## ----setup, include = FALSE--------------------------------------------------- knitr::opts_chunk$set(collapse = TRUE, comment = "#>", fig.width = 7, fig.height = 4.2, dpi = 110) library(glmfsa) set.seed(1) ## ----first-------------------------------------------------------------------- n <- 300; p <- 1000 x <- matrix(rnorm(n * p), n, p) beta <- numeric(p); beta[c(10, 50, 100, 200, 300)] <- 1.5 y <- as.numeric(x %*% beta + rnorm(n)) fit <- fsa(x, y, family = "gaussian", k = 5) fit which(coef(fit)[-1] != 0) ## ----coefs-------------------------------------------------------------------- round(coef(fit)[c(1, 1 + c(10, 50, 100, 200, 300)), ], 3) ## ----trace, fig.height = 4.5-------------------------------------------------- tr <- fsa(x, y, k = 5, niter = 200, keep_trace = TRUE) plot_trace(tr, highlight = c(10, 50, 100, 200, 300)) ## ----path--------------------------------------------------------------------- path <- fsa(x, y, k = c(50, 30, 20, 12, 8, 5, 3, 2, 1)) path plot(path, label = TRUE) ## ----cv, fig.height = 4.2----------------------------------------------------- cvfit <- cv.fsa(x, y, k = c(30, 20, 12, 8, 5, 3, 2, 1), nfolds = 5) cvfit plot(cvfit) ## ----cvpred------------------------------------------------------------------- head(predict(cvfit, newx = x, k = "k.1se")) ## ----sched, fig.height = 4.2-------------------------------------------------- plot_schedule(M = 1000, k = 10, niter = 500, mu = c(0, 1, 10, 100, 300, 1000)) ## ----eta---------------------------------------------------------------------- xc <- matrix(rnorm(n * 300), n, 300) + rnorm(n) # every column shares a factor bc <- numeric(300); bc[c(10, 60, 150, 220, 280)] <- 1 yc <- as.numeric(xc %*% bc + rnorm(n) * 0.5) fc <- fsa(xc, yc, k = 5, eta = 1) # asked for 1 ... fc$eta_final # ... capped to what is actually safe sort(fc$selected[[1]]) ## ----losses, fig.height = 4--------------------------------------------------- u <- seq(-20, 3, length.out = 400) L <- sapply(c("logistic", "lorenz", "svm", "hinge"), function(l) fsa_losses(u, l)) matplot(u, L, type = "l", lty = c(1, 1, 2, 1), lwd = 2, col = hcl.colors(4, "Dark 3"), xlab = "margin", ylab = "loss") legend("topright", colnames(L), lty = c(1, 1, 2, 1), lwd = 2, bty = "n", col = hcl.colors(4, "Dark 3")) ## ----noisy-------------------------------------------------------------------- yb <- as.integer(x %*% beta > 0) flip <- sample(n, 0.15 * n); yb[flip] <- 1 - yb[flip] # 15% wrong labels sapply(c("logistic", "lorenz"), function(l) { s <- fsa(x, factor(yb), family = "binomial", loss = l, k = 5)$selected[[1]] length(intersect(s, c(10, 50, 100, 200, 300))) }) ## ----ridge-------------------------------------------------------------------- data(dexter) # 300 observations, 20,000 features set.seed(11) cv <- cv.fsa(dexter$x, dexter$y, family = "binomial", loss = "lorenz", k = c(20, 10, 5), s = c(0, 1e-2, 1), nfolds = 5, type.measure = "class") c(k = cv$k.min, s = cv$s.min) ## ----sparse------------------------------------------------------------------- xs <- Matrix::rsparsematrix(500, 2000, density = 0.01) bs <- numeric(2000); bs[c(7, 300, 1500)] <- 4 ys <- as.numeric(xs %*% bs + rnorm(500) * 0.2) sort(fsa(xs, ys, k = 3)$selected[[1]])