This page lists ready to run shogun examples for the R Modular interface.
To run the examples issue
R -f name_of_example.R
or start R and then type
source('name_of_example.R')
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) label_train_multiclass <- as.real(read.table('../data/label_train_multiclass.dat')) # gmnpsvm print('GMNPSVM') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) width <- 2.1 kernel <- GaussianKernel(feats_train, feats_train, width) C <- 1.3 epsilon <- 1e-5 num_threads <- as.integer(1) labels <- Labels(label_train_multiclass) svm <- GMNPSVM(C, kernel, labels) dump <- svm$set_epsilon(svm, epsilon) dump <- svm$parallel$set_num_threads(svm$parallel, num_threads) dump <- svm$train(svm) dump <- kernel$init(kernel, feats_train, feats_test) lab <- svm$classify(svm) out <- lab$get_labels(lab)
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) label_train_twoclass <- as.real(read.table('../data/label_train_twoclass.dat')) # gpbtsvm print('GPBTSVM') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) width <- 2.1 kernel <- GaussianKernel(feats_train, feats_train, width) C <- 0.017 epsilon <- 1e-5 num_threads <- as.integer(2) labels <- Labels(label_train_twoclass) svm <- GPBTSVM(C, kernel, labels) dump <- svm$set_epsilon(svm, epsilon) dump <- svm$parallel$set_num_threads(svm$parallel, num_threads) dump <- svm$train(svm) dump <- kernel$init(kernel, feats_train, feats_test) lab <- svm$classify(svm) out <- lab$get_labels(lab)
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) label_train_multiclass <- as.real(read.table('../data/label_train_multiclass.dat')) # knn print('KNN') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) distance <- EuclidianDistance() k <- as.integer(3) num_threads <- as.integer(1) labels <- Labels(label_train_multiclass) knn <- KNN(k, distance, labels) dump <- knn$parallel$set_num_threads(knn$parallel, num_threads) dump <- knn$train(knn, feats_train) lab <- knn$classify(knn, feats_test) out <- lab$get_labels(lab)
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) label_train_twoclass <- as.real(read.table('../data/label_train_twoclass.dat')) # lda print('LDA') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) gamma <- 3 labels <- Labels(label_train_twoclass) lda <- LDA(gamma, feats_train, labels) dump <- lda$train(lda) dump <- lda$get_bias(lda) dump <- lda$get_w(lda) dump <- lda$set_features(lda, feats_test) lab <- lda$classify(lda) out <- lab$get_labels(lab)
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) label_train_twoclass <- as.real(read.table('../data/label_train_twoclass.dat')) # liblinear print('LibLinear') realfeat <- RealFeatures(fm_train_real) feats_train <- SparseRealFeatures() dump <- feats_train$obtain_from_simple(feats_train, realfeat) realfeat <- RealFeatures(fm_test_real) feats_test <- SparseRealFeatures() dump <- feats_test$obtain_from_simple(feats_test, realfeat) C <- 1.42 epsilon <- 1e-5 num_threads <- as.integer(1) labels <- Labels(label_train_twoclass) svm <- LibLinear(C, feats_train, labels) dump <- svm$set_epsilon(svm, epsilon) dump <- svm$parallel$set_num_threads(svm$parallel, num_threads) dump <- svm$set_bias_enabled(svm, TRUE) dump <- svm$train(svm) dump <- svm$set_features(svm, feats_test) lab <- svm$classify(svm) out <- lab$get_labels(lab)
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) label_train_twoclass <- as.real(read.table('../data/label_train_twoclass.dat')) # libsvm print('LibSVM') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) width <- 2.1 kernel <- GaussianKernel(feats_train, feats_train, width) C <- 1.017 epsilon <- 1e-5 num_threads <- as.integer(2) labels <- Labels(label_train_twoclass) svm <- LibSVM(C, kernel, labels) dump <- svm$set_epsilon(svm, epsilon) dump <- svm$parallel$set_num_threads(svm$parallel, num_threads) dump <- svm$train(svm) dump <- kernel$init(kernel, feats_train, feats_test) lab <- svm$classify(svm) out <- lab$get_labels(lab)
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) label_train_multiclass <- as.real(read.table('../data/label_train_multiclass.dat')) # libsvmmulticlass print('LibSVMMultiClass') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) width <- 2.1 kernel <- GaussianKernel(feats_train, feats_train, width) C <- 1.017 epsilon <- 1e-5 num_threads <- as.integer(8) labels <- Labels(label_train_multiclass) svm <- LibSVMMultiClass(C, kernel, labels) dump <- svm$set_epsilon(svm, epsilon) dump <- svm$parallel$set_num_threads(svm$parallel, num_threads) dump <- svm$train(svm) dump <- kernel$init(kernel, feats_train, feats_test) lab <- svm$classify(svm) out <- lab$get_labels(lab)
