Question

我有简单的数据框，包含短字符串，每个字符串都有一个特定的类：

datadb <- data.frame (
  Class = c('Class1', 'Class2', 'Class3'),
  Document = c('This is test', 'Yet another test', 'A last test')
)

datadb$Document <- tolower(datadb$Document)
datadb$Tokens   <- strsplit(datadb$Document, " ")

由此，我想构建另一个包含原始Class1列的数据框，但是为每个唯一标记添加了一个新列，如下所示：

all_tokens <- unlist(datadb$Tokens)
all_tokens <- unique(all_tokens)

number_of_columns <- length(all_tokens)
number_of_rows    <- NROW(datadb)

tokenDB <- data.frame( matrix(ncol=(1 + number_of_columns), nrow=number_of_rows) )

names(tokenDB) <- c("Classification", all_tokens)
tokenDB$Classification <- datadb$Class

tokenDB将如下所示：

Classification this is test yet another  a last
1         Class1   NA NA   NA  NA      NA NA   NA
2         Class2   NA NA   NA  NA      NA NA   NA
3         Class3   NA NA   NA  NA      NA NA   NA

如何浏览原始数据框并将值添加到与已识别的每个向量对应的新tokenDB？输出应如下所示：

Classification    this   is   test   yet   another  a last
1         Class1    1    1     1     0       0      0   0
2         Class2    0    0     1     1       1      0   0
3         Class3    0    0     1     0       0      1   1

理想情况下，输出应该是data.frame，但也可以是矩阵。

Answer 1

使用tm包或任何其他文本挖掘包来完成工作。我偏爱tm。您正在创建的是文档 - 术语矩阵。

library(tm)
datadb <- data.frame (
  Class = c('Class1', 'Class2', 'Class3'),
  Document = c('This is test', 'Yet another test', 'A last test')
)

corpus <- Corpus(VectorSource(datadb$Document))
dtm <- DocumentTermMatrix(corpus)
dtm2 <- cbind(datadb$Class, as.matrix(dtm))
colnames(dtm2) <- c("Classification", colnames(dtm))
dtm2
# Classification test this another yet last
# 1              1    1    1       0   0    0
# 2              2    1    0       1   1    0
# 3              3    1    0       0   0    1

以下是仅使用base

的另一种方法

txt <- lapply(txt, function(x) data.frame(x, count = 1))
txt <- lapply(txt, function(x) data.frame(count = tapply(x$count, x$x, sum)))
tdm <- Reduce(function(...) merge(..., all=TRUE, by="x"), 
              lapply(txt, function(x) data.frame(x=rownames(x), count=x$count)))
rownames(tdm) <- tdm[, 1]
dtm3 <- t(tdm[, -1])
dtm3[is.na(dtm3)] <- 0
rownames(dtm3) <- paste("Doc", 1:3)
dtm3 <- cbind(Classification=datadb$Class, dtm3)
dtm3
#     Classification is test This another Yet A last
# Doc 1              1  1    1    1       0   0 0    0
# Doc 2              2  0    1    0       1   1 0    0
# Doc 3              3  0    1    0       0   0 1    1

Answer 2

   k=lapply( datadb$Tokens,match,all_tokens)
   tokenDB[,-1]=t(mapply(function(x,y) {y[x]<-1;y[-x]<-0;y}, k,data.frame(t(tokenDB[,-1]))))
   tokenDB
   Classification this is test yet another a last
1         Class1    1  1    1   0       0 0    0
2         Class2    0  0    1   1       1 0    0
3         Class3    0  0    1   0       0 1    1

根据标记向量填充data.frame

2 个答案: