Description
The NamedEntityFinderEvaluator function invokes the NamedEntityFinderEvaluatorMap and NamedEntityFinderEvaluatorReduce functions, which operate as a row and a partition function, respectively. Each function takes a set of evaluating data and generates the precision, recall, and F-measure values of a specified maximum entropy data model. The function supports neither regular-expression-based nor dictionary-based models.
Usage
td_namedentity_finder_evaluator_mle (
newdata = NULL,
text.column = NULL,
model = NULL,
newdata.sequence.column = NULL,
newdata.order.column = NULL
)
Arguments
newdata |
Required Argument. |
newdata.order.column |
Optional Argument. |
text.column |
Required Argument. |
model |
Required Argument. |
newdata.sequence.column |
Optional Argument. |
Value
Function returns an object of class "td_namedentity_finder_evaluator_mle"
which is a named list containing object of class "tbl_teradata".
Named list member can be referenced directly with the "$" operator
using name: result.
Examples
# Get the current context/connection
con <- td_get_context()$connection
# Load example data.
loadExampleData("namedentityfinderevaluator_example", "nermem_sports_test")
loadExampleData("namedentityfindertrainer_example", "nermem_sports_train")
# Create object(s) of class "tbl_teradata".
nermem_sports_train <- tbl(con, "nermem_sports_train")
nermem_sports_test <- tbl(con, "nermem_sports_test")
# Train a namedentity finder model on entity type: "LOCATION".
# The trained model is stored in a binary file: "location.sports".
td_nef_trainer_out <- td_namedentity_finder_trainer_mle(data = nermem_sports_train,
text.column = "content",
entity.type = "LOCATION",
model.file = "location.sports"
)
# Example 1 - Use the model file: location.sports as the input model on the test
# data: nermem_sports_test.
td_nef_evaluator_out <- td_namedentity_finder_evaluator_mle(newdata = nermem_sports_test,
text.column = "content",
model = "location.sports"
)