mydatairis

Statistical analysis on IRIS data set

mydata=iris
summary(mydata)

##   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  
##                 
##                 
## 

str(mydata)

## 'data.frame':    150 obs. of  5 variables:
##  $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
##  $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
##  $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
##  $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
##  $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...

lapply(mydata[1:4],mean)

## $Sepal.Length
## [1] 5.843333
## 
## $Sepal.Width
## [1] 3.057333
## 
## $Petal.Length
## [1] 3.758
## 
## $Petal.Width
## [1] 1.199333

lapply(mydata[1:4],median)

## $Sepal.Length
## [1] 5.8
## 
## $Sepal.Width
## [1] 3
## 
## $Petal.Length
## [1] 4.35
## 
## $Petal.Width
## [1] 1.3

lapply(mydata[1:4],var)

## $Sepal.Length
## [1] 0.6856935
## 
## $Sepal.Width
## [1] 0.1899794
## 
## $Petal.Length
## [1] 3.116278
## 
## $Petal.Width
## [1] 0.5810063

lapply(mydata[1:4],sd)

## $Sepal.Length
## [1] 0.8280661
## 
## $Sepal.Width
## [1] 0.4358663
## 
## $Petal.Length
## [1] 1.765298
## 
## $Petal.Width
## [1] 0.7622377

mydata$size <- ifelse(mydata$Sepal.Length < median(mydata$Sepal.Length),
"small", "big")
table(mydata$Species, mydata$size)

##             
##              big small
##   setosa       1    49
##   versicolor  29    21
##   virginica   47     3

Plots

You can also embed plots, for iris dataset:

boxplot(mydata$Sepal.Length,mydata$Sepal.Width,mydata$Petal.Length,mydata$Petal.Width,
        col = c('blue','green','yellow','red'))

barplot(mydata$Sepal.Length,mydata$Sepal.Width,mydata$Petal.Length,mydata$Petal.Width, 
        col = c('blue','green','red','yellow'),(args.legend = colnames(mydata)))

plot(mydata)