Description
The NaiveBayesTextClassifierPredict function uses the model output by the
NaiveBayesTextClassifierTrainer (td_naivebayes_textclassifier_mle
) function to
predict outcomes for test data.
Note: This function is only available when tdplyr is connected to Vantage 1.1
or later versions.
Usage
td_naivebayes_textclassifier_predict_mle (
object = NULL,
newdata = NULL,
input.token.column = NULL,
doc.id.columns = NULL,
model.type = "MULTINOMIAL",
top.k = NULL,
model.token.column = NULL,
model.category.column = NULL,
model.prob.column = NULL,
terms = NULL,
output.prob = FALSE,
output.responses = NULL,
newdata.sequence.column = NULL,
object.sequence.column = NULL,
newdata.partition.column = NULL,
newdata.order.column = NULL,
object.order.column = NULL
)
Arguments
object |
Required Argument. |
object.order.column |
Optional Argument. |
newdata |
Required Argument. |
newdata.partition.column |
Required Argument. |
newdata.order.column |
Optional Argument. |
input.token.column |
Required Argument. |
doc.id.columns |
Required Argument. |
model.type |
Optional Argument. |
top.k |
Optional Argument. |
model.token.column |
Optional Argument. |
model.category.column |
Optional Argument. |
model.prob.column |
Optional Argument. |
terms |
Optional Argument. |
output.prob |
Optional Argument. |
output.responses |
Optional Argument.
Types: character OR vector of characters |
newdata.sequence.column |
Optional Argument. |
object.sequence.column |
Optional Argument. |
Value
Function returns an object of class
"td_naivebayes_textclassifier_predict_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("naivebayes_textclassifier_predict_example", "token_table",
"complaints_tokens_test")
# Create object(s) of class "tbl_teradata".
token_table <- tbl(con, "token_table")
complaints_tokens_test <- tbl(con,"complaints_tokens_test")
# Example -
# Run NaiveBayesTextClassifier on the train data (token_table).
nbt_out <- td_naivebayes_textclassifier_mle(data = token_table,
data.partition.column = c("category"),
token.column = "token",
doc.id.columns = c("doc_id"),
doc.category.column = "category",
model.type = "Bernoulli"
)
# Use the generated model to predict the tokens on the test data 'complaints_tokens_test'
# by using nbt_out model.
nbt_predict_out <- td_naivebayes_textclassifier_predict_mle(newdata = complaints_tokens_test,
object = nbt_out,
newdata.partition.column = "doc_id",
input.token.column = "token",
doc.id.columns = c("doc_id"),
model.type = "Bernoulli",
top.k = 1
)
# Use the argument "output.responses" to predict the tokens on the test data
# 'complaints_tokens_test' by using nbt_out model generated by
# td_naivebayes_textclassifier_mle() function.
nbt_predict_out1 <- td_naivebayes_textclassifier_predict_mle(newdata=complaints_tokens_test,
newdata.partition.column='doc_id',
object=nbt_out,
input.token.column='token',
doc.id.columns='doc_id',
model.token.column='token',
model.category.column='category',
model.prob.column='prob',
model.type='Bernoulli',
terms = 'token',
output.prob = TRUE,
output.responses = c('crash','no_crash'),
newdata.sequence.column = 'token',
object.sequence.column = 'token',
newdata.order.column = 'doc_id',
object.order.column = 'category'
)