A bundle is used to combine several objects (partition, context,
features, cooccurrences objects) into one S4 class object. Typically, a
class inheriting from the bundle superclass will be used. When working with
a context_bundle, a features_bundle, a cooccurrences_bundle, or a
context_bundle, a similar set of standard methods is available to perform
transformations.
# S4 method for class 'bundle'
name(x) <- value
# S4 method for class 'bundle'
length(x)
# S4 method for class 'bundle'
names(x)
# S4 method for class 'bundle,vector'
names(x) <- value
# S4 method for class 'bundle'
unique(x)
# S4 method for class 'bundle,bundle'
e1 + e2
# S4 method for class 'bundle,textstat'
e1 + e2
# S4 method for class 'bundle'
x[[i]]
# S4 method for class 'bundle,ANY,ANY,ANY'
x[i]
# S4 method for class 'bundle'
x[[i]] <- value
# S4 method for class 'bundle'
x$name
# S4 method for class 'bundle'
x$name <- value
# S4 method for class 'bundle'
sample(x, size)
# S4 method for class 'list'
as.bundle(object, ...)
# S4 method for class 'textstat'
as.bundle(object)
# S3 method for class 'bundle'
as.data.table(x, keep.rownames, col, ...)
# S4 method for class 'bundle'
as.matrix(x, col)
# S4 method for class 'bundle'
subset(x, ...)
# S4 method for class 'bundle'
as.list(x)
# S3 method for class 'bundle'
as.list(x, ...)
# S4 method for class 'bundle'
get_corpus(x)a bundle object
character string with a name to be assigned
object 1
object 2
integer or character values for indexing a bundle object.
The name of an object in the bundle object.
number of items to choose to generate a sample
A bundle object.
Further parameters
Required argument to safeguard consistency with S3
method definition in the data.table package. Unused in this context.
columns of the data.table to use to generate an object.
corpusThe CWB corpus the xobjects in the bundle are based on, a
length 1 character vector.
objectsAn object of class list.
p_attributeObject of class character.
encodingThe encoding of the corpus.
use("RcppCWB", "REUTERS")
#> ✔ corpus loaded: REUTERS
# generate bundle with articles in REUTERS corpus
b <- partition_bundle("REUTERS", s_attribute = "id")
#> ℹ s-attribute "id" has values: yes
#> ℹ get regions and get values
#> ✔ get regions and get values [6ms]
#>
#> ℹ instantiate objects (n = 20)
#> ✔ instantiate objects (n = 20) [10ms]
#>
#> ℹ assign names
#> ✔ assign names [6ms]
#>
# basic operations
length(b)
#> [1] 20
names(b)
#> [1] "127" "144" "191" "194" "211" "236" "237" "242" "246" "248" "273" "349"
#> [13] "352" "353" "368" "489" "502" "543" "704" "708"
get_corpus(b)
#> [1] "REUTERS"
summary(b)
#> name size
#> 1 127 92
#> 2 144 444
#> 3 191 55
#> 4 194 69
#> 5 211 93
#> 6 236 465
#> 7 237 434
#> 8 242 164
#> 9 246 331
#> 10 248 349
#> 11 273 378
#> 12 349 92
#> 13 352 105
#> 14 353 103
#> 15 368 110
#> 16 489 149
#> 17 502 199
#> 18 543 83
#> 19 704 282
#> 20 708 53
# enrich with count for p-attribute
b <- enrich(b, p_attribute = "word")
# Indexing and accessing bundle objects
reu <- corpus("REUTERS") %>% split(s_attribute = "id")
#> ℹ s-attribute "id" has values: yes
#> ℹ get regions and get values
#> ✔ get regions and get values [6ms]
#>
#> ℹ instantiate objects (n = 20)
#> ✔ instantiate objects (n = 20) [10ms]
#>
#> ℹ assign names
#> ✔ assign names [6ms]
#>
reu[1:3]
#> <<subcorpus_bundle>>
#> Number of subcorpora: 3
reu[-1]
#> <<subcorpus_bundle>>
#> Number of subcorpora: 19
reu[-(1:10)]
#> <<subcorpus_bundle>>
#> Number of subcorpora: 10
reu["127"]
#> <<subcorpus_bundle>>
#> Number of subcorpora: 1
reu$`127` # alternative access
#> <<subcorpus>>
#> corpus: REUTERS
#> encoding: latin1
#> type: NA
#> template: yes
#> size: 92
reu[c("127", "273")]
#> <<subcorpus_bundle>>
#> Number of subcorpora: 2
reu[["127"]] <- NULL
pb <- partition_bundle("GERMAPARLMINI", s_attribute = "party")
#> ℹ s-attribute "party" has values: yes
#> ℹ get regions and get values
#> ✔ get regions and get values [7ms]
#>
#> ℹ instantiate objects (n = 6)
#> ✔ instantiate objects (n = 6) [9ms]
#>
#> ℹ assign names
#> ✔ assign names [5ms]
#>
pb$"NA" <- NULL # quotation needed if name is "NA"
# Turn bundle into data.table (not tested to save time)
# \donttest{
dt <- partition_bundle("REUTERS", s_attribute = "id") %>%
cooccurrences(query = "oil", cqp = FALSE) %>%
as.data.table(col = "ll")
#> ℹ s-attribute "id" has values: yes
#> ℹ get regions and get values
#> ✔ get regions and get values [6ms]
#>
#> ℹ instantiate objects (n = 20)
#> ✔ instantiate objects (n = 20) [10ms]
#>
#> ℹ assign names
#> ✔ assign names [5ms]
#>
#> Warning: No hits for query oil (returning NULL)
# }