nlp_assertion_dl: Spark NLP AssertionDLApproach
In r-spark/sparknlp: R Interface to John Snow Labs Spark NLP

nlp_assertion_dl

R Documentation

Spark NLP AssertionDLApproach

Description

Spark ML estimator that classifies each clinically relevant named entity into its assertion type: “present”, “absent”, “hypothetical”, “conditional”, “associated_with_other_person”, etc. See https://nlp.johnsnowlabs.com/docs/en/licensed_annotators#assertiondl

Usage

nlp_assertion_dl(
  x,
  input_cols,
  output_col,
  graph_folder = NULL,
  config_proto_bytes = NULL,
  label_column = NULL,
  batch_size = NULL,
  epochs = NULL,
  learning_rate = NULL,
  dropout = NULL,
  max_sent_len = NULL,
  start_col = NULL,
  end_col = NULL,
  chunk_col = NULL,
  enable_output_logs = NULL,
  output_logs_path = NULL,
  validation_split = NULL,
  verbose = NULL,
  scope_window = NULL,
  uid = random_string("assertion_dl_")
)

Arguments

`x`	A `spark_connection`, `ml_pipeline`, or a `tbl_spark`.
`input_cols`	Input columns. String array.
`output_col`	Output column. String.
`graph_folder`	forlder containing the TF graph files
`config_proto_bytes`	array of integers
`label_column`	column name to use as the labels for training
`batch_size`	gradient descent batch size
`epochs`	number of training epochs
`learning_rate`	learning rate for the algorithm
`dropout`	dropout for the algorithm
`max_sent_len`	regulates the length of the longest sentence
`start_col`	the name of the column with the value for the start index of the target
`end_col`	the name of the column with the value for the ending index of the target
`chunk_col`	the name of the column containing the chunks
`enable_output_logs`	Whether to output to annotators log folder
`output_logs_path`	path for the output logs to go
`validation_split`	Choose the proportion of training dataset to be validated against the model on each Epoch.
`verbose`	level of verbosity. One of All, PerStep, Epochs, TrainingStat, Silent
`scope_window`	The scope window of the assertion (whole sentence by default)
`uid`	A character string used to uniquely identify the ML estimator.

Value

The object returned depends on the class of x.

spark_connection: When x is a spark_connection, the function returns an instance of a ml_estimator object. The object contains a pointer to a Spark Estimator object and can be used to compose Pipeline objects.
ml_pipeline: When x is a ml_pipeline, the function returns a ml_pipeline with the NLP estimator appended to the pipeline.
tbl_spark: When x is a tbl_spark, an estimator is constructed then immediately fit with the input tbl_spark, returning an NLP model.