支持向量机和决策树建模

Tree as rules: 

 Rule number: 2 [Species=setosa cover=38 (36%) prob=1.00]
   Petal.Length< 2.35

 Rule number: 7 [Species=virginica cover=30 (29%) prob=0.00]
   Petal.Length>=2.35
   Petal.Width>=1.65

 Rule number: 6 [Species=versicolor cover=37 (35%) prob=0.00]
   Petal.Length>=2.35
   Petal.Width< 1.65

[1] 2 1 5 4 3

#Rattle timestamp: 2021-03-24 21:18:48 yangmenglei

# Rattle timestamp: 2021-03-24 21:18:47 x86_64-w64-mingw32 

# Decision Tree 

# The 'rpart' package provides the 'rpart' function.

library(rpart, quietly=TRUE)

# Reset the random number seed to obtain the same results each time.

set.seed(crv$seed)

# Build the Decision Tree model.

crs$rpart <- rpart(Species ~ .,
    data=crs$dataset[crs$train, c(crs$input, crs$target)],
    method="class",
    parms=list(split="information"),
    control=rpart.control(usesurrogate=0, 
        maxsurrogate=0),
    model=TRUE)

# Generate a textual view of the Decision Tree model.

print(crs$rpart)
printcp(crs$rpart)
cat("\n")

# Time taken: 0.00 secs

# List the rules from the tree using a Rattle support function.

asRules(crs$rpart)

#=======================================================================

#支持向量机
# Rattle timestamp: 2021-03-24 21:19:17 x86_64-w64-mingw32 

# Plot the resulting Decision Tree. 

# We use the rpart.plot package.

fancyRpartPlot(crs$rpart, main="Decision Tree iris2.csv $ Species")

Summary of the SVM model (built using ksvm):

Support Vector Machine object of class "ksvm" 

SV type: C-svc  (classification) 
 parameter : cost C = 1 

Gaussian Radial Basis kernel function. 
 Hyperparameter : sigma =  0.52087038345841 

Number of Support Vectors : 49 

Objective Function Value : -3.5805 -3.6993 -18.2016 
Training error : 0.019048 
Probability model included. 

Time taken: 0.83 secs

Rattle timestamp: 2021-03-24 21:25:15 yangmenglei