Title: | Linear Predictive Models Based on the LIBLINEAR C/C++ Library |
---|---|
Description: | A wrapper around the LIBLINEAR C/C++ library for machine learning (available at <https://www.csie.ntu.edu.tw/~cjlin/liblinear/>). LIBLINEAR is a simple library for solving large-scale regularized linear classification and regression. It currently supports L2-regularized classification (such as logistic regression, L2-loss linear SVM and L1-loss linear SVM) as well as L1-regularized classification (such as L2-loss linear SVM and logistic regression) and L2-regularized support vector regression (with L1- or L2-loss). The main features of LiblineaR include multi-class classification (one-vs-the rest, and Crammer & Singer method), cross validation for model selection, probability estimates (logistic regression only) or weights for unbalanced data. The estimation of the models is particularly fast as compared to other libraries. |
Authors: | Thibault Helleputte [cre, aut, cph], Jérôme Paul [aut], Pierre Gramme [aut] |
Maintainer: | Thibault Helleputte <[email protected]> |
License: | GPL-2 |
Version: | 2.10-24 |
Built: | 2024-11-14 06:18:00 UTC |
Source: | CRAN |
heuristicC
implements a heuristics proposed by Thorsten Joachims in
order to make fast estimates of a convenient value for the C constant used by
support vector machines. This implementation only works for linear support
vector machines.
heuristicC(data)
heuristicC(data)
data |
a nxp data matrix. Each row stands for an example (sample, point) and each column stands for a dimension (feature, variable) |
A value for the C constant is returned, computed as follows:
where
Classification models usually perform better if each dimension of the data is first centered and scaled. If data are scaled, it is better to compute the heuristics on the scaled data as well.
Thibault Helleputte [email protected]
T. Joachims
SVM light (2002)
http://svmlight.joachims.org
data(iris) x=iris[,1:4] y=factor(iris[,5]) train=sample(1:dim(iris)[1],100) xTrain=x[train,] xTest=x[-train,] yTrain=y[train] yTest=y[-train] # Center and scale data s=scale(xTrain,center=TRUE,scale=TRUE) # Sparse Logistic Regression t=6 co=heuristicC(s) m=LiblineaR(data=s,labels=yTrain,type=t,cost=co,bias=TRUE,verbose=FALSE)
data(iris) x=iris[,1:4] y=factor(iris[,5]) train=sample(1:dim(iris)[1],100) xTrain=x[train,] xTest=x[-train,] yTrain=y[train] yTest=y[-train] # Center and scale data s=scale(xTrain,center=TRUE,scale=TRUE) # Sparse Logistic Regression t=6 co=heuristicC(s) m=LiblineaR(data=s,labels=yTrain,type=t,cost=co,bias=TRUE,verbose=FALSE)
LiblineaR
allows the estimation of predictive linear models for
classification and regression, such as L1- or L2-regularized logistic
regression, L1- or L2-regularized L2-loss support vector classification,
L2-regularized L1-loss support vector classification and multi-class support
vector classification. It also supports L2-regularized support vector regression
(with L1- or L2-loss). The estimation of the models is particularly fast as
compared to other libraries. The implementation is based on the LIBLINEAR C/C++
library for machine learning.
LiblineaR( data, target, type = 0, cost = 1, epsilon = 0.01, svr_eps = NULL, bias = 1, wi = NULL, cross = 0, verbose = FALSE, findC = FALSE, useInitC = TRUE, ... )
LiblineaR( data, target, type = 0, cost = 1, epsilon = 0.01, svr_eps = NULL, bias = 1, wi = NULL, cross = 0, verbose = FALSE, findC = FALSE, useInitC = TRUE, ... )
data |
a nxp data matrix. Each row stands for an example (sample, point) and each column stands for a dimension (feature, variable). Sparse matrices of class matrix.csr, matrix.csc and matrix.coo from package SparseM are accepted. Sparse matrices of class dgCMatrix, dgRMatrix or dgTMatrix from package Matrix are also accepted. Note that C code at the core of LiblineaR package corresponds to a row-based sparse format. Hence, dgCMatrix, dgTMatrix, matrix.csc and matrix.csr inputs are first transformed into matrix.csr or dgRMatrix formats, which requires small extra computation time. |
target |
a response vector for prediction tasks with one value for
each of the n rows of |
type |
|
cost |
cost of constraints violation (default: 1). Rules the trade-off
between regularization and correct classification on |
epsilon |
set tolerance of termination criterion for optimization.
