h2otools (version 0.4)

Fmeasure: F-Measure

Description

Calculates F-Measure for any given value of Beta

Usage

Fmeasure(perf, beta = 1, max = FALSE)

Value

a matrix of F-Measures for different thresholds or the highest F-Measure value

Arguments

perf

a h2o object of class "H2OBinomialMetrics" which is provided by 'h2o.performance' function.

beta

numeric, specifying beta value, which must be higher than zero

max

logical. default is FALSE. if TRUE, instead of providing the F-Measure for all the thresholds, the highest F-Measure is reported.

Author

E. F. Haghish

Examples

if (FALSE) {
library(h2o)
h2o.init(ignore_config = TRUE, nthreads = 2, bind_to_localhost = FALSE, insecure = TRUE)
prostate_path <- system.file("extdata", "prostate.csv", package = "h2o")
prostate <- h2o.importFile(path = prostate_path, header = TRUE)
y <- "CAPSULE"
prostate[,y] <- as.factor(prostate[,y])  #convert to factor for classification
aml <- h2o.automl(y = y, training_frame = prostate, max_runtime_secs = 30)

# evaluate the model performance
perf <- h2o.performance(aml@leader, xval = TRUE)

# evaluate F-Measure for a Beta = 3
Fmeasure(perf, beta = 3, max = TRUE)

# evaluate F-Measure for a Beta = 1.5
Fmeasure(perf, beta = 1.5, max = TRUE)

# evaluate F-Measure for a Beta = 4
Fmeasure(perf, beta = 4, max = TRUE)

}