Нахождение частот всех возможных пар в R

Ключевые моменты:

• unique, [ и т. Д.
• utils::combn, чтобы получить комбинации
• сумма (значения ЛОЖЬ / ИСТИНА) для подсчета

Надеюсь, это поможет!

require(utils)

df <- read.table(header=TRUE, 
text="LINE ID DRUG REACTION
1 1827 ASPIRIN CHEST_PAIN
2 1827 CLARINEX CHEST_PAIN
3 1827 ASPIRIN COUGH
4 1827 CLARINEX COUGH
5 1827 ASPIRIN HAEMOGLOBIN_DECREASED
6 1827 CLARINEX HAEMOGLOBIN_DECREASED
7 1827 ASPIRIN NEUTROPHIL_COUNT_INCREASED
8 1827 CLARINEX NEUTROPHIL_COUNT_INCREASED
9 1827 ASPIRIN PHARYNGOLARYNGEAL_PAIN
10 1827 CLARINEX PHARYNGOLARYNGEAL_PAIN")

# temporary object to collect if a combination is present
Results <- data.frame(Drug1=NA, Drug2=NA, Reaction=NA, Reaction.occurs=NA)
n=1 # start first line in Results object

#  walk through each ID ... 
for (ID in unique(df$ID)) { 

  # ... and each possible pair of drugs within a (report) ID ...
  drug.pairs <- utils::combn(x=unique(df[df$ID == ID, "DRUG"]), m=2) # the columns 
  for (ii in 1:ncol(drug.pairs)) {

    # ... and each reaction ...
    for (reaction in unique(df$REACTION)) {
      Results[n, "Drug1"] <- drug.pairs[1,ii]
      Results[n, "Drug2"] <- drug.pairs[2,ii]
      Results[n, "Reaction"] <- reaction
      Results[n, "Reaction.occurs"] <- drug.pairs[1,ii] %in% df[df$REACTION == reaction & df$ID == ID, "DRUG"] &
        drug.pairs[2,ii] %in% df[df$REACTION == reaction & df$ID == ID, "DRUG"]
      n <- n+1
    }
  }
}

head(Results)

# then find the unique Drug1 - Drug2 -Reaction combinations, and count the TRUE values:
(Results[!duplicated(Results[,1:3]), ][,1:3])
(unique(Results[, 1:3]))

# Results2 contains only the unique combinations
Results2 <- Results[!duplicated(Results[,1:3]), ][,1:3]

# calculatethe frequencies
for (i in 1:nrow(Results2)) {
  Results2[i, "Frequency"] <- sum(Results[Results$Drug1 == Results2[i, "Drug1"] & 
                                            Results$Drug2 == Results2[i, "Drug2"] & 
                                            Results$Reaction == Results2[i, "Reaction"], ]$Reaction.occurs)
}

Results2
# --- end ----

дает:

    Drug1    Drug2                   Reaction Frequency
1 ASPIRIN CLARINEX                 CHEST_PAIN         1
2 ASPIRIN CLARINEX                      COUGH         1
3 ASPIRIN CLARINEX      HAEMOGLOBIN_DECREASED         1
4 ASPIRIN CLARINEX NEUTROPHIL_COUNT_INCREASED         1
5 ASPIRIN CLARINEX     PHARYNGOLARYNGEAL_PAIN         1