##NEW SEGMENT |INSURANCE| ## Predicting Medical Expenses

#Getting the New Data Going #We can see what is identified #We can see other key information

## Step 2: Exploring and preparing the data ----
insurance <- read.csv("insurance.csv", stringsAsFactors = TRUE)
str(insurance)
## 'data.frame':    1338 obs. of  7 variables:
##  $ age     : int  19 18 28 33 32 31 46 37 37 60 ...
##  $ sex     : Factor w/ 2 levels "female","male": 1 2 2 2 2 1 1 1 2 1 ...
##  $ bmi     : num  27.9 33.8 33 22.7 28.9 25.7 33.4 27.7 29.8 25.8 ...
##  $ children: int  0 1 3 0 0 0 1 3 2 0 ...
##  $ smoker  : Factor w/ 2 levels "no","yes": 2 1 1 1 1 1 1 1 1 1 ...
##  $ region  : Factor w/ 4 levels "northeast","northwest",..: 4 3 3 2 2 3 3 2 1 2 ...
##  $ expenses: num  16885 1726 4449 21984 3867 ...

#I don’t think this really gives us any useful information #This shows us how much each of the insurance policies cost when being grouped up #However, It doesn’t compare it to other key information to understand how we got there

# summarize the charges variable
summary(insurance$expenses)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1122    4740    9382   13270   16640   63770

#This shows us the data as a visual #this helps me understand what I am looking at along with what I can compare #IT can show trends versus odd changes that the numbers may not show as easily

# histogram of insurance charges
hist(insurance$expenses)

#it’ll show that there are different data points for different regions #Insurance for the different regions #all are relatively similar amount of Data-Points

# table of region
table(insurance$region)
## 
## northeast northwest southeast southwest 
##       324       325       364       325

#Correlation between AGE,BMI,Kids or not, with total expenses #It shows the difference’s and helps us understand what is

# exploring relationships among features: correlation matrix
cor(insurance[c("age", "bmi", "children", "expenses")])
##                age        bmi   children   expenses
## age      1.0000000 0.10934101 0.04246900 0.29900819
## bmi      0.1093410 1.00000000 0.01264471 0.19857626
## children 0.0424690 0.01264471 1.00000000 0.06799823
## expenses 0.2990082 0.19857626 0.06799823 1.00000000

#Correlation Plot #Compares different variables listed below #gives a visual representation of the data above

# visualing relationships among features: scatterplot matrix
pairs(insurance[c("age", "bmi", "children", "expenses")])

#moving on because all the data looks good no issue’s so we don’t drop any data points

## Step 3: Training a model on the data ----
ins_model <- lm(expenses ~ age + children + bmi + sex + smoker + region,
                data = insurance)
ins_model <- lm(expenses ~ ., data = insurance) # this is equivalent to above

# see the estimated beta coefficients
ins_model
## 
## Call:
## lm(formula = expenses ~ ., data = insurance)
## 
## Coefficients:
##     (Intercept)              age          sexmale              bmi  
##        -11941.6            256.8           -131.4            339.3  
##        children        smokeryes  regionnorthwest  regionsoutheast  
##           475.7          23847.5           -352.8          -1035.6  
## regionsouthwest  
##          -959.3

Step 4: Evaluating model performance

#Compares data to the different regions as well #R SQ & Adjusted are similar as well this is important to note (Dont want a big difference)

