从数据帧创建一个长度(列表)与nrow(df)相同的列表

Question

下面是一个小示例数据框架：

> dput(head(cluster_socrata_csv))
structure(list(Cluster = structure(c(1L, 13L, 24L, 35L, 46L, 
57L), .Label = c("cluster1", "cluster10", "cluster100", "cluster11", 
"cluster12", "cluster13", "cluster14", "cluster15", "cluster16", 
"cluster17", "cluster18", "cluster19", "cluster2", "cluster20", 
"cluster21", "cluster22", "cluster23", "cluster24", "cluster25", 
"cluster26", "cluster27", "cluster28", "cluster29", "cluster3", 
"cluster30", "cluster31", "cluster32", "cluster33", "cluster34", 
"cluster35", "cluster36", "cluster37", "cluster38", "cluster39", 
"cluster4", "cluster40", "cluster41", "cluster42", "cluster43", 
"cluster44", "cluster45", "cluster46", "cluster47", "cluster48", 
"cluster49", "cluster5", "cluster50", "cluster51", "cluster52", 
"cluster53", "cluster54", "cluster55", "cluster56", "cluster57", 
"cluster58", "cluster59", "cluster6", "cluster60", "cluster61", 
"cluster62", "cluster63", "cluster64", "cluster65", "cluster66", 
"cluster67", "cluster68", "cluster69", "cluster7", "cluster70", 
"cluster71", "cluster72", "cluster73", "cluster74", "cluster75", 
"cluster76", "cluster77", "cluster78", "cluster79", "cluster8", 
"cluster80", "cluster81", "cluster82", "cluster83", "cluster84", 
"cluster85", "cluster86", "cluster87", "cluster88", "cluster89", 
"cluster9", "cluster90", "cluster91", "cluster92", "cluster93", 
"cluster94", "cluster95", "cluster96", "cluster97", "cluster98", 
"cluster99"), class = "factor"), Socrata = structure(c(17L, 17L, 
1L, 13L, 14L, 16L), .Label = c("Assault", "Assault with Deadly Weapon", 
"Breaking and Entering", "Community Policing", "Death", "Disorder", 
"Drugs ", "Missing Person", "Other", "Other Sexual Offense", 
"Property Crime", "Property Crime Residental", "Robbery", "Theft", 
"Theft from Vehicle", "Theft of Vehicle", "Traffic", "Unknown", 
"Vehicle Recovery", "Weapons Offense"), class = "factor")), .Names = c("Cluster", 
"Socrata"), row.names = c(NA, 6L), class = "data.frame")

看起来是这样的：

> head(cluster_socrata_csv)
   Cluster          Socrata
1 cluster1          Traffic
2 cluster2          Traffic
3 cluster3          Assault
4 cluster4          Robbery
5 cluster5            Theft
6 cluster6 Theft of Vehicle

我想要创建一个列表，其中集群是关键，而苏格拉塔是价值。

我尝试简单地在as.list()函数中嵌套，但它返回了一个包含2个值的列表，一个用于集群，另一个用于值。

在这个例子中，我想要一个包含6个条目的列表，其中的第一个条目键是cluster1，其值是流量。对于第六项，它的关键将是cluster6和它的价值“偷车”。

Answer 1

你可以这样做：

setNames(as.list(df$Socrata),df$Cluster)

setNames(as.list(as.character(df$Socrata)),df$Cluster) # not to return levels

Answer 2

我想像这样简单的事情..。

B = as.list(A$Socrata)
names(B) = A$Cluster

A是你的数据

如果您只想拥有一个级别的子集，可以尝试

B = as.list(droplevels(A$Socrata))

这只会给出实际存在的水平。如果您不想要任何级别，那么我们必须从A$苏格拉塔中移除因子类：

B = as.list(as.character(A$Socrata))