#Project Title:  Project: Data Analytics with Manegerial Application Internship
#NAME: Nimit Dhalia
#EMAIL: lucky.dhalia8@gmail.com
#COLLEGE : IIT Roorkee

Project Description:

My project relates to what is the balance amount of physicochemical make a good quality wine. I propose to investigate the impact of input variables ( based on physicochemical test ) on output variable- quality ( which is based on sensory data ) of two different wines: White and Red.

1. Reading datasets

#Reading: Red wine datset and White wine dataset
redWine<- read.csv("winequality-red.csv", sep = ";")
whiteWine<- read.csv("winequality-white.csv", sep = ";") 

dim(redWine) #dimension of red wine
## [1] 1599   12
dim(whiteWine) #dimension of white wine
## [1] 4898   12

Making a dummy variable ‘type’ and assigning it either ‘red’ or ‘white’ depending on wine and combining both dataset into one under ‘wine.df’

redWine$type<- "red"
whiteWine$type<- "white"

wine.df<- rbind(redWine,whiteWine) #dimension of newly joing wine.df

#Wine.df has no. of rows equals to summing of rows in redWine and whiteWine datset and no. of column is one extra compare to redWine / whiteWine because of dummy variable 'type' 
dim(wine.df)
## [1] 6497   13

Number of data rows in each dataset:

2. COLUMN DESCRIPTION and (Units)

#no of columns in Red wine dataset:
ncol(redWine)
## [1] 13
#no of columns in White wine dataset:
ncol(whiteWine)
## [1] 13
  • Both dataset have similar schema.
  1. Fixed acidity (g(tartaric acid)/dm3)
  2. Volatile acidity (g(acetic acid)/dm3)
  3. Citric acid (g/dm3)
  4. Residual sugar (g/dm3)
  5. Chlorides (g(sodium chloride)/dm3)
  6. Free sulfur dioxide (mg/dm3)
  7. Total sulfur dioxide (mg/dm3)
  8. Density (g/cm3)
  9. pH
  10. Sulphates (g(potassium sulphate)/dm3)
  11. Alcohol (vol.%)
  12. Quaity ( Score between 0 and 10)

Display the first few rows of the red wine data to understand its structure

head(redWine)
##   fixed.acidity volatile.acidity citric.acid residual.sugar chlorides
## 1           7.4             0.70        0.00            1.9     0.076
## 2           7.8             0.88        0.00            2.6     0.098
## 3           7.8             0.76        0.04            2.3     0.092
## 4          11.2             0.28        0.56            1.9     0.075
## 5           7.4             0.70        0.00            1.9     0.076
## 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 type
## 1       5  red
## 2       5  red
## 3       5  red
## 4       6  red
## 5       5  red
## 6       5  red

Display the first few rows of the white wine data to understand its structure

head(whiteWine)
##   fixed.acidity volatile.acidity citric.acid residual.sugar chlorides
## 1           7.0             0.27        0.36           20.7     0.045
## 2           6.3             0.30        0.34            1.6     0.049
## 3           8.1             0.28        0.40            6.9     0.050
## 4           7.2             0.23        0.32            8.5     0.058
## 5           7.2             0.23        0.32            8.5     0.058
## 6           8.1             0.28        0.40            6.9     0.050
##   free.sulfur.dioxide total.sulfur.dioxide density   pH sulphates alcohol
## 1                  45                  170  1.0010 3.00      0.45     8.8
## 2                  14                  132  0.9940 3.30      0.49     9.5
## 3                  30                   97  0.9951 3.26      0.44    10.1
## 4                  47                  186  0.9956 3.19      0.40     9.9
## 5                  47                  186  0.9956 3.19      0.40     9.9
## 6                  30                   97  0.9951 3.26      0.44    10.1
##   quality  type
## 1       6 white
## 2       6 white
## 3       6 white
## 4       6 white
## 5       6 white
## 6       6 white

3. DATA STRUCTURE

Red Wine:

str(redWine)
## 'data.frame':    1599 obs. of  13 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 ...
##  $ type                : chr  "red" "red" "red" "red" ...

White Wine:

str(whiteWine)
## 'data.frame':    4898 obs. of  13 variables:
##  $ fixed.acidity       : num  7 6.3 8.1 7.2 7.2 8.1 6.2 7 6.3 8.1 ...
##  $ volatile.acidity    : num  0.27 0.3 0.28 0.23 0.23 0.28 0.32 0.27 0.3 0.22 ...
##  $ citric.acid         : num  0.36 0.34 0.4 0.32 0.32 0.4 0.16 0.36 0.34 0.43 ...
##  $ residual.sugar      : num  20.7 1.6 6.9 8.5 8.5 6.9 7 20.7 1.6 1.5 ...
##  $ chlorides           : num  0.045 0.049 0.05 0.058 0.058 0.05 0.045 0.045 0.049 0.044 ...
##  $ free.sulfur.dioxide : num  45 14 30 47 47 30 30 45 14 28 ...
##  $ total.sulfur.dioxide: num  170 132 97 186 186 97 136 170 132 129 ...
##  $ density             : num  1.001 0.994 0.995 0.996 0.996 ...
##  $ pH                  : num  3 3.3 3.26 3.19 3.19 3.26 3.18 3 3.3 3.22 ...
##  $ sulphates           : num  0.45 0.49 0.44 0.4 0.4 0.44 0.47 0.45 0.49 0.45 ...
##  $ alcohol             : num  8.8 9.5 10.1 9.9 9.9 10.1 9.6 8.8 9.5 11 ...
##  $ quality             : int  6 6 6 6 6 6 6 6 6 6 ...
##  $ type                : chr  "white" "white" "white" "white" ...
  • Both wines have similar columns in their respective schemas.
  • ‘type’ needs to change into factors.
#convert them into factors
redWine$type<- factor(redWine$type)

whiteWine$type<- factor(whiteWine$type)

wine.df$type<- factor(wine.df$type)
#check the conversion was successful
str(redWine$type)
##  Factor w/ 1 level "red": 1 1 1 1 1 1 1 1 1 1 ...
str(whiteWine$type)
##  Factor w/ 1 level "white": 1 1 1 1 1 1 1 1 1 1 ...
str(wine.df$type)
##  Factor w/ 2 levels "red","white": 1 1 1 1 1 1 1 1 1 1 ...

4. DATA SUMMARY

Red Wine:

library(psych)
describe(redWine[,c(1:12)])
##                      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

White Wine:

describe(whiteWine[,c(1:12)])
##                      vars    n   mean    sd median trimmed   mad  min
## fixed.acidity           1 4898   6.85  0.84   6.80    6.82  0.74 3.80
## volatile.acidity        2 4898   0.28  0.10   0.26    0.27  0.09 0.08
## citric.acid             3 4898   0.33  0.12   0.32    0.33  0.09 0.00
## residual.sugar          4 4898   6.39  5.07   5.20    5.80  5.34 0.60
## chlorides               5 4898   0.05  0.02   0.04    0.04  0.01 0.01
## free.sulfur.dioxide     6 4898  35.31 17.01  34.00   34.36 16.31 2.00
## total.sulfur.dioxide    7 4898 138.36 42.50 134.00  136.96 43.00 9.00
## density                 8 4898   0.99  0.00   0.99    0.99  0.00 0.99
## pH                      9 4898   3.19  0.15   3.18    3.18  0.15 2.72
## sulphates              10 4898   0.49  0.11   0.47    0.48  0.10 0.22
## alcohol                11 4898  10.51  1.23  10.40   10.43  1.48 8.00
## quality                12 4898   5.88  0.89   6.00    5.85  1.48 3.00
##                         max  range skew kurtosis   se
## fixed.acidity         14.20  10.40 0.65     2.17 0.01
## volatile.acidity       1.10   1.02 1.58     5.08 0.00
## citric.acid            1.66   1.66 1.28     6.16 0.00
## residual.sugar        65.80  65.20 1.08     3.46 0.07
## chlorides              0.35   0.34 5.02    37.51 0.00
## free.sulfur.dioxide  289.00 287.00 1.41    11.45 0.24
## total.sulfur.dioxide 440.00 431.00 0.39     0.57 0.61
## density                1.04   0.05 0.98     9.78 0.00
## pH                     3.82   1.10 0.46     0.53 0.00
## sulphates              1.08   0.86 0.98     1.59 0.00
## alcohol               14.20   6.20 0.49    -0.70 0.02
## quality                9.00   6.00 0.16     0.21 0.01

5. CONTINGENCY TABLE

One way contingency table

wineTypeTable<- with(wine.df, table(type))
wineTypeTable # frequencies
## type
##   red white 
##  1599  4898
round(prop.table(wineTypeTable)*100,2) # percentages
## type
##   red white 
## 24.61 75.39

