library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6      ✔ purrr   0.3.4 
## ✔ tibble  3.1.8      ✔ dplyr   1.0.10
## ✔ tidyr   1.2.1      ✔ stringr 1.4.1 
## ✔ readr   2.1.3      ✔ forcats 0.5.2 
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
library(plotly)
## 
## Attaching package: 'plotly'
## 
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## 
## The following object is masked from 'package:stats':
## 
##     filter
## 
## The following object is masked from 'package:graphics':
## 
##     layout
library(GGally)
## Registered S3 method overwritten by 'GGally':
##   method from   
##   +.gg   ggplot2
library(ggplot2)
library(readr)
library(dplyr)
library(funModeling)
## Warning: package 'funModeling' was built under R version 4.2.2
## Loading required package: Hmisc
## Loading required package: lattice
## Loading required package: survival
## Loading required package: Formula
## 
## Attaching package: 'Hmisc'
## 
## The following object is masked from 'package:plotly':
## 
##     subplot
## 
## The following objects are masked from 'package:dplyr':
## 
##     src, summarize
## 
## The following objects are masked from 'package:base':
## 
##     format.pval, units
## 
## funModeling v.1.9.4 :)
## Examples and tutorials at livebook.datascienceheroes.com
##  / Now in Spanish: librovivodecienciadedatos.ai
## 
## Attaching package: 'funModeling'
## 
## The following object is masked from 'package:GGally':
## 
##     range01
library(lmtest)
## Loading required package: zoo
## 
## Attaching package: 'zoo'
## 
## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric
library(car)
## Loading required package: carData
## 
## Attaching package: 'car'
## 
## The following object is masked from 'package:dplyr':
## 
##     recode
## 
## The following object is masked from 'package:purrr':
## 
##     some
library(MLmetrics)
## Warning: package 'MLmetrics' was built under R version 4.2.2
## 
## Attaching package: 'MLmetrics'
## 
## The following object is masked from 'package:base':
## 
##     Recall
library(e1071)
## Warning: package 'e1071' was built under R version 4.2.2
## 
## Attaching package: 'e1071'
## 
## The following object is masked from 'package:Hmisc':
## 
##     impute
library(rsample)
## Warning: package 'rsample' was built under R version 4.2.2
## 
## Attaching package: 'rsample'
## 
## The following object is masked from 'package:e1071':
## 
##     permutations
library(caret)
## Warning: package 'caret' was built under R version 4.2.2
## 
## Attaching package: 'caret'
## 
## The following objects are masked from 'package:MLmetrics':
## 
##     MAE, RMSE
## 
## The following object is masked from 'package:survival':
## 
##     cluster
## 
## The following object is masked from 'package:purrr':
## 
##     lift
library(ROCR)
## Warning: package 'ROCR' was built under R version 4.2.2
library(partykit)
## Warning: package 'partykit' was built under R version 4.2.2
## Loading required package: grid
## Loading required package: libcoin
## Warning: package 'libcoin' was built under R version 4.2.2
## Loading required package: mvtnorm
titanic <- read.csv("train.csv")
str(titanic)
## 'data.frame':    891 obs. of  12 variables:
##  $ PassengerId: int  1 2 3 4 5 6 7 8 9 10 ...
##  $ Survived   : int  0 1 1 1 0 0 0 0 1 1 ...
##  $ Pclass     : int  3 1 3 1 3 3 1 3 3 2 ...
##  $ Name       : chr  "Braund, Mr. Owen Harris" "Cumings, Mrs. John Bradley (Florence Briggs Thayer)" "Heikkinen, Miss. Laina" "Futrelle, Mrs. Jacques Heath (Lily May Peel)" ...
##  $ Sex        : chr  "male" "female" "female" "female" ...
##  $ Age        : num  22 38 26 35 35 NA 54 2 27 14 ...
##  $ SibSp      : int  1 1 0 1 0 0 0 3 0 1 ...
##  $ Parch      : int  0 0 0 0 0 0 0 1 2 0 ...
##  $ Ticket     : chr  "A/5 21171" "PC 17599" "STON/O2. 3101282" "113803" ...
##  $ Fare       : num  7.25 71.28 7.92 53.1 8.05 ...
##  $ Cabin      : chr  "" "C85" "" "C123" ...
##  $ Embarked   : chr  "S" "C" "S" "S" ...

