R Notebook

INTRODUCTION TO IRIS

The Iris Dataset contains four features (length and width of sepals and petals) of 50 samples of three species of Iris (Setosa, Virginica, and Versicolor). This dataset was created by British biologist Ronald Fisher in 1936.

In this project, I will first explore, transform, and visualize the IRIS dataset. Secondly, I will execute a Hypothesis Testing with t-test (H0: Setosa and Versicolor have the same average petal length) and an ANOVA analysis (H0: Setosa, Virginica, and Versicolor have the same average petal length). Thirdly, I will adopt K-mean Clustering model to categorize IRIS species.

INSTALL PACKAGES AND EXPLORE IRIS DATASET

#Install package
install.packages('dplyr')

trying URL 'https://cran.rstudio.com/bin/macosx/big-sur-arm64/contrib/4.2/dplyr_1.1.2.tgz'
Content type 'application/x-gzip' length 1590090 bytes (1.5 MB)
==================================================
downloaded 1.5 MB

The downloaded binary packages are in
    /var/folders/yl/fk25qksj205djhgmm8ksmfv40000gn/T//RtmpbwJpCa/downloaded_packages

install.packages('ggplot2')

trying URL 'https://cran.rstudio.com/bin/macosx/big-sur-arm64/contrib/4.2/ggplot2_3.4.2.tgz'
Content type 'application/x-gzip' length 4299292 bytes (4.1 MB)
==================================================
downloaded 4.1 MB

The downloaded binary packages are in
    /var/folders/yl/fk25qksj205djhgmm8ksmfv40000gn/T//RtmpbwJpCa/downloaded_packages

install.packages('GGally')

trying URL 'https://cran.rstudio.com/bin/macosx/big-sur-arm64/contrib/4.2/GGally_2.1.2.tgz'
Content type 'application/x-gzip' length 1636372 bytes (1.6 MB)
==================================================
downloaded 1.6 MB

The downloaded binary packages are in
    /var/folders/yl/fk25qksj205djhgmm8ksmfv40000gn/T//RtmpbwJpCa/downloaded_packages

install.packages('cluster')

trying URL 'https://cran.rstudio.com/bin/macosx/big-sur-arm64/contrib/4.2/cluster_2.1.4.tgz'
Content type 'application/x-gzip' length 610729 bytes (596 KB)
==================================================
downloaded 596 KB

The downloaded binary packages are in
    /var/folders/yl/fk25qksj205djhgmm8ksmfv40000gn/T//RtmpbwJpCa/downloaded_packages

install.packages('fpc')

trying URL 'https://cran.rstudio.com/bin/macosx/big-sur-arm64/contrib/4.2/fpc_2.2-10.tgz'
Content type 'application/x-gzip' length 838841 bytes (819 KB)
==================================================
downloaded 819 KB

The downloaded binary packages are in
    /var/folders/yl/fk25qksj205djhgmm8ksmfv40000gn/T//RtmpbwJpCa/downloaded_packages

library(dplyr)

Attaching package: ‘dplyr’

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

library(reshape2)
library(ggplot2)
library(GGally)

Registered S3 method overwritten by 'GGally':
  method from   
  +.gg   ggplot2

library(cluster)
library(fpc)
#Explore Iris Dataset
iris

data(iris)
#Use head to show top rows from data
head(iris)

head(iris,10)

NA

STEP 1: EXPLORE DATA

#STEP 1: EXPLORE DATA ----------------------------
#1.1 Function summary to review data
summary(iris)

  Sepal.Length    Sepal.Width     Petal.Length    Petal.Width          Species  
 Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100   setosa    :50  
 1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300   versicolor:50  
 Median :5.800   Median :3.000   Median :4.350   Median :1.300   virginica :50  
 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                  

#1.2 Function names to show columns name
names(iris)

[1] "Sepal.Length" "Sepal.Width"  "Petal.Length" "Petal.Width"  "Species"     

names(iris) <- tolower(names(iris))

#1.3 Function dim to show row and column counts
dim(iris)

[1] 150   5

#1.4 Function class to show data structure
class(iris)

[1] "data.frame"

#1.5 Function typeof and str to show data type
typeof(iris$sepal.length)

[1] "double"

str(iris$sepal.length)

 num [1:150] 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...

typeof(iris$species)

[1] "integer"

class(iris$species)

[1] "factor"

str(iris$species)

 Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...

STEP 2: TRANSFORM DATA

#STEP 2: TRANSFORM DATA --------------------------
#2.1 Split data into subset
virginica <- iris[iris$species == 'virginica',]
virginica2 <- iris[iris$species == 'virginica' & iris$sepal.length > 6,]
head(virginica)

#2.2 Function select to select columns
selected <- select(iris, sepal.length, sepal.width)
head(selected)

#2.3 Function mutate to add column
newcol <- mutate(iris, longer = sepal.length / sepal.width )
newcol <- mutate(newcol, longer.2x = sepal.length > 2*sepal.width )
tail(newcol)

#2.4 Function arrange to sort data
newcol <- arrange(newcol, sepal.width)
newcol <- arrange(newcol, desc(sepal.width))

#2.5 Function melt to unpivot table (wide -> long)
iris.melt <- melt(iris, id = 'species', variable.name = 'size')
head(iris.melt)

STEP 3: VISUALIZE DATA

#STEP 3: VISUALIZE DATA -----------------------

Warning message:
In do_once((if (is_R_CMD_check()) stop else warning)("The function xfun::isFALSE() will be deprecated in the future. Please ",  :
  The function xfun::isFALSE() will be deprecated in the future. Please consider using base::isFALSE(x) or identical(x, FALSE) instead.