Two way contingency table

typeAndQuality <- xtabs(~ type + quality, data=wine.df)
typeAndQuality # frequencies
##        quality
## type       3    4    5    6    7    8    9
##   red     10   53  681  638  199   18    0
##   white   20  163 1457 2198  880  175    5
round(prop.table(typeAndQuality,1)*100,2) #row percentage
##        quality
## type        3     4     5     6     7     8     9
##   red    0.63  3.31 42.59 39.90 12.45  1.13  0.00
##   white  0.41  3.33 29.75 44.88 17.97  3.57  0.10
round(prop.table(typeAndQuality,2)*100,2) #column percentage
##        quality
## type         3      4      5      6      7      8      9
##   red    33.33  24.54  31.85  22.50  18.44   9.33   0.00
##   white  66.67  75.46  68.15  77.50  81.56  90.67 100.00
library(gmodels) 
CrossTable(wine.df$type, wine.df$quality)
## 
##  
##    Cell Contents
## |-------------------------|
## |                       N |
## | Chi-square contribution |
## |           N / Row Total |
## |           N / Col Total |
## |         N / Table Total |
## |-------------------------|
## 
##  
## Total Observations in Table:  6497 
## 
##  
##              | wine.df$quality 
## wine.df$type |         3 |         4 |         5 |         6 |         7 |         8 |         9 | Row Total | 
## -------------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|
##          red |        10 |        53 |       681 |       638 |       199 |        18 |         0 |      1599 | 
##              |     0.927 |     0.000 |    45.546 |     5.154 |    16.681 |    18.321 |     1.231 |           | 
##              |     0.006 |     0.033 |     0.426 |     0.399 |     0.124 |     0.011 |     0.000 |     0.246 | 
##              |     0.333 |     0.245 |     0.319 |     0.225 |     0.184 |     0.093 |     0.000 |           | 
##              |     0.002 |     0.008 |     0.105 |     0.098 |     0.031 |     0.003 |     0.000 |           | 
## -------------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|
##        white |        20 |       163 |      1457 |      2198 |       880 |       175 |         5 |      4898 | 
##              |     0.303 |     0.000 |    14.869 |     1.683 |     5.446 |     5.981 |     0.402 |           | 
##              |     0.004 |     0.033 |     0.297 |     0.449 |     0.180 |     0.036 |     0.001 |     0.754 | 
##              |     0.667 |     0.755 |     0.681 |     0.775 |     0.816 |     0.907 |     1.000 |           | 
##              |     0.003 |     0.025 |     0.224 |     0.338 |     0.135 |     0.027 |     0.001 |           | 
## -------------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|
## Column Total |        30 |       216 |      2138 |      2836 |      1079 |       193 |         5 |      6497 | 
##              |     0.005 |     0.033 |     0.329 |     0.437 |     0.166 |     0.030 |     0.001 |           | 
## -------------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|
## 
##

Chi-square test of independence of the wine type and quality variables.

1. H0: Type of wine and quality are independent

chisq.test(typeAndQuality)
## Warning in chisq.test(typeAndQuality): Chi-squared approximation may be
## incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  typeAndQuality
## X-squared = 116.54, df = 6, p-value < 2.2e-16
  • Since the probability is small (p < 0.01), we reject the Null hypothesis that type of wine and quality are independent.
  • This output suggests a relationship between the quality and type of wine (p < 0.01).

6. T-test

1 H0: There is no significant difference between quality of red wine and quality of white wine.

mean(redWine$quality)
## [1] 5.636023
mean(whiteWine$quality)
## [1] 5.877909
t.test(redWine$quality,whiteWine$quality)
## 
##  Welch Two Sample t-test
## 
## data:  redWine$quality and whiteWine$quality
## t = -10.149, df = 2950.8, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.2886173 -0.1951564
## sample estimates:
## mean of x mean of y 
##  5.636023  5.877909
  • We reject our null hypothesis since p < 0.05.
  • White wine had a higher mean quality of 5.88 as compared to Red wine which had a mean quality of 5.64.
  • The t test showed there was a significant difference in quality between Red and White wine.

2 H0: There is no significant difference between alcohol amount in red wine and quality of white wine.

mean(redWine$alcohol)
## [1] 10.42298
mean(whiteWine$alcohol)
## [1] 10.51427
t.test(redWine$alcohol,whiteWine$alcohol)
## 
##  Welch Two Sample t-test
## 
## data:  redWine$alcohol and whiteWine$alcohol
## t = -2.859, df = 3100.5, p-value = 0.004278
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.15388669 -0.02868117
## sample estimates:
## mean of x mean of y 
##  10.42298  10.51427
  • We reject our null hypothesis since p < 0.05.
  • White wine had a higher mean alcohol of 10.51(vol.%) as compared to Red wine which had a mean alcohol of 10.42(vol.%).
  • The t test showed there was a significant difference in alcohol amount between Red and White wine.

