Description
The Decision Tree Predict (td_decision_tree_predict_mle
) function applies
a tree model to input data, to output predicted labels for each data point.
Note: This function is only available when tdplyr is connected to Vantage 1.1
or later versions.
Usage
td_decision_tree_predict_mle ( object = NULL, newdata = NULL, attr.table.groupby.columns = NULL, attr.table.pid.columns = NULL, attr.table.val.column = NULL, output.response.probdist = FALSE, accumulate = NULL, 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. |
attr.table.groupby.columns |
Required Argument. |
attr.table.pid.columns |
Required Argument. |
attr.table.val.column |
Required Argument. |
output.response.probdist |
Optional Argument.
Default Value: FALSE |
accumulate |
Optional Argument. |
output.responses |
Optional Argument. |
newdata.sequence.column |
Optional Argument. |
object.sequence.column |
Optional Argument. |
Value
Function returns an object of class "td_decision_tree_predict_mle" which is a named list containing Teradata tbl object. 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("decisiontreepredict_example", "iris_attribute_test", "iris_attribute_output") loadExampleData("decision_tree_example", "iris_attribute_train", "iris_response_train", "iris_altinput") # Create remote tibble objects. iris_attribute_train <- tbl(con, "iris_attribute_train") iris_response_train <- tbl(con, "iris_response_train") iris_attribute_test <- tbl(con, "iris_attribute_test") # Example - 1 # First train the data, i.e. create a Model decision_tree_out <- td_decision_tree_mle(attribute.table = iris_attribute_train, response.table = iris_response_train, attribute.name.columns = c("attribute"), attribute.value.column = "attrvalue", id.columns = c("pid"), response.column = "response", num.splits = 3, approx.splits = FALSE, nodesize = 10, max.depth = 10, split.measure = "gini" ) # Run predict on the output of td_decision_tree_mle td_decision_tree_predict_out <- td_decision_tree_predict_mle(object = decision_tree_out, newdata = iris_attribute_test, newdata.partition.column = c("pid"), newdata.order.column = c("attribute"), attr.table.groupby.columns = c("attribute"), attr.table.pid.columns = c("pid"), attr.table.val.column = "attrvalue", accumulate = c("attrvalue") ) # Example - 2 # set output.response.probdist to TRUE to output the probability distributions. decision_tree_out2 <- td_decision_tree_mle(attribute.table=iris_attribute_train, response.table=iris_response_train, attribute.name.columns='attribute', id.columns='pid', attribute.value.column='attrvalue', response.column='response', num.splits=3, nodesize=5, max.depth=10, split.measure='gini', approx.splits=FALSE, output.response.probdist=TRUE, response.probdist.type = "Laplace" ) # use output.response.probdist, output.responses. td_decision_tree_predict_out <- td_decision_tree_predict_mle(newdata=iris_attribute_test, newdata.partition.column='pid', newdata.order.column='attribute', object=decision_tree_out2, attr.table.groupby.columns='attribute', attr.table.pid.columns='pid', attr.table.val.column='attrvalue', accumulate='attrvalue', output.response.probdist=TRUE, output.responses=c('1','2','3') )