lloss: Calculate the Log Lossfor predicted probabilities against a...
In gweissman/gmish: Miscellaneous Functions for Predictive Modeling

lloss

R Documentation

Calculate the Log Lossfor predicted probabilities against a binary outcome.

Description

Calculate the Log Lossfor predicted probabilities against a binary outcome.

Usage

lloss(preds, obs, eps = 1e-15)

Arguments

`preds`	A vector of predicted probabilities.
`obs`	A vector containing the observed binary outcomes (0 or 1).
`eps`	Epsilon representing the tolerance of the numeric result, used in order to avoid zero errors.

Value

The Log Loss given by

logloss = y_i(\log \hat y_i) + (1-y_i)\log(1-\hat y_i)

Examples

# Generate some predictions
predictions <- runif(1000)
# Generate some binary outcomes
observations <- sample(0:1, size = 1000, replace = TRUE)
# Calculate the Brier Score
lloss(predictions, observations)

gweissman/gmish documentation built on Feb. 21, 2025, 1:20 a.m.