dtm_bind {udpipe} | R Documentation |
These 2 methods provide cbind
and rbind
functionality
for sparse matrix objects which are returned by document_term_matrix
.
In case of dtm_cbind
, if the rows are not ordered in the same way in x and y, it will order them based on the rownames.
If there are missing rows these will be filled with NA values.
In case of dtm_rbind
, if the columns are not ordered in the same way in x and y, it will order them based on the colnames.
If there are missing columns these will be filled with NA values.
dtm_cbind(x, y) dtm_rbind(x, y)
x |
a sparse matrix such as a "dgTMatrix" object which is returned by |
y |
a sparse matrix such as a "dgTMatrix" object which is returned by |
a sparse matrix where either rows are put below each other in case of dtm_rbind
or columns are put next to each other in case of dtm_cbind
data(brussels_reviews_anno) x <- brussels_reviews_anno ## rbind dtm1 <- document_term_frequencies(x = subset(x, doc_id %in% c("10049756", "10284782")), document = "doc_id", term = "token") dtm1 <- document_term_matrix(dtm1) dtm2 <- document_term_frequencies(x = subset(x, doc_id %in% c("10789408", "12285061", "35509091")), document = "doc_id", term = "token") dtm2 <- document_term_matrix(dtm2) m <- dtm_rbind(dtm1, dtm2) dim(m) ## cbind library(data.table) x <- as.data.table(brussels_reviews_anno) x <- x[, token_bigram := txt_nextgram(token, n = 2), by = list(doc_id, sentence_id)] dtm1 <- document_term_frequencies(x = x, document = "doc_id", term = c("token")) dtm1 <- document_term_matrix(dtm1) dtm2 <- document_term_frequencies(x = x, document = "doc_id", term = c("token_bigram")) dtm2 <- document_term_matrix(dtm2) m <- dtm_cbind(dtm1, dtm2) dim(m) m <- dtm_cbind(dtm1[-c(100, 999), ], dtm2[-1000,]) dim(m)