# see more detail about the estimated beta coefficients
summary(ins_model)
## 
## Call:
## lm(formula = expenses ~ ., data = insurance)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -11302.7  -2850.9   -979.6   1383.9  29981.7 
## 
## Coefficients:
##                 Estimate Std. Error t value Pr(>|t|)    
## (Intercept)     -11941.6      987.8 -12.089  < 2e-16 ***
## age                256.8       11.9  21.586  < 2e-16 ***
## sexmale           -131.3      332.9  -0.395 0.693255    
## bmi                339.3       28.6  11.864  < 2e-16 ***
## children           475.7      137.8   3.452 0.000574 ***
## smokeryes        23847.5      413.1  57.723  < 2e-16 ***
## regionnorthwest   -352.8      476.3  -0.741 0.458976    
## regionsoutheast  -1035.6      478.7  -2.163 0.030685 *  
## regionsouthwest   -959.3      477.9  -2.007 0.044921 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 6062 on 1329 degrees of freedom
## Multiple R-squared:  0.7509, Adjusted R-squared:  0.7494 
## F-statistic: 500.9 on 8 and 1329 DF,  p-value: < 2.2e-16

Step 5: Improving model performance

#They added new column “AGE2”

# add a higher-order "age" term
insurance$age2 <- insurance$age^2

#Category not Numerical

# add an indicator for BMI >= 30
insurance$bmi30 <- ifelse(insurance$bmi >= 30, 1, 0)
# create final model
ins_model2 <- lm(expenses ~ age + age2 + children + bmi + sex +
                   bmi30*smoker + region, data = insurance)

#Sex Correlation is now signifcant –> #It previously was not, which is odd. Don’t quite understand why

summary(ins_model2)
## 
## Call:
## lm(formula = expenses ~ age + age2 + children + bmi + sex + bmi30 * 
##     smoker + region, data = insurance)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -17297.1  -1656.0  -1262.7   -727.8  24161.6 
## 
## Coefficients:
##                   Estimate Std. Error t value Pr(>|t|)    
## (Intercept)       139.0053  1363.1359   0.102 0.918792    
## age               -32.6181    59.8250  -0.545 0.585690    
## age2                3.7307     0.7463   4.999 6.54e-07 ***
## children          678.6017   105.8855   6.409 2.03e-10 ***
## bmi               119.7715    34.2796   3.494 0.000492 ***
## sexmale          -496.7690   244.3713  -2.033 0.042267 *  
## bmi30            -997.9355   422.9607  -2.359 0.018449 *  
## smokeryes       13404.5952   439.9591  30.468  < 2e-16 ***
## regionnorthwest  -279.1661   349.2826  -0.799 0.424285    
## regionsoutheast  -828.0345   351.6484  -2.355 0.018682 *  
## regionsouthwest -1222.1619   350.5314  -3.487 0.000505 ***
## bmi30:smokeryes 19810.1534   604.6769  32.762  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 4445 on 1326 degrees of freedom
## Multiple R-squared:  0.8664, Adjusted R-squared:  0.8653 
## F-statistic: 781.7 on 11 and 1326 DF,  p-value: < 2.2e-16

#High correlation level #This is higher than I anticipated because of looking at the previous data, but it is better to have a high than a low correlation in this instance #this is because of what we are specifically looking at along with what we are predicting

# making predictions with the regression model
insurance$pred <- predict(ins_model2, insurance)
cor(insurance$pred, insurance$expenses)
## [1] 0.9307999

#Visualization #important to realize that the line is always the “best fit” #it is possible for no points to be on the line if there is a lot of drastic changes

plot(insurance$pred, insurance$expenses)
abline(a = 0, b = 1, col = "red", lwd = 3, lty = 2)

#price difference’s not being explained by gender

predict(ins_model2,
        data.frame(age = 30, age2 = 30^2, children = 2,
                   bmi = 30, sex = "male", bmi30 = 1,
                   smoker = "no", region = "northeast"))
##        1 
## 5973.774

#more expensive for woman then men, which is interesting #they have same parameters with the only difference being gender ****

predict(ins_model2,
        data.frame(age = 30, age2 = 30^2, children = 2,
                   bmi = 30, sex = "female", bmi30 = 1,
                   smoker = "no", region = "northeast"))
##        1 
## 6470.543

#additional price point, with the difference being the number of children

predict(ins_model2,
        data.frame(age = 30, age2 = 30^2, children = 0,
                   bmi = 30, sex = "female", bmi30 = 1,
                   smoker = "no", region = "northeast"))
##       1 
## 5113.34

