##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
#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
#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
#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
#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, ]
#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)
#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
#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)