有条件地根据每个组的另一个查找表对一个数据帧的值进行插值?

时间:2019-09-25 07:05:10

标签: r dataframe dplyr data.table lookup-tables

这类似于以下的question。但是,我需要执行更多步骤:

•按列IDorder

分组

•对于val中的每个df_dat,请使用以下条件在ratio表中查找对应的df_lookup

o   If val < min(df_lookup$val), set new_ratio = min(df_lookup$ratio)

o   If val > max(df_lookup$val), set new_ratio = max(df_lookup$ratio)

o   If val falls within df_lookup$val range, do a simple linear interpolation

我的数据:

library(dplyr)

df_lookup <- tribble(
  ~ID, ~order, ~pct, ~val, ~ratio,
  "batch1", 1, 1,  1, 0.2,
  "batch1", 1, 10, 8, 0.5,
  "batch1", 1, 25, 25, 1.2,
  "batch2", 2, 1, 2, 0.1,
  "batch2", 2, 10, 15, 0.75,
  "batch2", 2, 25, 33, 1.5,
  "batch2", 2, 50, 55, 3.2,
)
df_lookup
#> # A tibble: 7 x 5
#>   ID     order   pct   val ratio
#>   <chr>  <dbl> <dbl> <dbl> <dbl>
#> 1 batch1     1     1     1  0.2 
#> 2 batch1     1    10     8  0.5 
#> 3 batch1     1    25    25  1.2 
#> 4 batch2     2     1     2  0.1 
#> 5 batch2     2    10    15  0.75
#> 6 batch2     2    25    33  1.5 
#> 7 batch2     2    50    55  3.2


df_dat <- tribble(
  ~order, ~ID, ~val,
  1, "batch1", 0.1,
  1, "batch1", 30,
  1, "batch1", 2,
  1, "batch1", 12,
  2, "batch1", 45,
  2, "batch2", 1.5,
  2, "batch2", 30,
  2, "batch2", 13,
  2, "batch2", 60,
)
df_dat
#> # A tibble: 9 x 3
#>   order ID       val
#>   <dbl> <chr>  <dbl>
#> 1     1 batch1   0.1
#> 2     1 batch1  30  
#> 3     1 batch1   2  
#> 4     1 batch1  12  
#> 5     2 batch1  45  
#> 6     2 batch2   1.5
#> 7     2 batch2  30  
#> 8     2 batch2  13  
#> 9     2 batch2  60

先前的解决方案不尊重产生错误结果的分组。

示例:

对于order = 2ID = batch1new_ratio应该为NA,因为这些条件不在查找表中。

对于order = 1ID = batch2val = 30new_ratio不应高于1.2(最大值ratio)。

对于order = 1ID = batch1val = 2new_ratio = 0.243,它是介于0.2和0.5之间的ratio值。

任何帮助表示赞赏!

#error
df_dat %>%
  group_by(ID, order) %>%
  mutate(new_ratio = with(df_lookup, approx(val, ratio, val))$y)
#> Error: Column `new_ratio` must be length 4 (the group size) or one, not 7

#wrong output
df_dat %>%
  group_by(ID, order) %>%
  mutate(val1 = val) %>%
  mutate(new_ratio = with(df_lookup, approx(val, ratio, val1))$y)
#> # A tibble: 9 x 5
#> # Groups:   ID, order [3]
#>   order ID       val  val1 new_ratio
#>   <dbl> <chr>  <dbl> <dbl>     <dbl>
#> 1     1 batch1   0.1   0.1    NA    
#> 2     1 batch1  30    30       1.39 
#> 3     1 batch1   2     2       0.1  
#> 4     1 batch1  12    12       0.643
#> 5     2 batch1  45    45       2.43 
#> 6     2 batch2   1.5   1.5     0.15 
#> 7     2 batch2  30    30       1.39 
#> 8     2 batch2  13    13       0.679
#> 9     2 batch2  60    60      NA

预期产量

# A tibble: 9 x 4
  order ID       val new_ratio
  <dbl> <chr>  <dbl>     <dbl>
1     1 batch1   0.1     0.2  
2     1 batch1  30       1.2  
3     1 batch1   2       0.243
4     1 batch1  12       0.643
5     2 batch1  45      NA    
6     2 batch2   1.5     0.1 
7     2 batch2  30       1.38 
8     2 batch2  13       0.65 
9     2 batch2  60       3.2  

3 个答案:

答案 0 :(得分:2)

library(dplyr)
df_dat %>% 
left_join(df_lookup, by=c('ID','order'), suffix = c(".dat", ".lkp")) %>% 
group_by(ID, order, val.dat) %>% 
mutate(ratio_new = case_when(val.dat < min(val.lkp) ~ min(ratio),
                             val.dat > max(val.lkp) ~ max(ratio),
                             #Add ifelse to handle the scenarios where val.lkp and ratio are NAs as approx will fail in these scenarios  
                             between(val.dat, min(val.lkp), max(val.lkp)) ~ ifelse(all(is.na(ratio)), NA_real_, approx(x=val.lkp, y=ratio, xout=val.dat)$y), 
                             TRUE ~ NA_real_)) %>% 
slice(1)