The name of variables are as follows: 1. PassengerId : Id number 2. Survived : Survival (0 = No, 1 = Yes) 3. Pclass : Ticket class (1 = 1st, 2 = 2nd, 3 = 3rd) 4. Name : Name 5. Sex : Sex 6. Age : Age in years 7. SibSp : # of siblings/spouses aboard the Titanic 8. Parch : # of parents/children aboard the Titanic 9. Ticket : Ticket number 10.Fare : Passenger fare 11.Cabin : Cabin number 12.Embarked : Port of Embarkation C = Cherbourg, Q = Queenstown, S = Southampton

titanic <- titanic %>% 
   select(-PassengerId, -Name, -Ticket, -Fare) %>% 
   mutate(Pclass = as.factor(Pclass),
          SibSp = as.factor(SibSp),
          Parch = as.factor(Parch))
str(titanic)
## 'data.frame':    891 obs. of  8 variables:
##  $ Survived: int  0 1 1 1 0 0 0 0 1 1 ...
##  $ Pclass  : Factor w/ 3 levels "1","2","3": 3 1 3 1 3 3 1 3 3 2 ...
##  $ Sex     : chr  "male" "female" "female" "female" ...
##  $ Age     : num  22 38 26 35 35 NA 54 2 27 14 ...
##  $ SibSp   : Factor w/ 7 levels "0","1","2","3",..: 2 2 1 2 1 1 1 4 1 2 ...
##  $ Parch   : Factor w/ 7 levels "0","1","2","3",..: 1 1 1 1 1 1 1 2 3 1 ...
##  $ Cabin   : chr  "" "C85" "" "C123" ...
##  $ Embarked: chr  "S" "C" "S" "S" ...
titanic %>% 
   is.na() %>% 
  colSums(is.na(titanic))
## Survived   Pclass      Sex      Age    SibSp    Parch    Cabin Embarked 
##        0        0        0      177        0        0        0        0
mean_impute<-function(x){
ifelse(is.na(x),mean(x,na.rm = T),x)
}
Age_1 <- titanic[,4]
Age_1 <- mean_impute(Age_1)
Age_1 <- as.data.frame(Age_1)
titanic_new <- c(titanic, Age_1)
titanic_new <- as.data.frame(titanic_new)
str(titanic_new)
## 'data.frame':    891 obs. of  9 variables:
##  $ Survived: int  0 1 1 1 0 0 0 0 1 1 ...
##  $ Pclass  : Factor w/ 3 levels "1","2","3": 3 1 3 1 3 3 1 3 3 2 ...
##  $ Sex     : chr  "male" "female" "female" "female" ...
##  $ Age     : num  22 38 26 35 35 NA 54 2 27 14 ...
##  $ SibSp   : Factor w/ 7 levels "0","1","2","3",..: 2 2 1 2 1 1 1 4 1 2 ...
##  $ Parch   : Factor w/ 7 levels "0","1","2","3",..: 1 1 1 1 1 1 1 2 3 1 ...
##  $ Cabin   : chr  "" "C85" "" "C123" ...
##  $ Embarked: chr  "S" "C" "S" "S" ...
##  $ Age_1   : num  22 38 26 35 35 ...
titanic_new %>% 
   is.na() %>% 
  colSums(is.na(titanic_new))
## Survived   Pclass      Sex      Age    SibSp    Parch    Cabin Embarked 
##        0        0        0      177        0        0        0        0 
##    Age_1 
##        0
titanic_new1 <- titanic_new %>% 
  select(-Age)
titanic_new1 %>% 
   is.na() %>% 
  colSums(is.na(titanic_new1))
## Survived   Pclass      Sex    SibSp    Parch    Cabin Embarked    Age_1 
##        0        0        0        0        0        0        0        0
summary(titanic_new1)
##     Survived      Pclass      Sex            SibSp   Parch      Cabin          
##  Min.   :0.0000   1:216   Length:891         0:608   0:678   Length:891        
##  1st Qu.:0.0000   2:184   Class :character   1:209   1:118   Class :character  
##  Median :0.0000   3:491   Mode  :character   2: 28   2: 80   Mode  :character  
##  Mean   :0.3838                              3: 16   3:  5                     
##  3rd Qu.:1.0000                              4: 18   4:  4                     
##  Max.   :1.0000                              5:  5   5:  5                     
##                                              8:  7   6:  1                     
##    Embarked             Age_1      
##  Length:891         Min.   : 0.42  
##  Class :character   1st Qu.:22.00  
##  Mode  :character   Median :29.70  
##                     Mean   :29.70  
##                     3rd Qu.:35.00  
##                     Max.   :80.00  
## 
round(prop.table(table(titanic_new1$Survived, titanic_new1$Pclass)),2)
##    
##        1    2    3
##   0 0.09 0.11 0.42
##   1 0.15 0.10 0.13
round(prop.table(table(titanic_new1$Survived, titanic_new1$Sex)),2)
##    
##     female male
##   0   0.09 0.53
##   1   0.26 0.12
round(prop.table(table(titanic_new1$Survived, titanic_new1$SibSp)),2)
##    
##        0    1    2    3    4    5    8
##   0 0.45 0.11 0.02 0.01 0.02 0.01 0.01
##   1 0.24 0.13 0.01 0.00 0.00 0.00 0.00
round(prop.table(table(titanic_new1$Survived, titanic_new1$Parch)),2)
##    
##        0    1    2    3    4    5    6
##   0 0.50 0.06 0.04 0.00 0.00 0.00 0.00
##   1 0.26 0.07 0.04 0.00 0.00 0.00 0.00
round(prop.table(table(titanic_new1$Survived)),2)
## 
##    0    1 
## 0.62 0.38

