Latihan rmarkdown w8
najwa
2025-04-25
#Latihan VDE w8
#latihan pake titanic
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, unionlibrary(ggplot2)
#import dataset
titanic = read.csv("D:/ITS/visualisasi data eksploratori/titanic2.csv.csv")tally(titanic)## n
## 1 891titanic %>%
select(1:9) %>%
sample_n(size = 10)## PassengerId Survived Pclass Name Sex
## 1 666 0 2 Hickman, Mr. Lewis male
## 2 100 0 2 Kantor, Mr. Sinai male
## 3 142 1 3 Nysten, Miss. Anna Sofia female
## 4 405 0 3 Oreskovic, Miss. Marija female
## 5 756 1 2 Hamalainen, Master. Viljo male
## 6 411 0 3 Sdycoff, Mr. Todor male
## 7 877 0 3 Gustafsson, Mr. Alfred Ossian male
## 8 446 1 1 Dodge, Master. Washington male
## 9 439 0 1 Fortune, Mr. Mark male
## 10 256 1 3 Touma, Mrs. Darwis (Hanne Youssef Razi) female
## Age SibSp Parch Ticket
## 1 32.00 2 0 S.O.C. 14879
## 2 34.00 1 0 244367
## 3 22.00 0 0 347081
## 4 20.00 0 0 315096
## 5 0.67 1 1 250649
## 6 NA 0 0 349222
## 7 20.00 0 0 7534
## 8 4.00 0 2 33638
## 9 64.00 1 4 19950
## 10 29.00 0 2 2650#summary
glimpse(titanic)#bisa plih salah stau dari ini, tp ini lebih rekomen## 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
## #Contoh visualisasi
#1. perbandingan jenis kelamin 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 = 30, fill='purple', colors='white')+
labs(title = "Distribusi Umur Penumpang")## Warning in geom_histogram(bins = 30, fill = "purple", colors = "white"):
## Ignoring unknown parameters: `colours`## 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. scatter plot
ggplot(titanic,aes(x = Age, y = Fare))+
geom_point()+
geom_smooth(method = "lm", color = 'skyblue')## `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()`).
labs(title="Pengaruh Umur terhadap Tiket")## $title
## [1] "Pengaruh Umur terhadap Tiket"
##
## attr(,"class")
## [1] "labels"