# A tibble: 9 x 7
# Groups:   ID, order, val.dat [9]
   order ID     val.dat   pct val.lkp ratio ratio_new
   <dbl> <chr>    <dbl> <dbl>   <dbl> <dbl>     <dbl>
1     1 batch1     0.1     1       1   0.2     0.2  
2     1 batch1     2       1       1   0.2     0.243
3     1 batch1    12       1       1   0.2     0.665
4     1 batch1    30       1       1   0.2     1.2  
5     2 batch1    45      NA      NA  NA      NA    
6     2 batch2     1.5     1       2   0.1     0.1  
7     2 batch2    13       1       2   0.1     0.65 
8     2 batch2    30       1       2   0.1     1.38 
9     2 batch2    60       1       2   0.1     3.2

答案 1 :(得分:2)

roll中使用rollendsdata.table的选项:

df_lookup[, m := (ratio - shift(ratio, -1L)) / (val - shift(val, -1L))]

df_dat[, new_ratio := 
        df_lookup[.SD, on=.(order, ID, val), roll=Inf, rollends=c(FALSE, FALSE), 
            x.m * (i.val - x.val) + x.ratio]
    ]

#for val in df_dat that are more than those in df_lookup
df_dat[is.na(new_ratio), new_ratio := 
    df_lookup[copy(.SD), on=.(order, ID, val), roll=Inf, x.ratio]]

#for val in df_dat that are less than those in df_lookup
df_dat[is.na(new_ratio), new_ratio := 
        df_lookup[copy(.SD), on=.(order, ID, val), roll=-Inf, x.ratio]]

输出:

   order     ID  val new_ratio
1:     1 batch1  0.1 0.2000000
2:     1 batch1 30.0 1.2000000
3:     1 batch1  2.0 0.2428571
4:     1 batch1 12.0 0.6647059
5:     2 batch1 45.0        NA
6:     2 batch2  1.5 0.1000000
7:     2 batch2 30.0 1.3750000
8:     2 batch2 13.0 0.6500000
9:     2 batch2 60.0 3.2000000

数据:

library(data.table)
df_lookup <- fread('ID, order, pct, val, ratio
"batch1", 1, 1,  1, 0.2
"batch1", 1, 10, 8, 0.5
"batch1", 1, 25, 25, 1.2
"batch2", 2, 1, 2, 0.1
"batch2", 2, 10, 15, 0.75
"batch2", 2, 25, 33, 1.5
"batch2", 2, 50, 55, 3.2')

df_dat <- fread('order, ID, val
1, "batch1", 0.1
1, "batch1", 30
1, "batch1", 2
1, "batch1", 12
2, "batch1", 45
2, "batch2", 1.5
2, "batch2", 30
2, "batch2", 13
2, "batch2", 60')

最后两行代码也可以用非等号联接代替:

df_dat[is.na(new_ratio), new_ratio:= 
    df_lookup[copy(.SD), on=.(order, ID, val<val), x.ratio, mult="last"]]
df_dat[is.na(new_ratio), new_ratio:= 
    df_lookup[copy(.SD), on=.(order, ID, val>val), x.ratio, mult="first"]]
df_dat

答案 2 :(得分:2)

请使用data.table

解决您的问题

我使用了很多中间步骤,因此您可以检查结果并操作每个步骤,并查看发生了什么,因此代码可以大大缩短。

library(data.table)

#set data to data.tables
setDT(df_dat); setDT(df_lookup)

#set range df_lookup values by ID and order combination
df_lookup[, `:=`( val2   = shift( val, type = "lead" ),
                  ratio2 = shift( ratio, type = "lead" ) ), 
          by = .( ID, order ) ][]

#join non-equi
df_dat[ df_lookup, 
        `:=`( val_start = i.val, 
              val_end = i.val2, 
              ratio_start = i.ratio, 
              ratio_end = i.ratio2 ), 
        on = .( ID, order, val > val, val < val2) ][]


#interpolatie new_ratio for values that fall within a range of dt_lookup
df_dat[, new_ratio := ratio_start + ( (val - val_start) * (ratio_end - ratio_start) / (val_end - val_start) )][]

#create data.table with ratio-value for minimum- and maximum value in df_lookup
df_lookup_min_max <- df_lookup[, .( val_min = min( val ), val_max = max( val ),
                                    ratio_min = min( ratio ), ratio_max = max( ratio ) ), 
                               by = .(ID, order) ]
df_lookup_min_max_melt <- melt( df_lookup_min_max, 
                                id.vars = c( "ID", "order" ),
                                measure.vars = patterns( val = "^val", 
                                                         ratio = "^ratio" ) )

df_dat[ is.na( new_ratio ), 
        new_ratio := df_lookup_min_max_melt[ df_dat[ is.na( new_ratio ), ],
                                             ratio, 
                                             on = .(ID, order, val ),
                                             roll = "nearest" ] ][]

df_dat[, `:=`(val_start = NULL, val_end = NULL, ratio_start = NULL, ratio_end = NULL)][]

最终输出

#    order     ID  val new_ratio
# 1:     1 batch1  0.1 0.2000000
# 2:     1 batch1 30.0 1.2000000
# 3:     1 batch1  2.0 0.2428571
# 4:     1 batch1 12.0 0.6647059
# 5:     2 batch1 45.0        NA
# 6:     2 batch2  1.5 0.1000000
# 7:     2 batch2 30.0 1.3750000
# 8:     2 batch2 13.0 0.6500000
# 9:     2 batch2 60.0 3.2000000

修改

5: 2 batch1 45.0 NA行在这里,因为df_lookup中没有订单== 2和ID == batch1组合...
也许这是一个错字?
但是:代码似乎可以很好地处理;-)