#Case #1

#In class assignment with new data #This is the new cost

predict(ins_model2,
        data.frame(age = 22, age2 = 22^2, children = 3,
                   bmi = 24, sex = "female", bmi30 = 0,
                   smoker = "no", region = "northwest"))
##        1 
## 5858.241

#Case #2 #This is shocking how much the price increased for a young male with one child compared to a female of the same age #Although, it is important to take into account that this young person is also a smoker #it litterally nearly tripled in price from the non smoker counter part which even had 2 more kids

predict(ins_model2,
        data.frame(age = 22, age2 = 22^2, children = 1,
                   bmi = 27, sex = "male", bmi30 = 0,
                   smoker = "yes", region = "southeast"))
##        1 
## 17219.31

Part 2: Regression Trees and Model Trees

Understanding regression trees and model trees

Example: Calculating SDR

#Setting up data points for the SDR (Standarized Deviation Ratio) #this is crucial to compute the rest

# set up the data
tee <- c(1, 1, 1, 2, 2, 3, 4, 5, 5, 6, 6, 7, 7, 7, 7)
at1 <- c(1, 1, 1, 2, 2, 3, 4, 5, 5)
at2 <- c(6, 6, 7, 7, 7, 7)
bt1 <- c(1, 1, 1, 2, 2, 3, 4)
bt2 <- c(5, 5, 6, 6, 7, 7, 7, 7)

#Identifying to different variables #SDR A&B could be named anything but this is simplistic for the purpose #However, I cannot figure out why data is not being computed here #Upon looking further into it, and looking it up im not sure why this is not working. #this is clearly a base formula that should compute data,

# compute the SDR
sdr_a <-sd(tee) - (length(at1) / length(tee) * sd(at1) + length(at2) / length(tee) * sd(at2))
sdr_b <-sd(tee) - (length(bt1) / length(tee) * sd(bt1) + length(bt2) / length(tee) * sd(bt2))

#Not sure why this is not working #i have played around with potential solutions with no success, I have reverted back to the original and it still isn’t working #unsure if I am missing a package, or library #the only error I am recieving is “error: object ‘sdr_a’ not found –> Even though it is identified the same. #Sdr_b is found but not giving information regarding the split

# compare the SDR for each split
sdr_a
## [1] 1.202815
sdr_b
## [1] 1.392751

Exercise No 3: Estimating Wine Quality

Step 2: Exploring and preparing the data

#I have the document downloaded, and uplaoded in R yet not recieving results.

wine <- read.csv("whitewines.csv")

#it is giving me errors here, yet, it is properly reading the data in the next chunk. #Could be an error with my computer at home I have tried #ASK ABOUT THis **** #Update, figured it out. Had to restart the application for whatever reason #shows lots of informaation about the wine itself

# examine the wine data
str(wine)
## 'data.frame':    4898 obs. of  12 variables:
##  $ fixed.acidity       : num  6.7 5.7 5.9 5.3 6.4 7 7.9 6.6 7 6.5 ...
##  $ volatile.acidity    : num  0.62 0.22 0.19 0.47 0.29 0.14 0.12 0.38 0.16 0.37 ...
##  $ citric.acid         : num  0.24 0.2 0.26 0.1 0.21 0.41 0.49 0.28 0.3 0.33 ...
##  $ residual.sugar      : num  1.1 16 7.4 1.3 9.65 0.9 5.2 2.8 2.6 3.9 ...
##  $ chlorides           : num  0.039 0.044 0.034 0.036 0.041 0.037 0.049 0.043 0.043 0.027 ...
##  $ free.sulfur.dioxide : num  6 41 33 11 36 22 33 17 34 40 ...
##  $ total.sulfur.dioxide: num  62 113 123 74 119 95 152 67 90 130 ...
##  $ density             : num  0.993 0.999 0.995 0.991 0.993 ...
##  $ pH                  : num  3.41 3.22 3.49 3.48 2.99 3.25 3.18 3.21 2.88 3.28 ...
##  $ sulphates           : num  0.32 0.46 0.42 0.54 0.34 0.43 0.47 0.47 0.47 0.39 ...
##  $ alcohol             : num  10.4 8.9 10.1 11.2 10.9 ...
##  $ quality             : int  5 6 6 4 6 6 6 6 6 7 ...