Preparing Train and Test Dataset (Cross Validation)

set.seed(100)
split_nb <- initial_split(data = titanic_new1, prop = 0.8, strata = Survived)
train_nb <- training(split_nb)
test_nb <- testing(split_nb)
prop.table(table(titanic_new1$Survived))
## 
##         0         1 
## 0.6161616 0.3838384
prop.table(table(titanic_new1$Survived))
## 
##         0         1 
## 0.6161616 0.3838384
prop.table(table(titanic_new1$Survived))
## 
##         0         1 
## 0.6161616 0.3838384

For Decision Tree

set.seed(100)
split_dt <- initial_split(data = titanic_new1, prop = 0.8, strata = Survived)
train_dt <- training(split_dt)
test_dt <- testing(split_dt)
prop.table(table(titanic_new1$Survived))
## 
##         0         1 
## 0.6161616 0.3838384
prop.table(table(train_dt$Survived))
## 
##        0        1 
## 0.616573 0.383427
prop.table(table(test_dt$Survived))
## 
##         0         1 
## 0.6145251 0.3854749

Developing Model For Naive Bayes

model_nb <- naiveBayes(formula = Survived ~., data = titanic_new1, laplace = 1)
model_nb
## 
## Naive Bayes Classifier for Discrete Predictors
## 
## Call:
## naiveBayes.default(x = X, y = Y, laplace = laplace)
## 
## A-priori probabilities:
## Y
##         0         1 
## 0.6161616 0.3838384 
## 
## Conditional probabilities:
##    Pclass
## Y           1         2         3
##   0 0.1467391 0.1775362 0.6757246
##   1 0.3971014 0.2550725 0.3478261
## 
##    Sex
## Y      female      male
##   0 0.1493625 0.8542805
##   1 0.6842105 0.3216374
## 
##    SibSp
## Y            0          1          2          3          4          5
##   0 0.71762590 0.17625899 0.02877698 0.02338129 0.02877698 0.01079137
##   1 0.60458453 0.32378223 0.04011461 0.01432665 0.01146132 0.00286533
##    SibSp
## Y            8
##   0 0.01438849
##   1 0.00286533
## 
##    Parch
## Y             0           1           2           3           4           5
##   0 0.802158273 0.097122302 0.073741007 0.005395683 0.008992806 0.008992806
##   1 0.670487106 0.189111748 0.117478510 0.011461318 0.002865330 0.005730659
##    Parch
## Y             6
##   0 0.003597122
##   1 0.002865330
## 
##    Cabin
## Y                       A10         A14         A16         A19         A20
##   0 0.877959927 0.003642987 0.003642987 0.001821494 0.003642987 0.001821494
##   1 0.605263158 0.002923977 0.002923977 0.005847953 0.002923977 0.005847953
##    Cabin
## Y           A23         A24         A26         A31         A32         A34
##   0 0.001821494 0.003642987 0.001821494 0.001821494 0.003642987 0.001821494
##   1 0.005847953 0.002923977 0.005847953 0.005847953 0.002923977 0.005847953
##    Cabin
## Y           A36          A5          A6          A7        B101        B102
##   0 0.003642987 0.003642987 0.001821494 0.003642987 0.001821494 0.003642987
##   1 0.002923977 0.002923977 0.005847953 0.002923977 0.005847953 0.002923977
##    Cabin
## Y           B18         B19         B20         B22         B28          B3
##   0 0.001821494 0.003642987 0.001821494 0.003642987 0.001821494 0.001821494
##   1 0.008771930 0.002923977 0.008771930 0.005847953 0.008771930 0.005847953
##    Cabin
## Y           B30         B35         B37         B38         B39          B4
##   0 0.003642987 