Ekonometri Final projesi

library(readr)
train <- read_csv("~/train.csv")

library(readr)
test <- read_csv("~/test.csv")

library(rmarkdown)

paged_table(train)

paged_table(test)

train.csv - Yolcuların yaklaşık üçte ikisinin (~8700) kişisel kayıtları, eğitim verileri olarak kullanılacak. PassengerId - Her yolcu için benzersiz bir Kimlik. Her Kimlik gggg_pp biçimini alır; burada gggg yolcunun birlikte seyahat ettiği grubu belirtir ve pp grup içindeki numaradır. Bir gruptaki insanlar çoğunlukla aile üyeleridir, ancak her zaman değil.

HomePlanet - Yolcunun ayrıldığı gezegen, genellikle daimi ikamet ettikleri gezegen.

CryoSleep - Yolcunun yolculuk süresince askıya alınmış animasyona alınmayı seçip seçmediğini gösterir. Dondurarak uykudaki yolcular kabinlerine hapsedilir.

Kabin - Yolcunun kaldığı kabin numarası. Güverte/numara/yan formunu alır; burada taraf, İskele için P veya Sancak için S olabilir. Hedef - Yolcunun gemiden ineceği gezegen.

Age - Yolcunun yaşı.

VIP - Yolcunun yolculuk sırasında özel VIP hizmeti için ödeme yapıp yapmadığı.

RoomService, FoodCourt, Alışveriş Merkezi, Spa, VRDeck - Yolcunun, Spaceship Titanic’in birçok lüks olanağının her birinde fatura ettiği tutar.

Name - Yolcunun adı ve soyadı.

Transported - Yolcunun başka bir boyuta taşınıp taşınmadığı. Bu hedeftir, tahmin etmeye çalıştığınız sütundur.

test.csv - Yolcuların geri kalan üçte birinin (~4300) kişisel kayıtları, test verisi olarak kullanılacak. Göreviniz bu setteki yolcular için Taşınan değerini tahmin etmektir.

sample_submission.csv - Doğru formatta bir gönderim dosyası.

PassengerId - Test setindeki her yolcunun kimliği.

Transported - Hedef.Her yolcu için Doğru veya Yanlış’ı tahmin edin.

library(tidyverse)

library(explore)

train %>% describe_all()

## # A tibble: 14 × 8
##    variable     type     na na_pct unique   min   mean   max
##    <chr>        <chr> <int>  <dbl>  <int> <dbl>  <dbl> <dbl>
##  1 PassengerId  chr       0    0     8693    NA  NA       NA
##  2 HomePlanet   chr     201    2.3      4    NA  NA       NA
##  3 CryoSleep    lgl     217    2.5      3     0   0.36     1
##  4 Cabin        chr     199    2.3   6561    NA  NA       NA
##  5 Destination  chr     182    2.1      4    NA  NA       NA
##  6 Age          dbl     179    2.1     81     0  28.8     79
##  7 VIP          lgl     203    2.3      3     0   0.02     1
##  8 RoomService  dbl     181    2.1   1274     0 225.   14327
##  9 FoodCourt    dbl     183    2.1   1508     0 458.   29813
## 10 ShoppingMall dbl     208    2.4   1116     0 174.   23492
## 11 Spa          dbl     183    2.1   1328     0 311.   22408
## 12 VRDeck       dbl     188    2.2   1307     0 305.   24133
## 13 Name         chr     200    2.3   8474    NA  NA       NA
## 14 Transported  lgl       0    0        2     0   0.5      1

test %>% describe_all()

## # A tibble: 13 × 8
##    variable     type     na na_pct unique   min   mean   max
##    <chr>        <chr> <int>  <dbl>  <int> <dbl>  <dbl> <dbl>
##  1 PassengerId  chr       0    0     4277    NA  NA       NA
##  2 HomePlanet   chr      87    2        4    NA  NA       NA
##  3 CryoSleep    lgl      93    2.2      3     0   0.37     1
##  4 Cabin        chr     100    2.3   3266    NA  NA       NA
##  5 Destination  chr      92    2.2      4    NA  NA       NA
##  6 Age          dbl      91    2.1     80     0  28.7     79
##  7 VIP          lgl      93    2.2      3     0   0.02     1
##  8 RoomService  dbl      82    1.9    843     0 219.   11567
##  9 FoodCourt    dbl     106    2.5    903     0 439.   25273
## 10 ShoppingMall dbl      98    2.3    716     0 177.    8292
## 11 Spa          dbl     101    2.4    834     0 303.   19844
## 12 VRDeck       dbl      80    1.9    797     0 311.   22272
## 13 Name         chr      94    2.2   4177    NA  NA       NA

train[c('group','pp')] <- str_split_fixed(train$PassengerId,'_',2)
test[c('group','pp')] <- str_split_fixed(test$PassengerId,'_',2)

head(train[, c("PassengerId", "group", "pp")])

## # A tibble: 6 × 3
##   PassengerId group pp   
##   <chr>       <chr> <chr>
## 1 0001_01     0001  01   
## 2 0002_01     0002  01   
## 3 0003_01     0003  01   
## 4 0003_02     0003  02   
## 5 0004_01     0004  01   
## 6 0005_01     0005  01

train$withgroup <- ifelse(duplicated(train$group)|duplicated(train$group,fromLast = TRUE),1,0)

test$withgroup <- ifelse(duplicated(test$group)|duplicated(test$group,fromLast = TRUE),1,0)

head(train[, c("PassengerId", "group", "pp","withgroup")])

## # A tibble: 6 × 4
##   PassengerId group pp    withgroup
##   <chr>       <chr> <chr>     <dbl>
## 1 0001_01     0001  01            0
## 2 0002_01     0002  01            0
## 3 0003_01     0003  01            1
## 4 0003_02     0003  02            1
## 5 0004_01     0004  01            0
## 6 0005_01     0005  01            0

train[c('deck','num','side')] <- str_split_fixed(train$Cabin, '/',3)

test[c('deck','num','side')] <- str_split_fixed(test$Cabin, '/',3)

train <- train %>% mutate_if(is.character,as.factor)

test <- test %>% mutate_if(is.character,as.factor)

summary(train)

##   PassengerId    HomePlanet   CryoSleep           Cabin     
##  0001_01:   1   Earth :4602   Mode :logical   G/734/S:   8  
##  0002_01:   1   Europa:2131   FALSE:5439      B/11/S :   7  
##  0003_01:   1   Mars  :1759   TRUE :3037      B/201/P:   7  
##  0003_02:   1   NA's  : 201   NA's :217       B/82/S :   7  
##  0004_01:   1                                 C/137/S:   7  
##  0005_01:   1                                 (Other):8458  
##  (Other):8687                                 NA's   : 199  
##         Destination        Age           VIP           RoomService     
##  55 Cancri e  :1800   Min.   : 0.00   Mode :logical   Min.   :    0.0  
##  PSO J318.5-22: 796   1st Qu.:19.00   FALSE:8291      1st Qu.:    0.0  
##  TRAPPIST-1e  :5915   Median :27.00   TRUE :199       Median :    0.0  
##  NA's         : 182   Mean   :28.83   NA's :203       Mean   :  224.7  
##                       3rd Qu.:38.00                   3rd Qu.:   47.0  
##                       Max.   :79.00                   Max.   :14327.0  
##                       NA's   :179                     NA's   :181      
##    FoodCourt        ShoppingMall          Spa              VRDeck       
##  Min.   :    0.0   Min.   :    0.0   Min.   :    0.0   Min.   :    0.0  
##  1st Qu.:    0.0   1st Qu.:    0.0   1st Qu.:    0.0   1st Qu.:    0.0  
##  Median :    0.0   Median :    0.0   Median :    0.0   Median :    0.0  
##  Mean   :  458.1   Mean   :  173.7   Mean   :  311.1   Mean   :  304.9  
##  3rd Qu.:   76.0   3rd Qu.:   27.0   3rd Qu.:   59.0   3rd Qu.:   46.0  
##  Max.   :29813.0   Max.   :23492.0   Max.   :22408.0   Max.   :24133.0  
##  NA's   :183       NA's   :208       NA's   :183       NA's   :188      
##                  Name      Transported         group            pp      
##  Alraium Disivering:   2   Mode :logical   0984   :   8   01     :6217  
##  Ankalik Nateansive:   2   FALSE:4315      4005   :   8   02     :1412  
##  Anton Woody       :   2   TRUE :4378      4256   :   8   03     : 571  
##  Apix Wala         :   2                   4498   :   8   04     : 231  
##  Asch Stradick     :   2                   5133   :   8   05     : 128  
##  (Other)           :8483                   5756   :   8   06     :  75  
##  NA's              : 200                   (Other):8645   (Other):  59  
##    withgroup           deck           num       side    
##  Min.   :0.0000   F      :2794          : 199    : 199  
##  1st Qu.:0.0000   G      :2559   82     :  28   P:4206  
##  Median :0.0000   E      : 876   19     :  22   S:4288  
##  Mean   :0.4473   B      : 779   86     :  22           
##  3rd Qu.:1.0000   C      : 747   176    :  21           
##  Max.   :1.0000   (Other): 739   56     :  21           
##                   NA's   : 199   (Other):8380

train[train ==''] <- NA
test[test ==''] <- NA

train$num <- droplevels(train$num)
test$num <- droplevels(test$num)
train$side <- droplevels(train$side)
test$side <- droplevels(test$side)

Bosluklari dolduralim

library(zoo)

## 
## Attachement du package : 'zoo'

## Les objets suivants sont masqués depuis 'package:base':
## 
##     as.Date, as.Date.numeric

train <- train %>%
group_by(group) %>%
mutate(HomePlanet = na.locf(HomePlanet,na.rm = FALSE))

test <- test %>%
group_by(group) %>%
mutate(HomePlanet = na.locf(HomePlanet,na.rm = FALSE))

most_frequent_hp <- train %>%
filter(! is.na(HomePlanet)) %>%
group_by(Destination,HomePlanet) %>%
summarize(count = n()) %>%
arrange(Destination,desc(count)) %>%
slice(1) %>%
ungroup()

## `summarise()` has grouped output by 'Destination'. You can override using the
## `.groups` argument.

most_frequent_hp

## # A tibble: 4 × 3
##   Destination   HomePlanet count
##   <fct>         <fct>      <int>
## 1 55 Cancri e   Europa       893
## 2 PSO J318.5-22 Earth        715
## 3 TRAPPIST-1e   Earth       3116
## 4 <NA>          Earth         99

train$HomePlanet <- as.character(train$HomePlanet)
train$Destination <- as.character(train$Destination)

train <- train %>% 
mutate(HomePlanet = ifelse(is.na(HomePlanet) & Destination == "55 Cancri e","Europa" ,
ifelse(is.na(HomePlanet), "Earth",HomePlanet)))

test$HomePlanet <- as.character(test$HomePlanet)
test$Destination <- as.character(test$Destination)

test <- test %>% 
mutate(HomePlanet = ifelse(is.na(HomePlanet) & Destination == "55 Cancri e","Europa" ,
ifelse(is.na(HomePlanet), "Earth",HomePlanet)))

train %>% describe_all()

## # A tibble: 20 × 8
##    variable     type     na na_pct unique   min   mean   max
##    <chr>        <chr> <int>  <dbl>  <int> <dbl>  <dbl> <dbl>
##  1 PassengerId  fct       0    0     8693    NA  NA       NA
##  2 HomePlanet   chr       4    0        4    NA  NA       NA
##  3 CryoSleep    lgl     217    2.5      3     0   0.36     1
##  4 Cabin        fct     199    2.3   6561    NA  NA       NA
##  5 Destination  chr     182    2.1      4    NA  NA       NA
##  6 Age          dbl     179    2.1     81     0  28.8     79
##  7 VIP          lgl     203    2.3      3     0   0.02     1
##  8 RoomService  dbl     181    2.1   1274     0 225.   14327
##  9 FoodCourt    dbl     183    2.1   1508     0 458.   29813
## 10 ShoppingMall dbl     208    2.4   1116     0 174.   23492
## 11 Spa          dbl     183    2.1   1328     0 311.   22408
## 12 VRDeck       dbl     188    2.2   1307     0 305.   24133
## 13 Name         fct     200    2.3   8474    NA  NA       NA
## 14 Transported  lgl       0    0        2     0   0.5      1
## 15 group        fct       0    0     6217    NA  NA       NA
## 16 pp           fct       0    0        8    NA  NA       NA
## 17 withgroup    dbl       0    0        2     0   0.45     1
## 18 deck         fct     199    2.3      9    NA  NA       NA
## 19 num          fct     199    2.3   1818    NA  NA       NA
## 20 side         fct     199    2.3      3    NA  NA       NA

test %>% describe_all()

