Question

使用dlply (from this post;我可以在data.frame的子集上生成线性模型列表。现在我有了这个列表，我想使用这些模型在另一个data.frame中生成值。

该列表包含每个DAY和variable子集的模型。我想将模型应用于另一个data.frame中的相同子集。例如，对于DAY == 1和变量== Var.1，模型（y = mx + b）为value = -4.521869(Location) + 21.315。使用适当子集的模型，我会在另一个data.frame中计算Var.1的值（例如dat_rec已经有DAY和Location的条目。

有没有办法在另一个data.frame中的相同子集上使用列表中的模型（例如，使用模型来DAY == 1和variable == Var.1到在data.frame中填充值到处[例如，不同的Sites] DAY == 1和variable == Var.1）是否有类似的列表方法来填充data.frame与使用列表中的模型计算的值？所需的最终产品（即下面的dat_rec）是data.frame。

# Data
dat <- structure(list(Site = c(32L, 32L, 32L, 32L, 10L, 10L, 10L, 10L, 
32L, 32L, 32L, 32L, 10L, 10L, 10L, 10L), Location = c(0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), DAY = c(5L, 
55L, 555L, 5555L, 5L, 55L, 555L, 5555L, 5L, 55L, 555L, 5555L, 
5L, 55L, 555L, 5555L), Var.1 = c(20.9, 20.8, 21.03, 21.36, 21.73, 
21.18, 20.73, 21.98, 21.73, 12.48702448, 12.19642662, 12.33218874, 
11.85626285, 11.88812108, 12.70549981, 11.89587521), Var.2 = c(100L, 
100L, 100L, 100L, 100L, 100L, 100L, 100L, 90L, 90L, 90L, 91L, 
92L, 88L, 89L, 90L), Var.3 = c(14.47, 14.4, 14.3, 14.14, 14.72, 
14.62, 14.14, 14.49, 10.27287765, 10.27287765, 10.41763527, 10.51725376, 
11.12918753, 10.81166867, 10.80656509, 11.00093898), Var.4 = c(890.19, 
888.9, 889.14, 888.15, 889.57, 888.41, 887.48, 886.87, 688.15, 
698.23, 650.99, 700.01, 699, 689.6, 658.7, 689.99)), .Names = c("Site", 
"Location", "DAY", "Var.1", "Var.2", "Var.3", "Var.4"), class = "data.frame", row.names = c(NA, 
-16L))

# melt data for use with dlply
mdat <- melt(dat, id=c("DAY", "Site", "Location"))

# this dlply solution was built from here https://stackoverflow.com/a/1214432/1670053
models_mdat <- dlply(mdat, c("DAY","variable"), function(df) 
                lm(value ~ Location, data = df))

