CW04032025

R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

# Load dataset
data(iris)

# Preview data
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

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  
##                 
##                 
##

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 ...

# Class distribution
table(iris$Species)

## 
##     setosa versicolor  virginica 
##         50         50         50

round(prop.table(table(iris$Species)) * 100, 1)

## 
##     setosa versicolor  virginica 
##       33.3       33.3       33.3

# Randomly split the data
set.seed(123)
ind <- sample(2, nrow(iris), replace = TRUE, prob = c(0.7, 0.3))
trainData <- iris[ind == 1, ]
testData  <- iris[ind == 2, ]

# Explain what sample() does
# sample() randomly assigns each row to training or testing based on the given probabilities

# Remove the target label (Species) from predictors
trainData1 <- trainData[, -5]
testData1  <- testData[, -5]

# Store target labels
trainLabels <- trainData$Species
testLabels  <- testData$Species

# Load KNN package
library(class)

## Warning: package 'class' was built under R version 4.4.3

# Train model using k = 3
iris_pred <- knn(train = trainData1, test = testData1, cl = trainLabels, k = 3)

# Install and load gmodels if needed
if (!require("gmodels")) install.packages("gmodels", repos = "http://cran.rstudio.com/")

## Loading required package: gmodels

## Warning: package 'gmodels' was built under R version 4.4.3

library(gmodels)

# Generate CrossTable
CrossTable(x = testLabels, y = iris_pred, prop.chisq = FALSE)

## 
##  
##    Cell Contents
## |-------------------------|
## |                       N |
## |           N / Row Total |
## |           N / Col Total |
## |         N / Table Total |
## |-------------------------|
## 
##  
## Total Observations in Table:  44 
## 
##  
##              | iris_pred 
##   testLabels |     setosa | versicolor |  virginica |  Row Total | 
## -------------|------------|------------|------------|------------|
##       setosa |         15 |          0 |          0 |         15 | 
##              |      1.000 |      0.000 |      0.000 |      0.341 | 
##              |      1.000 |      0.000 |      0.000 |            | 
##              |      0.341 |      0.000 |      0.000 |            | 
## -------------|------------|------------|------------|------------|
##   versicolor |          0 |         12 |          2 |         14 | 
##              |      0.000 |      0.857 |      0.143 |      0.318 | 
##              |      0.000 |      0.923 |      0.125 |            | 
##              |      0.000 |      0.273 |      0.045 |            | 
## -------------|------------|------------|------------|------------|
##    virginica |          0 |          1 |         14 |         15 | 
##              |      0.000 |      0.067 |      0.933 |      0.341 | 
##              |      0.000 |      0.077 |      0.875 |            | 
##              |      0.000 |      0.023 |      0.318 |            | 
## -------------|------------|------------|------------|------------|
## Column Total |         15 |         13 |         16 |         44 | 
##              |      0.341 |      0.295 |      0.364 |            | 
## -------------|------------|------------|------------|------------|
## 
##

# Accuracy calculation
accuracy <- sum(iris_pred == testLabels) / length(testLabels)
cat("Model Accuracy:", round(accuracy * 100, 2), "%")

## Model Accuracy: 93.18 %

# Basic scatter plot of Sepal features by species
plot(iris$Sepal.Length, iris$Sepal.Width,
     col = iris$Species,
     pch = 19,
     xlab = "Sepal Length",
     ylab = "Sepal Width",
     main = "Iris Sepal Dimensions by Species")
legend("topright", legend = levels(iris$Species),
       col = 1:3, pch = 19)

CW04032025

Chris Yeu

2025-04-03

R Markdown

Including Plots