## # A tibble: 19 × 8
##    variable     type     na na_pct unique   min   mean   max
##    <chr>        <chr> <int>  <dbl>  <int> <dbl>  <dbl> <dbl>
##  1 PassengerId  fct       0    0     4277    NA  NA       NA
##  2 HomePlanet   chr       0    0        3    NA  NA       NA
##  3 CryoSleep    lgl      93    2.2      3     0   0.37     1
##  4 Cabin        fct     100    2.3   3266    NA  NA       NA
##  5 Destination  chr      92    2.2      4    NA  NA       NA
##  6 Age          dbl      91    2.1     80     0  28.7     79
##  7 VIP          lgl      93    2.2      3     0   0.02     1
##  8 RoomService  dbl      82    1.9    843     0 219.   11567
##  9 FoodCourt    dbl     106    2.5    903     0 439.   25273
## 10 ShoppingMall dbl      98    2.3    716     0 177.    8292
## 11 Spa          dbl     101    2.4    834     0 303.   19844
## 12 VRDeck       dbl      80    1.9    797     0 311.   22272
## 13 Name         fct      94    2.2   4177    NA  NA       NA
## 14 group        fct       0    0     3063    NA  NA       NA
## 15 pp           fct       0    0        8    NA  NA       NA
## 16 withgroup    dbl       0    0        2     0   0.45     1
## 17 deck         fct     100    2.3      9    NA  NA       NA
## 18 num          fct     100    2.3   1506    NA  NA       NA
## 19 side         fct     100    2.3      3    NA  NA       NA

train <- transform(train,HomePlanet = replace(HomePlanet, is.na(HomePlanet),"Earth" ))

most_frequent_destinations <- train %>%
filter(!is.na(Destination)) %>%
group_by(HomePlanet,Destination) %>%
summarize(count = n()) %>%
arrange(HomePlanet,desc(count)) %>%
slice(1) %>%
ungroup()

## `summarise()` has grouped output by 'HomePlanet'. You can override using the
## `.groups` argument.

most_frequent_destinations

## # A tibble: 3 × 3
##   HomePlanet Destination count
##   <chr>      <chr>       <int>
## 1 Earth      TRAPPIST-1e  3221
## 2 Europa     TRAPPIST-1e  1204
## 3 Mars       TRAPPIST-1e  1490

train <- transform(train,Destination = replace(Destination,is.na(Destination), "TRAPPIST-1e"))

test <- transform(test,Destination = replace(Destination,is.na(Destination), "TRAPPIST-1e"))

train$HomePlanet <- as.factor(train$HomePlanet)
train$Destination <- as.factor(train$Destination)
test$HomePlanet <- as.factor(test$HomePlanet)
test$Destination <- as.factor(test$Destination)

train <- train %>%
mutate(RoomService = coalesce(RoomService, 0),
FoodCourt = coalesce(FoodCourt, 0),
ShoppingMall = coalesce(ShoppingMall, 0),
Spa = coalesce(Spa, 0),
VRDeck = coalesce(VRDeck, 0))

test <- test %>%
mutate(RoomService = coalesce(RoomService, 0),
FoodCourt = coalesce(FoodCourt, 0),
ShoppingMall = coalesce(ShoppingMall, 0),
Spa = coalesce(Spa, 0),
VRDeck = coalesce(VRDeck, 0))

train <- train %>%
group_by(HomePlanet,Destination) %>%
  mutate_at(vars(Age), ~replace_na(.,mean(., na.rm = TRUE)))

test <- test %>%
group_by(HomePlanet,Destination) %>%
  mutate_at(vars(Age), ~replace_na(.,mean(., na.rm = TRUE)))

train$expense <- train$RoomService + train$FoodCourt + train$ShoppingMall + train$Spa + train$VRDeck

test$expense <- test$RoomService + test$FoodCourt + test$ShoppingMall + test$Spa + test$VRDeck

train <- transform(train,CryoSleep = replace(CryoSleep, is.na(CryoSleep) & expense>0 & Age>12, "FALSE"))

test <- transform(test,CryoSleep = replace(CryoSleep, is.na(CryoSleep) & expense>0 & Age>12, "FALSE"))

train <- transform(train,CryoSleep = replace(CryoSleep,is.na(CryoSleep) & expense==0 & Age>12, "TRUE"))

test <- transform(test,CryoSleep = replace(CryoSleep,is.na(CryoSleep) & expense==0 & Age>12, "TRUE"))

train <- transform(train,CryoSleep = replace(CryoSleep, is.na(CryoSleep), "FALSE"))

test <- transform(train,CryoSleep = replace(CryoSleep, is.na(CryoSleep), "FALSE"))

train$CryoSleep <- as.factor(train$CryoSleep)
test$CryoSleep <- as.factor(test$CryoSleep)

train <- transform(train, VIP = replace(VIP, is.na(VIP),FALSE))

test <- transform(test, VIP = replace(VIP, is.na(VIP),FALSE))

train <- train %>%
group_by(group) %>%
mutate(deck = na.locf(deck, na.rm = FALSE))

test <- test %>%
group_by(group) %>%
mutate(deck = na.locf(deck, na.rm = FALSE))

train <- train %>%
group_by(group) %>%
mutate(side = na.locf(side, na.rm = FALSE))

test <- test %>%
group_by(group) %>%
mutate(side = na.locf(side, na.rm = FALSE))

most_frequent_decks <- train %>%
filter(!is.na(deck)) %>%
group_by(HomePlanet,deck) %>%
summarize(count = n()) %>%
arrange(HomePlanet,desc(count)) %>%
slice(1) %>%
ungroup()

## `summarise()` has grouped output by 'HomePlanet'. You can override using the
## `.groups` argument.

most_frequent_decks

## # A tibble: 3 × 3
##   HomePlanet deck  count
##   <fct>      <fct> <int>
## 1 Earth      G      2576
## 2 Europa     B       787
## 3 Mars       F      1122

train$HomePlanet <- as.character(train$HomePlanet)
train$deck <- as.character(train$deck)

test$HomePlanet <- as.character(train$HomePlanet)
test$deck <- as.character(train$deck)

train <- train %>% 
mutate(deck = ifelse(is.na(deck) & HomePlanet == "Earth", "G",
ifelse(is.na(deck) & HomePlanet == "Europa", "B",
ifelse(is.na(deck) & HomePlanet == "Mars", "F", deck))))

test <- test %>% 
mutate(deck = ifelse(is.na(deck) & HomePlanet == "Earth", "G",
ifelse(is.na(deck) & HomePlanet == "Europa", "B",
ifelse(is.na(deck) & HomePlanet == "Mars", "F", deck))))

most_frequent_sides <- train %>%
filter(!is.na(side)) %>%
group_by(HomePlanet,side) %>%
summarize(count = n()) %>%
arrange(HomePlanet,desc(count)) %>%
slice(1) %>%
ungroup()