#visual of the quality ratings #Shows the highest frequency compared to the overall quality

# the distribution of quality ratings
hist(wine$quality)

#summary of all statistics with wine #shows all categories data #not data many of us consider when picking out a particular wine #lots of interesting data points to see them listed

# summary statistics of the wine data
summary(wine)
##  fixed.acidity    volatile.acidity  citric.acid     residual.sugar  
##  Min.   : 3.800   Min.   :0.0800   Min.   :0.0000   Min.   : 0.600  
##  1st Qu.: 6.300   1st Qu.:0.2100   1st Qu.:0.2700   1st Qu.: 1.700  
##  Median : 6.800   Median :0.2600   Median :0.3200   Median : 5.200  
##  Mean   : 6.855   Mean   :0.2782   Mean   :0.3342   Mean   : 6.391  
##  3rd Qu.: 7.300   3rd Qu.:0.3200   3rd Qu.:0.3900   3rd Qu.: 9.900  
##  Max.   :14.200   Max.   :1.1000   Max.   :1.6600   Max.   :65.800  
##    chlorides       free.sulfur.dioxide total.sulfur.dioxide    density      
##  Min.   :0.00900   Min.   :  2.00      Min.   :  9.0        Min.   :0.9871  
##  1st Qu.:0.03600   1st Qu.: 23.00      1st Qu.:108.0        1st Qu.:0.9917  
##  Median :0.04300   Median : 34.00      Median :134.0        Median :0.9937  
##  Mean   :0.04577   Mean   : 35.31      Mean   :138.4        Mean   :0.9940  
##  3rd Qu.:0.05000   3rd Qu.: 46.00      3rd Qu.:167.0        3rd Qu.:0.9961  
##  Max.   :0.34600   Max.   :289.00      Max.   :440.0        Max.   :1.0390  
##        pH          sulphates         alcohol         quality     
##  Min.   :2.720   Min.   :0.2200   Min.   : 8.00   Min.   :3.000  
##  1st Qu.:3.090   1st Qu.:0.4100   1st Qu.: 9.50   1st Qu.:5.000  
##  Median :3.180   Median :0.4700   Median :10.40   Median :6.000  
##  Mean   :3.188   Mean   :0.4898   Mean   :10.51   Mean   :5.878  
##  3rd Qu.:3.280   3rd Qu.:0.5500   3rd Qu.:11.40   3rd Qu.:6.000  
##  Max.   :3.820   Max.   :1.0800   Max.   :14.20   Max.   :9.000

#training the program to predict and test wine statistics

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

Step 3: Training a model on the data

#new library being added for training purposes #also creating a new datapoint to correlate

# regression tree using rpart
library(rpart)
m.rpart <- rpart(quality ~ ., data = wine_train)

#information about the wine plants themselves #the plant is what makes the wine variables change so much #the roots change many of the existing variables

