Exploratory Data Analytics of Wine Dataset

Part 1: The wine dataset Introduction

Source of the data: https://archive.ics.uci.edu/ml/datasets/Wine+Quality

Attribute Information:

For more information, read [Cortez et al., 2009].

Input variables (based on physicochemical tests):

• fixed acidity
• volatile acidity
• citric acid
• residual sugar
• chlorides
• free sulfur dioxide
• total sulfur dioxide
• density
• pH
• sulphates
• alcohol

Output variable (based on sensory data):

• quality (score between 0 and 10)

Part 2: Exploratory Data Analysis

library(ggplot2)
library(scales)
library(DT)
library(tidyr)
library(dplyr)
library(psych)
library(gridExtra)
library(GGally)
library(corrplot)
library(ggExtra)
library(ggcorrplot)

2.1. Load csv file into a dataframe

df=read.csv("winequality-red.csv",sep=";")

datatable(head(df,5))

#knitr::kable(head(df,5))

2.2. The basics

• shape of data
• data types
• missing values
• descriptive statistics

#the shape of data and data types
str(df)

## '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 ...

#check for missing values
#num of obs. - num of complete cases = num of imcomplete cases
nrow(df)-sum(complete.cases(df))

## [1] 0

#descriptive stats
describe(df)

##                      vars    n  mean    sd median trimmed   mad  min
## fixed.acidity           1 1599  8.32  1.74   7.90    8.15  1.48 4.60
## volatile.acidity        2 1599  0.53  0.18   0.52    0.52  0.18 0.12
## citric.acid             3 1599  0.27  0.19   0.26    0.26  0.25 0.00
## residual.sugar          4 1599  2.54  1.41   2.20    2.26  0.44 0.90
## chlorides               5 1599  0.09  0.05   0.08    0.08  0.01 0.01
## free.sulfur.dioxide     6 1599 15.87 10.46  14.00   14.58 10.38 1.00
## total.sulfur.dioxide    7 1599 46.47 32.90  38.00   41.84 26.69 6.00
## density                 8 1599  1.00  0.00   1.00    1.00  0.00 0.99
## pH                      9 1599  3.31  0.15   3.31    3.31  0.15 2.74
## sulphates              10 1599  0.66  0.17   0.62    0.64  0.12 0.33
## alcohol                11 1599 10.42  1.07  10.20   10.31  1.04 8.40
## quality                12 1599  5.64  0.81   6.00    5.59  1.48 3.00
##                         max  range skew kurtosis   se
## fixed.acidity         15.90  11.30 0.98     1.12 0.04
## volatile.acidity       1.58   1.46 0.67     1.21 0.00
## citric.acid            1.00   1.00 0.32    -0.79 0.00
## residual.sugar        15.50  14.60 4.53    28.49 0.04
## chlorides              0.61   0.60 5.67    41.53 0.00
## free.sulfur.dioxide   72.00  71.00 1.25     2.01 0.26
## total.sulfur.dioxide 289.00 283.00 1.51     3.79 0.82
## density                1.00   0.01 0.07     0.92 0.00
## pH                     4.01   1.27 0.19     0.80 0.00
## sulphates              2.00   1.67 2.42    11.66 0.00
## alcohol               14.90   6.50 0.86     0.19 0.03
## quality                8.00   5.00 0.22     0.29 0.02

Findings:

1. The red wine dat has 1599 observations and 12 variables.

2. There is no missing value

3. All variables except quality are numeric, quality - the target variable - is an integer.

4. And based on the skew values, the residual sugar, chlorides, and sulphates are very skewed.

2.3. Target Variable - Quality

a=table(df$quality)
b=table(df$quality)/nrow(df)*100
c=rbind(a,b)
c=data.frame(c)
rownames(c)=c('Number of Wines','%')
colnames(c)=c(3,4,5,6,7,8)
c=round(c,digits = 2)
#knitr::kable(c,digits = 2)
datatable(c)

Findings

1. the red wine quality data is unbalanced, with a large majority of wines fall into quality 5 and 6, less than 4% of the overall sample is under 5, and less than 14 is above 6.

2.4. Visual Exploration of the Data

define variables for visualization

fill.color='#154360'  #"#1579D2"
fill.color2="#D35400" 
vline.color="#D0DBE5"
axis.line.color="#e5e7e9"
lab.color="#D68910"

all.theme=theme_bw()+
  theme(
    text = element_text(family="Courier"),#,size=16
    panel.border = element_blank(),
    panel.grid.major = element_blank(),
    panel.grid.minor = element_blank(),
    axis.line = element_line(color = axis.line.color),
    axis.ticks.x = element_blank(),
    axis.ticks.y = element_blank(),
    plot.title = element_text(hjust = 0.5),
    axis.text.x = element_text(family='Courier',vjust=0.6,hjust =0.2 ), 
    axis.text.y = element_text(family = 'Courier',vjust = 0.6,hjust = 0.2),
    plot.subtitle = element_text(hjust=0.5)
  )

2.4.1. density plot - examing the distribution of data

Density vs Histogram

reference:

• https://www.stat.auckland.ac.nz/~ihaka/787/lectures-distrib.pdf
• https://datavizcatalogue.com/methods/density_plot.html
• https://www.darkhorseanalytics.com/blog/visualizing-distributions-3
• http://serialmentor.com/dataviz/
• https://s3.amazonaws.com/assets.datacamp.com/blog_assets/Python_Seaborn_Cheat_Sheet.pdf

Density plot is also known as Kernel Density Plots, Density Trace Graph.

A Density Plot visualises the distribution of data over a continuous interval or time period. This chart is a variation of a Histogram that uses kernel smoothing to plot values, allowing for smoother distributions by smoothing out the noise. The peaks of a Density Plot help display where values are concentrated over the interval.

An advantage Density Plots have over Histograms is that they’re better at determining the distribution shape because they’re not affected by the number of bins used (each bar used in a typical histogram). A Histogram comprising of only 4 bins wouldn’t produce a distinguishable enough shape of distribution as a 20-bin Histogram would. However, with Density Plots, this isn’t an issue.

avg.cnt=round(mean(df$fixed.acidity),0)

g1=ggplot(df, aes(x=fixed.acidity))+
  geom_density(fill=fill.color,color=fill.color)+
  labs(
    title="Density plot",
    subtitle="The fixed acidity is slightly right skewed",
    caption="Data source: UCI (download year 2018)",
    x="Fixed acidity",
    y="Density"
  )+all.theme+
  scale_x_continuous(labels = comma,breaks = seq(0,21,5))+
  geom_vline(xintercept =avg.cnt,size=1,color=vline.color,linetype="dashed")+  
  geom_text(aes(label=comma(avg.cnt),x=avg.cnt+.2,y=.3),size=4,color=lab.color)


g2=ggplot(df,aes(volatile.acidity)) + 
  geom_density(fill=fill.color,color=fill.color)+all.theme

g3=ggplot(df,aes(citric.acid)) + 
  geom_density(fill=fill.color,color=fill.color)+all.theme

g4=ggplot(df,aes(residual.sugar)) + 
  geom_density(fill=fill.color,color=fill.color)+all.theme

g5=ggplot(df,aes(chlorides)) + 
  geom_density(fill=fill.color,color=fill.color)+all.theme

g6=ggplot(df,aes(free.sulfur.dioxide)) + 
  geom_density(fill=fill.color,color=fill.color)+all.theme

g7=ggplot(df,aes(total.sulfur.dioxide)) + 
  geom_density(fill=fill.color,color=fill.color)+all.theme

g8=ggplot(df,aes(density)) + 
  geom_density(fill=fill.color,color=fill.color)+all.theme

g9=ggplot(df,aes(pH)) + 
  geom_density(fill=fill.color,color=fill.color)+all.theme

g10=ggplot(df,aes(sulphates)) + 
  geom_density(fill=fill.color,color=fill.color)+all.theme

g11=ggplot(df,aes(alcohol)) + 
  geom_density(fill=fill.color,color=fill.color)+all.theme

grid.arrange(g1, g2, g3, g4,g5,g6,g7,g8,g9,g10,g11, ncol=3, nrow =4)

2.4.2. Histogram

avg.cnt=round(mean(df$quality),0)

ggplot(df, aes(quality))+geom_bar(fill=fill.color,color=fill.color)+
  labs(
  title="bar chart of wine quality",
  subtitle="The quality of wine follows normal distribution with the majority of wine with medium quality",
  caption="Data source: UCI (download year 2018)",
  x="quality",
  y="count"
)+
  all.theme

2.4.3. Scatter Plot

Scatterplot is also known as a Scatter Graph, Point Graph, X-Y Plot, Scatter Chart or Scattergram.

Scatterplots use a collection of points placed using Cartesian Coordinates to display values from two variables. By displaying a variable in each axis, you can detect if a relationship or correlation between the two variables exists.