## `summarise()` has grouped output by 'HomePlanet'. You can override using the
## `.groups` argument.

most_frequent_sides

## # A tibble: 3 × 3
##   HomePlanet side  count
##   <chr>      <fct> <int>
## 1 Earth      P      2352
## 2 Europa     S      1155
## 3 Mars       P       900

train$HomePlanet <- as.character(train$HomePlanet)
train$side <- as.character(train$side)

test$omePlanet <- as.character(train$HomePlanet)
test$side <- as.character(train$side)

train <- train %>% 
mutate(side = ifelse(is.na(side) & HomePlanet == "Earth", "P",
ifelse(is.na(side) & HomePlanet == "Europa", "S",
ifelse(is.na(side) & HomePlanet == "Mars", "P", side))))

test <- test %>% 
mutate(side = ifelse(is.na(side) & HomePlanet == "Earth", "P",
ifelse(is.na(side) & HomePlanet == "Europa", "S",
ifelse(is.na(side) & HomePlanet == "Mars", "P", side))))

train <- train %>% select(-c("Cabin", "Name", "group", "pp", "num"))

## Adding missing grouping variables: `group`

test <- test %>% select(-c("Cabin", "Name", "group", "pp", "num"))

## Adding missing grouping variables: `group`

train <- train %>% mutate_if(is.character,as.factor)

## `mutate_if()` ignored the following grouping variables:
## • Column `group`

test <- test %>% mutate_if(is.character,as.factor)

## `mutate_if()` ignored the following grouping variables:
## • Column `group`

train$PassengerId <- as.character(train$PassengerId)

test$PassengerId <- as.character(test$PassengerId)

train$group <- NULL

test$group <- NULL

summary(train)

##  PassengerId         HomePlanet   CryoSleep           Destination  
##  Length:8693        Europa:2174   FALSE:5581   55 Cancri e  :1800  
##  Class :character   Earth :4743   TRUE :3112   PSO J318.5-22: 796  
##  Mode  :character   Mars  :1776                TRAPPIST-1e  :6097  
##                                                                    
##                                                                    
##                                                                    
##                                                                    
##       Age           VIP           RoomService      FoodCourt      
##  Min.   : 0.00   Mode :logical   Min.   :    0   Min.   :    0.0  
##  1st Qu.:20.00   FALSE:8494      1st Qu.:    0   1st Qu.:    0.0  
##  Median :27.00   TRUE :199       Median :    0   Median :    0.0  
##  Mean   :28.84                   Mean   :  220   Mean   :  448.4  
##  3rd Qu.:37.00                   3rd Qu.:   41   3rd Qu.:   61.0  
##  Max.   :79.00                   Max.   :14327   Max.   :29813.0  
##                                                                   
##   ShoppingMall          Spa              VRDeck        Transported    
##  Min.   :    0.0   Min.   :    0.0   Min.   :    0.0   Mode :logical  
##  1st Qu.:    0.0   1st Qu.:    0.0   1st Qu.:    0.0   FALSE:4315     
##  Median :    0.0   Median :    0.0   Median :    0.0   TRUE :4378     
##  Mean   :  169.6   Mean   :  304.6   Mean   :  298.3                  
##  3rd Qu.:   22.0   3rd Qu.:   53.0   3rd Qu.:   40.0                  
##  Max.   :23492.0   Max.   :22408.0   Max.   :24133.0                  
##                                                                       
##    withgroup           deck      side        expense     
##  Min.   :0.0000   F      :2832   P:4335   Min.   :    0  
##  1st Qu.:0.0000   G      :2648   S:4358   1st Qu.:    0  
##  Median :0.0000   E      : 881            Median :  716  
##  Mean   :0.4473   B      : 825            Mean   : 1441  
##  3rd Qu.:1.0000   C      : 758            3rd Qu.: 1441  
##  Max.   :1.0000   D      : 483            Max.   :35987  
##                   (Other): 266

summary(test)

##  PassengerId         HomePlanet   CryoSleep           Destination  
##  Length:8693        Europa:2174   FALSE:5581   55 Cancri e  :1800  
##  Class :character   Earth :4743   TRUE :3112   PSO J318.5-22: 796  
##  Mode  :character   Mars  :1776                TRAPPIST-1e  :6097  
##                                                                    
##                                                                    
##                                                                    
##                                                                    
##       Age           VIP           RoomService      FoodCourt      
##  Min.   : 0.00   Mode :logical   Min.   :    0   Min.   :    0.0  
##  1st Qu.:20.00   FALSE:8494      1st Qu.:    0   1st Qu.:    0.0  
##  Median :27.00   TRUE :199       Median :    0   Median :    0.0  
##  Mean   :28.84                   Mean   :  220   Mean   :  448.4  
##  3rd Qu.:37.00                   3rd Qu.:   41   3rd Qu.:   61.0  
##  Max.   :79.00                   Max.   :14327   Max.   :29813.0  
##                                                                   
##   ShoppingMall          Spa              VRDeck        Transported    
##  Min.   :    0.0   Min.   :    0.0   Min.   :    0.0   Mode :logical  
##  1st Qu.:    0.0   1st Qu.:    0.0   1st Qu.:    0.0   FALSE:4315     
##  Median :    0.0   Median :    0.0   Median :    0.0   TRUE :4378     
##  Mean   :  169.6   Mean   :  304.6   Mean   :  298.3                  
##  3rd Qu.:   22.0   3rd Qu.:   53.0   3rd Qu.:   40.0                  
##  Max.   :23492.0   Max.   :22408.0   Max.   :24133.0                  
##                                                                       
##    withgroup           deck      side        expense       omePlanet   
##  Min.   :0.0000   F      :2832   P:4335   Min.   :    0   Europa:2174  
##  1st Qu.:0.0000   G      :2648   S:4358   1st Qu.:    0   Earth :4743  
##  Median :0.0000   E      : 881            Median :  716   Mars  :1776  
##  Mean   :0.4473   B      : 825            Mean   : 1441                
##  3rd Qu.:1.0000   C      : 758            3rd Qu.: 1441                
##  Max.   :1.0000   D      : 483            Max.   :35987                
##                   (Other): 266

write.csv(train, "train_c.csv", row.names=FALSE)

write.csv(test, "test_c.csv", row.names = FALSE)

train <- read.csv("train_c.csv")
test <- read.csv("test_c.csv")

paged_table(train)

paged_table(test)

describe_all(train)