0.001821494 0.003642987 0.003642987 0.001821494 0.001821494
##   1 0.002923977 0.008771930 0.002923977 0.002923977 0.005847953 0.005847953
##    Cabin
## Y           B41         B42         B49          B5         B50 B51 B53 B55
##   0 0.001821494 0.001821494 0.001821494 0.001821494 0.001821494 0.003642987
##   1 0.005847953 0.005847953 0.008771930 0.008771930 0.005847953 0.005847953
##    Cabin
## Y   B57 B59 B63 B66     B58 B60         B69         B71         B73         B77
##   0     0.001821494 0.003642987 0.001821494 0.003642987 0.001821494 0.001821494
##   1     0.008771930 0.005847953 0.005847953 0.002923977 0.005847953 0.008771930
##    Cabin
## Y           B78         B79         B80     B82 B84         B86         B94
##   0 0.001821494 0.001821494 0.001821494 0.003642987 0.003642987 0.003642987
##   1 0.005847953 0.005847953 0.005847953 0.002923977 0.002923977 0.002923977
##    Cabin
## Y       B96 B98        C101        C103        C104        C106        C110
##   0 0.001821494 0.001821494 0.001821494 0.001821494 0.001821494 0.003642987
##   1 0.014619883 0.005847953 0.005847953 0.005847953 0.005847953 0.002923977
##    Cabin
## Y          C111        C118        C123        C124        C125        C126
##   0 0.003642987 0.003642987 0.003642987 0.005464481 0.001821494 0.001821494
##   1 0.002923977 0.002923977 0.005847953 0.002923977 0.008771930 0.008771930
##    Cabin
## Y          C128        C148          C2     C22 C26 C23 C25 C27         C30
##   0 0.003642987 0.001821494 0.003642987 0.005464481 0.005464481 0.003642987
##   1 0.002923977 0.005847953 0.005847953 0.005847953 0.008771930 0.002923977
##    Cabin
## Y           C32         C45         C46         C47         C49         C50
##   0 0.001821494 0.001821494 0.003642987 0.001821494 0.003642987 0.001821494
##   1 0.005847953 0.005847953 0.002923977 0.005847953 0.002923977 0.005847953
##    Cabin
## Y           C52         C54     C62 C64         C65         C68          C7
##   0 0.001821494 0.001821494 0.001821494 0.003642987 0.003642987 0.001821494
##   1 0.008771930 0.005847953 0.005847953 0.005847953 0.005847953 0.005847953
##    Cabin
## Y           C70         C78         C82         C83         C85         C86
##   0 0.001821494 0.003642987 0.003642987 0.003642987 0.001821494 0.003642987
##   1 0.005847953 0.005847953 0.002923977 0.005847953 0.005847953 0.002923977
##    Cabin
## Y           C87         C90         C91         C92         C93         C95
##   0 0.003642987 0.001821494 0.003642987 0.001821494 0.001821494 0.003642987
##   1 0.002923977 0.005847953 0.002923977 0.008771930 0.008771930 0.002923977
##    Cabin
## Y           C99           D     D10 D12         D11         D15         D17
##   0 0.001821494 0.003642987 0.001821494 0.001821494 0.001821494 0.001821494
##   1 0.005847953 0.008771930 0.005847953 0.005847953 0.005847953 0.008771930
##    Cabin
## Y           D19         D20         D21         D26         D28         D30
##   0 0.001821494 0.001821494 0.001821494 0.005464481 0.001821494 0.003642987
##   1 0.005847953 0.008771930 0.005847953 0.002923977 0.005847953 0.002923977
##    Cabin
## Y           D33         D35         D36         D37         D45         D46
##   0 