Iris Flowers Dataset
June Claiborne
2022-08-15
Read iris dataset
iris <- read.csv("D:/AI4OPT/iris.csv")
head(iris)## sepallength sepalwidth petallength petalwidth class
## 1 5.1 3.5 1.4 0.2 Iris-setosa
## 2 4.9 3.0 1.4 0.2 Iris-setosa
## 3 4.7 3.2 1.3 0.2 Iris-setosa
## 4 4.6 3.1 1.5 0.2 Iris-setosa
## 5 5.0 3.6 1.4 0.2 Iris-setosa
## 6 5.4 3.9 1.7 0.4 Iris-setosatail(iris)## sepallength sepalwidth petallength petalwidth class
## 145 6.7 3.3 5.7 2.5 Iris-virginica
## 146 6.7 3.0 5.2 2.3 Iris-virginica
## 147 6.3 2.5 5.0 1.9 Iris-virginica
## 148 6.5 3.0 5.2 2.0 Iris-virginica
## 149 6.2 3.4 5.4 2.3 Iris-virginica
## 150 5.9 3.0 5.1 1.8 Iris-virginicasummary(iris)## sepallength sepalwidth petallength petalwidth
## 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 :3.054 Mean :3.759 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
## class
## Length:150
## Class :character
## Mode :character
##
##
## dim(iris)## [1] 150 5A random sampling of the data might be helpful, since there are three different types of species. Also, checking the types of attributes in iris dataset for further analysis
iris[sample(nrow(iris),10),]## sepallength sepalwidth petallength petalwidth class
## 49 5.3 3.7 1.5 0.2 Iris-setosa
## 145 6.7 3.3 5.7 2.5 Iris-virginica
## 116 6.4 3.2 5.3 2.3 Iris-virginica
## 39 4.4 3.0 1.3 0.2 Iris-setosa
## 35 4.9 3.1 1.5 0.1 Iris-setosa
## 113 6.8 3.0 5.5 2.1 Iris-virginica
## 8 5.0 3.4 1.5 0.2 Iris-setosa
## 130 7.2 3.0 5.8 1.6 Iris-virginica
## 126 7.2 3.2 6.0 1.8 Iris-virginica
## 128 6.1 3.0 4.9 1.8 Iris-virginicadata("iris")
sapply(iris,class)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## "numeric" "numeric" "numeric" "numeric" "factor"Instances that belong to each class label
library(mlbench)
data("iris")
y <- iris$class
cbind(freq=table(y), percentage=prop.table(table(y))*100)## freq percentagesummary(iris)## Sepal.Length Sepal.Width Petal.Length Petal.Width
## Min. :4.300 Min. :2.000 Min. :1.000 Min. :0.100
## 1st Qu.:5.100 1st Qu.:2.800 1st Qu.:1.600 1st Qu.:0.300
## Median :5.800 Median :3.000 Median :4.350 Median :1.300
## Mean :5.843 Mean :3.057 Mean :3.758 Mean :1.199
## 3rd Qu.:6.400 3rd Qu.:3.300 3rd Qu.:5.100 3rd Qu.:1.800
## Max. :7.900 Max. :4.400 Max. :6.900 Max. :2.500
## Species
## setosa :50
## versicolor:50
## virginica :50
##
##
## summary(y)## Length Class Mode
## 0 NULL NULLStudy the individual attributes for more information using histograms
data("iris")
par(mfrow=c(1,4))
for(i in 1:4){
hist(iris[,i], main=names(iris)[i])
}
#### Try density plot for another look at each variable distribution
data(iris)
par (mfrow=c(1,4))
for(i in 1:4){
plot(density(iris[,i]), main=names(iris)[i])
}
#### Since the dataset characteristics are multivariate, a correlation
plot of the attributes may give better relation
data(iris)
correlations <- cor(iris[,1:4])
corrplot(correlations,method="circle")
#### Show a scatter plot matrix
data(iris)
pairs(iris)
#### Check scatter plot matrix by Class
data(iris)
pairs(Species~., data=iris, col=iris$Species)
library(ggplot2)
ggplot(iris) +
aes(x = Petal.Length, y = Petal.Width) +
geom_point(aes(color = Species, shape = Species))
#### See if more information by using box-plot graph
ggplot(iris) + aes(x = Species, y = Sepal.Length, color = Species) +
geom_boxplot() +
geom_jitter(position = position_jitter(0.2))
#### Check Density Plot Length by Species
ggplot(iris) + aes(x = Petal.Length, fill = Species) +
geom_density(alpha = 0.3)
#### Check for similar density plots in subgroups using facets
ggplot(iris) + aes(x = Petal.Length, fill = Species) +
geom_density(alpha = 0.3) +
facet_wrap(~Species, nrow = 3)
#### Convert to a matrix for Clustering
mat1 <- as.matrix(iris[, 1:4])
disMa <- dist(mat1)
plot(hclust(disMa))
#### More detailed clustering The rows and columns are reorganized based
on hierarchical clustering, and the values in the matrix are coded by
colors. You can directly visualize millions of numbers in one plot. The
hierarchical trees also show the similarity among rows and columns.
heatmap(mat1,
scale = "column",
RowSideColors = rainbow(3)[iris$Species]
)
#### Using pheatmap to improve plot and provide scaling and
standardization
library(pheatmap)## Warning: package 'pheatmap' was built under R version 4.2.1#### Convert to a matrix
mat1 <- as.matrix(iris[, 1:4])
#### assign row names in the matrix
row.names(mat1) <- row.names(iris)
pheatmap(mat1,
scale = "column",
#### average linkage
clustering_method = "average",
# the 5th column as color bar
annotation_row = iris[, 5, drop = FALSE],
show_rownames = FALSE
)
#### Principal Component Analysis Transform
pcatrans <- prcomp(iris[, 1:4], scale = TRUE)
print(pcatrans)## Standard deviations (1, .., p=4):
## [1] 1.7083611 0.9560494 0.3830886 0.1439265
##
## Rotation (n x k) = (4 x 4):
## PC1 PC2 PC3 PC4
## Sepal.Length 0.5210659 -0.37741762 0.7195664 0.2612863
## Sepal.Width -0.2693474 -0.92329566 -0.2443818 -0.1235096
## Petal.Length 0.5804131 -0.02449161 -0.1421264 -0.8014492
## Petal.Width 0.5648565 -0.06694199 -0.6342727 0.5235971plot the variance of each principal component
plot(pcatrans)
#### showing the structure of the objects
str(pcatrans)## List of 5
## $ sdev : num [1:4] 1.708 0.956 0.383 0.144
## $ rotation: num [1:4, 1:4] 0.521 -0.269 0.58 0.565 -0.377 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
## .. ..$ : chr [1:4] "PC1" "PC2" "PC3" "PC4"
## $ center : Named num [1:4] 5.84 3.06 3.76 1.2
## ..- attr(*, "names")= chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
## $ scale : Named num [1:4] 0.828 0.436 1.765 0.762
## ..- attr(*, "names")= chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
## $ x : num [1:150, 1:4] -2.26 -2.07 -2.36 -2.29 -2.38 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : NULL
## .. ..$ : chr [1:4] "PC1" "PC2" "PC3" "PC4"
## - attr(*, "class")= chr "prcomp"New coordinate values for each of the 150 samples
head(pcatrans$x)## PC1 PC2 PC3 PC4
## [1,] -2.257141 -0.4784238 0.12727962 0.024087508
## [2,] -2.074013 0.6718827 0.23382552 0.102662845
## [3,] -2.356335 0.3407664 -0.04405390 0.028282305
## [4,] -2.291707 0.5953999 -0.09098530 -0.065735340
## [5,] -2.381863 -0.6446757 -0.01568565 -0.035802870
## [6,] -2.068701 -1.4842053 -0.02687825 0.006586116Change column names to ready the prediction
#### # First two columns extracted and convert to dataframe
pcaData <- as.data.frame(pcatrans$x[, 1:2])
#### bind the columns
pcaData <- cbind(pcaData, iris$Species)
colnames(pcaData) <- c("PC1", "PC2", "Species")
library(ggplot2)
#### define plot area and add data points
ggplot(pcaData) +
aes(PC1, PC2, color = Species, shape = Species) +
geom_point(size = 2) 
#### add plot details #### compute % variables
percentVar <- round(100 * summary(pcatrans)$importance[2, 1:2], 0)
#### add data points, labels, title, and width and height ratio
ggplot(pcaData, aes(PC1, PC2, color = Species, shape = Species)) +
geom_point(size = 2) +
xlab(paste0("PC1: ", percentVar[1], "% variance")) + ylab(paste0("PC2: ", percentVar[2], "% variance")) +
ggtitle("Principal component analysis (PCA)") +
theme(aspect.ratio = 1) 