# example (partial) result, with Var.1 filled in for two DAYs
# I've only filled in the values for Var.1 using the model from the list 
# for DAY 5 and 55.
# not melted
dat_rec <- structure(list(Site = c(1L, 1L, 1L, 1L, 3L, 3L, 3L, 3L), Location = c(0.1, 
0.2, 0.3, 0.4, 0.1, 0.2, 0.3, 0.4), DAY = c(5L, 5L, 5L, 5L, 55L, 
55L, 55L, 55L), Var.1 = c(20.8628131, 20.4106262, 19.9584393, 
19.5062524, 20.1097573, 19.2295146, 18.3492719, 17.4690292), 
    Var.2 = c(NA, NA, NA, NA, NA, NA, NA, NA), Var.3 = c(NA, 
    NA, NA, NA, NA, NA, NA, NA), Var.4 = c(NA, NA, NA, NA, NA, 
    NA, NA, NA)), .Names = c("Site", "Location", "DAY", "Var.1", 
"Var.2", "Var.3", "Var.4"), class = "data.frame", row.names = c(NA, 
-8L))
# melted
    dat_rec_melt <- structure(list(Site = c(1L, 1L, 1L, 1L, 3L, 3L, 3L, 3L, 1L, 1L, 
1L, 1L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 3L, 3L, 3L, 3L, 1L, 1L, 
1L, 1L, 3L, 3L, 3L, 3L), Location = c(0.1, 0.2, 0.3, 0.4, 0.1, 
0.2, 0.3, 0.4, 0.1, 0.2, 0.3, 0.4, 0.1, 0.2, 0.3, 0.4, 0.1, 0.2, 
0.3, 0.4, 0.1, 0.2, 0.3, 0.4, 0.1, 0.2, 0.3, 0.4, 0.1, 0.2, 0.3, 
0.4), DAY = c(5L, 5L, 5L, 5L, 55L, 55L, 55L, 55L, 5L, 5L, 5L, 
5L, 55L, 55L, 55L, 55L, 5L, 5L, 5L, 5L, 55L, 55L, 55L, 55L, 5L, 
5L, 5L, 5L, 55L, 55L, 55L, 55L), variable = structure(c(1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L), .Label = c("Var.1", 
"Var.2", "Var.3", "Var.4"), class = "factor"), value = c(20.8628131, 
20.4106262, 19.9584393, 19.5062524, 20.1097573, 19.2295146, 18.3492719, 
17.4690292, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA)), .Names = c("Site", 
"Location", "DAY", "variable", "value"), row.names = c(NA, -32L
), class = "data.frame")

Answer 1

我认为您正在寻找predict：

sapply(models_mdat ,predict,newdata=dat_rec)

编辑将结果与新数据对齐：

lapply(models_mdat ,function(x)
       cbind(dat_rec,fit=predict(x,newdata=dat_rec)))

Answer 2

使用来自agstudy的信息，似乎predict是我正在寻找的用于计算模型中的值的工具。知道我想使用dlply生成的模型列表来更新带有predictions的data.frame，我对搜索找到解决方案的内容有了更好的了解。

我在post找到了一个解决方案。为了实现我正在寻找的结果，我需要使用模型列表以及数据作为列表。然后，预测可以与mdply一起使用，最终得到更新的data.frame。

# melted
    dat_rec_melt <- structure(list(Site = c(1L, 1L, 1L, 1L, 3L, 3L, 3L, 3L, 1L, 1L, 
1L, 1L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 3L, 3L, 3L, 3L, 1L, 1L, 
1L, 1L, 3L, 3L, 3L, 3L), Location = c(0.1, 0.2, 0.3, 0.4, 0.1, 
0.2, 0.3, 0.4, 0.1, 0.2, 0.3, 0.4, 0.1, 0.2, 0.3, 0.4, 0.1, 0.2, 
0.3, 0.4, 0.1, 0.2, 0.3, 0.4, 0.1, 0.2, 0.3, 0.4, 0.1, 0.2, 0.3, 
0.4), DAY = c(5L, 5L, 5L, 5L, 55L, 55L, 55L, 55L, 5L, 5L, 5L, 
5L, 55L, 55L, 55L, 55L, 5L, 5L, 5L, 5L, 55L, 55L, 55L, 55L, 5L, 
5L, 5L, 5L, 55L, 55L, 55L, 55L), variable = structure(c(1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L), .Label = c("Var.1", 
"Var.2", "Var.3", "Var.4"), class = "factor"), value = c(20.8628131, 
20.4106262, 19.9584393, 19.5062524, 20.1097573, 19.2295146, 18.3492719, 
17.4690292, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA)), .Names = c("Site", 
"Location", "DAY", "variable", "value"), row.names = c(NA, -32L
), class = "data.frame")

dat_rec_list <- dlply(dat_rec_melt, c("DAY", "variable"))

predictions <- mdply(cbind(mod = models_mdat, df = dat_rec_list), function(mod, df) {
  mutate(df, pred = predict(mod, newdata = df))
})

使用模型列表计算data.frame中的新值

2 个答案: