Tugas Praktikum 3

Data Visualization

1 Comparison - MPG

library(ggplot2)
library(ggridges)
library(tidyverse)
library(dplyr)

manu_grup <- mpg |> 
  group_by(manufacturer) |> 
  summarise(mean_cty = mean(cty)) |> 
  arrange(desc(mean_cty)) |> 
  slice_head(n=10)
manu_grup

# A tibble: 10 × 2
   manufacturer mean_cty
   <chr>           <dbl>
 1 honda            24.4
 2 volkswagen       20.9
 3 subaru           19.3
 4 hyundai          18.6
 5 toyota           18.5
 6 nissan           18.1
 7 audi             17.6
 8 pontiac          17  
 9 chevrolet        15  
10 ford             14  

ggplot(
  manu_grup, 
  aes(
    x=reorder(manufacturer, mean_cty), 
    y = mean_cty)) + 
      geom_col() +
      coord_flip() + 
      labs(
        title = "Average Highway Fuel Efficiency by Manufacturer",
        x = NULL,
        y = "Average highway fuel efficiency (mpg)"
      ) +
        theme_minimal()

2 Distribution - Diamonds

ggplot(
  diamonds,
  aes(
    x = price,
    y=cut,
    fill = cut)) +
      geom_density_ridges(
        alpha = 0.8,
        show.legend= FALSE) +
          labs(
            title = "Distribution of Diamond Prices by Cut Quality",
            x = "Price (USD)",
            y = "Density"
            ) +
      theme_minimal() + 
      theme(legend.position = "bottom")

3 Relationship - Diamonds sample

diamonds_sample <- diamonds |> 
  slice_sample(n = 25000)

ggplot(
  diamonds_sample,
  aes(
    x = carat,
    y = price,
    color = cut)) +
      geom_point(alpha = 0.5) +
      labs(
        title = "Relationship Between Diamond Weight and Price by Cut Quality",
        x = "Diamond weight (carat)",
        y = "Price (USD)",
        color = "Cut quality"
      ) +
      theme_minimal() 

4 Time Series - Economics

ggplot(
  economics,
  aes(
    x = date,
    y = psavert)) +
      geom_line(linewidth = 0.7) +
      scale_y_continuous(
        labels = scales::comma) +
          labs(
            title = "Changes in the Personal Saving Rate",
            x = "Time",
            y = "Saving Rate"
            ) 

5 Improve Visualization

mpg_class <- mpg |> 
  group_by(class) |> 
  summarise(
    mean_hwy = mean(hwy),
    jumlah = n(),
    .groups = "drop"
  ) |> 
  arrange(mean_hwy)

mpg_class

# A tibble: 7 × 3
  class      mean_hwy jumlah
  <chr>         <dbl>  <int>
1 pickup         16.9     33
2 suv            18.1     62
3 minivan        22.4     11
4 2seater        24.8      5
5 midsize        27.3     41
6 subcompact     28.1     35
7 compact        28.3     47

plot_before <- ggplot(
  mpg_class,
  aes(x = class, y = mean_hwy, fill = class)
) +
  geom_col() +
    coord_cartesian(ylim = c(15, 30)) +
  labs(
    title = "MPG",
    x = "Class",
    y = "Value"
  ) +
    theme_minimal() +
    theme(legend.position = "none")
  
  plot_before

    # MASALAH 1:
    # Sumbu Y tidak dimulai dari 0 sehingga
    # perbedaan antar kategori terlihat terlalu besar.
  
    # MASALAH 2:
    # Judul dan label terlalu umum.

    # MASALAH 3:
    # Banyak warna digunakan hanya sebagai dekorasi.

plot_after <- ggplot(
  mpg_class,
  aes(x = reorder(class, mean_hwy), y = mean_hwy)
) +
  geom_col(width = 0.7) +

  # Label nilai
  geom_text(
    aes(label = sprintf("%.1f", mean_hwy)),
    hjust = -0.15,
    size = 3.8
  ) +

  # Membuat nama kategori lebih mudah dibaca
  coord_flip() +

  # Sumbu dimulai dari 0
  scale_y_continuous(
    limits = c(0, 32),
    breaks = seq(0, 30, 5)
  ) +

  labs(
    title = "Average Highway Fuel Efficiency by Vehicle Class",
    subtitle = "Higher values indicate better highway fuel efficiency",
    x = "Vehicle class",
    y = "Average highway fuel efficiency (mpg)"
  ) +

  theme_minimal(base_size = 12) +

  theme(
    plot.title = element_text(face = "bold"),
    panel.grid.major.y = element_blank(),
    panel.grid.minor = element_blank()
  )

plot_after