0 
"f","index","values","lo.80","lo.95","hi.80","hi.95"

"auto.arima",2017-07-31 16:40:00,2.81613884762163,NA,NA,NA,NA

"auto.arima",2017-07-31 16:40:10,2.83441637197378,NA,NA,NA,NA

"auto.arima",2017-07-31 20:39:10,3.18497899649267,2.73259824384436,2.49312233904087,3.63735974914098,3.87683565394447

"auto.arima",2017-07-31 20:39:20,3.16981166809297,2.69309866988864,2.44074205235297,3.64652466629731,3.89888128383297

"ets",2017-07-31 16:40:00,2.93983529828936,NA,NA,NA,NA

"ets",2017-07-31 16:40:10,3.09739640066054,NA,NA,NA,NA

"ets",2017-07-31 20:39:10,3.1951571771414,2.80966705285567,2.60560090776504,3.58064730142714,3.78471344651776

"ets",2017-07-31 20:39:20,3.33876776870274,2.93593322313957,2.72268549604222,3.7416023142659,3.95485004136325

"bats",2017-07-31 16:40:00,2.82795253090081,NA,NA,NA,NA

"bats",2017-07-31 16:40:10,2.96389759682623,NA,NA,NA,NA

"bats",2017-07-31 20:39:10,3.1383560278272,2.76890864400062,2.573335012715,3.50780341165378,3.7033770429394

"bats",2017-07-31 20:39:20,3.3561357998535,2.98646195085452,2.79076843614824,3.72580964885248,3.92150316355876

我有一个像上面这样的数据框，其列名称为：“f”、“index”、“values”、“lo.80”、“lo.95”、“hi.80”、“hi.95”。

我想要做的是计算来自不同模型的特定时间戳的预测结果的加权平均值。我的意思是

对于 auto.arima 中的每一行，在 ets 和 bats 中都有对应的行具有相同的时间戳值，因此加权平均值应该计算如下：

value_arima*1/3 + values_ets*1/3 + values_bats*1/3 ；应计算 lo.80 和其他列的相似值。

此结果应存储在具有所有加权平均值的新数据框中。

新的数据框可能类似于：

index(timesamp from above dataframe),avg,avg_lo_80,avg_lo_95,avg_hi_80,avg_hi_95

I think I need to use spread() and mutate () function to achieve this. Being new to R I'm unable to proceed after forming this dataframe.

Please help.

4

1 回答 1

1

The example you provide is not a weighted average but a simple average. What you want is a simple aggregate. The first part is your dataset as provided by dput (better for sharing here)

d <- structure(list(f = structure(c(1L, 1L, 1L, 1L, 3L, 3L, 3L, 3L, 
2L, 2L, 2L, 2L), .Label = c("auto.arima", "bats", "ets"), class = "factor"), 
index = structure(c(1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 
3L, 4L), .Label = c("2017-07-31 16:40:00", "2017-07-31 16:40:10", 
"2017-07-31 20:39:10", "2017-07-31 20:39:20"), class = "factor"), 
values = c(2.81613884762163, 2.83441637197378, 3.18497899649267, 
3.16981166809297, 2.93983529828936, 3.09739640066054, 3.1951571771414, 
3.33876776870274, 2.82795253090081, 2.96389759682623, 3.1383560278272, 
3.3561357998535), lo.80 = c(NA, NA, 2.73259824384436, 2.69309866988864, 
NA, NA, 2.80966705285567, 2.93593322313957, NA, NA, 2.76890864400062, 
2.98646195085452), lo.95 = c(NA, NA, 2.49312233904087, 2.44074205235297, 
NA, NA, 2.60560090776504, 2.72268549604222, NA, NA, 2.573335012715, 
2.79076843614824), hi.80 = c(NA, NA, 3.63735974914098, 3.64652466629731, 
NA, NA, 3.58064730142714, 3.7416023142659, NA, NA, 3.50780341165378, 
3.72580964885248), hi.95 = c(NA, NA, 3.87683565394447, 3.89888128383297, 
NA, NA, 3.78471344651776, 3.95485004136325, NA, NA, 3.7033770429394, 
3.92150316355876)), .Names = c("f", "index", "values", "lo.80", 
"lo.95", "hi.80", "hi.95"), class = "data.frame", row.names = c(NA, 
-12L))

> aggregate(d[,3:7], by = d["index"], FUN = mean)
                index   values    lo.80    lo.95    hi.80    hi.95
1 2017-07-31 16:40:00 2.861309       NA       NA       NA       NA
2 2017-07-31 16:40:10 2.965237       NA       NA       NA       NA
3 2017-07-31 20:39:10 3.172831 2.770391 2.557353 3.575270 3.788309
4 2017-07-31 20:39:20 3.288238 2.871831 2.651399 3.704646 3.925078

You can save this output in an object and change the column names as you want.

If you really want a weighted average this is a way to obtain it (here bat has a weight of 0.8 and the 2 others 0.1) : 

> d$weight <- (d$f)
> levels(d$weight) # check the levels
[1] "auto.arima" "bats"       "ets"       
> levels(d$weight) <- c(0.1, 0.8, 0.1)
> # transform the factor into numbers
> # warning as.numeric(d$weight) is not correct !!
> d$weight <- as.numeric(as.character((d$weight))) 
> 
> # Here the result is saved in a data.frame called "result
> result <- aggregate(d[,3:7] * d$weight, by = d["index"], FUN = sum)
> result
                index   values    lo.80    lo.95    hi.80    hi.95
1 2017-07-31 16:40:00 2.837959       NA       NA       NA       NA
2 2017-07-31 16:40:10 2.964299       NA       NA       NA       NA
3 2017-07-31 20:39:10 3.148698 2.769353 2.568540 3.528043 3.728857
4 2017-07-31 20:39:20 3.335767 2.952073 2.748958 3.719460 3.922576
于 2017-07-31T22:53:49.810 回答