library("e1071")
## Warning: package 'e1071' was built under R version 3.3.1
data(iris)
attach(iris)
## classification mode
# default with factor response:
model <- svm(Species ~ ., data = iris)
# alternatively the traditional interface:
x <- subset(iris, select = -Species)
y <- Species
model <- svm(x, y)
print(model)
##
## Call:
## svm.default(x = x, y = y)
##
##
## Parameters:
## SVM-Type: C-classification
## SVM-Kernel: radial
## cost: 1
## gamma: 0.25
##
## Number of Support Vectors: 51
summary(model)
##
## Call:
## svm.default(x = x, y = y)
##
##
## Parameters:
## SVM-Type: C-classification
## SVM-Kernel: radial
## cost: 1
## gamma: 0.25
##
## Number of Support Vectors: 51
##
## ( 8 22 21 )
##
##
## Number of Classes: 3
##
## Levels:
## setosa versicolor virginica
# test with train data
pred <- predict(model, x)
# (same as:)
pred <- fitted(model)
# Check accuracy:
table(pred, y)
## y
## pred setosa versicolor virginica
## setosa 50 0 0
## versicolor 0 48 2
## virginica 0 2 48
# compute decision values and probabilities:
pred <- predict(model, x, decision.values = TRUE)
attr(pred, "decision.values")[1:4,]
## setosa/versicolor setosa/virginica versicolor/virginica
## 1 1.196152 1.091757 0.6708810
## 2 1.064621 1.056185 0.8483518
## 3 1.180842 1.074542 0.6439798
## 4 1.110699 1.053012 0.6782041
# visualize (classes by color, SV by crosses):
plot(cmdscale(dist(iris[,-5])),col = as.integer(iris[,5]),pch = c("o","+")[1:150 %in% model$index + 1])
## try regression mode on two dimensions
# create data
x <- seq(0.1, 5, by = 0.05)
y <- log(x) + rnorm(x, sd = 0.2)
# estimate model and predict input values
m <- svm(x, y)
new <- predict(m, x)
# visualize
plot(x, y)
points(x, log(x), col = 2)
points(x, new, col = 4)
## density-estimation
# create 2-dim. normal with rho=0:
X <- data.frame(a = rnorm(1000), b = rnorm(1000))
attach(X)
# traditional way:
m <- svm(X, gamma = 0.1)
# formula interface:
m <- svm(~., data = X, gamma = 0.1)
# or:
m <- svm(~ a + b, gamma = 0.1)
# test:
newdata <- data.frame(a = c(0, 4), b = c(0, 4))
predict (m, newdata)
## 1 2
## TRUE FALSE
# visualize:
plot(X, col = 1:1000 %in% m$index + 1, xlim = c(-5,5), ylim=c(-5,5))
points(newdata, pch = "+", col = 2, cex = 5)
# weights: (example not particularly sensible)
i2 <- iris
levels(i2$Species)[3] <- "versicolor"
summary(i2$Species)
## setosa versicolor
## 50 100
wts <- 100 / table(i2$Species)
wts
##
## setosa versicolor
## 2 1
m <- svm(Species ~ ., data = i2, class.weights = wts)