String 基于字符串值重塑数据帧
我想根据字符串变量中的唯一值将数据帧融合为长格式。一些示例数据：String 基于字符串值重塑数据帧,string,r,reshape2,String,R,Reshape2,我想根据字符串变量中的唯一值将数据帧融合为长格式。一些示例数据： df1 <- structure(list(lllocatie = structure(c(3L, 13L, 5L, 10L, 4L, 32L, 10L, 10L, 22L, 4L, 36L, 37L, 31L, 15L, 23L, 20L, 34L, 8L, 35L, 24L, 19L, 19L, 2L, 29L, 26L, 25L, 25L, 30L, 8L, 22L, 9L, 20L, 19L, 12L, 16L, 3
df1 <- structure(list(lllocatie = structure(c(3L, 13L, 5L, 10L, 4L, 32L, 10L, 10L, 22L, 4L, 36L, 37L, 31L, 15L, 23L, 20L, 34L, 8L, 35L, 24L, 19L, 19L, 2L, 29L, 26L, 25L, 25L, 30L, 8L, 22L, 9L, 20L, 19L, 12L, 16L, 38L, 6L, 27L, 7L, 11L, 17L, 33L, 14L, 2L, 21L, 18L, 9L, 28L, 32L, 1L), .Label = c("Annen", "Appingedam", "Assen", "Eleveld", "Emmen", "Farmsum", "Froombosch", "Garrelsweer", "Garsthuizen", "Geelbroek", "Hellum", "Hoogezand", "Hooghalen", "Huizinge", "Langelo", "Leermens", "Meedhuizen", "Onderdendam", "Oosterwijtwerd", "Overschild", "Roodeschool", "Roswinkel", "Sappemeer", "Sint Annen", "Slochteren", "Startenhuizen", "Steendam", "Stitswerd", "t-Zandt", "Ten Post", "Tjuchem", "Toornwerd", "Tripscompagnie", "Westerbroek", "Westerwijtwerd", "Winneweer", "Woudbloem", "Zandeweer"), class = "factor"), lat = c(52.992, 52.928, 52.771, 52.952, 52.965, 53.358, 52.953, 52.956, 52.831, 52.961, 53.32, 53.21, 53.294, 53.084, 53.16, 53.285, 53.177, 53.305, 53.316, 53.315, 53.333, 53.336, 53.332, 53.363, 53.368, 53.208, 53.202, 53.294, 53.306, 52.833, 53.37, 53.279, 53.323, 53.17, 53.345, 53.39, 53.316, 53.275, 53.194, 53.226, 53.294, 53.156, 53.359, 53.335, 53.423, 53.324, 53.372, 53.365, 53.351, 53.061), lon = c(6.548, 6.552, 6.914, 6.575, 6.573, 6.657, 6.572, 6.562, 7.032, 6.57, 6.74, 6.747, 6.868, 6.465, 6.805, 6.795, 6.685, 6.793, 6.65, 6.66, 6.837, 6.808, 6.848, 6.765, 6.675, 6.812, 6.82, 6.753, 6.777, 7.045, 6.72, 6.807, 6.805, 6.747, 6.808, 6.68, 6.962, 6.828, 6.798, 6.835, 6.95, 6.823, 6.682, 6.852, 6.77, 6.613, 6.743, 6.577, 6.628, 6.698), mag.cat = c(3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 3L, 3L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 3L, 2L, 2L, 3L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 3L, 2L, 2L, 3L, 3L), names = structure(c(3L, 4L, 9L, 2L, 2L, 11L, 2L, 8L, 10L, 2L, 21L, 29L, 1L, 19L, 1L, 24L, 28L, 1L, 1L, 1L, 23L, 23L, 1L, 27L, 12L, 1L, 15L, 17L, 16L, 10L, 1L, 24L, 1L, 1L, 20L, 14L, 1L, 25L, 1L, 1L, 1L, 1L, 18L, 1L, 22L, 7L, 13L, 26L, 6L, 5L), .Label = c("", "Amen,Assen,Deurze,Ekehaar,Eleveld,Geelbroek,Hooghalen,Marwijksoord,Vredenheim", "Amen,Assen,Deurze,Ekehaar,Eleveld,Geelbroek,Taarlo,Ubbena", "Amen,Ekehaar,Eleveld,Geelbroek,Hooghalen", "Annen,Gasteren,Nieuw Annerveen,Oud Annerveen,Schipborg,Zeegse,Zuidlaren","Bedum,Eppenhuizen,Garsthuizen,Huizinge,Kantens,Middelstum,Onderdendam,Rottum,Sint