## # A tibble: 16 × 8
##    variable     type     na na_pct unique   min    mean   max
##    <chr>        <chr> <int>  <dbl>  <int> <dbl>   <dbl> <dbl>
##  1 PassengerId  chr       0      0   8693    NA   NA       NA
##  2 HomePlanet   chr       0      0      3    NA   NA       NA
##  3 CryoSleep    lgl       0      0      2     0    0.36     1
##  4 Destination  chr       0      0      3    NA   NA       NA
##  5 Age          dbl       0      0     88     0   28.8     79
##  6 VIP          lgl       0      0      2     0    0.02     1
##  7 RoomService  int       0      0   1273     0  220.   14327
##  8 FoodCourt    int       0      0   1507     0  448.   29813
##  9 ShoppingMall int       0      0   1115     0  170.   23492
## 10 Spa          int       0      0   1327     0  305.   22408
## 11 VRDeck       int       0      0   1306     0  298.   24133
## 12 Transported  lgl       0      0      2     0    0.5      1
## 13 withgroup    int       0      0      2     0    0.45     1
## 14 deck         chr       0      0      8    NA   NA       NA
## 15 side         chr       0      0      2    NA   NA       NA
## 16 expense      int       0      0   2336     0 1441.   35987

describe_all(test)

## # A tibble: 17 × 8
##    variable     type     na na_pct unique   min    mean   max
##    <chr>        <chr> <int>  <dbl>  <int> <dbl>   <dbl> <dbl>
##  1 PassengerId  chr       0      0   8693    NA   NA       NA
##  2 HomePlanet   chr       0      0      3    NA   NA       NA
##  3 CryoSleep    lgl       0      0      2     0    0.36     1
##  4 Destination  chr       0      0      3    NA   NA       NA
##  5 Age          dbl       0      0     88     0   28.8     79
##  6 VIP          lgl       0      0      2     0    0.02     1
##  7 RoomService  int       0      0   1273     0  220.   14327
##  8 FoodCourt    int       0      0   1507     0  448.   29813
##  9 ShoppingMall int       0      0   1115     0  170.   23492
## 10 Spa          int       0      0   1327     0  305.   22408
## 11 VRDeck       int       0      0   1306     0  298.   24133
## 12 Transported  lgl       0      0      2     0    0.5      1
## 13 withgroup    int       0      0      2     0    0.45     1
## 14 deck         chr       0      0      8    NA   NA       NA
## 15 side         chr       0      0      2    NA   NA       NA
## 16 expense      int       0      0   2336     0 1441.   35987
## 17 omePlanet    chr       0      0      3    NA   NA       NA

train$HomePlanet <- as.factor(train$HomePlanet)
train$Destination <- as.factor(train$Destination)
train$PassengerId <- as.factor(train$PassengerId)
train$deck <- as.factor(train$deck)
train$side <- as.factor(train$side)

test$HomePlanet <- as.factor(test$HomePlanet)
test$Destination <- as.factor(test$Destination)
test$deck <- as.factor(test$deck)
test$side <- as.factor(test$side)
test$PassengerId <- as.factor(test$PassengerId)

describe_all(train)

## # A tibble: 16 × 8
##    variable     type     na na_pct unique   min    mean   max
##    <chr>        <chr> <int>  <dbl>  <int> <dbl>   <dbl> <dbl>
##  1 PassengerId  fct       0      0   8693    NA   NA       NA
##  2 HomePlanet   fct       0      0      3    NA   NA       NA
##  3 CryoSleep    lgl       0      0      2     0    0.36     1
##  4 Destination  fct       0      0      3    NA   NA       NA
##  5 Age          dbl       0      0     88     0   28.8     79
##  6 VIP          lgl       0      0      2     0    0.02     1
##  7 RoomService  int       0      0   1273     0  220.   14327
##  8 FoodCourt    int       0      0   1507     0  448.   29813
##  9 ShoppingMall int       0      0   1115     0  170.   23492
## 10 Spa          int       0      0   1327     0  305.   22408
## 11 VRDeck       int       0      0   1306     0  298.   24133
## 12 Transported  lgl       0      0      2     0    0.5      1
## 13 withgroup    int       0      0      2     0    0.45     1
## 14 deck         fct       0      0      8    NA   NA       NA
## 15 side         fct       0      0      2    NA   NA       NA
## 16 expense      int       0      0   2336     0 1441.   35987

describe_all(test)

## # A tibble: 17 × 8
##    variable     type     na na_pct unique   min    mean   max
##    <chr>        <chr> <int>  <dbl>  <int> <dbl>   <dbl> <dbl>
##  1 PassengerId  fct       0      0   8693    NA   NA       NA
##  2 HomePlanet   fct       0      0      3    NA   NA       NA
##  3 CryoSleep    lgl       0      0      2     0    0.36     1
##  4 Destination  fct       0      0      3    NA   NA       NA
##  5 Age          dbl       0      0     88     0   28.8     79
##  6 VIP          lgl       0      0      2     0    0.02     1
##  7 RoomService  int       0      0   1273     0  220.   14327
##  8 FoodCourt    int       0      0   1507     0  448.   29813
##  9 ShoppingMall int       0      0   1115     0  170.   23492
## 10 Spa          int       0      0   1327     0  305.   22408
## 11 VRDeck       int       0      0   1306     0  298.   24133
## 12 Transported  lgl       0      0      2     0    0.5      1
## 13 withgroup    int       0      0      2     0    0.45     1
## 14 deck         fct       0      0      8    NA   NA       NA
## 15 side         fct       0      0      2    NA   NA       NA
## 16 expense      int       0      0   2336     0 1441.   35987
## 17 omePlanet    chr       0      0      3    NA   NA       NA

D <- train[,2:16] %>% mutate(across(everything(),~as.integer(.)))

kor <- cor(D)

library(corrplot)

## corrplot 0.92 loaded

corrplot.mixed(kor)

library(DataExplorer)
create_report(train)

model <- lm(Transported ~ ., data = train[, 2:16])

summary(model)

