---

Independent Exercise: Practice Data Science

Name : Naufal Akmal Rizqulloh
NIM : G6401231065
Day, Date (Lecture) : Wednesday, 16 September 2026 (5)
Teacher : Dr. Bagus Sartono, S.Si, M.Si
Grade :

---

Number 1

library(ggplot2)

## Warning: package 'ggplot2' was built under R version 4.4.3

library(dplyr)

## Warning: package 'dplyr' was built under R version 4.4.3

## 
## 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

data("mpg")
dt1_avg_cty <- mpg %>%
  group_by(manufacturer) %>%
  summarise(average = mean(cty)) %>%
  arrange(desc(average)) %>%
  slice_head(n = 10)

dt1_avg_cty

## # A tibble: 10 × 2
##    manufacturer average
##    <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(data = dt1_avg_cty, aes(x = reorder(manufacturer, average), y = average)) +
  geom_col(fill = "steelblue") + 
  coord_flip() + 
  labs(
    title = "Average of City Mileage (cty) based on Top 10 Manufacturers",
    x = "Manufacturer",
    y = "Average City Mileage (mpg)"
  ) + 
  theme_minimal()

Interpretation: The bar chart shows that Honda has the highest average city mileage among the top 10 manufacturers, followed closely by Volkswagen and Subaru.

Number 2

library(ggplot2)
data("diamonds")
ggplot(data = diamonds, aes(x = depth, fill = cut, color = cut)) +
  geom_density(alpha = 0.3, linewidth = 0.8) +
  labs(
    title = "Distribution of Depth across Cut Quality",
    x = "Depth",
    y = "Density",
    fill = "Cut Quality",
    color = "Cut Quality"
  ) +
  theme_minimal()

Interpretation: The density plot illustrates that diamonds with a “Fair” cut have a wider and more varied distribution of depth, whereas higher quality cuts like “Ideal” are highly concentrated around a specific depth value (around 61-62).

Number 3

library(ggplot2)
library(dplyr)
data("diamonds")
set.seed(123)
diamonds_sample <- diamonds %>% sample_n(1000)

ggplot(data = diamonds_sample,
       aes(x = carat, y = price,
           color = cut)) +
  geom_point(alpha = 0.7, size = 2) +
  scale_color_viridis_d() +
  labs(
    title = "Relationship between Price and Carat",
    subtitle = "Sample of 1000 diamonds",
    x = "Carat",
    y = "Price",
    color = "Cut Quality"
  ) +
  theme_minimal()

Interpretation: There is a strong positive, non-linear relationship between carat and price. As carat increases, the price tends to increase exponentially. Additionally, for a given carat size, diamonds with better cut qualities (e.g., Ideal, Premium) generally command higher prices.

Number 4

library(ggplot2)
library(dplyr)
data("economics")
ggplot(data = economics,
       aes(x = date,
           y = psavert)) +
  geom_line(color = "darkred", linewidth = 0.7) +
  geom_vline(xintercept = as.numeric(as.Date("2008-01-01")), linetype = "dashed", color = "blue", linewidth = 1) +
  annotate("text", x = as.Date("2008-01-01"), y = 15, label = "2008 Financial Crisis", hjust = -0.1, color = "blue", fontface = "bold") +
  scale_y_continuous(
    labels = scales::comma
  ) +
  labs(
    title = "Personal Savings Rate (psavert) Over Time",
    x = "Year",
    y = "Personal Savings Rate (%)"
  ) +
  theme_minimal()

## Warning in scale_x_date(): A <numeric> value was passed to a Date scale.
## ℹ The value was converted to a <Date> object.

Interpretation: The personal savings rate fluctuated significantly over time, showing a general downward trend from the 1970s until the mid-2000s. A noticeable spike occurred around the 2008 financial crisis, which is highlighted with a blue dashed line, likely as people began saving more during economic uncertainty.

Number 5

# 1. Visualization with 3 presentation problems
ggplot(data = mpg, aes(x = class, y = hwy)) +
  geom_point(color = "yellow", size = 1) + 
  theme_dark() + 
  labs(title = "hwy vs class", x = "c", y = "h")

# 2. Improved Visualization
ggplot(data = mpg, aes(x = reorder(class, hwy, FUN = median), y = hwy, fill = class)) +
  geom_boxplot(alpha = 0.7, show.legend = FALSE) +
  scale_fill_viridis_d() +
  coord_flip() +
  labs(
    title = "Highway Mileage Distribution by Vehicle Class",
    x = "Vehicle Class",
    y = "Highway Mileage (mpg)"
  ) +
  theme_minimal() +
  theme(plot.title = element_text(face = "bold"))

Explanation of Changes: 1. Inappropriate Geometry: The original plot used simple points (geom_point) for a categorical vs. continuous variable, causing severe overplotting. It was changed to geom_boxplot to properly show the distribution and summary statistics. 2. Poor Aesthetics and Theme: Yellow points on a dark background (theme_dark()) were hard to read and visually unappealing. This was replaced with a cleaner theme_minimal() and a colorblind-friendly palette (viridis). 3. Unclear Labels and Ordering: The original labels (“c”, “h”, “hwy vs class”) were uninformative and the classes were ordered alphabetically. I added clear, descriptive titles and axis labels, and reordered the boxes by median highway mileage for better readability.