3 H0: There is no significant difference between Residual sugar in both wine.

mean(redWine$residual.sugar)
## [1] 2.538806
mean(whiteWine$residual.sugar)
## [1] 6.391415
t.test(redWine$residual.sugar,whiteWine$residual.sugar)
## 
##  Welch Two Sample t-test
## 
## data:  redWine$residual.sugar and whiteWine$residual.sugar
## t = -47.802, df = 6392.1, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -4.010602 -3.694617
## sample estimates:
## mean of x mean of y 
##  2.538806  6.391415
  • We reject our null hypothesis since p < 0.05.
  • White wine had a higher mean residual sugar of 6.39 (g/dm3) as compared to Red wine which had a mean alcohol of 2.54 (g/dm3).
  • The t test showed there was a significant difference in residual sugar amount between Red and White wine.

4 H0: There is no significant difference between density in both wines.

mean(redWine$density)
## [1] 0.9967467
mean(whiteWine$density)
## [1] 0.9940274
t.test(redWine$density,whiteWine$density)
## 
##  Welch Two Sample t-test
## 
## data:  redWine$density and whiteWine$density
## t = 42.709, df = 4340.4, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  0.002594475 0.002844131
## sample estimates:
## mean of x mean of y 
## 0.9967467 0.9940274
  • We reject our null hypothesis since p < 0.05.
  • Red wine had a higher mean density of 0.996 (g/cm3) as compared to White wine which had a mean density of 0.994 (g/cm3).
  • The t test showed there was a significant difference in density amount between Red and White wine.

7. VIZUALISATION

1. Comparing Fixed Acidity, Volatile Acidity, and Critic Acid between Red wine and White wine:

boxplot(redWine$fixed.acidity, whiteWine$fixed.acidity ,col=c("red3","seashell1"),  horizontal  = FALSE, main="Acidity (tartaric)", ylab="tartaric acid, g / dm3", names=c("Red wine","White wine"))

boxplot(redWine$volatile.acidity, whiteWine$volatile.acidity ,col=c("red3","seashell1"),  horizontal  = FALSE, main="Acidity (acetic)", ylab="acetic acid, g / dm3", names=c("Red wine","White wine"))

boxplot(redWine$citric.acid, whiteWine$citric.acid ,col=c("red3","seashell1"),  horizontal  = FALSE, main="Critic acid", ylab="Critic acid, g / dm3", names=c("Red wine","White wine"))

  • Red wine is more acidic than the White wine.

2. Comparing Residual sugar, Sodium chloride, Free sulfur dioxide, and Total sulfur dioxide side by side between Red wine and White wine

boxplot(redWine$residual.sugar, whiteWine$residual.sugar ,col=c("red3","seashell1"),  horizontal  = FALSE, main="Residual sugar", ylab="g / dm3", names=c("Red wine","White wine"))

boxplot(redWine$chlorides, whiteWine$chlorides ,col=c("red3","seashell1"),  horizontal  = FALSE, main="Sodium chloride", ylab="g / dm3", names=c("Red wine","White wine"))

boxplot(redWine$free.sulfur.dioxide, whiteWine$free.sulfur.dioxide ,col=c("red3","seashell1"),  horizontal  = FALSE, main="Free sulfur dioxide", ylab="mg / dm3", names=c("Red wine","White wine"))

boxplot(redWine$total.sulfur.dioxide, whiteWine$total.sulfur.dioxide ,col=c("red3","seashell1"),  horizontal  = FALSE, main="Total sulfur dioxide", ylab="mg / dm3", names=c("Red wine","White wine"))

  • White wine have comparitively more sulfur dioxide [ Total and Free] in its contents

3. Comparing Density, pH, Potassium sulphates, and Alcohol side by side between Red wine and White wine

boxplot(redWine$density, whiteWine$density ,col=c("red3","seashell1"),  horizontal  = FALSE, main="Density", ylab="g / cm3", names=c("Red wine","White wine"))

boxplot(redWine$pH, whiteWine$pH ,col=c("red3","seashell1"),  horizontal  = FALSE, main="pH", ylab="pH", names=c("Red wine","White wine"))

boxplot(redWine$sulphates, whiteWine$sulphates ,col=c("red3","seashell1"),  horizontal  = FALSE, main="Potassium sulphates", ylab="g / dm3", names=c("Red wine","White wine"))

boxplot(redWine$alcohol, whiteWine$alcohol ,col=c("red3","seashell1"),  horizontal  = FALSE, main="Alcohol", ylab="vol %", names=c("Red wine","White wine"))

  • Red wine is more acidic than the white wine ( Red wine on average have more pH than White wine).

4. Looking at frequency distribution of quality rating given on scale of (0 to 10) of both wines.

library(lattice)
par(mfrow=c(1,2))

histogram(redWine$quality, xlab="Sensory score", main="Red wine ", col = "red3")

histogram(whiteWine$quality, xlab="Sensory score",main="White wine", col="seashell1")

par(mfrow=c(1,1))
  • Red wine given rating {3,4,5,6,7,8} and among them 5/10 occurs maximum number of tiems.
  • White wine given raring {3,4,5,6,7,8,9} and among them 6/10 occurs maximum number of times.

8. CORRELATION

Red Wine:

#1. Corrplot
library(corrplot)
## corrplot 0.84 loaded
N<- cor(redWine[,c(1:5,12)])
corrplot(N, method="circle") #first five variable with quailty 

N1<- cor(redWine[,c(6:11,12)])
corrplot(N1, method="circle") #last 6 variable with quality

#2. Correlation matrix

round(cor(redWine[,c(1:5,12)]),2) #first 5 variable with quality
##                  fixed.acidity volatile.acidity citric.acid residual.sugar
## fixed.acidity             1.00            -0.26        0.67           0.11
## volatile.acidity         -0.26             1.00       -0.55           0.00
## citric.acid               0.67            -0.55        1.00           0.14
## residual.sugar            0.11             0.00        0.14           1.00
## chlorides                 0.09             0.06        0.20           0.06
## quality                   0.12            -0.39        0.23           0.01
##                  chlorides quality
## fixed.acidity         0.09    0.12
## volatile.acidity      0.06   -0.39
## citric.acid           0.20    0.23
## residual.sugar        0.06    0.01
## chlorides             1.00   -0.13
## quality              -0.13    1.00
round(cor(redWine[,c(6:11,12)]),2) #last 6 variable with quality
##                      free.sulfur.dioxide total.sulfur.dioxide density
## free.sulfur.dioxide                 1.00                 0.67   -0.02
## total.sulfur.dioxide                0.67                 1.00    0.07
## density                            -0.02                 0.07    1.00
## pH                                  0.07                -0.07   -0.34
## sulphates                           0.05                 0.04    0.15
## alcohol                            -0.07                -0.21   -0.50
## quality                            -0.05                -0.19   -0.17
##                         pH sulphates alcohol quality
## free.sulfur.dioxide   0.07      0.05   -0.07   -0.05
## total.sulfur.dioxide -0.07      0.04   -0.21   -0.19
## density              -0.34      0.15   -0.50   -0.17
## pH                    1.00     -0.20    0.21   -0.06
## sulphates            -0.20      1.00    0.09    0.25
## alcohol               0.21      0.09    1.00    0.48
## quality              -0.06      0.25    0.48    1.00
#3. Correaltion matrix using Corrgram 
library(corrgram)
## Warning: replacing previous import by 'magrittr::%>%' when loading
## 'dendextend'
corrgram(redWine[,c(1:5,12)], lower.panel=panel.shade,
         upper.panel=panel.pie, diag.panel = panel.minmax, text.panel = panel.txt,
         main="Corrgram of Red wine intercorrelations I") #first five variable with quality

corrgram(redWine[,c(6:11,12)], lower.panel=panel.shade,
         upper.panel=panel.pie, diag.panel = panel.minmax, text.panel = panel.txt,
         main="Corrgram of Red wine intercorrelations II") #last 6 variable with quality

#4. Scatter plot matrix
library(psych)

pairs.panels(redWine[,c(1:4,12)], 
             method = "pearson", # correlation method
             hist.col = "#00AFBB",
             density = TRUE, # show density plots
             lm = TRUE
             ) #first 4 variable with quality

pairs.panels(redWine[,c(5:8,12)], 
             method = "pearson", # correlation method
             hist.col = "#00AFBB",
             density = TRUE, # show density plots
             lm = TRUE
             ) #mid 4 variable wit quality

pairs.panels(redWine[,c(8:11,12)], 
             method = "pearson", # correlation method
             hist.col = "#00AFBB",
             density = TRUE, # show density plots
             lm = TRUE
             ) #last five variable with quality

White Wine:

#1. Corrplot
library(corrplot)
M<- cor(whiteWine[,c(1:5,12)])
corrplot(M, method="circle") #first five variable with quality

M1<- cor(whiteWine[,c(6:11,12)])
corrplot(M1, method="circle") #last six variable with quality

#2. Correlation matrix

round(cor(whiteWine[,c(1:5,12)]),2) #first 5 variable with quality
##                  fixed.acidity volatile.acidity citric.acid residual.sugar
## fixed.acidity             1.00            -0.02        0.29           0.09
## volatile.acidity         -0.02             1.00       -0.15           0.06
## citric.acid               0.29            -0.15        1.00           0.09
## residual.sugar            0.09             0.06        0.09           1.00
## chlorides                 0.02             0.07        0.11           0.09
## quality                  -0.11            -0.19       -0.01          -0.10
##                  chlorides quality
## fixed.acidity         0.02   -0.11
## volatile.acidity      0.07   -0.19
## citric.acid           0.11   -0.01
## residual.sugar        0.09   -0.10
## chlorides             1.00   -0.21
## quality              -0.21    1.00
round(cor(whiteWine[,c(6:11,12)]),2) #last 6 variable with quality
##                      free.sulfur.dioxide total.sulfur.dioxide density
## free.sulfur.dioxide                 1.00                 0.62    0.29
## total.sulfur.dioxide                0.62                 1.00    0.53
## density                             0.29                 0.53    1.00
## pH                                  0.00                 0.00   -0.09
## sulphates                           0.06                 0.13    0.07
## alcohol                            -0.25                -0.45   -0.78
## quality                             0.01                -0.17   -0.31
##                         pH sulphates alcohol quality
## free.sulfur.dioxide   0.00      0.06   -0.25    0.01
## total.sulfur.dioxide  0.00      0.13   -0.45   -0.17
## density              -0.09      0.07   -0.78   -0.31
## pH                    1.00      0.16    0.12    0.10
## sulphates             0.16      1.00   -0.02    0.05
## alcohol               0.12     -0.02    1.00    0.44
## quality               0.10      0.05    0.44    1.00
#3. Correlation matrix using corrgram
library(corrgram)
corrgram(whiteWine[,c(1:5,12)], lower.panel=panel.shade,
         upper.panel=panel.pie, diag.panel = panel.minmax, text.panel = panel.txt,
         main="Corrgram of White wine intercorrelations I") #first five variables with quality

corrgram(whiteWine[,c(6:11,12)], lower.panel=panel.shade,
         upper.panel=panel.pie, diag.panel = panel.minmax, text.panel = panel.txt,
         main="Corrgram of White wine intercorrelations II") #last six variables with quality

*

#4. Scatter plot matrix
library(psych)

pairs.panels(whiteWine[,c(1:4,12)], 
             method = "pearson", # correlation method
             hist.col = "lightpink",
             density = TRUE, # show density plots
             lm = TRUE
             ) #first four variables with quality

pairs.panels(whiteWine[,c(5:8,12)], 
             method = "pearson", # correlation method
             hist.col = "lightpink",
             density = TRUE, # show density plots
             lm = TRUE
             ) #mid four variables with quality

pairs.panels(whiteWine[,c(8:11,12)], 
             method = "pearson", # correlation method
             hist.col = "lightpink",
             density = TRUE, # show density plots
             lm = TRUE
             ) #last five variables with quality

9. Looking at the impact of each variable on ‘Quality’ ( in Red wine and White wine) with scatterplot

A. Effect of Critic Acid, Volatile Acidity, and Fixed Acidity on quality of wine

Red wine:

#redWine
acidityRedWine<- aggregate(cbind( citric.acid, volatile.acidity, fixed.acidity) ~ quality,
data = redWine, mean)

library(car)
## 
## Attaching package: 'car'
## The following object is masked from 'package:psych':
## 
##     logit
scatterplot(acidityRedWine$quality, acidityRedWine$citric.acid, xlab="Quality", ylab = "Citric Acid", main="1. Citric Acid and Quality scatterplot")

scatterplot(acidityRedWine$quality, acidityRedWine$volatile.acidity, xlab="Quality", ylab = "Volatile Acidity", main="2. Volatile Acidity and Quality scatterplot")

scatterplot(acidityRedWine$quality, acidityRedWine$fixed.acidity, xlab="Quality", ylab = "Fixed Acidity", main="3. Fixed Acidity and Quality scatterplot")

White wine:

#whiteWine
acidityWhiteWine<- aggregate(cbind( citric.acid, volatile.acidity, fixed.acidity) ~ quality,
data = whiteWine, mean)


scatterplot(acidityWhiteWine$quality, acidityWhiteWine$citric.acid, xlab="Quality", ylab = "Citric Acid", main="1. Citric Acid and Quality scatterplot")

scatterplot(acidityWhiteWine$quality, acidityWhiteWine$volatile.acidity, xlab="Quality", ylab = "Volatile Acidity", main="2. Volatile Acidity and Quality scatterplot")

scatterplot(acidityWhiteWine$quality, acidityWhiteWine$fixed.acidity, xlab="Quality", ylab = "Fixed Acidity", main="3. Fixed Acidity and Quality scatterplot")

  • Quality of both wine are not depends on same factor. For example Quality of ‘white’ wine negatively correlated with Fixed Acidity while Quality of ‘red’ wine is positively correlated with it.
#correlataion Red wine and Fixed Acidity
cor(redWine$fixed.acidity, redWine$quality)
## [1] 0.1240516
#correlation White wine and Fixed Acidity
cor(whiteWine$fixed.acidity, whiteWine$quality)
## [1] -0.1136628

B. Effect of Residual Sugar, Chlorides, and Free Sulfur Dioxide on quality of wine

Red wine:

#redWine
impactRedWine<- aggregate(cbind( residual.sugar, chlorides, free.sulfur.dioxide) ~ quality,
data = redWine, mean)



scatterplot(impactRedWine$quality, impactRedWine$residual.sugar, xlab="Quality", ylab = "Residual sugar", main="4. Residual Sugar and Quality scatterplot")

scatterplot(impactRedWine$quality, impactRedWine$chlorides, xlab="Quality", ylab = "Chlorides", main="5. Chlorides and Quality scatterplot")
## Warning in smoother(.x, .y, col = col[2], log.x = logged("x"), log.y =
## logged("y"), : could not fit positive part of the spread

scatterplot(impactRedWine$quality, impactRedWine$free.sulfur.dioxide, xlab="Quality", ylab = "Free Sulfur Dioxide", main="6. Free Sulfur Dioxide and Quality scatterplot")

White wine:

#whiteWine
impactWhiteWine<- aggregate(cbind( residual.sugar, chlorides, free.sulfur.dioxide) ~ quality,
data = whiteWine, mean)

scatterplot(impactWhiteWine$quality, impactWhiteWine$residual.sugar, xlab="Quality", ylab = "Residual sugar", main="4. Residual Sugar and Quality scatterplot")

scatterplot(impactWhiteWine$quality, impactWhiteWine$chlorides, xlab="Quality", ylab = "Chlorides", main="5. Chlorides and Quality scatterplot")

scatterplot(impactWhiteWine$quality, impactWhiteWine$free.sulfur.dioxide, xlab="Quality", ylab = "6. Free Sulfur Dioxide", main="Free Sulfur Dioxide and Quality scatterplot")

C. Effect of Total Sulfur Dioxide, Density, pH, Sulphates, and Alcohol on quality of wine

Red wine:

#redWine

impact2RedWine<- aggregate(cbind( total.sulfur.dioxide, density, pH, sulphates, alcohol) ~ quality,
data = redWine, mean)

scatterplot(impact2RedWine$quality, impact2RedWine$total.sulfur.dioxide, xlab="Quality", ylab = "Total Sulfur Dioxide", main="7. Total Sulfur Dioxide and Quality scatterplot")
## Warning in smoother(.x, .y, col = col[2], log.x = logged("x"), log.y =
## logged("y"), : could not fit positive part of the spread

scatterplot(impact2RedWine$quality, impact2RedWine$density, xlab="Quality", ylab = "Density", main="8. Density and Quality scatterplot")

scatterplot(impact2RedWine$quality, impact2RedWine$pH, xlab="Quality", ylab = "pH", main="9. Free pH and Quality scatterplot")

scatterplot(impact2RedWine$quality, impact2RedWine$sulphates, xlab="Quality", ylab = "Sulphates", main="10. Sulphates and Quality scatterplot")

scatterplot(impact2RedWine$quality, impact2RedWine$alcohol, xlab="Quality", ylab = "Alcohol", main="11. Alcohol and Quality scatterplot")

White wine:

#whitedWine
impact2WhiteWine<- aggregate(cbind( total.sulfur.dioxide, density, pH, sulphates, alcohol) ~ quality,
data = whiteWine, mean)

scatterplot(impact2WhiteWine$quality, impact2WhiteWine$total.sulfur.dioxide, xlab="Quality", ylab = "Total Sulfur Dioxide", main="7. Total Sulfur Dioxide and Quality scatterplot")
## Warning in smoother(.x, .y, col = col[2], log.x = logged("x"), log.y =
## logged("y"), : could not fit positive part of the spread

scatterplot(impact2WhiteWine$quality, impact2WhiteWine$density, xlab="Quality", ylab = "Density", main="8. Density and Quality scatterplot")

scatterplot(impact2WhiteWine$quality, impact2WhiteWine$pH, xlab="Quality", ylab = "pH", main="9. Free pH and Quality scatterplot")
## Warning in smoother(.x, .y, col = col[2], log.x = logged("x"), log.y =
## logged("y"), : could not fit positive part of the spread

scatterplot(impact2WhiteWine$quality, impact2WhiteWine$sulphates, xlab="Quality", ylab = "Sulphates", main="10. Sulphates and Quality scatterplot")

scatterplot(impact2WhiteWine$quality, impact2WhiteWine$alcohol, xlab="Quality", ylab = "Alcohol", main="11. Alcohol and Quality scatterplot")
## Warning in smoother(.x, .y, col = col[2], log.x = logged("x"), log.y =
## logged("y"), : could not fit positive part of the spread

10. Comparing best quality wine with the low quality wine of both wines:

We devide the wines in best and normal as the red wine with quality greater than 5 are ‘best Red wine’ and otherwise ‘normal red wine’.

Red wine:

bestRedWine<- redWine[which(redWine$quality > 5),] #bestRedWine
normalRedWine<- redWine[which(redWine$quality <= 5),] #normalRedWine
library(lattice)
par(mfrow=c(1,2))
histogram(bestRedWine$quality, xlab="Sensory score", main="Best Red wine(Quality > 5)", col = "red3")

histogram(normalRedWine$quality, xlab="Sensory score",main="Normal Red wine(Quality <= 5)", col="red3")

par(mfrow=c(1,1))
library(corrgram)
corrgram(bestRedWine[,c(1:5,12)], lower.panel=panel.shade,
         upper.panel=panel.pie, diag.panel = panel.minmax, text.panel = panel.txt,
         main="Corrgram of Best Red wine intercorrelations I") #first five variables with quality of 'best red wine'

corrgram(bestRedWine[,c(6:11,12)], lower.panel=panel.shade,
         upper.panel=panel.pie, diag.panel = panel.minmax, text.panel = panel.txt,
         main="Corrgram of Best Red wine intercorrelations II")#last sex variables with quality of 'best red wine' 

library(corrgram)
corrgram(normalRedWine[,c(1:5,12)], lower.panel=panel.shade,
         upper.panel=panel.pie, diag.panel = panel.minmax, text.panel = panel.txt,
         main="Corrgram of Normal Red wine intercorrelations I")#first five variables with quality of 'normal red wine'

corrgram(normalRedWine[,c(6:11,12)], lower.panel=panel.shade,
         upper.panel=panel.pie, diag.panel = panel.minmax, text.panel = panel.txt,
         main="Corrgram of Normal Red wine intercorrelations II")#first five variables with quality of 'normal red wine'

White

bestWhiteWine<- whiteWine[which(whiteWine$quality > 5),]
normalWhiteWine<- whiteWine[which(whiteWine$quality <= 5),]
library(lattice)
par(mfrow=c(1,2))
histogram(bestWhiteWine$quality, xlab="Sensory score", main="Best White wine(Quality > 5)", col = "seashell1")

histogram(normalWhiteWine$quality, xlab="Sensory score",main="Normal White wine(Quality <= 5)", col="seashell1")

par(mfrow=c(1,1))
library(corrgram)
corrgram(bestWhiteWine[,c(1:5,12)], lower.panel=panel.shade,
         upper.panel=panel.pie, diag.panel = panel.minmax, text.panel = panel.txt,
         main="Corrgram of Best White wine intercorrelations I")#first five variables with quality of 'best white wine'

corrgram(bestWhiteWine[,c(6:11,12)], lower.panel=panel.shade,
         upper.panel=panel.pie, diag.panel = panel.minmax, text.panel = panel.txt,
         main="Corrgram of Best White wine intercorrelations II")#last variables with quality of 'best white wine'

library(corrgram)
corrgram(normalWhiteWine[,c(1:5,12)], lower.panel=panel.shade,
         upper.panel=panel.pie, diag.panel = panel.minmax, text.panel = panel.txt,
         main="Corrgram of Normal White wine intercorrelations I")#first five variables with quality of 'normal white wine'

corrgram(normalWhiteWine[,c(6:11,12)], lower.panel=panel.shade,
         upper.panel=panel.pie, diag.panel = panel.minmax, text.panel = panel.txt,
         main="Corrgram of Normal White wine intercorrelations II")#last six variables with quality of 'normal white wine'