机器学习与R之支持向量机svm（上）

支持向量机svm e1071包的svm()函数提供R和LIBSVM的接口
library(kernlab)
letter_classifier <- ksvm(letter ~ ., data = letters_train,
                          kernel = "vanilladot",C = 1)
kernel非线性映射函数(rbfdot径向基polydot多项式tanhdot双曲正切vanilladot线性函数等等)
C用于违法约束条件的惩罚-软边界大小-C越大边界越窄
tol终止准则  
ksvm(x, y = NULL, scaled = TRUE, type = NULL,
     kernel ="rbfdot", kpar = "automatic",
     C = 1, nu = 0.2, epsilon = 0.1, prob.model = FALSE,
     class.weights = NULL, cross = 0, fit = TRUE, cache = 40,
     tol = 0.001, shrinking = TRUE, ..., 
     subset, na.action = na.omit)
type取response分类或者probabilities概率

predict(letter_classifier, letters_test,type="response")

letters <- read.csv("letterdata.csv")
str(letters)

# divide into training and test data
letters_train <- letters[1:16000, ]
letters_test  <- letters[16001:20000, ]

## Step 3: Training a model on the data ----
# begin by training a simple linear SVM
library(kernlab)
letter_classifier <- ksvm(letter ~ ., data = letters_train,
                          kernel = "vanilladot")

# look at basic information about the model
letter_classifier

## Step 4: Evaluating model performance ----
# predictions on testing dataset
letter_predictions <- predict(letter_classifier, letters_test)

head(letter_predictions)

table(letter_predictions, letters_test$letter)

# look only at agreement vs. non-agreement
# construct a vector of TRUE/FALSE indicating correct/incorrect predictions
agreement <- letter_predictions == letters_test$letter
table(agreement)
prop.table(table(agreement))

## Step 5: Improving model performance ----
set.seed(12345)
letter_classifier_rbf <- ksvm(letter ~ ., data = letters_train, kernel = "rbfdot")
letter_predictions_rbf <- predict(letter_classifier_rbf, letters_test)

agreement_rbf <- letter_predictions_rbf == letters_test$letter
table(agreement_rbf)
prop.table(table(agreement_rbf))