Ytukyg

I have this data frame:

split.test.input <- data.frame(matrix(ncol=7,nrow=10,

                        c(rep("a",4),rep("b",4),rep("c",2),1910:1913,1902:1905,1925:1926,

                          rep("year",4),rep("month",3),rep("year",3),

                        rep("ITA",4),rep("HVR",2),rep("ITA",2),rep("ESP",2),

                      rep("GSA 17",5),rep("GSA 1",2),rep("GSA 12",3),

                      rep("gear 1",4),rep("gear 2",6),75,45,230,89,45,78,96,100,125,200)))



colnames(split.test.input) <-  c("species", "year", "Time.unit","country","GSA","Gear","Quantity")

I split for many variable:

split.res <- dlply(split.test.input,.(species),

      dlply,.(Time.unit),

      dlply,.(country),

      dlply,.(GSA),

      dlply,.(Gear))

Now, I would like to calculate some statistical analysis (in this case sum) for each quantity of each element of a list, I extract for example the first list (list of a list of a list etc..):

df.fromSplit <- data.frame(split.res[["a"]][["year"]][["ITA"]][["GSA 17"]][["gear 1"]][["Quantity"]])     





colnames(df.fromSplit) <-  "a,year,ITA,GSA 17,gear.1" #the name of my variables for the first list

     df.fromSplit

           a,year,ITA,GSA 17,gear.1

        1                    75

        2                    45

        3                    230

        4                    89

I would like to calculate sum for this column:

sum(as.numeric(levels(df.fromSplit[,1])[df.fromSplit[,1]] ))     

   439

but it's not elegant...

IMPORTANT

I would like to calculate dynamically the sum for each quantity
of each element of my list. The result could be (more or less) a data
frame or many data frame (one for each list) as:

    combination             sum

a,year,ITA,GSA 17,gear.1    439

b,month,HVR,GSA.1,gear.2    78

[...]

and so on for each combination of list

I thought a for loop which can extract each element of a list and it calculate the sum for the quantity of each list, but with for loop I don't know how extract each list based on variables (my experience with a list is very low)

Actually it's hard to imagine a purpose for which such a complicated object as split.res would be needed. What you are asking can be done much simpler.

First, let's convert Quantity to numeric type (currently it's a factor).

split.test.input$Quantity <- as.numeric(as.character(split.test.input$Quantity))

Then simply

tapply(split.test.input$Quantity, apply(split.test.input[c(1, 3:6)], 1, paste0, collapse = ", "), sum)

#  a, year, ITA, GSA 17, gear 1  b, month, HVR, GSA 1, gear 2 

#                           439                            78 

# b, month, HVR, GSA 17, gear 2  b, month, ITA, GSA 1, gear 2 

#                            45                            96 

#  b, year, ITA, GSA 12, gear 2  c, year, ESP, GSA 12, gear 2 

#                           100                           325 

or

(groups <- apply(split.test.input[c(1, 3:6)], 1, paste0, collapse = ", "))

#  [1] "a, year, ITA, GSA 17, gear 1"  "a, year, ITA, GSA 17, gear 1" 

#  [3] "a, year, ITA, GSA 17, gear 1"  "a, year, ITA, GSA 17, gear 1" 

#  [5] "b, month, HVR, GSA 17, gear 2" "b, month, HVR, GSA 1, gear 2" 

#  [7] "b, month, ITA, GSA 1, gear 2"  "b, year, ITA, GSA 12, gear 2" 

#  [9] "c, year, ESP, GSA 12, gear 2"  "c, year, ESP, GSA 12, gear 2" 

tapply(split.test.input$Quantity, groups, sum)

Also, since you already are using dlply, you may be interested in something like

ddply(split.test.input, .(species, Time.unit, country, GSA, Gear), summarise, Sum = sum(Quantity))

  species Time.unit country    GSA   Gear Sum

# 1       a      year     ITA GSA 17 gear 1 439

# 2       b     month     HVR  GSA 1 gear 2  78

# 3       b     month     HVR GSA 17 gear 2  45

# 4       b     month     ITA  GSA 1 gear 2  96

# 5       b      year     ITA GSA 12 gear 2 100

# 6       c      year     ESP GSA 12 gear 2 325

Consider aggregate on multiple columns:

split.test.input$Quantity <- as.numeric(as.character(split.test.input$Quantity))



agg_df <- aggregate(Quantity ~ species + Time.unit + country + GSA + Gear,

                    data=split.test.input, FUN=sum)



agg_df

#   species Time.unit country    GSA   Gear Quantity

# 1       a      year     ITA GSA 17 gear 1      439

# 2       b     month     HVR  GSA 1 gear 2       78

# 3       b     month     ITA  GSA 1 gear 2       96

# 4       c      year     ESP GSA 12 gear 2      325

# 5       b      year     ITA GSA 12 gear 2      100

# 6       b     month     HVR GSA 17 gear 2       45

If needing a list, run by (object-oriented wrapper to tapply) with paste(..., collapse="") for combination column:

df_list <- by(split.test.input, split.test.input[c("species", "Time.unit", "country", "GSA", "Gear")],

              function(sub) unique(transform(sub,

                                             combination = paste(unique(sub[c("species", "Time.unit", "country", "GSA", "Gear")]), collapse=" "),

                                             sum = sum(sub$Quantity))[c("combination", "sum")])

)

df_list <- Filter(NROW, df_list)

df_list



# [[1]]

#                combination sum

# 1 a year ITA GSA 17 gear 1 439



# [[2]]

#                combination sum

# 6 b month HVR GSA 1 gear 2  78



# [[3]]

#                combination sum

# 7 b month ITA GSA 1 gear 2  96



# [[4]]

#                combination sum

# 9 c year ESP GSA 12 gear 2 325



# [[5]]

#                combination sum

# 8 b year ITA GSA 12 gear 2 100



# [[6]]

#                 combination sum

# 5 b month HVR GSA 17 gear 2  45

We could use tidyverse

library(tidyverse)

split.test.input %>%

    group_by_at(vars(names(.)[c(1, 3:6)])) %>% 

    summarise(Quantity = sum(parse_number(Quantity)))

# A tibble: 6 x 6

# Groups:   species, Time.unit, country, GSA [?]

#  species Time.unit country GSA    Gear   Quantity

#  <fct>   <fct>     <fct>   <fct>  <fct>     <dbl>

#1 a       year      ITA     GSA 17 gear 1      439

#2 b       month     HVR     GSA 1  gear 2       78

#3 b       month     HVR     GSA 17 gear 2       45

#4 b       month     ITA     GSA 1  gear 2       96

#5 b       year      ITA     GSA 12 gear 2      100

#6 c       year      ESP     GSA 12 gear 2      325