[英]Merge several data frames on two common columns
我已经看到了一些问题,关于合并的CSV文件到一个数据帧。 如果数据框已在工作空间中,该怎么办。 我有五个广泛的动物园,我将它们投射为数据框,然后融为一体。 这是一个人的头:
> head(df.mon.ssf.ret)
date variable value
1 2009.000 AA1C NA
2 2009.083 AA1C NA
3 2009.167 AA1C NA
4 2009.250 AA1C NA
5 2009.333 AA1C NA
6 2009.417 AA1C NA
我可以在“日期”和“变量”中通过一系列嵌套合并来合并它们,但这似乎很笨拙。 有没有更多的编程方式合并?
如果我对所有动物园中的色谱柱都具有相同的顺序有信心,我cbind
melt保持这种顺序并使用cbind
? 谢谢!
更新:
关于melt的使用哲学,我缺少一些东西。 当我合并为动物园并使用三个动物园融合为一个非常宽的数据框时,会发生以下情况:
> temp <- merge(z.ssf.oi, z.ssf.oig, z.ssf.ret)
> class(temp)
[1] "zoo"
> temp2 <- cbind(index(temp), as.data.frame(temp))
> class(temp2)
[1] "data.frame"
> names(temp2)[1] <- "date"
> dim(temp2)
[1] 12 1204
> temp3 <- melt(temp2, id="date")
Error in data.frame(ids, variable, value) :
arguments imply differing number of rows: 12, 14436
> head(temp2)[, 1:5]
date AA1C.z.ssf.oi AAPL1C.z.ssf.oi ABT1C.z.ssf.oi ABX1C.z.ssf.oi
Jan 2009 Jan 2009 1895.800 49191.25 NA NA
Feb 2009 Feb 2009 1415.579 42650.26 NA 6267.96
Mar 2009 Mar 2009 1501.398 36712.20 NA 11581.65
Apr 2009 Apr 2009 1752.936 74376.27 NA 12168.29
May 2009 May 2009 1942.874 96307.30 NA 13490.60
Jun 2009 Jun 2009 NA 79170.70 NA 16337.21
更新2:感谢您的帮助! 这是一个非常手动的解决方案
> A <- cbind(index(z.ssf.oi), as.data.frame(z.ssf.oi))
> names(A)[1] <- "date"
> B <- cbind(index(z.ssf.oig), as.data.frame(z.ssf.oig))
> names(B)[1] <- "date"
> C <- cbind(index(z.ssf.ret), as.data.frame(z.ssf.ret))
> names(C)[1] <- "date"
> A.melt <- melt(A, id="date")
> head(A.melt)
date variable value
1 Jan 2009 A1C NA
2 Feb 2009 A1C NA
3 Mar 2009 A1C NA
4 Apr 2009 A1C NA
5 May 2009 A1C NA
6 Jun 2009 A1C NA
> B.melt <- melt(B, id="date")
> C.melt <- melt(C, id="date")
> ans <- merge(merge(A.melt, B.melt, by=c("date", "variable")), C.melt, by=c("date", "variable"))
> names(ans)[3:5] <- c("oi", "oig", "ret")
> head(ans)
date variable oi oig ret
1 Apr 2009 A1C NA NA NA
2 Apr 2009 AA1C NA NA NA
3 Apr 2009 AAPL1C 59316.88 0.3375786 0.008600073
4 Apr 2009 ABB1C NA NA NA
5 Apr 2009 ABT1C NA NA NA
6 Apr 2009 ABX1C NA NA NA
(并且NA来自家中不完整的数据集,需要从我的数据库进行筛选时使用拨号盘)
更新3:这是一些dput(我将每个宽阔的动物园的[1:10,1:10]子集转换为数据帧)
> dput(A)
structure(list(group = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L), class = "factor", .Label = "oi"), date = structure(c(2009,
2009.08333333333, 2009.16666666667, 2009.25, 2009.33333333333,
2009.41666666667, 2009.5, 2009.58333333333, 2009.66666666667,
2009.75), class = "yearmon"), AA1C = c(NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_
), AAPL1C = c(49226.391, 42662.1589473684, 35354.4254545455,
57161.6495238095, 84362.895, NA, NA, 47011.8519047619, 57852.2171428571,
33058.0090909091), ABT1C = c(NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_),
ABX1C = c(NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_), ACE1C = c(NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_), ACI1C = c(NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_), ACS1C = c(NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_), ADBE1C = c(NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_
), ADCT1C = c(NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_), ADI1C = c(NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_)), .Names = c("group", "date",
"AA1C", "AAPL1C", "ABT1C", "ABX1C", "ACE1C", "ACI1C", "ACS1C",
"ADBE1C", "ADCT1C", "ADI1C"), row.names = c("Jan 2009", "Feb 2009",
