quanteda (version 1.5.2)

textplot_network: Plot a network of feature co-occurrences

Description

Plot an fcm object as a network, where edges show co-occurrences of features.

Usage

textplot_network(
  x,
  min_freq = 0.5,
  omit_isolated = TRUE,
  edge_color = "#1F78B4",
  edge_alpha = 0.5,
  edge_size = 2,
  vertex_color = "#4D4D4D",
  vertex_size = 2,
  vertex_labelcolor = NULL,
  vertex_labelfont = NULL,
  vertex_labelsize = 5,
  offset = NULL,
  ...
)
# S3 method for fcm
as.network(x, min_freq = 0.5, omit_isolated = TRUE, ...)
# S3 method for fcm
as.igraph(x, min_freq = 0.5, omit_isolated = TRUE, ...)

Arguments

x

a fcm or dfm object

min_freq

a frequency count threshold or proportion for co-occurrence frequencies of features to be included.

omit_isolated

if TRUE, features do not occur more frequent than min_freq will be omitted.

edge_color

color of edges that connect vertices.

edge_alpha

opacity of edges ranging from 0 to 1.0.

edge_size

size of edges for most frequent co-occurrence The size of other edges are determined proportionally to the 99th percentile frequency instead of the maximum to reduce the impact of outliers.

vertex_color

color of vertices.

vertex_size

size of vertices

vertex_labelcolor

color of texts. Defaults to the same as vertex_color. If NA is given, texts are not rendered.

vertex_labelfont

font-family of texts. Use default font if NULL.

vertex_labelsize

size of vertex labels in mm. Defaults to size 5. Supports both integer values and vector values.

offset

if NULL, the distance between vertices and texts are determined automatically.

...

additional arguments passed to network or graph_from_adjacency_matrix. Not used for as.igraph.

Details

Currently the size of the network is limited to 1000, because of the computationally intensive nature of network formation for larger matrices. When the fcm is large, users should select features using fcm_select, set the threshold using min_freq, or implement own plotting function using as.network.

See Also

fcm

network

graph_from_adjacency_matrix

Examples

# NOT RUN {
set.seed(100)
toks <- corpus_subset(data_corpus_irishbudget2010) %>%
    tokens(remove_punct = TRUE) %>%
    tokens_tolower() %>%
    tokens_remove(pattern = stopwords("english"), padding = FALSE)
fcmat <- fcm(toks, context = "window", tri = FALSE)
feat <- names(topfeatures(fcmat, 30))
fcm_select(fcmat, pattern = feat) %>%
    textplot_network(min_freq = 0.5)
fcm_select(fcmat, pattern = feat) %>%
    textplot_network(min_freq = 0.8)
fcm_select(fcmat, pattern = feat) %>%
    textplot_network(min_freq = 0.8, vertex_labelcolor = rep(c('gray40', NA), 15))
fcm_select(fcmat, pattern = feat) %>%
    textplot_network(vertex_labelsize = 10)
fcm_30 <- fcm_select(fcmat, pattern = feat)
textplot_network(fcm_30, vertex_labelsize = rowSums(fcm_30)/min(rowSums(fcm_30)))
# Vector inputs to vertex_labelsize can be scaled if too small / large
textplot_network(fcm_30, vertex_labelsize = 1.5 * rowSums(fcm_30)/min(rowSums(fcm_30)))

# as.igraph
if (requireNamespace("igraph", quietly = TRUE)) {
    txt <- c("a a a b b c", "a a c e", "a c e f g")
    mat <- fcm(txt)
    as.igraph(mat, min_freq = 1, omit_isolated = FALSE)
}
# }

Run the code above in your browser using DataCamp Workspace