Collecting data, exploring and preparing the data

wine <- read.csv("C:/Users/Justice2/Desktop/Machine Learning & Data Science/R/data/whitewines.csv")
str(wine)
## 'data.frame':    4898 obs. of  12 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 ...
hist(wine$quality,col="brown")

wine_train <- wine[1:3750, ]
wine_test <- wine[3751:4898, ]

Training a model on the data

library(rpart)
m.rpart <- rpart(quality ~ ., data = wine_train)
m.rpart
## n= 3750 
## 
## node), split, n, deviance, yval
##       * denotes terminal node
## 
##  1) root 3750 3140.06000 5.886933  
##    2) alcohol< 10.85 2473 1510.66200 5.609381  
##      4) volatile.acidity>=0.2425 1406  740.15080 5.402560  
##        8) volatile.acidity>=0.4225 182   92.99451 4.994505 *
##        9) volatile.acidity< 0.4225 1224  612.34560 5.463235 *
##      5) volatile.acidity< 0.2425 1067  631.12090 5.881912 *
##    3) alcohol>=10.85 1277 1069.95800 6.424432  
##      6) free.sulfur.dioxide< 11.5 93   99.18280 5.473118 *
##      7) free.sulfur.dioxide>=11.5 1184  879.99920 6.499155  
##       14) alcohol< 11.85 611  447.38130 6.296236 *
##       15) alcohol>=11.85 573  380.63180 6.715532 *

Visualizing decision trees

library(rpart.plot)
rpart.plot(m.rpart, digits = 3)

rpart.plot(m.rpart, digits = 4, fallen.leaves = TRUE,type = 3, extra = 101)

Evaluating model performance

p.rpart <- predict(m.rpart, wine_test)
summary(p.rpart)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   4.995   5.463   5.882   5.999   6.296   6.716
summary(wine_test$quality)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   3.000   5.000   6.000   5.848   6.000   8.000
cor(p.rpart, wine_test$quality)
## [1] 0.4931608

Measuring performance with the mean absolute error

MAE <- function(actual, predicted) {
                                    mean(abs(actual - predicted))
                                    }
MAE(p.rpart, wine_test$quality)
## [1] 0.5732104
mean(wine_train$quality)
## [1] 5.886933
MAE(5.87, wine_test$quality)
## [1] 0.5815679

Improving model performance

library(RWeka)
m.m5p <- M5P(quality ~ ., data = wine_train)
m.m5p
## M5 pruned model tree:
## (using smoothed linear models)
## 
## alcohol <= 10.85 : LM1 (2473/77.476%)
## alcohol >  10.85 : 
## |   free.sulfur.dioxide <= 20.5 : 
## |   |   free.sulfur.dioxide <= 10.5 : LM2 (81/104.574%)
## |   |   free.sulfur.dioxide >  10.5 : LM3 (224/87.002%)
## |   free.sulfur.dioxide >  20.5 : LM4 (972/84.073%)
## 
## LM num: 1
## quality = 
##  0.0777 * fixed.acidity 
##  - 2.3087 * volatile.acidity 
##  + 0.0732 * residual.sugar 
##  + 0.0022 * free.sulfur.dioxide 
##  - 155.0175 * density 
##  + 0.6462 * pH 
##  + 0.7923 * sulphates 
##  + 0.0758 * alcohol 
##  + 156.2102
## 
## LM num: 2
## quality = 
##  -0.0314 * fixed.acidity 
##  - 0.3415 * volatile.acidity 
##  + 1.7929 * citric.acid 
##  + 0.1316 * residual.sugar 
##  - 0.2456 * chlorides 
##  + 0.1212 * free.sulfur.dioxide 
##  - 178.6281 * density 
##  + 0.054 * pH 
##  + 0.1392 * sulphates 
##  + 0.0108 * alcohol 
##  + 180.6069
## 
## LM num: 3
## quality = 
##  -0.2019 * fixed.acidity 
##  - 2.3804 * volatile.acidity 
##  - 1.0851 * citric.acid 
##  + 0.0905 * residual.sugar 
##  - 0.2456 * chlorides 
##  + 0.0041 * free.sulfur.dioxide 
##  - 177.078 * density 
##  + 0.054 * pH 
##  + 0.0868 * sulphates 
##  + 0.0108 * alcohol 
##  + 183.5076
## 
## LM num: 4
## quality = 
##  0.0004 * fixed.acidity 
##  - 0.0325 * volatile.acidity 
##  + 0.0957 * residual.sugar 
##  - 5.9702 * chlorides 
##  + 0.0002 * free.sulfur.dioxide 
##  - 172.3931 * density 
##  + 1.0123 * pH 
##  + 1.1653 * sulphates 
##  + 0.1542 * alcohol 
##  + 171.6842
## 
## Number of Rules : 4
summary(m.m5p)
## 
## === Summary ===
## 
## Correlation coefficient                  0.5932
## Mean absolute error                      0.5804
## Root mean squared error                  0.7367
## Relative absolute error                 83.3671 %
## Root relative squared error             80.507  %
## Total Number of Instances             3750
p.m5p <- predict(m.m5p, wine_test)
summary(p.m5p)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   4.170   5.646   6.032   6.079   6.501   7.913
cor(p.m5p, wine_test$quality)
## [1] 0.531723
MAE(wine_test$quality, p.m5p)
## [1] 0.5660352