If
The meaning of
|
svr_eps |
set tolerance margin (epsilon) in regression loss function of SVR. Not used for classification methods. |
bias |
if bias > 0, instance |
wi |
a named vector of weights for the different classes, used for asymmetric class sizes. Not all factor levels have to be supplied (default weight: 1). All components have to be named according to the corresponding class label. Not used in regression mode. |
cross |
if an integer value k>0 is specified, a k-fold cross validation
on |
verbose |
if |
findC |
if |
useInitC |
if |
... |
for backwards compatibility, parameter |
For details for the implementation of LIBLINEAR, see the README file of the original c/c++ LIBLINEAR library at https://www.csie.ntu.edu.tw/~cjlin/liblinear/.
If cross
>0, the average accuracy (classification) or mean square error (regression) computed over cross
runs of cross-validation is returned.
Otherwise, an object of class "LiblineaR"
containing the fitted model is returned, including:
TypeDetail |
A string decsribing the type of model fitted, as determined by |
Type |
An integer corresponding to |
W |
A matrix with the model weights. If |
Bias |
The value of |
ClassNames |
A vector containing the class names. This entry is not returned in case of regression models. |
Classification models usually perform better if each dimension of the data is first centered and scaled.
Thibault Helleputte [email protected] and
Jerome Paul [email protected] and Pierre Gramme.
Based on C/C++-code by Chih-Chung Chang and Chih-Jen Lin
For more information on LIBLINEAR itself, refer to:
R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin.
LIBLINEAR: A Library for Large Linear Classification,
Journal of Machine Learning Research 9(2008), 1871-1874.
https://www.csie.ntu.edu.tw/~cjlin/liblinear/
data(iris) attach(iris) x=iris[,1:4] y=factor(iris[,5]) train=sample(1:dim(iris)[1],100) xTrain=x[train,] xTest=x[-train,] yTrain=y[train] yTest=y[-train] # Center and scale data s=scale(xTrain,center=TRUE,scale=TRUE) # Find the best model with the best cost parameter via 10-fold cross-validations tryTypes=c(1:6) tryCosts=c(1000,0.001) bestCost=NA bestAcc=0 bestType=NA for(ty in tryTypes){ for(co in tryCosts){ acc=LiblineaR(data=s,target=yTrain,type=ty,cost=co,bias=1,cross=5,verbose=FALSE) cat("Results for C=",co," : ",acc," accuracy.\n",sep="") if(acc>bestAcc){ bestCost=co bestAcc=acc bestType=ty } } } cat("Best model type is:",bestType,"\n") cat("Best cost is:",bestCost,"\n") cat("Best accuracy is:",bestAcc,"\n") # Re-train best model with best cost value. m=LiblineaR(data=s,target=yTrain,type=bestType,cost=bestCost,bias=1,verbose=FALSE) # Scale the test data s2=scale(xTest,attr(s,"scaled:center"),attr(s,"scaled:scale")) # Make prediction pr=FALSE if(bestType==0 || bestType==7) pr=TRUE p=predict(m,s2,proba=pr,decisionValues=TRUE) # Display confusion matrix res=table(p$predictions,yTest) print(res) # Compute Balanced Classification Rate BCR=mean(c(res[1,1]/sum(res[,1]),res[2,2]/sum(res[,2]),res[3,3]/sum(res[,3]))) print(BCR) #' ############################################# # Example of the use of a sparse matrix of class matrix.csr : if(require(SparseM)){ # Sparsifying the iris dataset: iS=apply(iris[,1:4],2,function(a){a[a<quantile(a,probs=c(0.25))]=0;return(a)}) irisSparse<-as.matrix.csr(iS) # Applying a similar methodology as above: xTrain=irisSparse[train,] xTest=irisSparse[-train,] # Re-train best model with best cost value. m=LiblineaR(data=xTrain,target=yTrain,type=bestType,cost=bestCost,bias=1,verbose=FALSE) # Make prediction