Looping and adding a counter to R

Question

I have a dataframe dfthat contains a couple of columns, but below are the only relevant ones.

node    |   precedingWord
-------------------------
A-bom       de
A-bom       die
A-bom       de
A-bom       een
A-bom       n
A-bom       de
acroniem    het
acroniem    t
acroniem    het
acroniem    n
acroniem    een
act         de
act         het
act         die
act         dat
act         t
act         n

node, . : neuter, non-neuter rest. neuter , beforeWord : t, het, dat. non-neuter de die, rest , neuter non-neuter. ( , , , rest - , . - node.)

( , , freqDf, :

node    |   neuter   | nonNeuter   | rest
-----------------------------------------
A-bom       0          4             2
acroniem    3          0             2
act         3          2             1

freqDf $ node, :

freqDf<- data.frame(node = unique(df$node), stringsAsFactors = FALSE)

, ; , . , - , , , ++ , .

freqDf$neuter[grep("dat|het|t", df$precedingWord, perl=TRUE)] <- ++
freqDf$nonNeuter[grep("de|die", df$precedingWord, perl=TRUE)] <- ++

e <- table(df$Node)
freqDf$rest <- as.numeric(e - freqDf$neuter - freqDf$nonNeuter)

, node . - , freqDf$node.

Answer 1

- , table .

neuter <- c("t", "het", "dat")
non.neuter <- c("de", "die")

df$precedingWord[df$precedingWord %in% neuter] <- "neuter"
df$precedingWord[df$precedingWord %in% non.neuter] <- "non.neuter"
df$precedingWord[!df$precedingWord %in% c(neuter, non.neuter)] <- "rest"

table(df)

      precedingWord
  node       neuter non.neuter rest
  A-bom         0          4    2
  acroniem      3          0    2
  act           3          2    1

, dplyr, .

EDIT: , - : ( "previousWord", "" ).

library(dplyr)
df %>%
  mutate(gender = ifelse(!precedingWord %in% c(neuter, non.neuter), "rest", 
                         ifelse(precedingWord %in% neuter, "neuter", "non.neuter"))) %>%
  count(node, gender)


Source: local data frame [7 x 3]
Groups: node

      node     gender n
1    A-bom non.neuter 4
2    A-bom       rest 2
3 acroniem     neuter 3
4 acroniem       rest 2
5      act     neuter 3
6      act non.neuter 2
7      act       rest 1

# And if you want the same output you put in your question, you can use table
df2 <- mutate(df, gender = ifelse(!precedingWord %in% c(neuter, non.neuter), "rest", 
                       ifelse(precedingWord %in% neuter, "neuter", "non.neuter")))

table(df2$node, df2$gender)

           neuter non.neuter rest
  A-bom         0          4    2
  acroniem      3          0    2
  act           3          2    1

:

myTable <- table(df2$node, df2$gender) %>% 
  as.data.frame.matrix %>%
  mutate(node = row.names(.))

 > myTable
  neuter non.neuter rest     node
1      0          4    2    A-bom
2      3          0    2 acroniem
3      3          2    1      act
> str(myTable)
'data.frame':   3 obs. of  4 variables:
 $ neuter    : int  0 3 3
 $ non.neuter: int  4 0 2
 $ rest      : int  2 2 1
 $ node      : chr  "A-bom" "acroniem" "act"

# And here is a more understandable way if you are not familiar with piping
# To learn more about forward piping : https://github.com/smbache/magrittr 
myTable <- table(df2$node, df2$gender)
myTable2 <- as.data.frame.matrix(myTable)
myTable3 <- mutate(myTable2, node = row.names(myTable2))

Answer 2

R . apply. tapply, table , .

Julien , (, ) , , . , "neuter", "neuter" , , . , .

, ( "" ), .

df<-as.data.frame(matrix(c("A-bom","de","A-bom","die","A-bom","de","A-bom","een","A-bom","n","A-bom","de","acroniem","het","acroniem","t","acroniem","het","acroniem","n","acroniem","een","act","de","act","het","act","die","act","dat","act","t","act","n"), byrow=T, ncol=2), stringsAsFactors=F)
names(df)<-c("node", "precedingWord")

# dictionary of word types. 
# I added a fourth type of word to demonstrate what happens 
# if no words of a given type are present.
classes<-c("t"="neuter", "het"="neuter" ,"dat"="neuter", "de"="non-neuter", "die"="non-neuter", "blorble"="nonword")

# create class variable and initialize to "rest"
df$class<-"rest"
df$class<-ifelse(!is.na(classes[df$precedingWord]), classes[df$precedingWord], "rest")

# note fourth category, "nonword", is missing.
table(df$node, df$class)

# make sure any missing categories are still possible levels for class
df$class<-factor(df$class)
levels(df$class)<-c(levels(df$class), unique(classes))

#now non-represented categories are still there. 
table(df$node, df$class)