FitEva: Evaluate the fitting result.

In TriangularCell/PgaMsgl: Proximal Gradient Algorithm for Multi-variate Sparse Group Lasso

Description

Evaluate the fitting result by calculating the TPR (ratio of true positives to real positives), FPR (ratio of false positives to real negatives), precision (ratio of true positives to predicted positives) , accuracy (ratio of the sum of true positives and true negatives to total number of predictions) and F1 score (the harmonic average of the precision and recall (TPR)).

Usage

FitEva(Beta.simulate, Beta.fit, Gm, cutoff.sc, cutoff.g)

Arguments

Beta.simulate	The simulated or golden standarded B matrix.
Beta.fit	The fitted B matrix using PgaMsgl or other algorithms.
Gm	Matrix of the group structure of coefficient matrix B. It is the a matrix of group boundaries, with each row indicating a group, four columns indicate the row-start, row-end, column-start and column-end of the group. The row/column index is 1-based.
cutoff.sc	A non-negative number indicates the cutoff of a single coefficient in B to be positive in the fitted B matrix.
cutoff.g	A non-negative number indicates the cutoff of the norm of a group (a sub-matrix in truth) in the fitted B matrix to be positive.

Value

sc.TPR	The true positive rate of single coefficients prediction.
sc.FPR	The false positive rate of single coefficients prediction.
sc.TTPR	The "true" true positive rate of single coefficients prediction.
sc.precision	The precision of single coefficients prediction.
sc.accuracy	The accuracy of single coefficients prediction.
sc.F1	The F1 score of single coefficients prediction.
g.TPR	The true positive rate of group prediction.
g.FPR	The false positive rate of group prediction
g.precision	The precision of goup prediction.
g.accuracy	The accuracy of group prediction.
g.F1	The F1 score of group prediction.

Examples

data(lowD)
result <- PgaMsgl(lowD$X, lowD$Y, lowD$B0, model="L121", lowD$Gm, lowD$mi, lowD$mg, lowD$mc)
FitEva_result <- FitEva(lowD$Beta, result$Beta, lowD$Gm, cutoff.sc=0, cutoff.g=0)

TriangularCell/PgaMsgl documentation built on May 28, 2019, 9:33 a.m.