R Markdown

library(ggplot2)
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
titanic = read.csv("/Users/rikata/Downloads/titanic2.csv.csv")
tally(titanic)
##     n
## 1 891
titanic%>% select(1:9) %>% sample_n(size=10)
##    PassengerId Survived Pclass                              Name  Sex Age SibSp
## 1           93        0      1       Chaffee, Mr. Herbert Fuller male  46     1
## 2          429        0      3                  Flynn, Mr. James male  NA     0
## 3          121        0      2       Hickman, Mr. Stanley George male  21     2
## 4          842        0      2          Mudd, Mr. Thomas Charles male  16     0
## 5          468        0      1        Smart, Mr. John Montgomery male  56     0
## 6          169        0      1               Baumann, Mr. John D male  NA     0
## 7           37        1      3                  Mamee, Mr. Hanna male  NA     0
## 8          282        0      3  Olsson, Mr. Nils Johan Goransson male  28     0
## 9          150        0      2 Byles, Rev. Thomas Roussel Davids male  42     0
## 10         525        0      3                 Kassem, Mr. Fared male  NA     0
##    Parch       Ticket
## 1      0  W.E.P. 5734
## 2      0       364851
## 3      0 S.O.C. 14879
## 4      0  S.O./P.P. 3
## 5      0       113792
## 6      0     PC 17318
## 7      0         2677
## 8      0       347464
## 9      0       244310
## 10     0         2700
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 1. Perbandingan jenis kelamin

ggplot(titanic, aes(x = Sex)) + geom_bar(fill = "lightblue") +
  labs(title = "Perbandingan jenis kelamin penumpang")

  1. Perbandingan data selamat atau tidak berdasar kelas
ggplot(titanic, aes(x = factor(Pclass), fill = factor(Survived))) + 
  geom_bar(position = "fill") + labs(title = "Proporsi Survival berdasarkan kelas")

  1. Distribusi usia penumpang
ggplot(titanic, aes(x = Age)) + geom_histogram(bins=30, fill = "lightpink") + 
  labs(title = "Distribusi usia penumpang")
## Warning: Removed 177 rows containing non-finite outside the scale range
## (`stat_bin()`).

  1. Boxplot
ggplot(titanic, aes(x = factor(Survived), y = Age, fill = factor(Survived))) + 
  geom_boxplot() + labs(title = "Boxplot")
## Warning: Removed 177 rows containing non-finite outside the scale range
## (`stat_boxplot()`).

  1. distribusi harga tiket
ggplot(titanic, aes(x = Age, y = Fare)) + geom_point() + geom_smooth(method = "lm", color = "red") + labs("pengaruh umur thd 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()`).