p=predict(m,xTest,proba=pr,decisionValues=TRUE) } #' ############################################# # Example of the use of a sparse matrix of class dgCMatrix : if(require(Matrix)){ # Sparsifying the iris dataset: iS=apply(iris[,1:4],2,function(a){a[a<quantile(a,probs=c(0.25))]=0;return(a)}) irisSparse<-as(iS,"sparseMatrix") # Applying a similar methodology as above: xTrain=irisSparse[train,] xTest=irisSparse[-train,] # Re-train best model with best cost value. m=LiblineaR(data=xTrain,target=yTrain,type=bestType,cost=bestCost,bias=1,verbose=FALSE) # Make prediction p=predict(m,xTest,proba=pr,decisionValues=TRUE) } ############################################# # Try regression instead, to predict sepal length on the basis of sepal width and petal width: xTrain=iris[c(1:25,51:75,101:125),2:3] yTrain=iris[c(1:25,51:75,101:125),1] xTest=iris[c(26:50,76:100,126:150),2:3] yTest=iris[c(26:50,76:100,126:150),1] # Center and scale data s=scale(xTrain,center=TRUE,scale=TRUE) # Estimate MSE in cross-vaidation on a train set MSECross=LiblineaR(data = s, target = yTrain, type = 13, cross = 5, svr_eps=.01) # Build the model m=LiblineaR(data = s, target = yTrain, type = 13, cross=0, svr_eps=.01) # Test it, after test data scaling: s2=scale(xTest,attr(s,"scaled:center"),attr(s,"scaled:scale")) pred=predict(m,s2)$predictions MSETest=mean((yTest-pred)^2) # Was MSE well estimated? print(MSETest-MSECross) # Distribution of errors print(summary(yTest-pred))
data(iris) attach(iris) x=iris[,1:4] y=factor(iris[,5]) train=sample(1:dim(iris)[1],100) xTrain=x[train,] xTest=x[-train,] yTrain=y[train] yTest=y[-train] # Center and scale data s=scale(xTrain,center=TRUE,scale=TRUE) # Find the best model with the best cost parameter via 10-fold cross-validations tryTypes=c(1:6) tryCosts=c(1000,0.001) bestCost=NA bestAcc=0 bestType=NA for(ty in tryTypes){ for(co in tryCosts){ acc=LiblineaR(data=s,target=yTrain,type=ty,cost=co,bias=1,cross=5,verbose=FALSE) cat("Results for C=",co," : ",acc," accuracy.\n",sep="") if(acc>bestAcc){ bestCost=co bestAcc=acc bestType=ty } } } cat("Best model type is:",bestType,"\n") cat("Best cost is:",bestCost,"\n") cat("Best accuracy is:",bestAcc,"\n") # Re-train best model with best cost value. m=LiblineaR(data=s,target=yTrain,type=bestType,cost=bestCost,bias=1,verbose=FALSE) # Scale the test data s2=scale(xTest,attr(s,"scaled:center"),attr(s,"scaled:scale")) # Make prediction pr=FALSE if(bestType==0 || bestType==7) pr=TRUE p=predict(m,s2,proba=pr,decisionValues=TRUE) # Display confusion matrix res=table(p$predictions,yTest) print(res) # Compute Balanced Classification Rate BCR=mean(c(res[1,1]/sum(res[,1]),res[2,2]/sum(res[,2]),res[3,3]/sum(res[,3]))) print(BCR) #' ############################################# # Example of the use of a sparse matrix of class matrix.csr : if(require(SparseM)){ # Sparsifying the iris dataset: iS=apply(iris[,1:4],2,function(a){a[a<quantile(a,probs=c(0.25))]=0;return(a)}) irisSparse<-as.matrix.csr(iS) # Applying a similar methodology as above: xTrain=irisSparse[train,] xTest=irisSparse[-train,] # Re-train best model with best cost value. m=LiblineaR(data=xTrain,target=yTrain,type=bestType,cost=bestCost,bias=1,verbose=FALSE) # Make prediction p=predict(m,xTest,proba=pr,decisionValues=TRUE) } #' ############################################# # Example of the use of a sparse matrix of class dgCMatrix : if(require(Matrix)){ # Sparsifying the iris dataset: iS=apply(iris[,1:4],2,function(a){a[a<quantile(a,probs=c(0.25))]=0;return(a)}) irisSparse<-as(iS,"sparseMatrix") # Applying a similar methodology as above: xTrain=irisSparse[train,] xTest=irisSparse[-train,] # Re-train best model with best cost value. m=LiblineaR(data=xTrain,target=yTrain,type=bestType,cost=bestCost,bias=1,verbose=FALSE) # Make prediction p=predict(m,xTest,proba=pr,decisionValues=TRUE) } ############################################# # Try regression instead, to predict sepal length on the basis of sepal width and petal width: xTrain=iris[c(1:25,51:75,101:125),2:3] yTrain=iris[c(1:25,51:75,101:125),1] xTest=iris[c(26:50,76:100,126:150),2:3] yTest=iris[c(26:50,76:100,126:150),1] # Center and scale data s=scale(xTrain,center=TRUE,scale=TRUE) # Estimate MSE in cross-vaidation on a train set MSECross=LiblineaR(data = s, target = yTrain, type = 13, cross = 5, svr_eps=.01) # Build the model m=LiblineaR(data = s, target = yTrain, type = 13, cross=0, svr_eps=.01) # Test it, after test data scaling: s2=scale(xTest,attr(s,"scaled:center"),attr(s,"scaled:scale")) pred=predict(m,s2)$predictions MSETest=mean((yTest-pred)^2) # Was MSE well estimated? print(MSETest-MSECross) # Distribution of errors print(summary(yTest-pred))
The function applies a model (classification or regression) produced by the LiblineaR
function to every row of a
data matrix and returns the model predictions.
## S3 method for class 'LiblineaR' predict(object, newx, proba = FALSE, decisionValues = FALSE, ...)
## S3 method for class 'LiblineaR' predict(object, newx, proba = FALSE, decisionValues = FALSE, ...)
object |
Object of class |
newx |
An n x p matrix containing the new input data. A vector will be transformed to a n x 1 matrix. Sparse matrices of class matrix.csr, matrix.csc and matrix.coo from package SparseM are accepted. Sparse matrices of class dgCMatrix, dgRMatrix or dgTMatrix from package Matrix are also accepted. Note that C code at the core of LiblineaR package corresponds to a row-based sparse format. Hence, dgCMatrix, dgTMatrix, matrix.csc and matrix.csr inputs are first transformed into matrix.csr or dgRMatrix formats, which requires small extra computation time. |
proba |
Logical indicating whether class probabilities should be
computed and returned. Only possible if the model was fitted with
|
decisionValues |
Logical indicating whether model decision values should
be computed and returned. Only possible for classification models
( |
... |
Currently not used |
By default, the returned value is a list with a single entry:
predictions |
A vector of predicted labels (or values for regression). |
If proba
is set to TRUE
, and the model is a logistic
regression, an additional entry is returned:
probabilities |
An n x k matrix (k number of classes) of the class probabilities. The columns of this matrix are named after class labels. |
If decisionValues
is set to TRUE
, and the model is not a
regression model, an additional entry is returned:
decisionValues |
An n x k matrix (k number of classes) of the model decision values. The columns of this matrix are named after class labels. |
If the data on which the model has been fitted have been centered
and/or scaled, it is very important to apply the same process on the
newx
data as well, with the scale and center values of the training
data.
Thibault Helleputte [email protected] and
Jerome Paul [email protected] and Pierre Gramme.
Based on C/C++-code by Chih-Chung Chang and Chih-Jen Lin
For more information on LIBLINEAR itself, refer to:
R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin.
LIBLINEAR: A Library for Large Linear Classification,
Journal of Machine Learning Research 9(2008), 1871-1874.
https://www.csie.ntu.edu.tw/~cjlin/liblinear/