LATIHAN VDE W8

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
library(ggplot2)

#import dataset
titanic = read.csv("C:/Users/HP/Downloads/kuliah/vde/titanic2.csv.csv")

Contoh Visualisasi

1. perbandingan jenis kelamin

#1 perbandingan jenis kelamin
ggplot(titanic, aes(x=Sex)) + geom_bar(fill="maroon") +
  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. persebaran distribusi umur penumpang

ggplot(titanic, aes(x=Age)) +
  geom_histogram(bins=30, fill='navy') +
  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='navy') +
  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()`).

#Selesai yeay