library(readr)
train<- read_csv("train.csv")## Rows: 8693 Columns: 14
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): PassengerId, HomePlanet, Cabin, Destination, Name
## dbl (6): Age, RoomService, FoodCourt, ShoppingMall, Spa, VRDeck
## lgl (3): CryoSleep, VIP, Transported
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.test<- read_csv("test.csv")## Rows: 4277 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): PassengerId, HomePlanet, Cabin, Destination, Name
## dbl (6): Age, RoomService, FoodCourt, ShoppingMall, Spa, VRDeck
## lgl (2): CryoSleep, VIP
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.library(rmarkdown)paged_table(train)paged_table(test)-PassengerId - Her yolcu için benzersiz bir Kimlik. Her Kimlik, gggg_pp biçiminde olup, gggg, yolcuyla seyahat eden grubu ve pp, gruptaki sırasını belirtir. Bir gruptaki insanlar genellikle aile üyeleridir, ancak her zaman değil.
HomePlanet - Yolcunun ayrıldığı gezegen, genellikle kalıcı ikamet gezegenleri.
CryoSleep - Yolcunun yolculuğun süresince dondurularak animasyonu durdurmayı seçip seçmediğini belirtir. Cryosleep’teki yolcular kabinlerine kapatılmıştır.
Cabin - Yolcunun konakladığı kabin numarası. deck/num/side şeklinde alır, burada side, Port için P veya Starboard için S olabilir . -Destination - Yolcunun ineceği gezegen.
Age - Yolcunun yaşı.
VIP - Yolcunun yolculuk sırasında özel VIP hizmeti için ödeme yapmış olup olmadığını belirtir.
RoomService, FoodCourt, ShoppingMall, Spa, VRDeck - Spaceship Titanic’in birçok lüks olanaklarında yolcunun fatura ettiği miktar.
Name- Yolcunun adı ve soyadı.
Transported - Yolcunun başka bir boyuta taşınıp taşınmadığını belirtir. Bu, tahmin etmeye çalıştığınız sütun olan hedeftir.
test.csv - Test verisi olarak kullanılmak üzere geriye kalan üçte birlik (~4300) yolcunun kişisel kayıtları. Göreviniz, bu setteki yolcular için Transported değerini tahmin etmektir.
sample_submission.csv - Doğru formatta bir gönderim dosyası.
PassengerId - Test setindeki her yolcu için Kimlik.
Transported- Hedef. Her yolcu için, True veya False tahmin edin.
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ purrr 1.0.2
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(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 1test %>% 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 NAtrain[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 01train$withgroup <- ifelse(duplicated(train$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 0
## 4 0003_02 0003 02 1
## 5 0004_01 0004 01 0
## 6 0005_01 0005 01 0train[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 :0.2848 B : 779 86 : 22
## 3rd Qu.:1.0000 C : 747 176 : 21
## Max. :1.0000 (Other): 739 56 : 21
## NA's : 199 (Other):8380train[train == ' '] <- NA
test [test == ' ']<- NAtrain$num <- droplevels(train$num)
test$num <- droplevels(test$num)
train$side <- droplevels(train$side)
test$side <- droplevels(test$side)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 :0.2848 B : 779 86 : 22
## 3rd Qu.:1.0000 C : 747 176 : 21
## Max. :1.0000 (Other): 739 56 : 21
## NA's : 199 (Other):8380library(zoo)##
## Attachement du package : 'zoo'## Les objets suivants sont masqués depuis 'package:base':
##
## as.Date, as.Date.numerictrain <- 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 99train$HomePlanet <- as.character(train$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 0.28 1
## 18 deck fct 199 2.3 9 NA NA NA
## 19 num fct 0 0 1818 NA NA NA
## 20 side fct 0 0 3 NA NA NAtest %>% 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 0.28 1
## 17 deck fct 100 2.3 9 NA NA NA
## 18 num fct 0 0 1506 NA NA NA
## 19 side fct 0 0 3 NA NA NAtrain <- 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(Destination, 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 55 Cancri e 713
## 2 Europa 55 Cancri e 893
## 3 Mars 55 Cancri e 194train<- 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$Spa + train$VRDecktest$expense <- test$RoomService + test$FoodCourt + test$ShoppingMall + test$Spa + test$VRDecktrain <- 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"))summary(train)## PassengerId HomePlanet CryoSleep Cabin
## 0001_01: 1 Earth :4764 Length:8693 G/734/S: 8
## 0002_01: 1 Europa:2153 Class :character B/11/S : 7
## 0003_01: 1 Mars :1776 Mode :character B/201/P: 7
## 0003_02: 1 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
## Length:8693 Min. : 0.00 Mode :logical Min. : 0
## Class :character 1st Qu.:20.00 FALSE:8291 1st Qu.: 0
## Mode :character Median :27.00 TRUE :199 Median : 0
## Mean :28.84 NA's :203 Mean : 220
## 3rd Qu.:37.00 3rd Qu.: 41
## Max. :79.00 Max. :14327
##
## 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 : 448.4 Mean : 169.6 Mean : 304.6 Mean : 298.3
## 3rd Qu.: 61.0 3rd Qu.: 22.0 3rd Qu.: 53.0 3rd Qu.: 40.0
## Max. :29813.0 Max. :23492.0 Max. :22408.0 Max. :24133.0
##
## 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 destination
## Min. :0.0000 F :2794 : 199 : 199 55 Cancri e :1800
## 1st Qu.:0.0000 G :2559 82 : 28 P:4206 PSO J318.5-22: 796
## Median :0.0000 E : 876 19 : 22 S:4288 TRAPPIST-1e :6097
## Mean :0.2848 B : 779 86 : 22
## 3rd Qu.:1.0000 C : 747 176 : 21
## Max. :1.0000 (Other): 739 56 : 21
## NA's : 199 (Other):8380
## expense
## Min. : 0
## 1st Qu.: 0
## Median : 716
## Mean : 1441
## 3rd Qu.: 1441
## Max. :35987
## 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"))describe_all (train)## # A tibble: 22 × 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 chr 23 0.3 3 NA NA NA
## 4 Cabin fct 199 2.3 6561 NA NA NA
## 5 Destination chr 0 0 3 NA NA NA
## 6 Age dbl 0 0 88 0 28.8 79
## 7 VIP lgl 203 2.3 3 0 0.02 1
## 8 RoomService dbl 0 0 1273 0 220. 14327
## 9 FoodCourt dbl 0 0 1507 0 448. 29813
## 10 ShoppingMall dbl 0 0 1115 0 170. 23492
## # ℹ 12 more rowstrain$CryoSleep <- as.factor(train$CryoSleep)
test$CryoSleep <- as.factor(test$CryoSleep)summary(train)## PassengerId HomePlanet CryoSleep Cabin Destination
## 0001_01: 1 Earth :4764 FALSE:5558 G/734/S: 8 Length:8693
## 0002_01: 1 Europa:2153 TRUE :3112 B/11/S : 7 Class :character
## 0003_01: 1 Mars :1776 NA's : 23 B/201/P: 7 Mode :character
## 0003_02: 1 B/82/S : 7
## 0004_01: 1 C/137/S: 7
## 0005_01: 1 (Other):8458
## (Other):8687 NA's : 199
## Age VIP RoomService FoodCourt
## Min. : 0.00 Mode :logical Min. : 0 Min. : 0.0
## 1st Qu.:20.00 FALSE:8291 1st Qu.: 0 1st Qu.: 0.0
## Median :27.00 TRUE :199 Median : 0 Median : 0.0
## Mean :28.84 NA's :203 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
## Min. : 0.0 Min. : 0.0 Min. : 0.0
## 1st Qu.: 0.0 1st Qu.: 0.0 1st Qu.: 0.0
## Median : 0.0 Median : 0.0 Median : 0.0
## 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
##
## 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 destination
## Min. :0.0000 F :2794 : 199 : 199 55 Cancri e :1800
## 1st Qu.:0.0000 G :2559 82 : 28 P:4206 PSO J318.5-22: 796
## Median :0.0000 E : 876 19 : 22 S:4288 TRAPPIST-1e :6097
## Mean :0.2848 B : 779 86 : 22
## 3rd Qu.:1.0000 C : 747 176 : 21
## Max. :1.0000 (Other): 739 56 : 21
## NA's : 199 (Other):8380
## expense
## Min. : 0
## 1st Qu.: 0
## Median : 716
## Mean : 1441
## 3rd Qu.: 1441
## Max. :35987
## train <- transform(train, VIP = replace(VIP , is.na (VIP), FALSE))test <- transform(test, VIP = replace(VIP , is.na (VIP), FALSE))train %>% describe_all()## # A tibble: 22 × 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 fct 23 0.3 3 NA NA NA
## 4 Cabin fct 199 2.3 6561 NA NA NA
## 5 Destination chr 0 0 3 NA NA NA
## 6 Age dbl 0 0 88 0 28.8 79
## 7 VIP lgl 0 0 2 0 0.02 1
## 8 RoomService dbl 0 0 1273 0 220. 