#3.1 Function hist to show histogram
hist(iris$sepal.length)

hist(iris$sepal.length,
 col='light blue',
 main='Histogram',
 xlab='Sepal.Length',
 ylab='Frequency')

hist(iris$sepal.length, col='red', breaks=20, main='Histogram', xlab='Size')

hist(iris$petal.length, col='green',breaks=30, add=TRUE)

legend('topright',
 c('Sepal Length', 'Petal Length'),
 fill=c('red', 'green'))

#3.2 Use ggplot to create charts
ggplot(iris.melt, aes(x=value, fill=size)) +
 geom_histogram(color ='#e9ecef', alpha = 0.6, position = 'identity')

ggplot(iris.melt, aes(x=value, fill=size)) +
 geom_histogram(color ='#e9ecef', alpha = 0.6, position = 'identity') +
 facet_wrap(~size)

#3.3 Function boxplot to create boxplot
boxplot(sepal.length ~ species,
 data = iris,
 main = 'Sepal Length by Species',
 xlab = 'Species',
 ylab = 'Sepal Length',
 col = 'light blue',
 border = 'black')

boxplot(value ~ size,
 data = iris.melt,
 main = 'Compare different size',
 xlab = 'Size',
 ylab = 'Value',
 col = 'light blue',
 border = 'black')

ggplot(iris.melt, aes(x=size, y=value, fill=size)) +
 geom_boxplot()+
 geom_jitter(color = 'black', size = 0.4, alpha = 0.9)

#3.4 Function plot to create scatter plot
plot(iris)

plot(iris[,1:4])

plot(iris$sepal.width, iris$sepal.length,
 col = 'steelblue',
 main = 'Scatterplot',
 xlab = 'Sepal Width',
 ylab = 'Sepal Length',
 pch = 19)

pairs(iris[,1:4],col=iris[,5],oma=c(4,4,6,12))
par(xpd=TRUE)

ggplot(iris, aes(x=sepal.length, y=sepal.width, color=species)) +
 geom_point(size=5)

ggpairs(iris,
 columns = 1:4,
 aes(color = species, alpha = 0.5))

STEP 4: HYPOTHESIS TESTING WITH T-TEST

H0: Setosa and Versicolor have the same average petal length

H1: Setosa and Versicolor do not have the same average petal length

#STEP 4: HYPOTHESIS TESTING WITH T-test ---------------
setosa <- iris[iris$species == 'setosa',]
versicolor <- iris[iris$species == 'versicolor',]
t.test(x= setosa$petal.length, y = versicolor$petal.length)

    Welch Two Sample t-test

data:  setosa$petal.length and versicolor$petal.length
t = -39.493, df = 62.14, p-value < 2.2e-16
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -2.939618 -2.656382
sample estimates:
mean of x mean of y 
    1.462     4.260 

STEP 5: ANOVA ANALYSIS

H0: Setosa, Virginica, and Versicolor have the same average petal length

H1: Setosa, Virginica, and Versicolor do not have the same average petal length

#STEP 5: ANALYSIS WITH ANOVA -----------------------------
petal.length.aov <- aov(formula = petal.length ~ species, data = iris)
summary(petal.length.aov)

             Df Sum Sq Mean Sq F value Pr(>F)    
species       2  437.1  218.55    1180 <2e-16 ***
Residuals   147   27.2    0.19                   
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

TukeyHSD(petal.length.aov)

  Tukey multiple comparisons of means
    95% family-wise confidence level

Fit: aov(formula = petal.length ~ species, data = iris)

$species
                      diff     lwr     upr p adj
versicolor-setosa    2.798 2.59422 3.00178     0
virginica-setosa     4.090 3.88622 4.29378     0
virginica-versicolor 1.292 1.08822 1.49578     0

STEP 6: K-MEAN CLUSTERING MODEL

#STEP 6: CATEGORIZE SPECIES WITH K-MEAN CLUSTERING -------------
iris.test <- iris
iris.test$species <- NULL
head(iris.test)

kmeans.result <- kmeans(iris.test, 3)
table(iris$species, kmeans.result$cluster)

            
              1  2  3
  setosa      0  0 50
  versicolor  2 48  0
  virginica  36 14  0

plot(iris.test[c('sepal.length', 'sepal.width')], col = kmeans.result$cluster)

plotcluster(iris.test, kmeans.result$cluster)

clusplot(iris.test, kmeans.result$cluster, color = TRUE, shade = TRUE)