Makes sure the document term matrix has exactly the rows and columns which you specify. If missing rows or columns are occurring, the function fills these up either with empty cells or with the value that you provide. See the examples.
dtm_conform(dtm, rows, columns, fill)
the sparse matrix dtm
with exactly the specified rows and columns
a document term matrix: an object returned by document_term_matrix
a character vector of row names which dtm
should have
a character vector of column names which dtm
should have
a value to use to fill up missing rows / columns. Defaults to using an empty cell.
document_term_matrix
x <- data.frame(doc_id = c("doc_1", "doc_1", "doc_1", "doc_2"),
text = c("a", "a", "b", "c"),
stringsAsFactors = FALSE)
dtm <- document_term_frequencies(x)
dtm <- document_term_matrix(dtm)
dtm
dtm_conform(dtm,
rows = c("doc_1", "doc_2", "doc_3"), columns = c("a", "b", "c", "Z", "Y"))
dtm_conform(dtm,
rows = c("doc_1", "doc_2", "doc_3"), columns = c("a", "b", "c", "Z", "Y"),
fill = 1)
dtm_conform(dtm, rows = c("doc_1", "doc_3"), columns = c("a", "b", "c", "Z", "Y"))
dtm_conform(dtm, columns = c("a", "b", "Z"))
dtm_conform(dtm, rows = c("doc_1"))
dtm_conform(dtm, rows = character())
dtm_conform(dtm, columns = character())
dtm_conform(dtm, rows = character(), columns = character())
##
## Some examples on border line cases
##
special1 <- dtm[, character()]
special2 <- dtm[character(), character()]
special3 <- dtm[character(), ]
dtm_conform(special1,
rows = c("doc_1", "doc_2", "doc_3"), columns = c("a", "b", "c", "Z", "Y"))
dtm_conform(special1,
rows = c("doc_1", "doc_2", "doc_3"), columns = c("a", "b", "c", "Z", "Y"),
fill = 1)
dtm_conform(special1, rows = c("doc_1", "doc_3"), columns = c("a", "b", "c", "Z", "Y"))
dtm_conform(special1, columns = c("a", "b", "Z"))
dtm_conform(special1, rows = c("doc_1"))
dtm_conform(special1, rows = character())
dtm_conform(special1, columns = character())
dtm_conform(special1, rows = character(), columns = character())
dtm_conform(special2,
rows = c("doc_1", "doc_2", "doc_3"), columns = c("a", "b", "c", "Z", "Y"))
dtm_conform(special2,
rows = c("doc_1", "doc_2", "doc_3"), columns = c("a", "b", "c", "Z", "Y"),
fill = 1)
dtm_conform(special2, rows = c("doc_1", "doc_3"), columns = c("a", "b", "c", "Z", "Y"))
dtm_conform(special2, columns = c("a", "b", "Z"))
dtm_conform(special2, rows = c("doc_1"))
dtm_conform(special2, rows = character())
dtm_conform(special2, columns = character())
dtm_conform(special2, rows = character(), columns = character())
dtm_conform(special3,
rows = c("doc_1", "doc_2", "doc_3"), columns = c("a", "b", "c", "Z", "Y"))
dtm_conform(special3,
rows = c("doc_1", "doc_2", "doc_3"), columns = c("a", "b", "c", "Z", "Y"),
fill = 1)
dtm_conform(special3, rows = c("doc_1", "doc_3"), columns = c("a", "b", "c", "Z", "Y"))
dtm_conform(special3, columns = c("a", "b", "Z"))
dtm_conform(special3, rows = c("doc_1"))
dtm_conform(special3, rows = character())
dtm_conform(special3, columns = character())
dtm_conform(special3, rows = character(), columns = character())
Run the code above in your browser using DataLab