Display text explanation in an interactive way. You can :
Create an output to insert text explanation plot in Shiny application.
Render the text explanations in Shiny application.
interactive_text_explanations(
explainer,
window_title = "Text model explainer",
title = "Local Interpretable Model-agnostic Explanations",
place_holder = "Put here the text to explain",
minimum_lentgh = 3,
minimum_lentgh_error = "Text provided is too short to be explained (>= 3).",
max_feature_to_select = 20
)
text_explanations_output(outputId, width = "100%", height = "400px")
render_text_explanations(expr, env = parent.frame(), quoted = FALSE)parameters
text to be displayed on the page
don't update display if text is shorter than this parameter
up limit to the number of words that can be selected
output variable to read from
Must be a valid CSS unit or a number, which will be coerced to a string and have "px" appended.
An expression that generates an HTML widget
The environment in which to evaluate expr.
Is expr a quoted expression (with quote())? This
is useful if you want to save an expression in a variable.
An output function that enables the use of the widget within Shiny applications.
A render function that enables the use of the widget within Shiny applications.
send a new sentence
update the parameters of the explainer
if (FALSE) {
library(text2vec)
library(xgboost)
data(train_sentences)
data(test_sentences)
get_matrix <- function(text) {
it <- itoken(text, progressbar = FALSE)
create_dtm(it, vectorizer = hash_vectorizer())
}
dtm_train = get_matrix(train_sentences$text)
xgb_model <- xgb.train(list(max_depth = 7, eta = 0.1, objective = "binary:logistic",
eval_metric = "error", nthread = 1),
xgb.DMatrix(dtm_train, label = train_sentences$class.text == "OWNX"),
nrounds = 50)
sentences <- head(test_sentences[test_sentences$class.text == "OWNX", "text"], 1)
explainer <- lime(train_sentences$text, xgb_model, get_matrix)
# The explainer can now be queried interactively:
interactive_text_explanations(explainer)
}