# Load packages
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.4.3
## Warning: package 'ggplot2' was built under R version 4.4.3
## Warning: package 'tibble' was built under R version 4.4.3
## Warning: package 'tidyr' was built under R version 4.4.3
## Warning: package 'readr' was built under R version 4.4.3
## Warning: package 'purrr' was built under R version 4.4.3
## Warning: package 'dplyr' was built under R version 4.4.3
## Warning: package 'stringr' was built under R version 4.4.3
## Warning: package 'forcats' was built under R version 4.4.3
## Warning: package 'lubridate' was built under R version 4.4.3
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.2 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.0.4
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(caret)
## Warning: package 'caret' was built under R version 4.4.3
## Loading required package: lattice
## Warning: package 'lattice' was built under R version 4.4.3
##
## Attaching package: 'caret'
##
## The following object is masked from 'package:purrr':
##
## lift
library(GGally)
## Warning: package 'GGally' was built under R version 4.4.3
## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2
library(corrplot)
## Warning: package 'corrplot' was built under R version 4.4.3
## corrplot 0.95 loaded
library(DataExplorer)
## Warning: package 'DataExplorer' was built under R version 4.4.3
#Load datasets & read CSV files
pima <- read.csv("C:\\Users\\shann\\Downloads\\diabetes.csv") #file path for pima (diabetes) database applied
library(readr)
wine <- read.csv("C:/Users/shann/Downloads/winequality-red.csv") #file path for wine dataset uses semicolon separator
readLines("C:/Users/shann/Downloads/winequality-red.csv", n = 2)
## [1] "fixed acidity,volatile acidity,citric acid,residual sugar,chlorides,free sulfur dioxide,total sulfur dioxide,density,pH,sulphates,alcohol,quality"
## [2] "7.4,0.7,0,1.9,0.076,11,34,0.9978,3.51,0.56,9.4,5"
#Data summaries
# Pima Dataset Summary
str(pima)
## 'data.frame': 768 obs. of 9 variables:
## $ Pregnancies : int 6 1 8 1 0 5 3 10 2 8 ...
## $ Glucose : int 148 85 183 89 137 116 78 115 197 125 ...
## $ BloodPressure : int 72 66 64 66 40 74 50 0 70 96 ...
## $ SkinThickness : int 35 29 0 23 35 0 32 0 45 0 ...
## $ Insulin : int 0 0 0 94 168 0 88 0 543 0 ...
## $ BMI : num 33.6 26.6 23.3 28.1 43.1 25.6 31 35.3 30.5 0 ...
## $ DiabetesPedigreeFunction: num 0.627 0.351 0.672 0.167 2.288 ...
## $ Age : int 50 31 32 21 33 30 26 29 53 54 ...
## $ Outcome : int 1 0 1 0 1 0 1 0 1 1 ...
summary(pima)
## Pregnancies Glucose BloodPressure SkinThickness
## Min. : 0.000 Min. : 0.0 Min. : 0.00 Min. : 0.00
## 1st Qu.: 1.000 1st Qu.: 99.0 1st Qu.: 62.00 1st Qu.: 0.00
## Median : 3.000 Median :117.0 Median : 72.00 Median :23.00
## Mean : 3.845 Mean :120.9 Mean : 69.11 Mean :20.54
## 3rd Qu.: 6.000 3rd Qu.:140.2 3rd Qu.: 80.00 3rd Qu.:32.00
## Max. :17.000 Max. :199.0 Max. :122.00 Max. :99.00
## Insulin BMI DiabetesPedigreeFunction Age
## Min. : 0.0 Min. : 0.00 Min. :0.0780 Min. :21.00
## 1st Qu.: 0.0 1st Qu.:27.30 1st Qu.:0.2437 1st Qu.:24.00
## Median : 30.5 Median :32.00 Median :0.3725 Median :29.00
## Mean : 79.8 Mean :31.99 Mean :0.4719 Mean :33.24
## 3rd Qu.:127.2 3rd Qu.:36.60 3rd Qu.:0.6262 3rd Qu.:41.00
## Max. :846.0 Max. :67.10 Max. :2.4200 Max. :81.00
## Outcome
## Min. :0.000
## 1st Qu.:0.000
## Median :0.000
## Mean :0.349
## 3rd Qu.:1.000
## Max. :1.000
dim(pima)
## [1] 768 9
# Wine Dataset Summary
str(wine)