# get basic information about the tree
m.rpart
## n= 3750 
## 
## node), split, n, deviance, yval
##       * denotes terminal node
## 
##  1) root 3750 2945.53200 5.870933  
##    2) alcohol< 10.85 2372 1418.86100 5.604975  
##      4) volatile.acidity>=0.2275 1611  821.30730 5.432030  
##        8) volatile.acidity>=0.3025 688  278.97670 5.255814 *
##        9) volatile.acidity< 0.3025 923  505.04230 5.563380 *
##      5) volatile.acidity< 0.2275 761  447.36400 5.971091 *
##    3) alcohol>=10.85 1378 1070.08200 6.328737  
##      6) free.sulfur.dioxide< 10.5 84   95.55952 5.369048 *
##      7) free.sulfur.dioxide>=10.5 1294  892.13600 6.391036  
##       14) alcohol< 11.76667 629  430.11130 6.173291  
##         28) volatile.acidity>=0.465 11   10.72727 4.545455 *
##         29) volatile.acidity< 0.465 618  389.71680 6.202265 *
##       15) alcohol>=11.76667 665  403.99400 6.596992 *

#detailed information about wine itself and how it gets certain levels based on other outcomes #tons of information that I am struggling to fully comprehend the splits truthfully #

# get more detailed information about the tree
summary(m.rpart)
## Call:
## rpart(formula = quality ~ ., data = wine_train)
##   n= 3750 
## 
##           CP nsplit rel error    xerror       xstd
## 1 0.15501053      0 1.0000000 1.0004622 0.02446319
## 2 0.05098911      1 0.8449895 0.8457752 0.02333740
## 3 0.02796998      2 0.7940004 0.8032585 0.02282887
## 4 0.01970128      3 0.7660304 0.7782961 0.02165014
## 5 0.01265926      4 0.7463291 0.7644018 0.02105920
## 6 0.01007193      5 0.7336698 0.7541969 0.02081230
## 7 0.01000000      6 0.7235979 0.7471086 0.02069433
## 
## Variable importance
##              alcohol              density     volatile.acidity 
##                   34                   21                   15 
##            chlorides total.sulfur.dioxide  free.sulfur.dioxide 
##                   11                    7                    6 
##       residual.sugar            sulphates          citric.acid 
##                    3                    1                    1 
## 
## Node number 1: 3750 observations,    complexity param=0.1550105
##   mean=5.870933, MSE=0.7854751 
##   left son=2 (2372 obs) right son=3 (1378 obs)
##   Primary splits:
##       alcohol              < 10.85    to the left,  improve=0.15501050, (0 missing)
##       density              < 0.992035 to the right, improve=0.10915940, (0 missing)
##       chlorides            < 0.0395   to the right, improve=0.07682258, (0 missing)
##       total.sulfur.dioxide < 158.5    to the right, improve=0.04089663, (0 missing)
##       citric.acid          < 0.235    to the left,  improve=0.03636458, (0 missing)
##   Surrogate splits:
##       density              < 0.991995 to the right, agree=0.869, adj=0.644, (0 split)
##       chlorides            < 0.0375   to the right, agree=0.757, adj=0.339, (0 split)
##       total.sulfur.dioxide < 103.5    to the right, agree=0.690, adj=0.155, (0 split)
##       residual.sugar       < 5.375    to the right, agree=0.667, adj=0.094, (0 split)
##       sulphates            < 0.345    to the right, agree=0.647, adj=0.038, (0 split)
## 
## Node number 2: 2372 observations,    complexity param=0.05098911
##   mean=5.604975, MSE=0.5981709 
##   left son=4 (1611 obs) right son=5 (761 obs)
##   Primary splits:
##       volatile.acidity    < 0.2275   to the right, improve=0.10585250, (0 missing)
##       free.sulfur.dioxide < 13.5     to the left,  improve=0.03390500, (0 missing)
##       citric.acid         < 0.235    to the left,  improve=0.03204075, (0 missing)
##       alcohol             < 10.11667 to the left,  improve=0.03136524, (0 missing)
##       chlorides           < 0.0585   to the right, improve=0.01633599, (0 missing)
##   Surrogate splits:
##       pH                   < 3.485    to the left,  agree=0.694, adj=0.047, (0 split)
##       sulphates            < 0.755    to the left,  agree=0.685, adj=0.020, (0 split)
##       total.sulfur.dioxide < 105.5    to the right, agree=0.683, adj=0.011, (0 split)
##       residual.sugar       < 0.75     to the right, agree=0.681, adj=0.007, (0 split)
##       chlorides            < 0.0285   to the right, agree=0.680, adj=0.003, (0 split)
## 
## Node number 3: 1378 