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) # libsvm oneclass print('LibSVMOneClass') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) width <- 2.1 kernel <- GaussianKernel(feats_train, feats_train, width) C <- 1.017 epsilon <- 1e-5 num_threads <- as.integer(4) svm <- LibSVMOneClass(C, kernel) dump <- svm$set_epsilon(svm, epsilon) dump <- svm$parallel$set_num_threads(svm$parallel, num_threads) dump <- svm$train(svm) dump <- kernel$init(kernel, feats_train, feats_test) lab <- svm$classify(svm) out <- lab$get_labels(lab)
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) label_train_multiclass <- as.real(read.table('../data/label_train_multiclass.dat')) # libsvmmulticlass print('LibSVMMultiClass') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) width <- 2.1 kernel <- GaussianKernel(feats_train, feats_train, width) C <- 1.2 epsilon <- 1e-5 num_threads <- as.integer(8) labels <- Labels(label_train_multiclass) svm <- LibSVMMultiClass(C, kernel, labels) dump <- svm$set_epsilon(svm, epsilon) dump <- svm$parallel$set_num_threads(svm$parallel, num_threads) dump <- svm$train(svm) dump <- kernel$init(kernel, feats_train, feats_test) lab <- svm$classify(svm) out <- lab$get_labels(lab)
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) label_train_twoclass <- as.real(read.table('../data/label_train_twoclass.dat')) # perceptron print('Perceptron') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) learn_rate <- 1. max_iter <- as.integer(1000) num_threads <- as.integer(1) labels <- Labels(label_train_twoclass) perceptron <- Perceptron(feats_train, labels) dump <- perceptron$set_learn_rate(perceptron, learn_rate) dump <- perceptron$set_max_iter(perceptron, max_iter) dump <- perceptron$train(perceptron) dump <- perceptron$set_features(perceptron, feats_test) lab <- perceptron$classify(perceptron) out <- lab$get_labels(lab)
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) label_train_twoclass <- as.real(read.table('../data/label_train_twoclass.dat')) # subgradient based svm print('SubGradientSVM') realfeat <- RealFeatures(fm_train_real) feats_train <- SparseRealFeatures() dump <- feats_train$obtain_from_simple(feats_train, realfeat) realfeat <- RealFeatures(fm_test_real) feats_test <- SparseRealFeatures() dump <- feats_test$obtain_from_simple(feats_test, realfeat) C <- 1.42 epsilon <- 1e-3 num_threads <- as.integer(1) max_train_time <- 1. labels <- Labels(label_train_twoclass) svm <- SubGradientSVM(C, feats_train, labels) dump <- svm$set_epsilon(svm, epsilon) dump <- svm$parallel$set_num_threads(svm$parallel, num_threads) dump <- svm$set_bias_enabled(svm, FALSE) dump <- svm$set_max_train_time(svm, max_train_time) dump <- svm$train(svm) dump <- svm$set_features(svm, feats_test) lab <- svm$classify(svm) out <- lab$get_labels(lab)
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) label_train_dna <- as.real(read.table('../data/label_train_dna42.dat')) # svm light dosvmlight <- function() { print('SVMLight') feats_train <- StringCharFeatures("DNA") dump <- feats_train$set_features(feats_train, fm_train_dna) feats_test <- StringCharFeatures("DNA") dump <- feats_test$set_features(feats_test, fm_test_dna) degree <- as.integer(20) kernel <- WeightedDegreeStringKernel(feats_train, feats_train, degree) C <- 1.017 epsilon <- 1e-5 num_threads <- as.integer(3) labels <- Labels(as.real(label_train_dna)) svm <- SVMLight(C, kernel, labels) dump <- svm$set_epsilon(svm, epsilon) dump <- svm$parallel$set_num_threads(svm$parallel, num_threads) dump <- svm$train(svm) dump <- kernel$init(kernel, feats_train, feats_test) lab <- svm$classify(svm) out <- lab$get_labels(lab) } try(dosvmlight())
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) label_train_twoclass <- as.real(read.table('../data/label_train_twoclass.dat')) # svm lin print('SVMLin') realfeat <- RealFeatures(fm_train_real) feats_train <- SparseRealFeatures() dump <- feats_train$obtain_from_simple(feats_train, realfeat) realfeat <- RealFeatures(fm_test_real) feats_test <- SparseRealFeatures() dump <- feats_test$obtain_from_simple(feats_test, realfeat) C <- 1.42 epsilon <- 1e-5 num_threads <- as.integer(1) labels <- Labels(label_train_twoclass) svm <- SVMLin(C, feats_train, labels) dump <- svm$set_epsilon(svm, epsilon) dump <- svm$parallel$set_num_threads(svm$parallel, num_threads) dump <- svm$set_bias_enabled(svm, TRUE) dump <- svm$train(svm) dump <- svm$set_features(svm, feats_test) dump <- svm$get_bias(svm) dump <- svm$get_w(svm) lab <- svm$classify(svm) out <- lab$get_labels(lab)
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) label_train_twoclass <- as.real(read.table('../data/label_train_twoclass.dat')) # svm ocas print('SVMOcas') realfeat <- RealFeatures(fm_train_real) feats_train <- SparseRealFeatures() dump <- feats_train$obtain_from_simple(feats_train, realfeat) realfeat <- RealFeatures(fm_test_real) dump <- feats_test <- SparseRealFeatures() feats_test$obtain_from_simple(feats_test, realfeat) C <- 1.42 epsilon <- 1e-5 num_threads <- as.integer(1) labels <- Labels(label_train_twoclass) svm <- SVMOcas(C, feats_train, labels) dump <- svm$set_epsilon(svm, epsilon) dump <- svm$parallel$set_num_threads(svm$parallel, num_threads) dump <- svm$set_bias_enabled(svm, FALSE) dump <- svm$train(svm) dump <- svm$set_features(svm, feats_test) lab <- svm$classify(svm) out <- lab$get_labels(lab)