## 'data.frame': 1599 obs. of 12 variables:
## $ fixed.acidity : num 7.4 7.8 7.8 11.2 7.4 7.4 7.9 7.3 7.8 7.5 ...
## $ volatile.acidity : num 0.7 0.88 0.76 0.28 0.7 0.66 0.6 0.65 0.58 0.5 ...
## $ citric.acid : num 0 0 0.04 0.56 0 0 0.06 0 0.02 0.36 ...
## $ residual.sugar : num 1.9 2.6 2.3 1.9 1.9 1.8 1.6 1.2 2 6.1 ...
## $ chlorides : num 0.076 0.098 0.092 0.075 0.076 0.075 0.069 0.065 0.073 0.071 ...
## $ free.sulfur.dioxide : num 11 25 15 17 11 13 15 15 9 17 ...
## $ total.sulfur.dioxide: num 34 67 54 60 34 40 59 21 18 102 ...
## $ density : num 0.998 0.997 0.997 0.998 0.998 ...
## $ pH : num 3.51 3.2 3.26 3.16 3.51 3.51 3.3 3.39 3.36 3.35 ...
## $ sulphates : num 0.56 0.68 0.65 0.58 0.56 0.56 0.46 0.47 0.57 0.8 ...
## $ alcohol : num 9.4 9.8 9.8 9.8 9.4 9.4 9.4 10 9.5 10.5 ...
## $ quality : int 5 5 5 6 5 5 5 7 7 5 ...
summary(wine)
## fixed.acidity volatile.acidity citric.acid residual.sugar
## Min. : 4.60 Min. :0.1200 Min. :0.000 Min. : 0.900
## 1st Qu.: 7.10 1st Qu.:0.3900 1st Qu.:0.090 1st Qu.: 1.900
## Median : 7.90 Median :0.5200 Median :0.260 Median : 2.200
## Mean : 8.32 Mean :0.5278 Mean :0.271 Mean : 2.539
## 3rd Qu.: 9.20 3rd Qu.:0.6400 3rd Qu.:0.420 3rd Qu.: 2.600
## Max. :15.90 Max. :1.5800 Max. :1.000 Max. :15.500
## chlorides free.sulfur.dioxide total.sulfur.dioxide density
## Min. :0.01200 Min. : 1.00 Min. : 6.00 Min. :0.9901
## 1st Qu.:0.07000 1st Qu.: 7.00 1st Qu.: 22.00 1st Qu.:0.9956
## Median :0.07900 Median :14.00 Median : 38.00 Median :0.9968
## Mean :0.08747 Mean :15.87 Mean : 46.47 Mean :0.9967
## 3rd Qu.:0.09000 3rd Qu.:21.00 3rd Qu.: 62.00 3rd Qu.:0.9978
## Max. :0.61100 Max. :72.00 Max. :289.00 Max. :1.0037
## pH sulphates alcohol quality
## Min. :2.740 Min. :0.3300 Min. : 8.40 Min. :3.000
## 1st Qu.:3.210 1st Qu.:0.5500 1st Qu.: 9.50 1st Qu.:5.000
## Median :3.310 Median :0.6200 Median :10.20 Median :6.000
## Mean :3.311 Mean :0.6581 Mean :10.42 Mean :5.636
## 3rd Qu.:3.400 3rd Qu.:0.7300 3rd Qu.:11.10 3rd Qu.:6.000
## Max. :4.010 Max. :2.0000 Max. :14.90 Max. :8.000
dim(wine)
## [1] 1599 12
#Preprocessing
# Check for missing values
colSums(is.na(pima))
## Pregnancies Glucose BloodPressure
## 0 0 0
## SkinThickness Insulin BMI
## 0 0 0
## DiabetesPedigreeFunction Age Outcome
## 0 0 0
colSums(is.na(wine))
## fixed.acidity volatile.acidity citric.acid
## 0 0 0
## residual.sugar chlorides free.sulfur.dioxide
## 0 0 0
## total.sulfur.dioxide density pH
## 0 0 0
## sulphates alcohol quality
## 0 0 0
# Outlier detection (boxplots)
boxplot(pima[,1:8], main = "Pima: Boxplots of Features", las = 2) #boxplots for Pima
boxplot(wine[,1:11], main = "Wine: Boxplots of Features", las = 2) #boxplots for Wine
# Normalize numeric features
pima_norm <- pima
pima_norm[,1:8] <- scale(pima[,1:8])
wine_norm <- wine
wine_norm[,1:11] <- scale(wine[,1:11])
# Partition data
# Split Pima data
set.seed(123)
trainIndex <- createDataPartition(pima_norm$Outcome, p = 0.7, list = FALSE)
pima_train <- pima_norm[trainIndex, ]
pima_test <- pima_norm[-trainIndex, ]
# Split Wine data
wine$quality_bin <- ifelse(wine$quality >= 7, "Good", "Bad")
wine$quality_bin <- factor(wine$quality_bin)
set.seed(123)
wineIndex <- createDataPartition(wine$quality_bin, p = 0.7, list = FALSE)
wine_train <- wine_norm[wineIndex, ]
wine_test <- wine_norm[-wineIndex, ]
#Data visualization
# Correlation matrix for Pima
corrplot(cor(pima_norm[,1:8]), method = "color", tl.cex = 0.8)
# Correlation matrix for Wine
corrplot(cor(wine_norm[,1:11]), method = "color", tl.cex = 0.8)
# Pairplots
# Pima Pairplot
ggpairs(pima_norm, columns = 1:8, aes(color = as.factor(Outcome)))
# Wine Pairplot
ggpairs(wine_norm, columns = 1:11, aes(color = wine$quality_bin))
# Distribution plots
plot_density(pima_norm)
plot_density(wine_norm)
# Pima: Glucose vs Outcome
ggplot(pima, aes(x = as.factor(Outcome), y = Glucose)) +
geom_boxplot(fill = "lightblue") +
labs(title = "Glucose vs Outcome", x = "Diabetes", y = "Glucose Level")
# Wine: Alcohol vs Quality Bin
ggplot(wine, aes(x = quality_bin, y = alcohol, fill = quality_bin)) +
geom_boxplot() +
labs(title = "Alcohol Content by Wine Quality")
