cal.acc {GAGAs}

Calculate ACC for classification, the inputs must be characters

Description

Calculate ACC for classification, the inputs must be characters

Usage

cal.acc(predictions, truelabels)

Arguments

predictions

predictions

truelabels

true labels

Value

ACC

Examples

set.seed(2022)
p_size = 30
sample_size=300
R1 = 3
R2 = 2
ratio = 0.5 #The ratio of zeroes in coefficients
# Set the true coefficients
zeroNum = round(ratio*p_size)
ind = sample(1:p_size,zeroNum)
beta_true = runif(p_size,0,R2)
beta_true[ind] = 0
X = R1*matrix(rnorm(sample_size * p_size), ncol = p_size)
y=X%*%beta_true + rnorm(sample_size,mean=0,sd=2)
# Estimation
fit = GAGAs(X,y,alpha = 3,family="gaussian")
Eb = fit$beta
#Create testing data
X_t = R1*matrix(rnorm(sample_size * p_size), ncol = p_size)
y_t=X_t%*%beta_true + rnorm(sample_size,mean=0,sd=2)
#Prediction
Ey = predict.GAGA(fit,newx=X_t)

cat("\n err:", norm(Eb-beta_true,type="2")/norm(beta_true,type="2"))
cat("\n acc:", cal.acc(as.character(Eb!=0),as.character(beta_true!=0)))
cat("\n perr:", norm(Ey-y_t,type="2")/sqrt(sample_size))