14327
## 9 FoodCourt dbl 0 0 1507 0 448. 29813
## 10 ShoppingMall dbl 0 0 1115 0 170. 23492
## # ℹ 12 more rowstrain <- 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))summary(train)## PassengerId HomePlanet CryoSleep Cabin Destination
## 0001_01: 1 Earth :4764 FALSE:5558 G/734/S: 8 Length:8693
## 0002_01: 1 Europa:2153 TRUE :3112 B/11/S : 7 Class :character
## 0003_01: 1 Mars :1776 NA's : 23 B/201/P: 7 Mode :character
## 0003_02: 1 B/82/S : 7
## 0004_01: 1 C/137/S: 7
## 0005_01: 1 (Other):8458
## (Other):8687 NA's : 199
## 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
## Min. : 0.0 Min. : 0.0 Min. : 0.0
## 1st Qu.: 0.0 1st Qu.: 0.0 1st Qu.: 0.0
## Median : 0.0 Median : 0.0 Median : 0.0
## 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
##
## 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 destination
## Min. :0.0000 F :2801 : 199 : 199 55 Cancri e :1800
## 1st Qu.:0.0000 G :2580 82 : 28 P:4206 PSO J318.5-22: 796
## Median :0.0000 E : 881 19 : 22 S:4288 TRAPPIST-1e :6097
## Mean :0.2848 B : 790 86 : 22
## 3rd Qu.:1.0000 C : 758 176 : 21
## Max. :1.0000 (Other): 749 56 : 21
## NA's : 134 (Other):8380
## expense
## Min. : 0
## 1st Qu.: 0
## Median : 716
## Mean : 1441
## 3rd Qu.: 1441
## Max. :35987
## most_frequent_deck <- 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_deck## # A tibble: 3 × 3
## HomePlanet deck count
## <fct> <fct> <int>
## 1 Earth G 2580
## 2 Europa B 786
## 3 Mars F 1122train$HomePlanet <- as.character(train$HomePlanet)
train$deck <- as.character(train$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))))most_frequent_side <- train %>%
filter(!is.na(deck)) %>%
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_side## # A tibble: 3 × 3
## HomePlanet side count
## <chr> <fct> <int>
## 1 Earth P 2349
## 2 Europa S 1131
## 3 Mars P 897train$side <- as.character(train$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$side <- as.character(test$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 %>% describe_all()## # A tibble: 22 × 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 0 0 3 NA NA NA
## 3 CryoSleep fct 23 0.3 3 NA NA NA
## 4 Cabin fct 199 2.3 6561 NA NA NA
## 5 Destination chr 0 0 3 NA NA NA
## 6 Age dbl 0 0 88 0 28.8 79
## 7 VIP lgl 0 0 2 0 0.02 1
## 8 RoomService dbl 0 0 1273 0 220. 14327
## 9 FoodCourt dbl 0 0 1507 0 448. 29813
## 10 ShoppingMall dbl 0 0 1115 0 170. 23492
## # ℹ 12 more rowstrain <- 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`describe_all(train)## # A tibble: 18 × 8
## variable type na na_pct unique min mean max
## <chr> <chr> <int> <dbl> <int> <dbl> <dbl> <dbl>
## 1 group fct 0 0 6217 NA NA NA
## 2 PassengerId fct 0 0 8693 NA NA NA
## 3 HomePlanet chr 0 0 3 NA NA NA
## 4 CryoSleep fct 23 0.3 3 NA NA NA
## 5 Destination chr 0 0 3 NA NA NA
## 6 Age dbl 0 0 88 0 28.8 79
## 7 VIP lgl 0 0 2 0 0.02 1
## 8 RoomService dbl 0 0 1273 0 220. 14327
## 9 FoodCourt dbl 0 0 1507 0 448. 29813
## 10 ShoppingMall dbl 0 0 1115 0 170. 23492
## 11 Spa dbl 0 0 1327 0 305. 22408
## 12 VRDeck dbl 0 0 1306 0 298. 24133
## 13 Transported lgl 0 0 2 0 0.5 1
## 14 withgroup dbl 0 0 2 0 0.28 1
## 15 deck chr 0 0 8 NA NA NA
## 16 side chr 0 0 3 NA NA NA
## 17 destination fct 0 0 3 NA NA NA
## 18 expense dbl 0 0 2336 0 1441. 35987train <- 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$group <- NULLtest$group <- NULLwrite.csv(train, "train_c.csv", row.names=FALSE)write.csv(test, "test_c.csv", row.names=FALSE)