Lab2

Графический анализ данных

library(caret)

## Загрузка требуемого пакета: ggplot2

## Загрузка требуемого пакета: lattice

x <- matrix(rnorm(50*5), ncol=5)
y <- factor(rep(c("A", "B"), 25))
data <- data.frame(x, y)
featurePlot(x = data[,1:5], y = data$y, plot = "pairs")

Важность признаков

library(FSelector)
data(iris)
weights <- information.gain(Species ~ ., iris)
print(weights)

##              attr_importance
## Sepal.Length       0.4521286
## Sepal.Width        0.2672750
## Petal.Length       0.9402853
## Petal.Width        0.9554360

Преобразование переменных

library(arules)

## Загрузка требуемого пакета: Matrix

## 
## Присоединяю пакет: 'arules'

## Следующие объекты скрыты от 'package:base':
## 
##     abbreviate, write

data(iris)
iris$Sepal.Length.interval <- discretize(iris$Sepal.Length, method = "interval", categories = 3)

## Warning in discretize(iris$Sepal.Length, method = "interval", categories = 3):
## Parameter categories is deprecated. Use breaks instead! Also, the default
## method is now frequency!

iris$Sepal.Length.frequency <- discretize(iris$Sepal.Length, method = "frequency", categories = 3)

## Warning in discretize(iris$Sepal.Length, method = "frequency", categories = 3):
## Parameter categories is deprecated. Use breaks instead! Also, the default
## method is now frequency!

iris$Sepal.Length.cluster <- discretize(iris$Sepal.Length, method = "cluster", categories = 3)

## Warning in discretize(iris$Sepal.Length, method = "cluster", categories = 3):
## Parameter categories is deprecated. Use breaks instead! Also, the default
## method is now frequency!

iris$Sepal.Length.fixed <- discretize(iris$Sepal.Length, method = "fixed", categories = c(4.3, 5.8, 7.9))

## Warning in discretize(iris$Sepal.Length, method = "fixed", categories = c(4.3,
## : Parameter categories is deprecated. Use breaks instead! Also, the default
## method is now frequency!

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   Sepal.Length.interval Sepal.Length.frequency
##  setosa    :50   [4.3,5.5):52          [4.3,5.4):46          
##  versicolor:50   [5.5,6.7):70          [5.4,6.3):53          
##  virginica :50   [6.7,7.9]:28          [6.3,7.9]:51          
##                                                              
##                                                              
##                                                              
##   Sepal.Length.cluster Sepal.Length.fixed
##  [4.3,5.33) :46        [4.3,5.8):73      
##  [5.33,6.27):53        [5.8,7.9]:77      
##  [6.27,7.9] :51                          
##                                          
##                                          
## 

Выбор признаков

library(Boruta)
data(mtcars)

Применение Boruta для выбора признаков

set.seed(123)
boruta_output <- Boruta(mpg ~ ., data = mtcars, doTrace = 2)

##  1. run of importance source...

##  2. run of importance source...

##  3. run of importance source...

##  4. run of importance source...

##  5. run of importance source...

##  6. run of importance source...

##  7. run of importance source...

##  8. run of importance source...

##  9. run of importance source...

##  10. run of importance source...

## After 10 iterations, +0.1 secs:

##  confirmed 10 attributes: am, carb, cyl, disp, drat and 5 more;

##  no more attributes left.

plot(boruta_output)

print(boruta_output)

## Boruta performed 10 iterations in 0.101815 secs.
##  10 attributes confirmed important: am, carb, cyl, disp, drat and 5
## more;
##  No attributes deemed unimportant.