Data Titanic
Sharliz Mayalpen Zafirah
2025-04-25
LATIHAN VDE W8
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.0.4
## ── 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 errorstitanic = read.csv("C:/Users/Sharliz/Downloads/titanic2.csv.csv")
head(titanic)## PassengerId Survived Pclass
## 1 1 0 3
## 2 2 1 1
## 3 3 1 3
## 4 4 1 1
## 5 5 0 3
## 6 6 0 3
## Name Sex Age SibSp Parch
## 1 Braund, Mr. Owen Harris male 22 1 0
## 2 Cumings, Mrs. John Bradley (Florence Briggs Thayer) female 38 1 0
## 3 Heikkinen, Miss. Laina female 26 0 0
## 4 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35 1 0
## 5 Allen, Mr. William Henry male 35 0 0
## 6 Moran, Mr. James male NA 0 0
## Ticket Fare Cabin Embarked
## 1 A/5 21171 7.2500 S
## 2 PC 17599 71.2833 C85 C
## 3 STON/O2. 3101282 7.9250 S
## 4 113803 53.1000 C123 S
## 5 373450 8.0500 S
## 6 330877 8.4583 Qtally(titanic)## n
## 1 891titanic %>%
select(1:9) %>%
sample_n(size = 10)## PassengerId Survived Pclass Name
## 1 220 0 2 Harris, Mr. Walter
## 2 623 1 3 Nakid, Mr. Sahid
## 3 606 0 3 Lindell, Mr. Edvard Bengtsson
## 4 884 0 2 Banfield, Mr. Frederick James
## 5 465 0 3 Maisner, Mr. Simon
## 6 231 1 1 Harris, Mrs. Henry Birkhardt (Irene Wallach)
## 7 275 1 3 Healy, Miss. Hanora "Nora"
## 8 361 0 3 Skoog, Mr. Wilhelm
## 9 357 1 1 Bowerman, Miss. Elsie Edith
## 10 881 1 2 Shelley, Mrs. William (Imanita Parrish Hall)
## Sex Age SibSp Parch Ticket
## 1 male 30 0 0 W/C 14208
## 2 male 20 1 1 2653
## 3 male 36 1 0 349910
## 4 male 28 0 0 C.A./SOTON 34068
## 5 male NA 0 0 A/S 2816
## 6 female 35 1 0 36973
## 7 female NA 0 0 370375
## 8 male 40 1 4 347088
## 9 female 22 0 1 113505
## 10 female 25 0 1 230433summary
glimpse(titanic)## Rows: 891
## Columns: 12
## $ PassengerId <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17,…
## $ Survived <int> 0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1…
## $ Pclass <int> 3, 1, 3, 1, 3, 3, 1, 3, 3, 2, 3, 1, 3, 3, 3, 2, 3, 2, 3, 3…
## $ Name <chr> "Braund, Mr. Owen Harris", "Cumings, Mrs. John Bradley (Fl…
## $ Sex <chr> "male", "female", "female", "female", "male", "male", "mal…
## $ Age <dbl> 22, 38, 26, 35, 35, NA, 54, 2, 27, 14, 4, 58, 20, 39, 14, …
## $ SibSp <int> 1, 1, 0, 1, 0, 0, 0, 3, 0, 1, 1, 0, 0, 1, 0, 0, 4, 0, 1, 0…
## $ Parch <int> 0, 0, 0, 0, 0, 0, 0, 1, 2, 0, 1, 0, 0, 5, 0, 0, 1, 0, 0, 0…
## $ Ticket <chr> "A/5 21171", "PC 17599", "STON/O2. 3101282", "113803", "37…
## $ Fare <dbl> 7.2500, 71.2833, 7.9250, 53.1000, 8.0500, 8.4583, 51.8625,…
## $ Cabin <chr> "", "C85", "", "C123", "", "", "E46", "", "", "", "G6", "C…
## $ Embarked <chr> "S", "C", "S", "S", "S", "Q", "S", "S", "S", "C", "S", "S"…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" ...summary(titanic)## PassengerId Survived Pclass Name
## Min. : 1.0 Min. :0.0000 Min. :1.000 Length:891
## 1st Qu.:223.5 1st Qu.:0.0000 1st Qu.:2.000 Class :character
## Median :446.0 Median :0.0000 Median :3.000 Mode :character
## Mean :446.0 Mean :0.3838 Mean :2.309
## 3rd Qu.:668.5 3rd Qu.:1.0000 3rd Qu.:3.000
## Max. :891.0 Max. :1.0000 Max. :3.000
##
## Sex Age SibSp Parch
## Length:891 Min. : 0.42 Min. :0.000 Min. :0.0000
## Class :character 1st Qu.:20.12 1st Qu.:0.000 1st Qu.:0.0000
## Mode :character Median :28.00 Median :0.000 Median :0.0000
## Mean :29.70 Mean :0.523 Mean :0.3816
## 3rd Qu.:38.00 3rd Qu.:1.000 3rd Qu.:0.0000
## Max. :80.00 Max. :8.000 Max. :6.0000
## NA's :177
## Ticket Fare Cabin Embarked
## Length:891 Min. : 0.00 Length:891 Length:891
## Class :character 1st Qu.: 7.91 Class :character Class :character
## Mode :character Median : 14.45 Mode :character Mode :character
## Mean : 32.20
## 3rd Qu.: 31.00
## Max. :512.33
## EDA - Eksploratori Data Analisis
#1 - Perbandingan jenis kelaming di titanic
ggplot(titanic, aes(x=Sex)) +
geom_bar(fill = "pink") +
labs(title = "Perbandingan Jenis Kelamin Penumpang Titanic")
#2 - Perbandingan data selamat atau tidak berdasarkan kelas
ggplot(titanic, aes(x=factor(Pclass), fill = factor(Survived))) +
geom_bar(position = "fill") +
labs(title = "Proporsi Survival berdasarkan Kelas")
#3 - Distribusi umur penumpang
ggplot(titanic, aes(x=Age)) +
geom_histogram(bins = 50, fill = "lightgreen") +
labs(title="Distribusi Umur Penumpang")## Warning: Removed 177 rows containing non-finite outside the scale range
## (`stat_bin()`).
#4 - Boxplot
ggplot(titanic, aes(x=factor(Survived), y=Age, fill=factor(Survived))) +
geom_boxplot(outlier.color = "red") +
labs(title = "Boxplot")## Warning: Removed 177 rows containing non-finite outside the scale range
## (`stat_boxplot()`).
#5 - Scatterplot
ggplot(titanic, aes(x=Age, y=Fare)) +
geom_point() +
geom_smooth(method="lm", color="lightblue") +
labs(title="Pengaruh Umur terhadap Harga Tiket")## `geom_smooth()` using formula = 'y ~ x'## Warning: Removed 177 rows containing non-finite outside the scale range
## (`stat_smooth()`).## Warning: Removed 177 rows containing missing values or values outside the scale range
## (`geom_point()`).