observations,    complexity param=0.02796998
##   mean=6.328737, MSE=0.7765472 
##   left son=6 (84 obs) right son=7 (1294 obs)
##   Primary splits:
##       free.sulfur.dioxide  < 10.5     to the left,  improve=0.07699080, (0 missing)
##       alcohol              < 11.76667 to the left,  improve=0.06210660, (0 missing)
##       total.sulfur.dioxide < 67.5     to the left,  improve=0.04438619, (0 missing)
##       residual.sugar       < 1.375    to the left,  improve=0.02905351, (0 missing)
##       fixed.acidity        < 7.35     to the right, improve=0.02613259, (0 missing)
##   Surrogate splits:
##       total.sulfur.dioxide < 53.5     to the left,  agree=0.952, adj=0.214, (0 split)
##       volatile.acidity     < 0.875    to the right, agree=0.940, adj=0.024, (0 split)
## 
## Node number 4: 1611 observations,    complexity param=0.01265926
##   mean=5.43203, MSE=0.5098121 
##   left son=8 (688 obs) right son=9 (923 obs)
##   Primary splits:
##       volatile.acidity    < 0.3025   to the right, improve=0.04540111, (0 missing)
##       alcohol             < 10.05    to the left,  improve=0.03874403, (0 missing)
##       free.sulfur.dioxide < 13.5     to the left,  improve=0.03338886, (0 missing)
##       chlorides           < 0.0495   to the right, improve=0.02574623, (0 missing)
##       citric.acid         < 0.195    to the left,  improve=0.02327981, (0 missing)
##   Surrogate splits:
##       citric.acid          < 0.215    to the left,  agree=0.633, adj=0.141, (0 split)
##       free.sulfur.dioxide  < 20.5     to the left,  agree=0.600, adj=0.063, (0 split)
##       chlorides            < 0.0595   to the right, agree=0.593, adj=0.047, (0 split)
##       residual.sugar       < 1.15     to the left,  agree=0.583, adj=0.023, (0 split)
##       total.sulfur.dioxide < 219.25   to the right, agree=0.582, adj=0.022, (0 split)
## 
## Node number 5: 761 observations
##   mean=5.971091, MSE=0.5878633 
## 
## Node number 6: 84 observations
##   mean=5.369048, MSE=1.137613 
## 
## Node number 7: 1294 observations,    complexity param=0.01970128
##   mean=6.391036, MSE=0.6894405 
##   left son=14 (629 obs) right son=15 (665 obs)
##   Primary splits:
##       alcohol              < 11.76667 to the left,  improve=0.06504696, (0 missing)
##       chlorides            < 0.0395   to the right, improve=0.02758705, (0 missing)
##       fixed.acidity        < 7.35     to the right, improve=0.02750932, (0 missing)
##       pH                   < 3.055    to the left,  improve=0.02307356, (0 missing)
##       total.sulfur.dioxide < 191.5    to the right, improve=0.02186818, (0 missing)
##   Surrogate splits:
##       density              < 0.990885 to the right, agree=0.720, adj=0.424, (0 split)
##       volatile.acidity     < 0.2675   to the left,  agree=0.637, adj=0.253, (0 split)
##       chlorides            < 0.0365   to the right, agree=0.630, adj=0.238, (0 split)
##       residual.sugar       < 1.475    to the left,  agree=0.575, adj=0.126, (0 split)
##       total.sulfur.dioxide < 128.5    to the right, agree=0.574, adj=0.124, (0 split)
## 
## Node number 8: 688 observations
##   mean=5.255814, MSE=0.4054895 
## 
## Node number 9: 923 observations
##   mean=5.56338, MSE=0.5471747 
## 
## Node number 14: 629 observations,    complexity param=0.01007193
##   mean=6.173291, MSE=0.6838017 
##   left son=28 (11 obs) right son=29 (618 obs)
##   Primary splits:
##       volatile.acidity     < 0.465    to the right, improve=0.06897561, (0 missing)
##       total.sulfur.dioxide < 200      to the right, improve=0.04223066, (0 missing)
##       residual.sugar       < 0.975    to the left,  improve=0.03061714, (0 missing)
##       fixed.acidity        < 7.35     to the right, improve=0.02978501, (0 missing)
##       sulphates            < 0.575    to the left,  improve=0.02165970, (0 missing)
##   Surrogate splits:
##       citric.acid          < 0.045    to the left,  agree=0.986, adj=0.182, (0 split)
##       total.sulfur.dioxide < 279.25   to the right, agree=0.986, adj=0.182, (0 split)
## 
## Node number 15: 665 observations
##   mean=6.596992, MSE=0.6075098 
## 
## Node number 28: 11 observations
##   mean=4.545455, MSE=0.9752066 
## 
## Node number 29: 618 observations
##   mean=6.202265, MSE=0.6306098