Various types of correlation can be interpreted through the patterns displayed on Scatterplots. These are: - positive (values increase together), - negative (one value decreases as the other increases), - null (no correlation), - linear, exponential and U-shaped. The strength of the correlation can be determined by how closely packed the points are to each other on the graph. Points that end up far outside the general cluster of points are known as outliers.

Lines or curves are fitted within the graph to aid in analysis and are drawn as close to all the points as possible and to show how all the points were condensed into a single line would look. This is typically known as the Line of Best Fit or a Trend Line and can be used to make estimates via interpolation.

Scatterplots are ideal when you have paired numerical data and you want to see if one variable impacts the other. However, do remember that correlation is not causation and another unnoticed variable may be influencing results.

ggplot(df,aes(x=fixed.acidity,y=volatile.acidity))+
  geom_point(fill=fill.color,color=fill.color)+
  #geom_point(aes(color=as.factor(quality)))+
  labs(
    title="Scatterplot",
    subtitle="fixed acidity vs. volatile acidity",
    caption="Data source: UCI (download year 2018)",
    x="fixed acidity",
    y="volatile acidity"
  )+all.theme+
  scale_y_continuous(labels = comma,breaks = seq(0,2,.5))+
  scale_x_continuous(breaks = seq(0,20,5))

2.4.4. Joint Plot

g=ggplot(df,aes(x=fixed.acidity,y=volatile.acidity))+
  geom_point(fill=fill.color,color=fill.color)+
  geom_smooth(method="lm", se=F, color=fill.color2)+
  labs(
    title="Scatterplot",
    subtitle="fixed acidity vs. volatile acidity",
    caption="Data source: UCI (download year 2018)",
    x="fixed acidity",
    y="volatile acidity"
  )+all.theme+
  scale_y_continuous(labels = comma,breaks = seq(0,2,.5))+
  scale_x_continuous(breaks = seq(0,20,5))

ggMarginal(g, type = "histogram", fill="transparent")

ggMarginal(g, type = "boxplot", fill="transparent")

2.4.5. Violin plot

g1=ggplot(df,aes(as.factor(quality),fixed.acidity)) + 
  geom_violin(aes(fill=quality))+
  geom_boxplot(width = 0.1)+all.theme

g2=ggplot(df,aes(as.factor(quality),volatile.acidity)) + 
  geom_violin(aes(fill=quality))+
  geom_boxplot(width = 0.1)+all.theme

g3=ggplot(df,aes(as.factor(quality),citric.acid)) + 
  geom_violin(aes(fill=quality))+
  geom_boxplot(width = 0.1)+all.theme

g4=ggplot(df,aes(as.factor(quality),residual.sugar)) + 
  geom_violin(aes(fill=quality))+
  geom_boxplot(width = 0.1)+all.theme

g5=ggplot(df,aes(as.factor(quality),chlorides)) + 
  geom_violin(aes(fill=quality))+
  geom_boxplot(width = 0.1)+all.theme

g6=ggplot(df,aes(as.factor(quality),free.sulfur.dioxide)) + 
  geom_violin(aes(fill=quality))+
  geom_boxplot(width = 0.1)+all.theme

g7=ggplot(df,aes(as.factor(quality),total.sulfur.dioxide)) + 
  geom_violin(aes(fill=quality))+
  geom_boxplot(width = 0.1)+all.theme

g8=ggplot(df,aes(as.factor(quality),density)) + 
  geom_violin(aes(fill=quality))+
  geom_boxplot(width = 0.1)+all.theme

g9=ggplot(df,aes(as.factor(quality),pH)) + 
  geom_violin(aes(fill=quality))+
  geom_boxplot(width = 0.1)+all.theme

g10=ggplot(df,aes(as.factor(quality),sulphates)) + 
  geom_violin(aes(fill=quality))+
  geom_boxplot(width = 0.1)+all.theme

g11=ggplot(df,aes(as.factor(quality),alcohol)) + 
  geom_violin(aes(fill=quality))+
  geom_boxplot(width = 0.1)+all.theme


grid.arrange(g1, g2, g3, g4,g5,g6,g7,g8,g9,g10,g11, ncol=3, nrow =4)

2.4.6. Pairplot

ggpairs(df, columns=1:12, axisLabels="show",title='Red Wine Quality Data')+all.theme

2.4.7. Correlation Heatmap

corr=round(cor(df), 1)

# Plot
ggcorrplot(corr, hc.order = TRUE, 
           type = "lower", 
           lab = TRUE, 
           lab_size = 3, 
           method="circle", 
           colors = c("tomato2", "white", "springgreen3"), 
           title="Correlation of redwine variables")