Annen,Startenhuizen,Stedum,Stitswerd,Tinallinge,Toornwerd,Uithuizen,Usquert,Warffum,Westeremden,Westerwijtwerd,Zandeweer", "Bedum,Huizinge,Kantens,Lellens,Middelstum,Onderdendam,Rottum,Sauwerd,Sint Annen,Stedum,Stitswerd,Thesinge,Tinallinge,Toornwerd,Westeremden,Westerwijtwerd,Wetsinge,Winsum", "Eleveld,Geelbroek", "Emmen", "Emmer-Compascuum,Roswinkel", "Eppenhuizen,Garsthuizen,Huizinge,Kantens,Middelstum,Oldenzijl,Onderdendam,Rottum,Startenhuizen,Stedum,Stitswerd,Toornwerd,Uithuizen,Westeremden,Westerwijtwerd,Zandeweer","Eppenhuizen,Garsthuizen,Huizinge,Kantens,Middelstum,Oldenzijl,Rottum,Startenhuizen,Toornwerd,Westeremden,Zandeweer", "Eppenhuizen,Garsthuizen,Oldenzijl,Startenhuizen,t-Zandt,Westeremden,Zeerijp,Zijldijk", "Eppenhuizen,Oldenzijl,Startenhuizen,Uithuizen,Zandeweer", "Froombosch,Hellum,Noordbroek,Sappemeer,Schildwolde,Slochteren", "Garrelsweer", "Garrelsweer,Overschild,Ten Post,Winneweer", "Huizinge,Startenhuizen", "Langelo", "Leermens,Oosterwijtwerd", "Loppersum,Winneweer", "Oosteinde,Roodeschool", "Oosterwijtwerd", "Overschild", "Steendam", "Stitswerd", "t-Zandt,Zeerijp", "Westerbroek", "Woudbloem"), class = "factor")), .Names = c("lllocatie", "lat", "lon", "mag.cat", "names"), class = "data.frame", row.names = c(NA, -50L))
lllocatie lat lon mag.cat names
Assen 52.992 6.548 3 Amen
Assen 52.992 6.548 3 Assen
Assen 52.992 6.548 3 Deurze
Assen 52.992 6.548 3 Ekehaar
Assen 52.992 6.548 3 Eleveld
Assen 52.992 6.548 3 Geelbroek
Assen 52.992 6.548 3 Taarlo
Assen 52.992 6.548 3 Ubbena
names库（data.table）
library(data.table)
dt <- data.table(df1)
result <- dt[,strsplit(as.character(names),",",fixed=T),
by=list(lllocatie,lat,lon,mag.cat)]
head(result,10)
# lllocatie lat lon mag.cat V1
# 1: Assen 52.992 6.548 3 Amen
# 2: Assen 52.992 6.548 3 Assen
# 3: Assen 52.992 6.548 3 Deurze
# 4: Assen 52.992 6.548 3 Ekehaar
# 5: Assen 52.992 6.548 3 Eleveld
# 6: Assen 52.992 6.548 3 Geelbroek
# 7: Assen 52.992 6.548 3 Taarlo
# 8: Assen 52.992 6.548 3 Ubbena
# 9: Hooghalen 52.928 6.552 3 Amen
# 10: Hooghalen 52.928 6.552 3 Ekehaar
这是一种地理编码数据。熔化的数据帧每个位置都有一个lat、long和mag.cat？对于单行，所有位置都将具有着色坐标。这就是你想要的吗？@Henrik这确实回答了我的问题。另一方面，jlhoward的答案给出了一个很好的替代解决方案。由于jlhoward的方法更容易理解，我认为这个问题和答案是对SO的一个有价值的补充。我编辑了我的问题。希望它描述了我现在想要取得更好的成绩。我编辑了我的回复。感谢@BrodieG让我意识到data.tables这个非常简洁的特性。
library(data.table)
dt <- data.table(df1)
result <- dt[,strsplit(as.character(names),",",fixed=T),
by=list(lllocatie,lat,lon,mag.cat)]
head(result,10)
# lllocatie lat lon mag.cat V1
# 1: Assen 52.992 6.548 3 Amen
# 2: Assen 52.992 6.548 3 Assen
# 3: Assen 52.992 6.548 3 Deurze
# 4: Assen 52.992 6.548 3 Ekehaar
# 5: Assen 52.992 6.548 3 Eleveld
# 6: Assen 52.992 6.548 3 Geelbroek
# 7: Assen 52.992 6.548 3 Taarlo
# 8: Assen 52.992 6.548 3 Ubbena
# 9: Hooghalen 52.928 6.552 3 Amen
# 10: Hooghalen 52.928 6.552 3 Ekehaar