## 
## Call:
## lm(formula = Transported ~ ., data = train[, 2:16])
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -1.48097 -0.30495 -0.02786  0.28279  1.75905 
## 
## Coefficients: (1 not defined because of singularities)
##                            Estimate Std. Error t value Pr(>|t|)    
## (Intercept)               3.046e-01  4.003e-02   7.609 3.05e-14 ***
## HomePlanetEuropa          2.110e-01  2.864e-02   7.367 1.91e-13 ***
## HomePlanetMars            8.968e-02  1.479e-02   6.062 1.40e-09 ***
## CryoSleepTRUE             3.901e-01  1.158e-02  33.680  < 2e-16 ***
## DestinationPSO J318.5-22 -4.323e-02  1.802e-02  -2.400 0.016438 *  
## DestinationTRAPPIST-1e   -4.570e-02  1.128e-02  -4.051 5.14e-05 ***
## Age                      -2.217e-03  3.192e-04  -6.947 4.00e-12 ***
## VIPTRUE                  -3.367e-02  2.967e-02  -1.135 0.256466    
## RoomService              -1.147e-04  7.050e-06 -16.269  < 2e-16 ***
## FoodCourt                 4.403e-05  3.053e-06  14.422  < 2e-16 ***
## ShoppingMall              8.240e-05  7.448e-06  11.063  < 2e-16 ***
## Spa                      -8.531e-05  4.106e-06 -20.777  < 2e-16 ***
## VRDeck                   -8.127e-05  4.109e-06 -19.776  < 2e-16 ***
## withgroup                 1.999e-02  9.260e-03   2.159 0.030867 *  
## deckB                     1.076e-01  2.866e-02   3.755 0.000175 ***
## deckC                     1.442e-01  2.893e-02   4.986 6.28e-07 ***
## deckD                     5.455e-02  3.462e-02   1.575 0.115193    
## deckE                     1.033e-02  3.602e-02   0.287 0.774351    
## deckF                     1.074e-01  3.693e-02   2.907 0.003655 ** 
## deckG                     5.576e-02  3.855e-02   1.446 0.148098    
## deckT                     6.774e-02  1.810e-01   0.374 0.708306    
## sideS                     8.559e-02  8.606e-03   9.946  < 2e-16 ***
## expense                          NA         NA      NA       NA    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.4001 on 8671 degrees of freedom
## Multiple R-squared:  0.3612, Adjusted R-squared:  0.3596 
## F-statistic: 233.4 on 21 and 8671 DF,  p-value: < 2.2e-16

library(caTools)
set.seed(123)
split = sample.split(train$Transported,SplitRatio = 0.75)
train_train = subset(train, split == TRUE)
train_test = subset(train, split == FALSE)

regresyon <- lm(Transported ~ ., data = train_train[, -c(1)])

summary(regresyon)

## 
## Call:
## lm(formula = Transported ~ ., data = train_train[, -c(1)])
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -1.55277 -0.30795 -0.02772  0.28588  1.74204 
## 
## Coefficients: (1 not defined because of singularities)
##                            Estimate Std. Error t value Pr(>|t|)    
## (Intercept)               3.373e-01  4.627e-02   7.290 3.46e-13 ***
## HomePlanetEuropa          1.979e-01  3.338e-02   5.927 3.25e-09 ***
## HomePlanetMars            8.044e-02  1.706e-02   4.715 2.46e-06 ***
## CryoSleepTRUE             3.849e-01  1.335e-02  28.834  < 2e-16 ***
## DestinationPSO J318.5-22 -6.053e-02  2.076e-02  -2.915 0.003563 ** 
## DestinationTRAPPIST-1e   -5.053e-02  1.304e-02  -3.876 0.000107 ***
## Age                      -2.382e-03  3.714e-04  -6.414 1.52e-10 ***
## VIPTRUE                  -1.268e-02  3.376e-02  -0.375 0.707329    
## RoomService              -1.147e-04  7.788e-06 -14.729  < 2e-16 ***
## FoodCourt                 4.005e-05  3.466e-06  11.555  < 2e-16 ***
## ShoppingMall              8.546e-05  8.407e-06  10.166  < 2e-16 ***
## Spa                      -8.430e-05  4.704e-06 -17.921  < 2e-16 ***
## VRDeck                   -8.077e-05  4.771e-06 -16.930  < 2e-16 ***
## withgroup                 1.620e-02  1.073e-02   1.510 0.130979    
## deckB                     1.003e-01  3.283e-02   3.057 0.002248 ** 
## deckC                     1.388e-01  3.311e-02   4.193 2.78e-05 ***
## deckD                     3.548e-02  3.952e-02   0.898 0.369332    
## deckE                    -1.945e-02  4.186e-02  -0.465 0.642212    
## deckF                     8.940e-02  4.267e-02   2.095 0.036188 *  
## deckG                     4.025e-02  4.456e-02   0.903 0.366367    
## deckT                     5.872e-02  1.818e-01   0.323 0.746676    
## sideS                     8.994e-02  9.958e-03   9.033  < 2e-16 ***
## expense                          NA         NA      NA       NA    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.4003 on 6498 degrees of freedom
## Multiple R-squared:  0.3611, Adjusted R-squared:  0.3591 
## F-statistic: 174.9 on 21 and 6498 DF,  p-value: < 2.2e-16

reg_tahmin = predict(regresyon,newdata = train_test[, -c(1,12)])

reg_transported_tahmin <- ifelse(reg_tahmin > 0.5,1,0)

transported_gercek <- ifelse(train_test[12] == TRUE,1,0)

cm = table(transported_gercek, reg_transported_tahmin)

cm

##                   reg_transported_tahmin
## transported_gercek   0   1
##                  0 904 175
##                  1 320 774

(904+774)/(904+774+320+175)

## [1] 0.7722043

reg_tahmin = predict(regresyon,newdata = train_train[, -c(1,12)])

reg_transported_tahmin <- ifelse(reg_tahmin > 0.5,1,0)

transported_gercek <- ifelse(train_train[12] == TRUE,1,0)

cm = table(transported_gercek, reg_transported_tahmin)

cm

##                   reg_transported_tahmin
## transported_gercek    0    1
##                  0 2673  563
##                  1  936 2348

(2673+2348)/(2673+2348+563+936)

## [1] 0.770092

reg_tahmin_bd = predict(model,newdata = test[, -c(1)])

reg_transported_test_tahmin <- ifelse(reg_tahmin_bd > 0.5,TRUE,FALSE)

Transported <- as.character(reg_transported_test_tahmin)

PassengerId <- test$PassengerId

Transported<- as.vector(Transported)

submission_regresyon <- cbind(PassengerId, Transported)

submission_regresyon <- as.data.frame(submission_regresyon)

library(stringr)

submission_regresyon$Transported <- str_to_title(submission_regresyon$Transported)

write.csv(submission_regresyon, "submission_regresyon.csv", row.names = FALSE,quote = FALSE)

library(glmulti)

## Le chargement a nécessité le package : rJava

## Le chargement a nécessité le package : leaps

regresyon_opt <- glmulti(Transpoted ~ HomePlanet + CryoSleep + Destination + Age +VIP
+ RoomService + FoodCourt + ShoppingMall + Spa + VRDeck + winthgroup + deck + side, level =
 1, crit = bic, data = train)

modelglmulti <- lm(Transported ~ 1 + HomePlanet + Destination + deck + side + CryoSleep + Age + RoomService + FoodCourt + ShoppingMall + Spa + VRDeck, data = train)

write.csv(submission_regresyon_glmulti, "submission_regresyon_glmulti.csv",
row. names =FALSE, quote=FALSE)

train_log <- train %>%
mutate_at(c(5, 7:11, 16), ~ log(1 + .))