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) label_train_twoclass <- as.real(read.table('../data/label_train_twoclass.dat')) # sgd print('SVMSGD') realfeat <- RealFeatures(fm_train_real) feats_train <- SparseRealFeatures() dump <- feats_train$obtain_from_simple(feats_train, realfeat) realfeat <- RealFeatures(fm_test_real) feats_test <- SparseRealFeatures() dump <- feats_test$obtain_from_simple(feats_test, realfeat) C <- 2.3 num_threads <- as.integer(1) labels <- Labels(label_train_twoclass) svm <- SVMSGD(C, feats_train, labels) #dump <- svm$io$set_loglevel(svm$io, 0) dump <- svm$train(svm) dump <- svm$set_features(svm, feats_test) lab <- svm$classify(svm) out <- lab$get_labels(lab)
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) # Histogram print('Histogram') order <- as.integer(3) start <- as.integer(order-1) gap <- as.integer(0) reverse <- FALSE charfeat <- StringCharFeatures("DNA") dump <- charfeat$set_features(charfeat, fm_train_dna) feats=StringWordFeatures(charfeat$get_alphabet()) dump <- feats$obtain_from_char(feats, charfeat, start, order, gap, reverse) preproc=SortWordString() dump <- preproc$init(preproc, feats) dump <- feats$add_preproc(feats, preproc) dump <- feats$apply_preproc(feats) histo=Histogram(feats) dump <- histo$train(histo) dump <- histo$get_histogram() num_examples <- feats$get_num_vectors() num_param <- histo$get_num_model_parameters() # commented out as this is quite time consuming #derivs=matrix(0,num_param, num_examples) #for (i in 0:(num_examples-1)) #{ # for (j in 0:(num_param-1)) # { # derivs[j,i]=histo$get_log_derivative(histo, j, i) # } #} dump <- histo$get_log_likelihood(histo, as.integer(0)) dump <- histo$get_log_likelihood_sample()
library(shogun) fm_train_cube <- as.matrix(read.table('../data/fm_train_cube.dat', colClasses=c('character'))) # HMM print('HMM') N <- as.integer(3) M <- as.integer(6) pseudo <- 1e-1 order <- as.integer(1) start <- as.integer(order-1) gap <- as.integer(0) reverse <- FALSE num_examples <- as.integer(2) charfeat <- StringCharFeatures("CUBE") dump <- charfeat$set_features(charfeat, fm_train_cube) feats <- StringWordFeatures(charfeat$get_alphabet()) dump <- feats$obtain_from_char(feats, charfeat, start, order, gap, reverse) preproc <- SortWordString() dump <- preproc$init(preproc, feats) dump <- feats$add_preproc(feats, preproc) dump <- feats$apply_preproc(feats) hmm <- HMM(feats, N, M, pseudo) dump <- hmm$train(hmm) dump <- hmm$baum_welch_viterbi_train(hmm, "BW_NORMAL") num_examples <- feats$get_num_vectors() num_param <- hmm$get_num_model_parameters() derivs <- matrix(0, num_param, num_examples) for (i in 0:(num_examples-1)) { for (j in 0:(num_param-1)) { derivs[j,i] <- hmm$get_log_derivative(hmm, j, i) } } best_path <- 0 best_path_state <- 0 for (i in 0:(num_examples-1)) { best_path = best_path + hmm$best_path(hmm, i) for (j in 0:(N-1)) { best_path_state = best_path_state + hmm$get_best_path_state(hmm, i, j) } } dump <- hmm$get_log_likelihood(hmm, as.integer(0)) dump <- hmm$get_log_likelihood_sample()
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) # Linear HMM print('LinearHMM') order <- as.integer(3) start <- as.integer(order-1) gap <- as.integer(0) reverse <- FALSE charfeat <- StringCharFeatures("DNA") dump <- charfeat$set_features(charfeat, fm_train_dna) feats <- StringWordFeatures(charfeat$get_alphabet()) dump <- feats$obtain_from_char(feats, charfeat, start, order, gap, reverse) preproc <- SortWordString() dump <- preproc$init(preproc, feats) dump <- feats$add_preproc(feats, preproc) dump <- feats$apply_preproc(feats) hmm <- LinearHMM(feats) dump <- hmm$train(hmm) dump <- hmm$get_transition_probs() num_examples <- feats$get_num_vectors() num_param <- hmm$get_num_model_parameters() derivs <- matrix(0, num_param, num_examples) for (i in 0:(num_examples-1)) { for (j in 0:(num_param-1)) { derivs[j,i] <- hmm$get_log_derivative(hmm, j, i) } } dump <- hmm$get_log_likelihood(hmm, as.integer(0)) dump <- hmm$get_log_likelihood_sample()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) # auc #print('AUC') # #feats_train <- RealFeatures(fm_train_real) #feats_test <- RealFeatures(fm_test_real) #width <- 1.7 #subkernel <- GaussianKernel(feats_train, feats_test, width) # #num_feats <- 2; # do not change! #len_train <- 11 #len_test <- 17 #data <- uint16((len_train-1)*rand(num_feats, len_train)) #feats_train <- WordFeatures(data) #data <- uint16((len_test-1)*rand(num_feats, len_test)) #feats_test <- WordFeatures(data) # #kernel <- AUCKernel(feats_train, feats_test, subkernel) # #km_train <- kernel$get_kernel_matrix() #kernel$init(kernel, feats_train, feats_test) #km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) # chi2 print('Chi2') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) width <- 1.4 size_cache <- as.integer(10) kernel <- Chi2Kernel(feats_train, feats_train, width, size_cache) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) # combined print('Combined') kernel <- CombinedKernel() feats_train <- CombinedFeatures() feats_test <- CombinedFeatures() subkfeats_train <- RealFeatures(fm_train_real) subkfeats_test <- RealFeatures(fm_test_real) subkernel <- GaussianKernel(as.integer(10), 1.6) dump <- feats_train$append_feature_obj(feats_train, subkfeats_train) dump <- feats_test$append_feature_obj(feats_test, subkfeats_test) dump <- kernel$append_kernel(kernel, subkernel) subkfeats_train <- StringCharFeatures("DNA") dump <- subkfeats_train$set_features(subkfeats_train, fm_train_dna) subkfeats_test <- StringCharFeatures("DNA") dump <- subkfeats_test$set_features(subkfeats_test, fm_test_dna) degree <- as.integer(3) subkernel <- FixedDegreeStringKernel(as.integer(10), degree) dump <- feats_train$append_feature_obj(feats_train, subkfeats_train) dump <- feats_test$append_feature_obj(feats_test, subkfeats_test) dump <- kernel$append_kernel(kernel, subkernel) subkfeats_train <- StringCharFeatures("DNA") dump <- subkfeats_train$set_features(subkfeats_train, fm_train_dna) subkfeats_test <- StringCharFeatures("DNA") dump <- subkfeats_test$set_features(subkfeats_test, fm_test_dna) subkernel <- LocalAlignmentStringKernel(as.integer(10)) dump <- feats_train$append_feature_obj(feats_train, subkfeats_train) dump <- feats_test$append_feature_obj(feats_test, subkfeats_test) dump <- kernel$append_kernel(kernel, subkernel) dump <- kernel$init(kernel, feats_train, feats_train) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) # comm_ulong_string print('CommUlongString') order <- as.integer(3) start <- as.integer(order-1) gap <- as.integer(0) reverse <- FALSE charfeat <- StringCharFeatures("DNA") dump <- charfeat$set_features(charfeat, fm_train_dna) feats_train <- StringUlongFeatures(charfeat$get_alphabet()) dump <- feats_train$obtain_from_char(feats_train, charfeat, start, order, gap, reverse) preproc <- SortUlongString() dump <- preproc$init(preproc, feats_train) dump <- feats_train$add_preproc(feats_train, preproc) dump <- feats_train$apply_preproc(feats_train) charfeat <- StringCharFeatures("DNA") dump <- charfeat$set_features(charfeat, fm_test_dna) feats_test <- StringUlongFeatures(charfeat$get_alphabet()) dump <- feats_test$obtain_from_char(feats_test, charfeat, start, order, gap, reverse) dump <- feats_test$add_preproc(feats_test, preproc) dump <- feats_test$apply_preproc(feats_test) use_sign <- FALSE kernel <- CommUlongStringKernel(feats_train, feats_train, use_sign) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) # comm_word_string print('CommWordString') order <- as.integer(3) gap <- as.integer(0) start <- as.integer(order-1) reverse <- FALSE charfeat <- StringCharFeatures("DNA") dump <- charfeat$set_features(charfeat, fm_train_dna) feats_train <- StringWordFeatures(charfeat$get_alphabet()) dump <- feats_train$obtain_from_char(feats_train, charfeat, start, order, gap, reverse) preproc <- SortWordString() dump <- preproc$init(preproc, feats_train) dump <- feats_train$add_preproc(feats_train, preproc) dump <- feats_train$apply_preproc(feats_train) charfeat <- StringCharFeatures("DNA") dump <- charfeat$set_features(charfeat, fm_test_dna) feats_test <- StringWordFeatures(charfeat$get_alphabet()) dump <- feats_test$obtain_from_char(feats_test, charfeat, start, order, gap, reverse) dump <- feats_test$add_preproc(feats_test, preproc) dump <- feats_test$apply_preproc(feats_test) use_sign <- FALSE kernel <- CommWordStringKernel(feats_train, feats_train, use_sign) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) # const print('Const') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) c <- 23. kernel <- ConstKernel(feats_train, feats_train, c) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) ## custom #print('Custom') # #dim <- 7 #data <- rand(dim, dim) #feats <- RealFeatures(data) #symdata <- data+data' #lowertriangle <- array([symdata[(x,y)] for x in xrange(symdata.shape[1]) # for y in xrange(symdata.shape[0]) if y< <- x]) # #kernel <- CustomKernel(feats, feats) # #kernel$set_triangle_kernel_matrix_from_triangle(lowertriangle) #km_triangletriangle <- kernel$get_kernel_matrix() # #kernel$set_triangle_kernel_matrix_from_full(symdata) #km_fulltriangle <- kernel$get_kernel_matrix() # #kernel$set_full_kernel_matrix_from_full(data) #km_fullfull <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) # diag print('Diag') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) diag <- 23. kernel <- DiagKernel(feats_train, feats_train, diag) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) # distance print('Distance') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) width <- 1.7 distance <- EuclidianDistance() kernel <- DistanceKernel(feats_train, feats_test, width, distance) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) # fixed_degree_string print('FixedDegreeString') feats_train <- StringCharFeatures("DNA") dump <- feats_train$set_features(feats_train, fm_train_dna) feats_test <- StringCharFeatures("DNA") dump <- feats_test$set_features(feats_test, fm_test_dna) degree <- as.integer(3) kernel <- FixedDegreeStringKernel(feats_train, feats_train, degree) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) # gaussian print('Gaussian') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) width <- 1.9 kernel <- GaussianKernel(feats_train, feats_train, width) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) # gaussian_shift print('GaussianShift') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) width <- 1.8 max_shift <- as.integer(2) shift_step <- as.integer(1) kernel <- GaussianShiftKernel( feats_train, feats_train, width, max_shift, shift_step) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) label_train_dna <- as.real(as.matrix(read.table('../data/label_train_dna.dat'))) # plugin_estimate print('PluginEstimate w/ HistogramWord') order <- as.integer(3) start <- as.integer(order-1) gap <- as.integer(0) reverse <- FALSE charfeat <- StringCharFeatures("DNA") dump <- charfeat$set_features(charfeat, fm_train_dna) feats_train <- StringWordFeatures(charfeat$get_alphabet()) dump <- feats_train$obtain_from_char(feats_train, charfeat, start, order, gap, reverse) charfeat <- StringCharFeatures("DNA") dump <- charfeat$set_features(charfeat, fm_test_dna) feats_test <- StringWordFeatures(charfeat$get_alphabet()) dump <- feats_test$obtain_from_char(feats_test, charfeat, start, order, gap, reverse) pie <- PluginEstimate() labels <- Labels(label_train_dna) dump <- pie$set_labels(pie, labels) dump <- pie$set_features(pie, feats_train) dump <- pie$train(pie) kernel <- HistogramWordStringKernel(feats_train, feats_train, pie) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) dump <- pie$set_features(pie, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) # linear print('Linear') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) scale <- 1.2 kernel <- LinearKernel() dump <- kernel$set_normalizer(kernel, AvgDiagKernelNormalizer(scale)) dump <- kernel$init(kernel, feats_train, feats_train) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_byte <- as.matrix(read.table('../data/fm_train_byte')) fm_test_byte <- as.matrix(read.table('../data/fm_test_byte')) # linear byte print('LinearByte') num_feats <- 11 feats_train <- ByteFeatures(RAWBYTE) feats_train$copy_feature_matrix(traindata_byte) feats_test <- ByteFeatures(RAWBYTE) feats_test$copy_feature_matrix(testdata_byte) kernel <- LinearByteKernel(feats_train, feats_train) km_train <- kernel$get_kernel_matrix() kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) # linear_string print('LinearString') feats_train <- StringCharFeatures("DNA") dump <- feats_train$set_features(feats_train, fm_train_dna) feats_test <- StringCharFeatures("DNA") dump <- feats_test$set_features(feats_test, fm_test_dna) kernel <- LinearStringKernel(feats_train, feats_train) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_word <- as.matrix(read.table('../data/fm_train_word.dat')) fm_test_word <- as.matrix(read.table('../data/fm_test_word.dat')) ## linear_word #print('LinearWord') # #feats_train <- WordFeatures(fm_train_word) #feats_test <- WordFeatures(fm_test_word) #do_rescale <- TRUE #scale <- 1.4 # #kernel <- LinearWordKernel(feats_train, feats_train, do_rescale, scale) # #km_train <- kernel$get_kernel_matrix() #kernel$init(kernel, feats_train, feats_test) #km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) # local_alignment_string print('LocalAlignmentString') feats_train <- StringCharFeatures("DNA") dump <- feats_train$set_features(feats_train, fm_train_dna) feats_test <- StringCharFeatures("DNA") dump <- feats_test$set_features(feats_test, fm_test_dna) kernel <- LocalAlignmentStringKernel(feats_train, feats_train) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) # locality_improved_string print('LocalityImprovedString') feats_train <- StringCharFeatures("DNA") dump <- feats_train$set_features(feats_train, fm_train_dna) feats_test <- StringCharFeatures("DNA") dump <- feats_test$set_features(feats_test, fm_test_dna) l <- as.integer(5) inner_degree <- as.integer(5) outer_degree <- as.integer(7) kernel <- LocalityImprovedStringKernel( feats_train, feats_train, l, inner_degree, outer_degree) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) # oligo_string print('OligoString') feats_train <- StringCharFeatures("DNA") dump <- feats_train$set_features(feats_train, fm_train_dna) feats_test <- StringCharFeatures("DNA") dump <- feats_test$set_features(feats_test, fm_test_dna) k <- as.integer(3) width <- 1.2 size_cache <- as.integer(10) kernel <- OligoStringKernel(size_cache, k, width) dump <- kernel$init(kernel, feats_train, feats_train) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) # poly print('Poly') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) degree <- as.integer(4) inhomogene <- FALSE kernel <- PolyKernel( feats_train, feats_train, degree, inhomogene) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) # poly_match_string print('PolyMatchString') feats_train <- StringCharFeatures("DNA") dump <- feats_train$set_features(feats_train, fm_train_dna) feats_test <- StringCharFeatures("DNA") dump <- feats_test$set_features(feats_test, fm_test_dna) degree <- as.integer(3) inhomogene <- FALSE kernel <- PolyMatchStringKernel(feats_train, feats_train, degree, inhomogene) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_word <- as.matrix(read.table('../data/fm_train_word.dat')) fm_test_word <- as.matrix(read.table('../data/fm_test_word.dat')) ## poly_match_word #print('PolyMatchWord') # #feats_train <- WordFeatures(traindata_word) #feats_test <- WordFeatures(testdata_word) #degree <- 2 #inhomogene <- TRUE # #kernel <- PolyMatchWordKernel(feats_train, feats_train, degree, inhomogene) # #km_train <- kernel$get_kernel_matrix() #kernel$init(kernel, feats_train, feats_test) #km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) # sigmoid print('Sigmoid') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) size_cache <- as.integer(10) gamma <- 1.2 coef0 <- 1.3 kernel <- SigmoidKernel(feats_train, feats_train, size_cache, gamma, coef0) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) # simple_locality_improved_string print('SimpleLocalityImprovedString') feats_train <- StringCharFeatures("DNA") dump <- feats_train$set_features(feats_train, fm_train_dna) feats_test <- StringCharFeatures("DNA") dump <- feats_test$set_features(feats_test, fm_test_dna) l <- as.integer(5) inner_degree <- as.integer(5) outer_degree <- as.integer(7) kernel <- SimpleLocalityImprovedStringKernel( feats_train, feats_train, l, inner_degree, outer_degree) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) # sparse_gaussian print('SparseGaussian') feat <- RealFeatures(fm_train_real) feats_train <- SparseRealFeatures() dump <- feats_train$obtain_from_simple(feats_train, feat) feat <- RealFeatures(fm_test_real) feats_test <- SparseRealFeatures() dump <- feats_test$obtain_from_simple(feats_test, feat) width <- 1.1 kernel <- SparseGaussianKernel(feats_train, feats_train, width) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) # sparse_linear print('SparseLinear') feat <- RealFeatures(fm_train_real) feats_train <- SparseRealFeatures() dump <- feats_train$obtain_from_simple(feats_train, feat) feat <- RealFeatures(fm_test_real) feats_test <- SparseRealFeatures() dump <- feats_test$obtain_from_simple(feats_test, feat) scale <- 1.1 kernel <- SparseLinearKernel() dump <- kernel$set_normalizer(kernel, AvgDiagKernelNormalizer(scale)) dump <- kernel$init(kernel, feats_train, feats_train)
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) # sparse_poly print('SparsePoly') feat <- RealFeatures(fm_train_real) feats_train <- SparseRealFeatures() dump <- feats_train$obtain_from_simple(feats_train, feat) feat <- RealFeatures(fm_test_real) feats_test <- SparseRealFeatures() dump <- feats_test$obtain_from_simple(feats_test, feat) size_cache <- as.integer(10) degree <- as.integer(3) inhomogene <- TRUE kernel <- SparsePolyKernel(feats_train, feats_train, size_cache, degree, inhomogene) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) size_cache=as.integer(0) fm_train_cube <- as.matrix(read.table('../data/fm_train_cube.dat', colClasses=c('character'))) fm_test_cube <- as.matrix(read.table('../data/fm_test_cube.dat', colClasses=c('character'))) # top_fisher print('TOP/Fisher on PolyKernel') N <- as.integer(3) M <- as.integer(6) pseudo <- 1e-1 order <- as.integer(1) start <- as.integer(order-1) gap <- as.integer(0) reverse <- FALSE charfeat <- StringCharFeatures("CUBE") dump <- charfeat$set_features(charfeat, fm_train_cube) wordfeats_train <- StringWordFeatures(charfeat$get_alphabet()) dump <- wordfeats_train$obtain_from_char(wordfeats_train, charfeat, start, order, gap, reverse) preproc <- SortWordString() dump <- preproc$init(preproc, wordfeats_train) dump <- wordfeats_train$add_preproc(wordfeats_train, preproc) dump <- wordfeats_train$apply_preproc(wordfeats_train) charfeat <- StringCharFeatures("CUBE") dump <- charfeat$set_features(charfeat, fm_test_cube) wordfeats_test <- StringWordFeatures(charfeat$get_alphabet()) dump <- wordfeats_test$obtain_from_char(wordfeats_test, charfeat, start, order, gap, reverse) dump <- wordfeats_test$add_preproc(wordfeats_test, preproc) dump <- wordfeats_test$apply_preproc(wordfeats_test) pos <- HMM(wordfeats_train, N, M, pseudo) dump <- pos$train(pos) dump <- pos$baum_welch_viterbi_train(pos, "BW_NORMAL") neg <- HMM(wordfeats_train, N, M, pseudo) dump <- neg$train(neg) dump <- neg$baum_welch_viterbi_train(neg, "BW_NORMAL") pos_clone <- HMM(pos) neg_clone <- HMM(neg) dump <- pos_clone$set_observations(pos_clone, wordfeats_test) dump <- neg_clone$set_observations(neg_clone, wordfeats_test) feats_train <- TOPFeatures(size_cache, pos, neg, FALSE, FALSE) feats_test <- TOPFeatures(size_cache, pos_clone, neg_clone, FALSE, FALSE) kernel <- PolyKernel(feats_train, feats_train, as.integer(1), FALSE) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix() feats_train <- FKFeatures(size_cache, pos, neg) dump <- feats_train$set_opt_a(feats_train, -1); #estimate prior feats_test <- FKFeatures(size_cache, pos_clone, neg_clone) dump <- feats_test$set_a(feats_test, feats_train$get_a()); #use prior from training data kernel <- PolyKernel(feats_train, feats_train, as.integer(1), FALSE) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) # weighted_comm_word_string print('WeightedCommWordString') order <- as.integer(3) start <- as.integer(order-1) gap <- as.integer(0) reverse <- TRUE charfeat <- StringCharFeatures("DNA") dump <- charfeat$set_features(charfeat, fm_train_dna) feats_train <- StringWordFeatures(charfeat$get_alphabet()) dump <- feats_train$obtain_from_char(feats_train, charfeat, start, order, gap, reverse) preproc <- SortWordString() dump <- preproc$init(preproc, feats_train) dump <- feats_train$add_preproc(feats_train, preproc) dump <- feats_train$apply_preproc(feats_train) charfeat <- StringCharFeatures("DNA") dump <- charfeat$set_features(charfeat, fm_test_dna) feats_test <- StringWordFeatures(charfeat$get_alphabet()) dump <- feats_test$obtain_from_char(feats_test, charfeat, start, order, gap, reverse) dump <- feats_test$add_preproc(feats_test, preproc) dump <- feats_test$apply_preproc(feats_test) use_sign <- FALSE kernel <- WeightedCommWordStringKernel(feats_train, feats_train, use_sign) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) # weighted_degree_position_string print('WeightedDegreePositionString') feats_train <- StringCharFeatures("DNA") dump <- feats_train$set_features(feats_train, fm_train_dna) feats_test <- StringCharFeatures("DNA") dump <- feats_test$set_features(feats_test, fm_test_dna) degree <- as.integer(20) kernel <- WeightedDegreePositionStringKernel(feats_train, feats_train, degree) #kernel$set_shifts(zeros(len(fm_train_dna[0]), dtype <- int)) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) # weighted_degree_string print('WeightedDegreeString') feats_train <- StringCharFeatures("DNA") dump <- feats_train$set_features(feats_train, fm_train_dna) feats_test <- StringCharFeatures("DNA") dump <- feats_test$set_features(feats_test, fm_test_dna) degree <- as.integer(20) kernel <- WeightedDegreeStringKernel(feats_train, feats_train, degree) #weights <- arange(1,degree+1,dtype <- double)[::-1]/ \ # sum(arange(1,degree+1,dtype <- double)) #kernel$set_wd_weights(weights) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) # Explicit examples on how to use the different kernels fm_train_word <- as.matrix(read.table('../data/fm_train_word.dat')) fm_test_word <- as.matrix(read.table('../data/fm_test_word.dat')) ## word_match #print('WordMatch') # #feats_train <- WordFeatures(fm_train_word) #feats_test <- WordFeatures(fm_test_word) #degree <- 3 #do_rescale <- TRUE #scale <- 1.4 # #kernel <- WordMatchKernel(feats_train, feats_train, degree, do_rescale, scale) # #km_train <- kernel$get_kernel_matrix() #kernel$init(kernel, feats_train, feats_test) #km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) label_train_multiclass <- as.real(read.table('../data/label_train_multiclass.dat')) # MKLMultiClass print('MKLMultiClass') kernel <- CombinedKernel() feats_train <- CombinedFeatures() feats_test <- CombinedFeatures() subkfeats_train <- RealFeatures(fm_train_real) subkfeats_test <- RealFeatures(fm_test_real) subkernel <- GaussianKernel(as.integer(10), 1.2) dump <- feats_train$append_feature_obj(feats_train, subkfeats_train) dump <- feats_test$append_feature_obj(feats_test, subkfeats_test) dump <- kernel$append_kernel(kernel, subkernel) kernel <- CombinedKernel() feats_train <- CombinedFeatures() feats_test <- CombinedFeatures() subkfeats_train <- RealFeatures(fm_train_real) subkfeats_test <- RealFeatures(fm_test_real) subkernel <- LinearKernel(as.integer(10)) dump <- feats_train$append_feature_obj(feats_train, subkfeats_train) dump <- feats_test$append_feature_obj(feats_test, subkfeats_test) dump <- kernel$append_kernel(kernel, subkernel) kernel <- CombinedKernel() feats_train <- CombinedFeatures() feats_test <- CombinedFeatures() subkfeats_train <- RealFeatures(fm_train_real) subkfeats_test <- RealFeatures(fm_test_real) subkernel <- PolyKernel(as.integer(10), as.integer(2)) dump <- feats_train$append_feature_obj(feats_train, subkfeats_train) dump <- feats_test$append_feature_obj(feats_test, subkfeats_test) dump <- kernel$append_kernel(kernel, subkernel) dump <- kernel$init(kernel, feats_train, feats_train) C <- 1.2 epsilon <- 1e-5 mkl_eps <- 0.001 mkl_norm <- 1 num_threads <- as.integer(1) labels <- Labels(label_train_multiclass) svm <- MKLMultiClass(C, kernel, labels) dump <- svm$set_epsilon(svm, epsilon) dump <- svm$parallel$set_num_threads(svm$parallel, num_threads) dump <- svm$set_mkl_epsilon(svm,mkl_eps) dump <- svm$train(svm) dump <- kernel$init(kernel, feats_train, feats_test) lab <- svm$classify(svm) out <- lab$get_labels(lab)
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) #CommUlongString print('CommUlongString') order <- as.integer(3) start <- as.integer(order-1) gap <- as.integer(0) reverse <- FALSE charfeat <- StringCharFeatures("DNA") dump <- charfeat$set_features(charfeat, fm_train_dna) feats_train <- StringUlongFeatures(charfeat$get_alphabet()) dump <- feats_train$obtain_from_char(feats_train, charfeat, start, order, gap, reverse) charfeat <- StringCharFeatures("DNA") dump <- charfeat$set_features(charfeat, fm_test_dna) feats_test <- StringUlongFeatures(charfeat$get_alphabet()) dump <- feats_test$obtain_from_char(feats_test, charfeat, start, order, gap, reverse) preproc <- SortUlongString() dump <- preproc$init(preproc, feats_train) dump <- feats_train$add_preproc(feats_train, preproc) dump <- feats_train$apply_preproc(feats_train) dump <- feats_test$add_preproc(feats_test, preproc) dump <- feats_test$apply_preproc(feats_test) use_sign <- FALSE kernel <- CommUlongStringKernel(feats_train, feats_train, use_sign) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_dna <- as.matrix(read.table('../data/fm_train_dna.dat')) fm_test_dna <- as.matrix(read.table('../data/fm_test_dna.dat')) #CommWordString print('CommWordString') order <- as.integer(3) start <- as.integer(order-1) gap <- as.integer(0) reverse <- FALSE charfeat <- StringCharFeatures("DNA") dump <- charfeat$set_features(charfeat, fm_train_dna) feats_train <- StringWordFeatures(charfeat$get_alphabet()) dump <- feats_train$obtain_from_char(feats_train, charfeat, start, order, gap, reverse) preproc <- SortWordString() dump <- preproc$init(preproc, feats_train) dump <- feats_train$add_preproc(feats_train, preproc) dump <- feats_train$apply_preproc(feats_train) charfeat <- StringCharFeatures("DNA") dump <- charfeat$set_features(charfeat, fm_test_dna) feats_test <- StringWordFeatures(charfeat$get_alphabet()) dump <- feats_test$obtain_from_char(feats_test, charfeat, start, order, gap, reverse) dump <- feats_test$add_preproc(feats_test, preproc) dump <- feats_test$apply_preproc(feats_test) use_sign <- FALSE kernel <- CommWordStringKernel(feats_train, feats_train, use_sign) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) #LogPlusOne print('LogPlusOne') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) preproc <- LogPlusOne() dump <- preproc$init(preproc, feats_train) dump <- feats_train$add_preproc(feats_train, preproc) dump <- feats_train$apply_preproc(feats_train) dump <- feats_test$add_preproc(feats_test, preproc) dump <- feats_test$apply_preproc(feats_train) width <- 1.4 size_cache <- as.integer(10) kernel <- Chi2Kernel(feats_train, feats_train, width, size_cache) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) #NormOne print('NormOne') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) preproc <- NormOne() dump <- preproc$init(preproc, feats_train) dump <- feats_train$add_preproc(feats_train, preproc) dump <- feats_train$apply_preproc(feats_train) dump <- feats_test$add_preproc(feats_test, preproc) dump <- feats_test$apply_preproc(feats_test) width <- 1.4 size_cache <- as.integer(10) kernel <- Chi2Kernel(feats_train, feats_train, width, size_cache) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()
library(shogun) fm_train_real <- as.matrix(read.table('../data/fm_train_real.dat')) fm_test_real <- as.matrix(read.table('../data/fm_test_real.dat')) #PruneVarSubMean print('PruneVarSubMean') feats_train <- RealFeatures(fm_train_real) feats_test <- RealFeatures(fm_test_real) preproc <- PruneVarSubMean() dump <- preproc$init(preproc, feats_train) dump <- feats_train$add_preproc(feats_train, preproc) dump <- feats_train$apply_preproc(feats_train) dump <- feats_test$add_preproc(feats_test, preproc) dump <- feats_test$apply_preproc(feats_test) width <- 1.4 size_cache <- as.integer(10) kernel <- Chi2Kernel(feats_train, feats_train, width, size_cache) km_train <- kernel$get_kernel_matrix() dump <- kernel$init(kernel, feats_train, feats_test) km_test <- kernel$get_kernel_matrix()