0.001821494 0.001821494 0.001821494 0.001821494 0.001821494 0.003642987
##   1 0.008771930 0.008771930 0.008771930 0.005847953 0.005847953 0.002923977
##    Cabin
## Y           D47         D48         D49         D50         D56          D6
##   0 0.001821494 0.003642987 0.001821494 0.003642987 0.001821494 0.003642987
##   1 0.005847953 0.002923977 0.005847953 0.002923977 0.005847953 0.002923977
##    Cabin
## Y            D7          D9         E10        E101         E12        E121
##   0 0.001821494 0.001821494 0.001821494 0.001821494 0.001821494 0.001821494
##   1 0.005847953 0.005847953 0.005847953 0.011695906 0.005847953 0.008771930
##    Cabin
## Y           E17         E24         E25         E31         E33         E34
##   0 0.001821494 0.001821494 0.001821494 0.003642987 0.001821494 0.001821494
##   1 0.005847953 0.008771930 0.008771930 0.002923977 0.008771930 0.005847953
##    Cabin
## Y           E36         E38         E40         E44         E46         E49
##   0 0.001821494 0.003642987 0.001821494 0.003642987 0.003642987 0.001821494
##   1 0.005847953 0.002923977 0.005847953 0.005847953 0.002923977 0.005847953
##    Cabin
## Y           E50         E58         E63         E67         E68         E77
##   0 0.001821494 0.003642987 0.003642987 0.003642987 0.001821494 0.003642987
##   1 0.005847953 0.002923977 0.002923977 0.005847953 0.005847953 0.002923977
##    Cabin
## Y            E8       F E69       F G63       F G73          F2         F33
##   0 0.001821494 0.001821494 0.003642987 0.005464481 0.003642987 0.001821494
##   1 0.008771930 0.005847953 0.002923977 0.002923977 0.008771930 0.011695906
##    Cabin
## Y           F38          F4          G6           T
##   0 0.003642987 0.001821494 0.005464481 0.003642987
##   1 0.002923977 0.008771930 0.008771930 0.002923977
## 
##    Embarked
## Y                         C           Q           S
##   0 0.001821494 0.138433515 0.087431694 0.779599271
##   1 0.008771930 0.274853801 0.090643275 0.637426901
## 
##    Age_1
## Y       [,1]     [,2]
##   0 30.41510 12.45737
##   1 28.54978 13.77250

For Random Forest

model_rf <- train(form = Survived ~., data = titanic_new1)
## Warning in train.default(x, y, weights = w, ...): You are trying to do
## regression and your outcome only has two possible values Are you trying to do
## classification? If so, use a 2 level factor as your outcome column.
## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?

## Warning in randomForest.default(x, y, mtry = param$mtry, ...): The response has
## five or fewer unique values. Are you sure you want to do regression?
model_rf
## Random Forest 
## 
## 891 samples
##   7 predictor
## 
## No pre-processing
## Resampling: Bootstrapped (25 reps) 
## Summary of sample sizes: 891, 891, 891, 891, 891, 891, ... 
## Resampling results across tuning parameters:
## 
##   mtry  RMSE       Rsquared   MAE      
##     2   0.4721908  0.3353219  0.4570699
##    84   0.3886766  0.3829849  0.2481347
##   166   0.4027872  0.3584555  0.2423302
## 
## RMSE was used to select the optimal model using the smallest value.
## The final value used for the model was mtry = 84.
pred_nb <- predict(model_nb, test_nb)
head(pred_nb)
## [1] 0 0 1 0 1 0
## Levels: 0 1