meteo (version 2.0-3)

acc.metric.fun: Accuracy metrics calculation

Description

Calculates classification and regression accuracy metrics for given coresponding observation and prediction vectors.

Usage

acc.metric.fun(obs, pred, acc.m)

Value

Accuracy metric value.

Arguments

obs

numeric or factor vector; Observations.

pred

numeric or factor vector; Predictions.

acc.m

character; Accuracy metric. Possible values for regression: "ME", "MAE", "NMAE", "RMSE", "NRMSE", "R2", "CCC". Possible values for classification: "Accuracy", "Kappa", "AccuracyLower", "AccuracyUpper", "AccuracyNull", "AccuracyPValue", "McnemarPValue".

Author

Aleksandar Sekulic

References

Sekulić, A., Kilibarda, M., Heuvelink, G. B., Nikolić, M. & Bajat, B. Random Forest Spatial Interpolation.Remote. Sens. 12, 1687, https://doi.org/10.3390/rs12101687 (2020).

See Also

acc.metric.fun rfsi pred.rfsi tune.rfsi cv.rfsi pred.strk cv.strk

Examples

library(sp)
library(sf)
library(CAST)
library(ranger)
library(plyr)
library(meteo)

# preparing data
demo(meuse, echo=FALSE)
meuse <- meuse[complete.cases(meuse@data),]
data = st_as_sf(meuse, coords = c("x", "y"), crs = 28992, agr = "constant")
fm.RFSI <- as.formula("zinc ~ dist + soil + ffreq")

# making tgrid
n.obs <- 1:3
min.node.size <- 2:10
sample.fraction <- seq(1, 0.632, -0.05) # 0.632 without / 1 with replacement
splitrule <- "variance"
ntree <- 250 # 500
mtry <- 3:(2+2*max(n.obs))
tgrid = expand.grid(min.node.size=min.node.size, num.trees=ntree,
                    mtry=mtry, n.obs=n.obs, sample.fraction=sample.fraction)

# \donttest{
# do cross-validation
rfsi_cv <- cv.rfsi(formula=fm.RFSI, # without nearest obs
                   data = data,
                   zero.tol=0,
                   tgrid = tgrid, # combinations for tuning
                   tgrid.n = 5, # number of randomly selected combinations from tgrid for tuning
                   tune.type = "LLO", # Leave-Location-Out CV
                   k = 5, # number of folds
                   seed = 42,
                   acc.metric = "RMSE", # R2, CCC, MAE
                   output.format = "data.frame",
                   cpus=2, # detectCores()-1,
                   progress=1,
                   importance = "impurity")
summary(rfsi_cv)

# accuracy metric calculation
acc.metric.fun(rfsi_cv$obs, rfsi_cv$pred, "R2")
acc.metric.fun(rfsi_cv$obs, rfsi_cv$pred, "RMSE")
acc.metric.fun(rfsi_cv$obs, rfsi_cv$pred, "NRMSE")
acc.metric.fun(rfsi_cv$obs, rfsi_cv$pred, "MAE")
acc.metric.fun(rfsi_cv$obs, rfsi_cv$pred, "NMAE")
acc.metric.fun(rfsi_cv$obs, rfsi_cv$pred, "CCC")
# }