WineQT
2024-03-21
#Author: Fanshi Zhang
mydata <- read.table("./WineQT.csv",
header = TRUE,
sep = ",",
dec = ".")
head(mydata)## Id fixed.acidity volatile.acidity citric.acid residual.sugar chlorides
## 1 1 7.4 0.70 0.00 1.9 0.076
## 2 2 7.8 0.88 0.00 2.6 0.098
## 3 3 7.8 0.76 0.04 2.3 0.092
## 4 4 11.2 0.28 0.56 1.9 0.075
## 5 5 7.4 0.70 0.00 1.9 0.076
## 6 6 7.4 0.66 0.00 1.8 0.075
## free.sulfur.dioxide total.sulfur.dioxide density pH sulphates alcohol
## 1 11 34 0.9978 3.51 0.56 9.4
## 2 25 67 0.9968 3.20 0.68 9.8
## 3 15 54 0.9970 3.26 0.65 9.8
## 4 17 60 0.9980 3.16 0.58 9.8
## 5 11 34 0.9978 3.51 0.56 9.4
## 6 13 40 0.9978 3.51 0.56 9.4
## quality
## 1 5
## 2 5
## 3 5
## 4 6
## 5 5
## 6 5#Description
Source: https://www.kaggle.com/datasets/yasserh/wine-quality-dataset/data
ID: ID of wines
Fixed.acidity: fixed acidity of wines based on physicochemical tests
Citric.acid: citric acid of wines
Residual.sugar: residual sugar in g/L
Chlorides: cholorides in mg/L
Free.sulfur.dioxide: free sulfur dioxide in mg/L
Total.sulfur.dioxide: total sulfur dioxide in mg/L
Density: density in g/mL
pH: pH of wines
Sulphates: sulphates in mg/L
Alcohol: alcohol in V/V
Quality: quality of wine (score between 0 to 9)
library(psych)
describe(mydata[,-1])## vars n mean sd median trimmed mad min max
## fixed.acidity 1 1143 8.31 1.75 7.90 8.13 1.33 4.60 15.90
## volatile.acidity 2 1143 0.53 0.18 0.52 0.52 0.18 0.12 1.58
## citric.acid 3 1143 0.27 0.20 0.25 0.26 0.25 0.00 1.00
## residual.sugar 4 1143 2.53 1.36 2.20 2.26 0.44 0.90 15.50
## chlorides 5 1143 0.09 0.05 0.08 0.08 0.01 0.01 0.61
## free.sulfur.dioxide 6 1143 15.62 10.25 13.00 14.34 8.90 1.00 68.00
## total.sulfur.dioxide 7 1143 45.91 32.78 37.00 41.20 26.69 6.00 289.00
## density 8 1143 1.00 0.00 1.00 1.00 0.00 0.99 1.00
## pH 9 1143 3.31 0.16 3.31 3.31 0.15 2.74 4.01
## sulphates 10 1143 0.66 0.17 0.62 0.64 0.12 0.33 2.00
## alcohol 11 1143 10.44 1.08 10.20 10.33 1.04 8.40 14.90
## quality 12 1143 5.66 0.81 6.00 5.60 1.48 3.00 8.00
## range skew kurtosis se
## fixed.acidity 11.30 1.04 1.37 0.05
## volatile.acidity 1.46 0.68 1.36 0.01
## citric.acid 1.00 0.37 -0.72 0.01
## residual.sugar 14.60 4.35 27.50 0.04
## chlorides 0.60 6.01 46.78 0.00
## free.sulfur.dioxide 67.00 1.23 1.91 0.30
## total.sulfur.dioxide 283.00 1.66 5.06 0.97
## density 0.01 0.10 0.87 0.00
## pH 1.27 0.22 0.91 0.00
## sulphates 1.67 2.49 11.93 0.01
## alcohol 6.50 0.86 0.21 0.03
## quality 5.00 0.29 0.30 0.02#The average fixed acidity is 8.31, the median is 7.90 and the range is 11.30.
#Among the variables, the sd of total sulfur dioxide is the biggest.
mydata$qualityF <- factor(mydata$quality,
levels = c("1","2","3","4","5","6","7","8","9"),
labels = c("Faulty or unbalanced","borderline of faulty or unbalanced","Deadly dull","Average","Distinguished","Superior","A cut above superior","A humdinger","Truly exceptional"))describeBy(mydata$alcohol,group = mydata$qualityF)##
## Descriptive statistics by group
## group: Faulty or unbalanced
## NULL
## ------------------------------------------------------------
## group: borderline of faulty or unbalanced
## NULL
## ------------------------------------------------------------
## group: Deadly dull
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 6 9.69 0.89 9.82 9.69 0.89 8.4 10.9 2.5 -0.14 -1.59 0.36
## ------------------------------------------------------------
## group: Average
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 33 10.26 1.03 10 10.17 1.19 9 13.1 4.1 0.75 -0.27 0.18
## ------------------------------------------------------------
## group: Distinguished
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 483 9.9 0.75 9.7 9.79 0.44 8.5 14.9 6.4 1.88 5.71 0.03
## ------------------------------------------------------------
## group: Superior
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 462 10.66 1.05 10.5 10.58 1.19 8.4 14 5.6 0.59 -0.07 0.05
## ------------------------------------------------------------
## group: A cut above superior
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 143 11.48 0.98 11.6 11.48 1.04 9.2 14 4.8 0 -0.35 0.08
## ------------------------------------------------------------
## group: A humdinger
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 16 11.94 1.19 11.75 11.94 1.19 9.8 14 4.2 -0.14 -1.01 0.3
## ------------------------------------------------------------
## group: Truly exceptional
## NULLhist(mydata$quality,
main = "Distribution of Quality",
xlab = "Quality",
ylab = "Levels",
breaks = seq(from = 1, to = 9, by = 1))
#The distribution of quality is right skewed.
library(car)## 载入需要的程辑包：carData##
## 载入程辑包：'car'## The following object is masked from 'package:psych':
##
## logitscatterplot(x = mydata$volatile.acidity,
y = mydata$quality,
xlab = "Volatile Acidity",
ylab = "Quality",
smooth = F)
#The quality and the volatile acidity are negatively correlated. The higher the volatile acidity, the lower the quality.
library(ggplot2)##
## 载入程辑包：'ggplot2'## The following objects are masked from 'package:psych':
##
## %+%, alphaggplot(mydata,aes(x = qualityF,y = pH)) +
geom_boxplot() +
xlab("Quality") +
theme_bw()
mydata2 <- mydata[,c(9,12,13)]
scatterplotMatrix(mydata2, smooth = F)
#The density and alcohol is negatively corelated. The alcohol and the quality is positively corelated.