#commented out, in order to download data

#install.packages("rpart.plot")

#new library #visualization purpsoes allows us to make a detaield diagram

# use the rpart.plot package to create a visualization
library(rpart.plot)

#easy to read diagram that shows correlation and why certain numbers are what they are #many variables to overall alchol % #which i believe is a major part of quality

# a basic decision tree diagram
rpart.plot(m.rpart, digits = 3)

#more detailed numbers to give a better understanding to the overall data #we can see where it comes from and how it is computed

# a few adjustments to the diagram
rpart.plot(m.rpart, digits = 4, fallen.leaves = TRUE, type = 3, extra = 101)

Step 4: Evaluate model performanc

#prediction

# generate predictions for the testing dataset
p.rpart <- predict(m.rpart, wine_test)

#summary of prediction versus actual numbers #interesting to see the predicted data #it is very similar between the predcitions and the actual values

# compare the distribution of predicted values vs. actual values
summary(p.rpart)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   4.545   5.563   5.971   5.893   6.202   6.597
summary(wine_test$quality)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   3.000   5.000   6.000   5.901   6.000   9.000

#signicant correlation

# compare the correlation
cor(p.rpart, wine_test$quality)
## [1] 0.5369525

#identifying actual vs predicted including mean #this will help us correlate the error %

# function to calculate the mean absolute error
MAE <- function(actual, predicted) {
  mean(abs(actual - predicted))  
}

#this is the error % between actual and predicted values

# mean absolute error between predicted and actual values
MAE(p.rpart, wine_test$quality)
## [1] 0.5872652

#5.87%, this is why the decimal point was moved from the previous chunk of .5872 #this allows us to see the total mean %

# mean absolute error between actual values and mean value
mean(wine_train$quality) # result = 5.87
## [1] 5.870933
MAE(5.87, wine_test$quality)
## [1] 0.6722474

Step 5: Improving model performance

#install.packages("plyr")
#install.packages("Cubist")

#cubist does not work #commented out so it can be turned in properly

# train a Cubist Model Tree
#library(Cubist)
#m.cubist <- cubist(x = wine_train[-12], y = wine_train$quality)

#displays not working because cubist doesnt work

# display basic information about the model tree
#m.cubist

#summary not working because cubist doesnt work

# display the tree itself
#summary(m.cubist)

#prediction not working because cubist doesnt work

# generate predictions for the model
#p.cubist <- predict(m.cubist, wine_test)

#summary once again not working cubist issues

# summary statistics about the predictions
#summary(p.cubist)

#cubist issues

# correlation between the predicted and true values
#cor(p.cubist, wine_test$quality)

#cubist issues

# mean absolute error of predicted and true values
# (uses a custom function defined above)
#MAE(wine_test$quality, p.cubist)