MetricsWeighted v0.3.0

0

Monthly downloads

0th

Percentile

Weighted Metrics, Scoring Functions and Performance Measures for Machine Learning

Provides weighted versions of several metrics, scoring functions and performance measures used in machine learning, including average unit deviances of the Bernoulli, Tweedie, Poisson, and Gamma distributions, see Jorgensen B. (1997, ISBN: 978-0412997112). The package also contains a weighted version of generalized R-squared, see e.g. Cohen, J. et al. (2002, ISBN: 978-0805822236). Furthermore, 'dplyr' chains are supported.

Readme

MetricsWeighted

The goal of this package is to provide weighted versions of metrics, scoring functions and performance measures for machine learning.

Installation

You can install the released version of MetricsWeighted from CRAN with:

install.packages("MetricsWeighted")

To get the bleeding edge version, you can run

library(devtools)
install_github("mayer79/MetricsWeighted")

Application

There are two ways to apply the package. We will go through them in the following examples. Please have a look at the vignette on CRAN for further information and examples.

Example 1: Directly apply the metrics

library(MetricsWeighted)

y <- 1:10
pred <- c(2:10, 14)

rmse(y, pred)
rmse(y, pred, w = 1:10)

r_squared(y, pred)
r_squared(y, pred, deviance_function = deviance_gamma)

Example 2: Call the metrics through a common function that can be used within a dplyr chain

dat <- data.frame(y = y, pred = pred)

performance(dat, actual = "y", predicted = "pred")
performance(dat, actual = "y", predicted = "pred", metrics = r_squared)
performance(dat, actual = "y", predicted = "pred", 
            metrics = list(rmse = rmse, `R-squared` = r_squared))

Functions in MetricsWeighted

Name Description
precision Precision
recall Recall
rmse Root-Mean-Squared Error
deviance_normal Normal Deviance
r_squared Pseudo R-Squared
weighted_median Weighted Median
weighted_mean Weighted Mean
mape Mean Absolute Percentage Error
medae Median Absolute Error
performance Performance
weighted_var Weighted Variance
mse Mean-Squared Error
weighted_quantile Weighted Quantiles
logLoss Log Loss/Binary Cross Entropy
mae Mean Absolute Error
deviance_poisson Poisson Deviance
AUC Area under the ROC
classification_error Classification Error
deviance_gamma Gamma Deviance
deviance_tweedie Tweedie Deviance
deviance_bernoulli Bernoulli Deviance
accuracy Accuracy
f1_score F1 Score
gini_coefficient Gini Coefficient
No Results!

Vignettes of MetricsWeighted

Name
MetricsWeighted.Rmd
No Results!

Last month downloads

Details

Type Package
Date 2019-11-08
License GPL (>= 2)
VignetteBuilder knitr
Encoding UTF-8
LazyData true
RoxygenNote 6.1.1
NeedsCompilation no
Packaged 2019-11-08 15:00:11 UTC; Michael
Repository CRAN
Date/Publication 2019-11-08 18:10:02 UTC
suggests dplyr , knitr
depends R (>= 3.5.0)
imports stats
Contributors Christian Lorentzen

Include our badge in your README

[![Rdoc](http://www.rdocumentation.org/badges/version/MetricsWeighted)](http://www.rdocumentation.org/packages/MetricsWeighted)