model.adapter.prediction-class: model.adapter.prediction-class

model.adapter.prediction-classR Documentation

model.adapter.prediction-class

Description

model.adapter.prediction-class

model.adapter.prediction-class

Public fields

fit

a matrix containing predicted result. For continuous variables, predicted values are placed in "fit" column. If an interval (e.g., confidence, prediction, etc.) is available, iupper and lower values are placed in "upper" and "lower" columns.

For discrete variables, content of this field depends on value of type field. If type is "probability", fit is a matrix with columns representing probability of each class. If response variable is binary (0/1) variable, fit is a matrix with the first column representing probability of "0" and the second column representing probability of "1".

For classification models and type = "class", predicted classes.

type

a character literal representing type of prediction, one of "response", "link", "prob" and "class".

fixed

a data.frame containing data used for prediction. If original data.frame is not available, this field is NULL.

interval.type

a character literal representing type and level of the interval. If no interval is available, this field is NULL. If the interval is confidence interval, this field has "confidence". If the interval is prediction interval, this field has "prediction".

interval.level

a number representing level of interval (0 <= interval.level <= 1). If no interval is calculated, this field should be NULL.

Methods

Public methods


Method new()

Usage
model.adapter.prediction.class$new(
  fit,
  type = c("response", "link", "prob", "class"),
  fixed = NULL,
  interval.type = NULL,
  interval.level = NULL,
  logical.response = FALSE
)

Method clone()

The objects of this class are cloneable with this method.

Usage
model.adapter.prediction.class$clone(deep = FALSE)
Arguments
deep

Whether to make a deep clone.


Marchen/model.adapter documentation built on July 3, 2023, 11:07 a.m.