This function implements a time-sliced ABC model for validation. It uses historical data to predict connections that will appear in the future.
abc_timeslice(
entity_data,
time_column = "publication_year",
split_time,
a_term,
a_type = NULL,
c_type = NULL,
min_score = 0.1,
n_results = 100
)A list with prediction results and validation metrics.
A data frame of entity data with time information.
Name of the column containing time information.
Time point to split historical and future data.
Character string, the source term (A).
Character string, the entity type for A terms.
Character string, the entity type for C terms.
Minimum score threshold for results.
Maximum number of results to return.