test_log <- test %>%
mutate_at(c(5, 7:11, 16), ~ log(1 + .))

modellog <- lm(Transported ~ 1 + HomePlanet + Destination + deck + side + CryoSleep + Age + RoomService + FoodCourt + ShoppingMall + Spa + VRDeck, data = train_log)

reg_tahmin_log = predict(modellog, newdata = test_log[, -c(1)])

reg_transported_test_tahmin_log <- ifelse(reg_tahmin_log > 0.5, TRUE, FALSE)

Transported <- as.character(reg_transported_test_tahmin_log)
PassengerId <- test$PassengerId

Transported <- as.vector(Transported)

submission_regresyon_log <- cbind(PassengerId, Transported)

submission_regresyon_log <- as.data.frame(submission_regresyon_log)

submission_regresyon_log$Transported <- str_to_title(submission_regresyon_log$Transported)

write.csv(submission_regresyon_log, "submission_regresyon_log.csv", row.names = FALSE,
quote = FALSE)

logistic = glm(formula = Transported ~ .,
      family = binomial,
      data = train_train[, -c(1)])

## Warning: glm.fit: des probabilités ont été ajustées numériquement à 0 ou 1

summary(logistic)

## 
## Call:
## glm(formula = Transported ~ ., family = binomial, data = train_train[, 
##     -c(1)])
## 
## Coefficients: (1 not defined because of singularities)
##                            Estimate Std. Error z value Pr(>|z|)    
## (Intercept)              -4.737e-01  3.584e-01  -1.322 0.186261    
## HomePlanetEuropa          1.533e+00  2.654e-01   5.775 7.72e-09 ***
## HomePlanetMars            5.094e-01  1.112e-01   4.580 4.65e-06 ***
## CryoSleepTRUE             1.297e+00  9.304e-02  13.942  < 2e-16 ***
## DestinationPSO J318.5-22 -4.995e-01  1.299e-01  -3.844 0.000121 ***
## DestinationTRAPPIST-1e   -4.608e-01  9.424e-02  -4.889 1.01e-06 ***
## Age                      -8.758e-03  2.463e-03  -3.555 0.000378 ***
## VIPTRUE                  -1.507e-01  2.917e-01  -0.517 0.605422    
## RoomService              -1.711e-03  1.136e-04 -15.059  < 2e-16 ***
## FoodCourt                 4.582e-04  4.450e-05  10.297  < 2e-16 ***
## ShoppingMall              5.436e-04  7.623e-05   7.131 9.95e-13 ***
## Spa                      -1.947e-03  1.166e-04 -16.707  < 2e-16 ***
## VRDeck                   -1.876e-03  1.155e-04 -16.241  < 2e-16 ***
## withgroup                 1.231e-01  7.188e-02   1.712 0.086855 .  
## deckB                     1.113e+00  2.896e-01   3.842 0.000122 ***
## deckC                     2.427e+00  3.314e-01   7.325 2.39e-13 ***
## deckD                     6.808e-01  3.245e-01   2.098 0.035935 *  
## deckE                     8.476e-02  3.347e-01   0.253 0.800066    
## deckF                     7.591e-01  3.393e-01   2.237 0.025257 *  
## deckG                     3.459e-01  3.489e-01   0.991 0.321465    
## deckT                    -1.204e-01  1.854e+00  -0.065 0.948224    
## sideS                     6.035e-01  6.668e-02   9.051  < 2e-16 ***
## expense                          NA         NA      NA       NA    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 9038.3  on 6519  degrees of freedom
## Residual deviance: 5599.8  on 6498  degrees of freedom
## AIC: 5643.8
## 
## Number of Fisher Scoring iterations: 7

logistic_tahmin = predict(logistic, newdata = train_test[, -c(1,12)])

head(logistic_tahmin)

##           2           3           7          14          16          21 
##  -1.1025143 -10.9381357   0.9585015  -1.6451179  -0.4385553  -1.6923796

logistic_Transpoted_tahmin <- ifelse(logistic_tahmin > 0.5, 1,0)

transported_gercek <- ifelse(train_test[12] == TRUE,1,0)

library(tidymodels)

## ── Attaching packages ────────────────────────────────────── tidymodels 1.2.0 ──

## ✔ broom        1.0.5      ✔ rsample      1.2.1 
## ✔ dials        1.2.1      ✔ tune         1.2.1 
## ✔ infer        1.0.7      ✔ workflows    1.1.4 
## ✔ modeldata    1.3.0      ✔ workflowsets 1.1.0 
## ✔ parsnip      1.2.1      ✔ yardstick    1.3.1 
## ✔ recipes      1.0.10

## ── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
## ✖ scales::discard() masks purrr::discard()
## ✖ dplyr::filter()   masks stats::filter()
## ✖ recipes::fixed()  masks stringr::fixed()
## ✖ dplyr::lag()      masks stats::lag()
## ✖ yardstick::spec() masks readr::spec()
## ✖ recipes::step()   masks stats::step()
## • Search for functions across packages at https://www.tidymodels.org/find/

result = data.frame(cbind(transported_gercek, logistic_Transpoted_tahmin))

result$Transported <- as.factor(result$Transported)
result$logistic_Transpoted_tahmin <- as.factor(result$logistic_Transpoted_tahmin)

accuracy(result,truth = Transported, estimate = logistic_Transpoted_tahmin)

## # A tibble: 1 × 3
##   .metric  .estimator .estimate
##   <chr>    <chr>          <dbl>
## 1 accuracy binary         0.782

conf_mat(result, truth = Transported,estimate = logistic_Transpoted_tahmin)

##           Truth
## Prediction   0   1
##          0 918 312
##          1 161 782

library(caret)

## Le chargement a nécessité le package : lattice

## 
## Attachement du package : 'caret'

## Les objets suivants sont masqués depuis 'package:yardstick':
## 
##     precision, recall, sensitivity, specificity

## L'objet suivant est masqué depuis 'package:purrr':
## 
##     lift

cm = table(transported_gercek, logistic_Transpoted_tahmin)

cm

##                   logistic_Transpoted_tahmin
## transported_gercek   0   1
##                  0 918 161
##                  1 312 782

logistic_bd = glm(formula = Transported ~ .,
family = binomial,
data = train[, -c(1)])

