#############CORRESPONDENCE ANALYSIS


> library(ggplot2, pos=16)

> library(factoextra, pos=16)

> library(FactoMineR, pos=18)

> data(housetasks, package="factoextra")

> library(MASS, pos=19)

> attach (housetasks)


> house1 <- CA(housetasks)

> fviz_eig(house1)

> get_eigenvalue (house1)
      eigenvalue variance.percent cumulative.variance.percent
Dim.1  0.5428893         48.69222                    48.69222
Dim.2  0.4450028         39.91269                    88.60491
Dim.3  0.1270484         11.39509                   100.00000

> #############TREE -BASED MODELLING

> library(tree, pos=21)

> library(randomForest, pos=22)



> summary (iris)
  Sepal.Length    Sepal.Width     Petal.Length    Petal.Width   
 Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100  
 1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300  
 Median :5.800   Median :3.000   Median :4.350   Median :1.300  
 Mean   :5.843   Mean   :3.057   Mean   :3.758   Mean   :1.199  
 3rd Qu.:6.400   3rd Qu.:3.300   3rd Qu.:5.100   3rd Qu.:1.800  
 Max.   :7.900   Max.   :4.400   Max.   :6.900   Max.   :2.500  
       Species  
 setosa    :50  
 versicolor:50  
 virginica :50  
                
                
                

> mytree <- tree (Species ~ Sepal.Length + Sepal.Width + Petal.Length + Petal.Width, data = iris)

> plot (mytree)

> text (mytree)

> summary (mytree)

Classification tree:
tree(formula = Species ~ Sepal.Length + Sepal.Width + Petal.Length + 
    Petal.Width, data = iris)
Variables actually used in tree construction:
[1] "Petal.Length" "Petal.Width"  "Sepal.Length"
Number of terminal nodes:  6 
Residual mean deviance:  0.1253 = 18.05 / 144 
Misclassification error rate: 0.02667 = 4 / 150 

> mytree
node), split, n, deviance, yval, (yprob)
      * denotes terminal node

 1) root 150 329.600 setosa ( 0.33333 0.33333 0.33333 )  
   2) Petal.Length < 2.45 50   0.000 setosa ( 1.00000 0.00000 0.00000 ) *
   3) Petal.Length > 2.45 100 138.600 versicolor ( 0.00000 0.50000 0.50000 )  
     6) Petal.Width < 1.75 54  33.320 versicolor ( 0.00000 0.90741 0.09259 )  
      12) Petal.Length < 4.95 48   9.721 versicolor ( 0.00000 0.97917 0.02083 )  
        24) Sepal.Length < 5.15 5   5.004 versicolor ( 0.00000 0.80000 0.20000 ) *
        25) Sepal.Length > 5.15 43   0.000 versicolor ( 0.00000 1.00000 0.00000 ) *
      13) Petal.Length > 4.95 6   7.638 virginica ( 0.00000 0.33333 0.66667 ) *
     7) Petal.Width > 1.75 46   9.635 virginica ( 0.00000 0.02174 0.97826 )  
      14) Petal.Length < 4.95 6   5.407 virginica ( 0.00000 0.16667 0.83333 ) *
      15) Petal.Length > 4.95 40   0.000 virginica ( 0.00000 0.00000 1.00000 ) *


> ##########RANDOM FOREST

> iris.forest <- randomForest(Species ~ Sepal.Length + Sepal.Width + Petal.Length + Petal.Width, data=iris, importance=TRUE, proximity=TRUE)

> print(iris.forest)

Call:
 randomForest(formula = Species ~ Sepal.Length + Sepal.Width +      Petal.Length + Petal.Width, data = iris, importance = TRUE,      proximity = TRUE) 
               Type of random forest: classification
                     Number of trees: 500
No. of variables tried at each split: 2

        OOB estimate of  error rate: 4.67%
Confusion matrix:
           setosa versicolor virginica class.error
setosa         50          0         0        0.00
versicolor      0         47         3        0.06
virginica       0          4        46        0.08

> importance(iris.forest)
                setosa versicolor virginica MeanDecreaseAccuracy MeanDecreaseGini
Sepal.Length  6.608420   8.721397  9.346867            12.092858        10.393502
Sepal.Width   5.059958   1.347413  5.463243             6.113979         2.324208
Petal.Length 22.151979  34.858941 27.287901            34.162053        42.093222
Petal.Width  22.205381  32.496050 30.104606            32.602838        44.494161



> plot(iris.forest)

#######################SCRIPT


#############CORRESPONDENCE ANALYSIS

library(ggplot2, pos=16)
library(factoextra, pos=16)
library(FactoMineR, pos=18)
data(housetasks, package="factoextra")

attach (housetasks)

house1 <- CA(housetasks)
fviz_eig(house1)
get_eigenvalue (house1)


#############TREE -BASED MODELLING

library(tree, pos=21)

library(randomForest, pos=22)
summary (iris)
mytree <- tree (Species ~ Sepal.Length + Sepal.Width + Petal.Length + Petal.Width, data = iris)
plot (mytree)
text (mytree)
summary (mytree)
mytree

##########RANDOM FOREST

iris.forest <- randomForest(Species ~ Sepal.Length + Sepal.Width + Petal.Length + Petal.Width, data=iris, importance=TRUE, proximity=TRUE)
print(iris.forest)
importance(iris.forest)
plot(iris.forest)