可能会有帮助，然后每年乘以列。谢谢。尝试了你的解决方案，尽管我在重塑软件包中使用了熔化功能，而不是你的方式。谢谢。尝试了你的解决方案，尽管我使用了“重塑”中的熔化功能，而不是你的方式。在我到达“merged$converted检查您试图乘法的变量的class（）
。该错误意味着其中一个属于类“factor”。您可能需要通过类似as.numeric（as.character（variable））
的方式将变量类修改为numeric。是的。我的数据似乎有问题（即某些单元格中的非数字字符）。您的解决方案对于非发起人来说既简单又显而易见，我已经将一些修改后的代码用于其他操作。再次感谢！
long <- reshape(dat, times = 1996:1998, v.names = "Value",
varying = c("v_1996", "v_1997", "v_1998"),
direction = "long")
head(long, 3)
# Country Var time Value id
# 1.1996 AUS GO 1996 -0.6264538 1
# 2.1996 AUS L 1996 0.1836433 2
# 3.1996 AUS K 1996 -0.8356286 3
# 4.1996 AUT GO 1996 1.5952808 4
mlong <- reshape(multipliers, times = 1995:1998, v.names = "mult",
varying = c("v_1995","v_1996", "v_1997", "v_1998"),
direction = "long")
head(mlong, 3)
# Country time mult id
# 1.1995 AUS 1995 0.74150 1
# 2.1995 AUT 1995 1.36646 2
# 1.1996 AUS 1996 0.78295 1
merged <- merge(long, mlong, by = c("Country", "time"))
merged$converted <- merged$Value * merged$mult
head(merged, 3)
# Country time Var Value id.x mult id.y converted
# 1 AUS 1996 GO -0.6264538 1 0.78295 1 -0.4904820
# 2 AUS 1996 L 0.1836433 2 0.78295 1 0.1437835
# 3 AUS 1996 K -0.8356286 3 0.78295 1 -0.6542554
reshape(merged, idvar = c("Country", "Var"), direction = "wide",
drop = c("id.x", "id.y","mult"))
# Country Var Value.1996 converted.1996 Value.1997 converted.1997 Value.1998 converted.1998
# 1 AUS GO -0.6264538 -0.4904820 0.4874291 0.3626765 -0.62124058 -0.39100882
# 2 AUS L 0.1836433 0.1437835 0.7383247 0.5493579 -2.21469989 -1.39393211
# 3 AUS K -0.8356286 -0.6542554 0.5757814 0.4284159 1.12493092 0.70803152
# 10 AUT GO 1.5952808 2.0743596 -0.3053884 -0.3447957 -0.04493361 -0.05001964
# 11 AUT L 0.3295078 0.4284623 1.5117812 1.7068614 -0.01619026 -0.01802284
# 12 AUT K -0.8204684 -1.0668632 0.3898432 0.4401486 0.94383621 1.05066903
#unfactorise Country or you'll get very strange results
local$Country <- as.character(local$Country); conv$Country <- as.character(conv$Country)
countries <- unique(local$Country)
for(i in 1:length(countries)) {
cy <- countries[i]
rates <- matrix(conv[conv$Country==cy, -1])
local[local$Country==cy, -c(1,2)] <- local[local$Country==cy, -c(1,2)] * rates
}
df <- read.table(header = TRUE, text = '
Country Var _1995 _1996 _1997 _1998
AUS GO 1014828 1059326 1119101 1194995
AUS L 36873 38895 39502 40425
AUS K 41498 45008 48683 47252
AUT GO 289923 299487 309734 323273
AUT GO 8032 7849 8049 7815
AUT L 1094 1151 1163 1152
AUT K 12032 11760 11743 11611
')
conversions <- read.table(header = TRUE, text='
Country _1995 _1996 _1997 _1998
AUS 0.7415 0.78295 0.74406 0.6294
AUT 1.36646 1.30031 1.12904 1.11319
')
# the primary code to use
# set row.names, makes indexing cleaner below
row.names(conversions) <- conversions$Country
conversions <- conversions[,-1]
# helper function for conversions
myfun <- function(df1, df2) {
df1[,3:6] <- df1[,3:6] * df2[df1$Country,]
df1
}
library(dplyr)
df %>%
group_by(Country) %>%
do(myfun(., conversions))
Source: local data frame [7 x 6]
Groups: Country
Country Var X_1995 X_1996 X_1997 X_1998
1 AUS GO 752494.962 829399.292 832678.290 752129.853
2 AUS L 27341.330 30452.840 29391.858 25443.495
3 AUS K 30770.767 35239.014 36223.073 29740.409
4 AUT GO 396168.183 389425.941 349702.075 359864.271
5 AUT GO 10975.407 10206.133 9087.643 8699.580
6 AUT L 1494.907 1496.657 1313.074 1282.395
7 AUT K 16441.247 15291.646 13258.317 12925.249
lapply(split(mydf, mydf$Country), function(i) {
foo <- rate[rate$Country == unique(i$Country),]
mutate_each(i, funs(. * foo$.), y_1995:y_1998)
}) %>%
bind_rows
# Country Var y_1995 y_1996 y_1997 y_1998
#1 AUS GO 752494.962 829399.292 832678.290 752129.853
#2 AUS L 27341.330 30452.840 29391.858 25443.495
#3 AUS K 30770.767 35239.014 36223.073 29740.409
#4 AUT GO 396168.183 389425.941 349702.075 359864.271
#5 AUT GO 10975.407 10206.133 9087.643 8699.580
#6 AUT L 1494.907 1496.657 1313.074 1282.395
#7 AUT K 16441.247 15291.646 13258.317 12925.249
mydf <- structure(list(Country = structure(c(1L, 1L, 1L, 2L, 2L, 2L,
2L), .Label = c("AUS", "AUT"), class = "factor"), Var = structure(c(1L,
3L, 2L, 1L, 1L, 3L, 2L), .Label = c("GO", "K", "L"), class = "factor"),
y_1995 = c(1014828, 36873, 41498, 289923, 8032, 1094, 12032
), y_1996 = c(1059326, 38895, 45008, 299487, 7849, 1151,
11760), y_1997 = c(1119101, 39502, 48683, 309734, 8049, 1163,
11743), y_1998 = c(1194995, 40425, 47252, 323273, 7815, 1152,
11611)), .Names = c("Country", "Var", "y_1995", "y_1996",
"y_1997", "y_1998"), row.names = c(NA, -7L), class = "data.frame")
# Country Var y_1995 y_1996 y_1997 y_1998
#1 AUS GO 1014828 1059326 1119101 1194995
#2 AUS L 36873 38895 39502 40425
#3 AUS K 41498 45008 48683 47252
#4 AUT GO 289923 299487 309734 323273
#5 AUT GO 8032 7849 8049 7815
#6 AUT L 1094 1151 1163 1152
#7 AUT K 12032 11760 11743 11611
rate <- structure(list(Country = structure(1:2, .Label = c("AUS", "AUT"
), class = "factor"), y_1995 = c(0.7415, 1.36646), y_1996 = c(0.78295,
1.30031), y_1997 = c(0.74406, 1.12904), y_1998 = c(0.6294, 1.11319
)), .Names = c("Country", "y_1995", "y_1996", "y_1997", "y_1998"
), row.names = c(NA, -2L), class = "data.frame")
# Country y_1995 y_1996 y_1997 y_1998
#1 AUS 0.74150 0.78295 0.74406 0.62940
#2 AUT 1.36646 1.30031 1.12904 1.11319