## Warning: glm.fit: des probabilités ont été ajustées numériquement à 0 ou 1

logistic_tahmin_bd = predict(logistic_bd, newdata = test[, -c(1)])

logistic_transpoted_test_tahmin <- ifelse(logistic_tahmin_bd > 0.5,TRUE,FALSE)

Transported <- as.character(logistic_transpoted_test_tahmin)
PassengerId <- test$PassengerId

Transported <- as.vector(Transported)

submission_logistic <- cbind(PassengerId, Transported)

submission_logistic <- as.data.frame(submission_logistic)

submission_logistic$Transported <- str_to_title(submission_logistic$Transported)

write.csv(submission_logistic,"submission_logistic.csv", row.names = FALSE, quote = FALSE)

Naive bayes

library(e1071)

## 
## Attachement du package : 'e1071'

## L'objet suivant est masqué depuis 'package:tune':
## 
##     tune

## L'objet suivant est masqué depuis 'package:rsample':
## 
##     permutations

## L'objet suivant est masqué depuis 'package:parsnip':
## 
##     tune

fit_nb <- naiveBayes(Transported ~ .,data = train_train[, -1])

fit_nb

## 
## Naive Bayes Classifier for Discrete Predictors
## 
## Call:
## naiveBayes.default(x = X, y = Y, laplace = laplace)
## 
## A-priori probabilities:
## Y
##    FALSE     TRUE 
## 0.496319 0.503681 
## 
## Conditional probabilities:
##        HomePlanet
## Y           Earth    Europa      Mars
##   FALSE 0.6220643 0.1755253 0.2024104
##   TRUE  0.4604141 0.3306943 0.2088916
## 
##        CryoSleep
## Y           FALSE      TRUE
##   FALSE 0.8652658 0.1347342
##   TRUE  0.4205238 0.5794762
## 
##        Destination
## Y       55 Cancri e PSO J318.5-22 TRAPPIST-1e
##   FALSE  0.16069221    0.09363412  0.74567367
##   TRUE   0.24969549    0.09043849  0.65986602
## 
##        Age
## Y           [,1]     [,2]
##   FALSE 30.01119 13.45225
##   TRUE  27.85293 14.87588
## 
##        VIP
## Y            FALSE       TRUE
##   FALSE 0.97126082 0.02873918
##   TRUE  0.98142509 0.01857491
## 
##        RoomService
## Y            [,1]     [,2]
##   FALSE 402.20365 916.6547
##   TRUE   56.93484 246.8105
## 
##        FoodCourt
## Y           [,1]     [,2]
##   FALSE 396.2923 1258.123
##   TRUE  514.8018 1918.620
## 
##        ShoppingMall
## Y           [,1]     [,2]
##   FALSE 160.2250 432.1103
##   TRUE  182.7135 748.5867
## 
##        Spa
## Y            [,1]      [,2]
##   FALSE 561.16193 1554.2636
##   TRUE   61.11571  264.0556
## 
##        VRDeck
## Y            [,1]      [,2]
##   FALSE 533.98733 1542.8703
##   TRUE   69.07186  295.0542
## 
##        withgroup
## Y            [,1]      [,2]
##   FALSE 0.3952410 0.4889780
##   TRUE  0.4960414 0.5000605
## 
##        deck
## Y                  A            B            C            D            E
##   FALSE 0.0296662546 0.0543881335 0.0574783684 0.0661310260 0.1344252163
##   TRUE  0.0310596833 0.1385505481 0.1199756395 0.0490255786 0.0676004872
##        deck
## Y                  F            G            T
##   FALSE 0.3637206428 0.2929542645 0.0012360939
##   TRUE  0.2828867235 0.3105968331 0.0003045067
## 
##        side
## Y               P         S
##   FALSE 0.5568603 0.4431397
##   TRUE  0.4448843 0.5551157
## 
##        expense
## Y            [,1]     [,2]
##   FALSE 2053.8702 3224.219
##   TRUE   884.6376 2307.962

pred_nb <- predict(fit_nb,newdata = train_test[, -c(1,12)],type = "raw") %>% data.frame()

head(pred_nb)

##       FALSE.         TRUE.
## 1 0.22726191  7.727381e-01
## 2 1.00000000 8.444155e-135
## 3 0.02805365  9.719464e-01
## 4 0.59934478  4.006552e-01
## 5 0.02471507  9.752849e-01
## 6 0.39125602  6.087440e-01

Transported_pred_nb = ifelse(pred_nb$TRUE. > 0.5,1,0)

Transported_train_test <- ifelse(train_test[12] == TRUE, 1,0)

cm = table(Transported_train_test,Transported_pred_nb)
cm

##                       Transported_pred_nb
## Transported_train_test    0    1
##                      0  482  597
##                      1   77 1017

(482+1017)/ (482+1017+77+597)

## [1] 0.6898297

nb = naiveBayes(Transported ~ .,data = train[, -1])

pred_nb <- predict(nb, newdata = test,type = "raw") %>% data.frame()

Transported_pred_nb = ifelse(pred_nb$TRUE. > 0.5,TRUE,FALSE)

Transported <- as.character(Transported_pred_nb)
PassengerId <- test$PassengerId
Transported <- as.vector(Transported)
sample_submission <- cbind(PassengerId,Transported)
sample_submission <- as.data.frame(sample_submission)
sample_submission$Transported <- str_to_title(sample_submission$Transported)
write.csv(sample_submission,"sub_nb.csv",row.names = FALSE, quote = FALSE)

SVM

fit_svm <- svm(Transported ~ ., data = train_train[, -1], type= 'C-classification',
       kernel = 'linear' )
preds <- predict(fit_svm, newdata= train_test[, -c(1,12)], type= "raw") %>% data.frame()

Transported_pred_svm = ifelse(preds$.== TRUE, 1,0)
cm = table(Transported_train_test,Transported_pred_svm)

cm

##                       Transported_pred_svm
## Transported_train_test   0   1
##                      0 841 238
##                      1 193 901

(836+907)/(836 +243+187+907)

## [1] 0.8021169

fit_svm <- svm(Transported ~ ., data = train[, -1], 
        type= 'C-classification',
       kernel = 'linear' )
preds <- predict(fit_svm, newdata= test, type= "raw") %>% data.frame()

Transported_pred_svm = ifelse(preds$.== TRUE,TRUE,FALSE)

Transported <- as.character(Transported_pred_svm)
PassengerId <- test$PassengerId
Transported <- as.vector(Transported)
sample_submission <- cbind(PassengerId,Transported)
sample_submission <- as.data.frame(sample_submission)
sample_submission$Transported <- str_to_title(sample_submission$Transported)
write.csv(sample_submission,"sub_svm.csv",row.names = FALSE, quote = FALSE)