Suggests the most similar records. It automatically constructs a data
generator from the left and right datasets iterating over all the elements
of their Cartesian product. The method calls the
predict
method of the passed model using the constructed generator. For each record
in the left dataset of, the function returns count records from the
right dataset having the greatest matching predictions.
Usage
suggest(object, left, right, count, ...)
# S4 method for class 'neer_match.matching_model.DLMatchingModel'
suggest(object, left, right, count, ...)
# S4 method for class 'neer_match.matching_model.NSMatchingModel'
suggest(object, left, right, count, batch_size = 32L, ...)
# S4 method for class 'neer_match.reasoning.RefutationModel'
suggest(object, left, right, count, batch_size = 32L, ...)Arguments
- object
A matching model object.
- left
A data frame with the left records.
- right
A data frame with the right records.
- count
The number of returned suggestions from the right dataset for each record in the left dataset.
- ...
Additional arguments passed to the
predictmethod.- batch_size
The batch size (integer).
Examples
smap <- SimilarityMap(
instructions = list(
`score` = list("gaussian", "euclidean"),
`platform` = list("osa", "indel")
)
)
model <- NSMatchingModel(smap)
compile(model)
matching_data <- fuzzy_games_example_data()
fit(
model,
matching_data$left, matching_data$right, matching_data$matches,
epochs = 1L,
verbose = 0L
)
suggest(
model, matching_data$left[1:2, ], matching_data$right[1:2, ],
count = 2L
)
#> left right prediction
#> 1 1 2 0.5349829
#> 0 1 1 0.5345929
#> 2 2 1 0.5349829
#> 3 2 2 0.5345929