Teradata Package for R Function Reference | 17.00 - SentimentEvaluator - Teradata Package for R - Look here for syntax, methods and examples for the functions included in the Teradata Package for R.

EvaluateSentimentExtractor

Description

The EvaluateSentimentExtractor function uses test data to evaluate the precision and recall of the predictions output by the function ExtractSentiment (td_sentiment_extractor_mle). The precision and recall are affected by the model that the function td_sentiment_extractor_mle uses; therefore, if the model is changed, EvaluateSentimentExtractor must be rerun on the new predictions.

Usage

  td_sentiment_evaluator_mle (
      object = NULL,
      obs.column = NULL,
      sentiment.column = NULL,
      object.sequence.column = NULL,
      object.order.column = NULL
  )

Arguments

object	Required Argument. Specifies the input tbl_teradata with a text column which contains input text.
object.order.column	Optional Argument. Specifies Order By columns for "object". Values to this argument can be provided as a vector, if multiple columns are used for ordering. Types: character OR vector of Strings (character)
obs.column	Required Argument. Specifies the name of the input column with the observed sentiment (POS, NEG or NEU). Types: character
sentiment.column	Required Argument. Specifies the name of the input column with the predicted sentiment (POS, NEG or NEU). Types: character
object.sequence.column	Optional Argument. Specifies the vector of column(s) that uniquely identifies each row of the input argument "object". The argument is used to ensure deterministic results for functions which produce results that vary from run to run. Types: character OR vector of Strings (character)

Value

Function returns an object of class "td_sentiment_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("sentimenttrainer_example", "sentiment_train")
    loadExampleData("sentimentextractor_example", "sentiment_extract_input", "sentiment_word")

    # Create object(s) of class "tbl_teradata".
    sentiment_train <- tbl(con, "sentiment_train")
    sentiment_extract_input <- tbl(con, "sentiment_extract_input")
    sentiment_word <- tbl(con, "sentiment_word")

    # Example 1 - This example uses the dictionary model file 'default_sentiment_lexicon.txt'.
    td_sentiment_extractor_out1 <- td_sentiment_extractor_mle(object = "dictionary",
                                                              newdata = sentiment_extract_input,
                                                              text.column = "review",
                                                              accumulate = c("category")
                                                              )

    td_sent_eval_out1 <- td_sentiment_evaluator_mle(object=td_sentiment_extractor_out1$result,
                                                    obs.column='category',
                                                    sentiment.column='out_polarity'
                                                    )

    # Example 2 - This example uses the classification model file
    # 'default_sentiment_classification_model.bin'
    td_sentiment_extractor_out2 <- td_sentiment_extractor_mle(
                            object = "classification:default_sentiment_classification_model.bin",
                            newdata = sentiment_extract_input,
                            text.column = "review",
                            accumulate = c("category")
                            )

    td_sent_eval_out2 <- td_sentiment_evaluator_mle(object=td_sentiment_extractor_out2$result,
                                                    obs.column='category',
                                                    sentiment.column='out_polarity'
                                                    )

    # Example 3 - This example uses classification model file output by
    # the td_sentiment_trainer_mle() function.
    td_sentiment_trainer_out <- td_sentiment_trainer_mle(data = sentiment_train,
                                                         text.column = "review",
                                                         sentiment.column = "category",
                                                         model.file = "sentimentmodel1.bin"
                                                         )

    # Use the td_sentiment_extractor_mle() function to extract sentiment of each input document.
    td_sentiment_extractor_out3 <- td_sentiment_extractor_mle(
                                                  object = "classification:sentimentmodel1.bin",
                                                  newdata = sentiment_extract_input,
                                                  text.column = "review",
                                                  accumulate = c("category")
                                                  )

    td_sent_eval_out3 <- td_sentiment_evaluator_mle(object=td_sentiment_extractor_out3$result,
                                                    obs.column="category",
                                                    sentiment.column="out_polarity"
                                                    )

    # Example 4 - This example uses a dictionary tbl_teradata ('sentiment_word')
    # instead of model file.
    td_sentiment_extractor_out4 <- td_sentiment_extractor_mle(newdata = sentiment_extract_input,
                                                              dict.data = sentiment_word,
                                                              text.column = "review",
                                                              accumulate = c("category")
                                                              )

    td_sent_eval_out4 <- td_sentiment_evaluator_mle(object=td_sentiment_extractor_out4$result,
                                                    obs.column="category",
                                                    sentiment.column="out_polarity"
                                                    )