multiclass_probability_tibble: Generate a multiclass probability tibble

In cvms: Cross-Validation for Model Selection

Generate a multiclass probability tibble

Description

\Sexpr[results=rd, stage=render]{lifecycle::badge("maturing")}

Generate a tibble with random numbers containing one column per specified class. When the softmax function is applied, the numbers become probabilities that sum to 1 row-wise. Optionally, add columns with targets and predicted classes.

Usage

multiclass_probability_tibble(
  num_classes,
  num_observations,
  apply_softmax = TRUE,
  FUN = runif,
  class_name = "class_",
  add_predicted_classes = FALSE,
  add_targets = FALSE
)

Arguments

num_classes	The number of classes. Also the number of columns in the tibble.
num_observations	The number of observations. Also the number of rows in the tibble.
apply_softmax	Whether to apply the softmax function row-wise. This will transform the numbers to probabilities that sum to 1 row-wise.
FUN	Function for generating random numbers. The first argument must be the number of random numbers to generate, as no other arguments are supplied.
class_name	The prefix for the column names. The column index is appended.
add_predicted_classes	Whether to add a column with the predicted classes. (Logical) The class with the highest value is the predicted class.
add_targets	Whether to add a column with randomly selected target classes. (Logical)

Author(s)

Ludvig Renbo Olsen, [e-mail]

Examples

# Attach cvms
library(cvms)

# Create a tibble with 5 classes and 10 observations
# Apply softmax to make sure the probabilities sum to 1
multiclass_probability_tibble(
  num_classes = 5,
  num_observations = 10,
  apply_softmax = TRUE
)

# Using the rnorm function to generate the random numbers
multiclass_probability_tibble(
  num_classes = 5,
  num_observations = 10,
  apply_softmax = TRUE,
  FUN = rnorm
)

# Add targets and predicted classes
multiclass_probability_tibble(
  num_classes = 5,
  num_observations = 10,
  apply_softmax = TRUE,
  FUN = rnorm,
  add_predicted_classes = TRUE,
  add_targets = TRUE
)

# Creating a custom generator function that
# exponentiates the numbers to create more "certain" predictions
rcertain <- function(n) {
  (runif(n, min = 1, max = 100)^1.4) / 100
}
multiclass_probability_tibble(
  num_classes = 5,
  num_observations = 10,
  apply_softmax = TRUE,
  FUN = rcertain
)

cvms documentation built on July 9, 2023, 6:56 p.m.