"Mar 2009", "Apr 2009", "May 2009", "Jun 2009", "Jul 2009", "Aug 2009",
"Sep 2009", "Oct 2009"), class = "data.frame")
> dput(B)
structure(list(group = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L), class = "factor", .Label = "oig"), date = structure(c(2009.08333333333,
2009.16666666667, 2009.25, 2009.33333333333, 2009.41666666667,
2009.5, 2009.58333333333, 2009.66666666667, 2009.75, 2009.83333333333
), class = "yearmon"), AA1C = c(NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_
), AAPL1C = c(-0.143117562125788, -0.187888745830302, 0.480459636485712,
0.389244461579155, NA, NA, NA, 0.207492040517069, -0.559627909130612,
NA), ABT1C = c(NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_), ABX1C = c(NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_), ACE1C = c(NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_
), ACI1C = c(NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_), ACS1C = c(NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_), ADBE1C = c(NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_
), ADCT1C = c(NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_), ADI1C = c(NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_)), .Names = c("group", "date", "AA1C", "AAPL1C",
"ABT1C", "ABX1C", "ACE1C", "ACI1C", "ACS1C", "ADBE1C", "ADCT1C",
"ADI1C"), row.names = c("Feb 2009", "Mar 2009", "Apr 2009", "May 2009",
"Jun 2009", "Jul 2009", "Aug 2009", "Sep 2009", "Oct 2009", "Nov 2009"
), class = "data.frame")
> dput(C)
structure(list(group = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L), class = "factor", .Label = "ret"), date = structure(c(2009,
2009.08333333333, 2009.16666666667, 2009.25, 2009.33333333333,
2009.41666666667, 2009.5, 2009.58333333333, 2009.66666666667,
2009.75), class = "yearmon"), AA1C = c(NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_
), AAPL1C = c(-0.143117562125788, -0.187888745830302, 0.480459636485712,
0.389244461579155, NA, NA, NA, 0.207492040517069, -0.559627909130612,
NA), ABT1C = c(NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_), ABX1C = c(NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_), ACE1C = c(NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_
), ACI1C = c(NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_), ACS1C = c(NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_), ADBE1C = c(NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_
), ADCT1C = c(NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_), ADI1C = c(NA_real_,
NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_)), .Names = c("group", "date", "AA1C", "AAPL1C",
"ABT1C", "ABX1C", "ACE1C", "ACI1C", "ACS1C", "ADBE1C", "ADCT1C",
"ADI1C"), row.names = c("Feb 2009", "Mar 2009", "Apr 2009", "May 2009",
"Jun 2009", "Jul 2009", "Aug 2009", "Sep 2009", "Oct 2009", "Nov 2009"
), class = "data.frame")
你可以试试看。 未经测试,因为您的示例不可复制。 如果您想要一个更好的答案,请给我们一些有关z.sfff.oi,z.sff.oig和z.sff.ret的伪数据。 您可以使用dput()为可重现的数据集生成代码。
A <- data.frame(Group = "oi", date = as.factor(index(z.ssf.oi),) as.data.frame(z.ssf.oi)))
B <- data.frame(Group = "oig", date = as.factor(index(z.ssf.oig)), as.data.frame(z.ssf.oig)))
C <- data.frame(Group = "ret", date = as.factor(index(z.ssf.ret)), as.data.frame(z.ssf.ret)))
Long <- melt(rbind(A, B, C), id.vars = c("Group", "date")))
cast(date ~ Group, data = Long)
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.