In [1]:

    

using RDatasets
using DecisionTree


    

    




INFO: Precompiling module DecisionTree.

In [2]:

    

iris = dataset("datasets", "iris")

head(iris)


    

    
Out[2]:




SepalLength
SepalWidth
PetalLength
PetalWidth
Species
1
5.1
3.5
1.4
0.2
setosa
2
4.9
3.0
1.4
0.2
setosa
3
4.7
3.2
1.3
0.2
setosa
4
4.6
3.1
1.5
0.2
setosa
5
5.0
3.6
1.4
0.2
setosa
6
5.4
3.9
1.7
0.4
setosa

In [3]:

    

features = convert(Array, iris[:, 1:4])
labels = convert(Array, iris[:, 5])


    

    
Out[3]:





150-element Array{String,1}:
 "setosa"   
 "setosa"   
 "setosa"   
 "setosa"   
 "setosa"   
 "setosa"   
 "setosa"   
 "setosa"   
 "setosa"   
 "setosa"   
 "setosa"   
 "setosa"   
 "setosa"   
 ⋮          
 "virginica"
 "virginica"
 "virginica"
 "virginica"
 "virginica"
 "virginica"
 "virginica"
 "virginica"
 "virginica"
 "virginica"
 "virginica"
 "virginica"

In [4]:

    

# train full-tree classifier
model = build_tree(labels, features)


    

    
Out[4]:





Decision Tree
Leaves: 9
Depth:  5

In [5]:

    

# prune tree: merge leaves having >= 90% combined purity (default: 100%)
model = prune_tree(model, 0.9)


    

    
Out[5]:





Decision Tree
Leaves: 8
Depth:  5

In [6]:

    

# pretty print of the tree, to a depth of 5 nodes (optional)
print_tree(model, 5)


    

    




Feature 3, Threshold 3.0
L-> setosa : 50/50
R-> Feature 4, Threshold 1.8
    L-> Feature 3, Threshold 5.0
        L-> versicolor : 47/48
        R-> Feature 4, Threshold 1.6
            L-> virginica : 3/3
            R-> Feature 1, Threshold 7.2
                L-> versicolor : 2/2
                R-> virginica : 1/1
    R-> Feature 3, Threshold 4.9
        L-> Feature 1, Threshold 6.0
            L-> versicolor : 1/1
            R-> virginica : 2/2
        R-> virginica : 43/43

In [7]:

    

# apply learned model
apply_tree(model, [5.9,3.0,5.1,1.9])


    

    
Out[7]:





"virginica"

In [8]:

    

# get the probability of each label
apply_tree_proba(model, [5.9,3.0,5.1,1.9], ["setosa", "versicolor", "virginica"])


    

    
Out[8]:





3-element Array{Float64,1}:
 0.0
 0.0
 1.0

In [9]:

    

# run n-fold cross validation for pruned tree,
# using 90% purity threshold pruning, and 3 CV folds
accuracy = nfoldCV_tree(labels, features, 0.9, 3)


    

    




Fold 1
Classes:  





    






3×3 Array{Int64,2}:
 19   0   0
  0  15   0
  0   3  13






    




Any["setosa","versicolor","virginica"]
Matrix:   





    






3×3 Array{Int64,2}:
 18   0   0
  1  11   0
  0   2  18






    






3×3 Array{Int64,2}:
 13   0   0
  0  21   2
  0   1  13






    




Accuracy: 0.94
Kappa:    0.9096929560505719

Fold 2
Classes:  Any["setosa","versicolor","virginica"]
Matrix:   
Accuracy: 0.94
Kappa:    0.9086479902557856

Fold 3
Classes:  Any["setosa","versicolor","virginica"]
Matrix:   
Accuracy: 0.94
Kappa:    0.9071207430340557

Mean Accuracy: 0.94






    
Out[9]:





3-element Array{Float64,1}:
 0.94
 0.94
 0.94

In [10]:

    

# train random forest classifier
# using 2 random features, 10 trees, and 0.5 portion of samples per tree (optional)
model = build_forest(labels, features, 2, 10, 0.5)


    

    
Out[10]:





Ensemble of Decision Trees
Trees:      10
Avg Leaves: 6.2
Avg Depth:  4.5

In [11]:

    

# apply learned model
apply_forest(model, [5.9,3.0,5.1,1.9])


    

    
Out[11]:





"virginica"

In [12]:

    

# get the probability of each label
apply_forest_proba(model, [5.9,3.0,5.1,1.9], ["setosa", "versicolor", "virginica"])


    

    
Out[12]:





3-element Array{Float64,1}:
 0.0
 0.0
 1.0

In [13]:

    

# run n-fold cross validation for forests
# using 2 random features, 10 trees, 3 folds and 0.5 of samples per tree (optional)
accuracy = nfoldCV_forest(labels, features, 2, 10, 3, 0.5)


    

    




Fold 1





    






3×3 Array{Int64,2}:
 24   0   0
  0  13   0
  0   0  13






    






3×3 Array{Int64,2}:
 13   0   0
  1  17   2
  0   0  17






    






3×3 Array{Int64,2}:
 13   0   0
  0  16   1
  0   2  18






    




Classes:  Any["setosa","versicolor","virginica"]
Matrix:   
Accuracy: 1.0
Kappa:    1.0

Fold 2
Classes:  Any["setosa","versicolor","virginica"]
Matrix:   
Accuracy: 0.94
Kappa:    0.9093655589123866

Fold 3
Classes:  Any["setosa","versicolor","virginica"]
Matrix:   
Accuracy: 0.94
Kappa:    0.9088145896656534

Mean Accuracy: 0.96






    
Out[13]:





3-element Array{Float64,1}:
 1.0 
 0.94
 0.94