#introduction

#load the inbuilt dataset
data("iris")

#display the first few rows
head(iris) 
##   Sepal.Length Sepal.Width Petal.Length Petal.Width 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

What are the structure and summary of the dataset?

# Question 1 
str(iris)
## '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 ...
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  
##                 
##                 
##

How many observations and variables are in the dataset?

# Question 2
dim(iris)
## [1] 150   5
nrow(iris)
## [1] 150
ncol(iris)
## [1] 5

How many observations and variables are in the dataset?

# Question 3
unique(iris$Species)
## [1] setosa     versicolor virginica 
## Levels: setosa versicolor virginica
table(iris$Species)
## 
##     setosa versicolor  virginica 
##         50         50         50

How many observations and variables are in the dataset?

# Question 4
sapply(iris[, 1:4], function(x) c(mean=mean(x), median=median(x), sd=sd(x)))
##        Sepal.Length Sepal.Width Petal.Length Petal.Width
## mean      5.8433333   3.0573333     3.758000   1.1993333
## median    5.8000000   3.0000000     4.350000   1.3000000
## sd        0.8280661   0.4358663     1.765298   0.7622377

What is the correlation between numeric features?

# Question 5
cor(iris[, 1:4])
##              Sepal.Length Sepal.Width Petal.Length Petal.Width
## Sepal.Length    1.0000000  -0.1175698    0.8717538   0.8179411
## Sepal.Width    -0.1175698   1.0000000   -0.4284401  -0.3661259
## Petal.Length    0.8717538  -0.4284401    1.0000000   0.9628654
## Petal.Width     0.8179411  -0.3661259    0.9628654   1.0000000

Visualize pairwise relationships using a scatterplot matrix

# Question 6
pairs(iris[, 1:4], col=iris$Species, main="Pairwise Scatterplot of Iris Features")

Compare distributions of Sepal.Length across species

# Question 7
boxplot(Sepal.Length ~ Species, data=iris,
        main="Sepal Length by Species",
        col=c("lightblue", "lightgreen", "lightpink"))

Check if there are any missing values

# Question 8
sum(is.na(iris))
## [1] 0

Compute summary statistics by species

# Question 9
aggregate(. ~ Species, data=iris, FUN=mean)
##      Species Sepal.Length Sepal.Width Petal.Length Petal.Width
## 1     setosa        5.006       3.428        1.462       0.246
## 2 versicolor        5.936       2.770        4.260       1.326
## 3  virginica        6.588       2.974        5.552       2.026
aggregate(. ~ Species, data=iris, FUN=sd)
##      Species Sepal.Length Sepal.Width Petal.Length Petal.Width
## 1     setosa    0.3524897   0.3790644    0.1736640   0.1053856
## 2 versicolor    0.5161711   0.3137983    0.4699110   0.1977527
## 3  virginica    0.6358796   0.3224966    0.5518947   0.2746501

Plot the relationship between Petal.Length and Petal.Width

# Question 10
plot(iris$Petal.Length, iris$Petal.Width,
     col=iris$Species, pch=19,
     xlab="Petal Length", ylab="Petal Width",
     main="Petal Length vs Petal Width by Species")
legend("topleft", legend=levels(iris$Species),
       col=1:3, pch=19)