TITANIC

Import data

data = read.csv("titanic2.csv.csv")

DISTRIBUSI USIA PENUMPANG

ggplot(data, aes(x=Age, fill=Sex)) + 
  geom_histogram(bins=20, position = "dodge") +
  scale_fill_manual(values = c("female" = "pink","male" = "cyan"))

## Warning: Removed 177 rows containing non-finite outside the scale range
## (`stat_bin()`).

  labs(title = "Distribusi Usia Penumpang")

## $title
## [1] "Distribusi Usia Penumpang"
## 
## attr(,"class")
## [1] "labels"

JENIS KELAMIN PENUMPANG

ggplot(data, aes(x=Sex, fill=Sex)) +
  geom_bar() + 
  scale_fill_manual(values = c("male" = "cyan", "female" = "pink")) +
  labs(title = "JENIS KELAMIN PENUMPANG") +
    geom_text(
    stat = "count",
    aes(label = ..count..),
    vjust = -0.5
    )

## Warning: The dot-dot notation (`..count..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(count)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

PROPORSI PENUMPANG SELAMAT SETIAP PASSANGER CLASS

ggplot(data, aes(x = factor(Pclass), fill = factor(Survived))) +
  geom_bar(position = "dodge") +
  scale_fill_manual(values = c("0" = "grey", "1" = "green")) +
  labs(title = "Proporsi Survival Setiap PClass") +
   geom_text(
    stat = "count",
    aes(label = ..count..),
    position = position_dodge(width = 0.9), 
    vjust = -0.2
  )

RELASI UMUR TERHADAP HARGA TIKET

ggplot(data, aes(x=Age, y=Fare)) + 
geom_point(color = 'blue') +
geom_smooth(method="lm", color='red') +
  labs(title="Pengaruh Usia 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()`).