Exploratory Diamonds report - ‘diamonds’ dataset

Dataset Description

The diamonds dataset contains information on 53940 diamonds.
Variables include:

• carat — weight of the diamond (in carats)
  
• cut — quality of the cut (Fair, Good, Very Good, Premium, Ideal)
  
• color — diamond color
• clarity — clarity of the diamond
• depth, table — proportions describing the diamond’s geometry
  
• x, y, z — physical dimensions (length, width, depth in mm)
  
• price — price in US dollars

head(diamonds,10)

## # A tibble: 10 × 10
##    carat cut       color clarity depth table price     x     y     z
##    <dbl> <ord>     <ord> <ord>   <dbl> <dbl> <int> <dbl> <dbl> <dbl>
##  1  0.23 Ideal     E     SI2      61.5    55   326  3.95  3.98  2.43
##  2  0.21 Premium   E     SI1      59.8    61   326  3.89  3.84  2.31
##  3  0.23 Good      E     VS1      56.9    65   327  4.05  4.07  2.31
##  4  0.29 Premium   I     VS2      62.4    58   334  4.2   4.23  2.63
##  5  0.31 Good      J     SI2      63.3    58   335  4.34  4.35  2.75
##  6  0.24 Very Good J     VVS2     62.8    57   336  3.94  3.96  2.48
##  7  0.24 Very Good I     VVS1     62.3    57   336  3.95  3.98  2.47
##  8  0.26 Very Good H     SI1      61.9    55   337  4.07  4.11  2.53
##  9  0.22 Fair      E     VS2      65.1    61   337  3.87  3.78  2.49
## 10  0.23 Very Good H     VS1      59.4    61   338  4     4.05  2.39

summary(diamonds)

##      carat               cut        color        clarity          depth      
##  Min.   :0.2000   Fair     : 1609   D: 6774   SI1    :13063   Min.   :43.00  
##  1st Qu.:0.4000   Good     : 4902   E: 9797   VS2    :12254   1st Qu.:61.00  
##  Median :0.7000   Very Good:12081   F: 9538   SI2    : 9185   Median :61.80  
##  Mean   :0.7977   Premium  :13780   G:11284   VS1    : 8170   Mean   :61.75  
##  3rd Qu.:1.0400   Ideal    :21548   H: 8298   VVS2   : 5066   3rd Qu.:62.50  
##  Max.   :5.0100                     I: 5421   VVS1   : 3654   Max.   :79.00  
##                                     J: 2808   (Other): 2528                  
##      table           price             x                y         
##  Min.   :43.00   Min.   :  326   Min.   : 3.730   Min.   : 3.680  
##  1st Qu.:56.00   1st Qu.:  949   1st Qu.: 4.710   1st Qu.: 4.720  
##  Median :57.00   Median : 2401   Median : 5.700   Median : 5.710  
##  Mean   :57.46   Mean   : 3931   Mean   : 5.732   Mean   : 5.735  
##  3rd Qu.:59.00   3rd Qu.: 5323   3rd Qu.: 6.540   3rd Qu.: 6.540  
##  Max.   :95.00   Max.   :18823   Max.   :10.740   Max.   :58.900  
##                                                                   
##        z        
##  Min.   : 1.07  
##  1st Qu.: 2.91  
##  Median : 3.53  
##  Mean   : 3.54  
##  3rd Qu.: 4.04  
##  Max.   :31.80  
## 

Scatterplots with Trends

1. Carat vs Price

ggplot(diamonds, aes(x = carat, y = price)) +
  geom_point(alpha = 0.5, color = "steelblue") +
  geom_smooth(method = "lm", se = FALSE, color = "darkred", linewidth = 1) +
  scale_y_continuous(labels = dollar_format(), limits = c(0, 20000)) +
  scale_x_continuous(breaks = seq(0, 5, 0.5)) +
  labs(
    title = "Diamond Price vs Weight (carat)",
    x = "Carat",
    y = "Price (USD)"
  ) +
  theme(
    plot.title = element_text(face = "bold"),
    panel.grid.minor = element_blank()
  )

## `geom_smooth()` using formula = 'y ~ x'

Comment: Larger diamonds generally have higher prices - strong positive relationship.

2. Carat vs Price (log–log scale)

ggplot(diamonds, aes(x = carat, y = price)) +
  geom_point(alpha = 0.3, color = "darkgreen") +
  geom_smooth(method = "lm", se = FALSE, color = "black", linewidth = 1) +
  scale_x_log10(breaks = c(0.2, 0.5, 1, 2, 5)) +
  scale_y_log10(labels = dollar_format()) +
  labs(
    title = "Diamond Price vs Carat (log–log scale)",
    x = "Carat (log)",
    y = "Price (USD, log)"
  ) +
  theme(
    plot.title = element_text(face = "bold"),
    panel.grid.minor = element_blank()
  )

## `geom_smooth()` using formula = 'y ~ x'

Comment: On a log-log scale, the relationship looks linear.

3. Depth vs Price

ggplot(diamonds, aes(x = depth, y = price)) +
  geom_point(alpha = 0.3, color = "purple") +
  geom_smooth(method = "lm", se = FALSE, color = "orange", linewidth = 1) +
  scale_x_continuous(limits = c(50, 70), breaks = seq(50, 70, 2)) +
  scale_y_continuous(labels = dollar_format(), limits = c(0, 20000)) +
  labs(
    title = "Diamond Price vs Depth Percentage",
    x = "Depth (%)",
    y = "Price (USD)"
  ) +
  theme(
    plot.title = element_text(face = "bold"),
    panel.grid.minor = element_blank()
  )

## `geom_smooth()` using formula = 'y ~ x'

Comment: Depth alone has a weak effect on price.

4. Price vs Length

ggplot(diamonds, aes(x = x, y = price)) +
  geom_point(alpha = 0.3, color = "darkcyan") +
  geom_smooth(method = "lm", se = FALSE, color = "brown", linewidth = 1) +
  scale_x_continuous(limits = c(3, 10), breaks = seq(3, 10, 1)) +
  scale_y_continuous(labels = dollar_format(), limits = c(0, 20000)) +
  labs(
    title = "Diamond Price vs Length (in mm)",
    x = "Length (mm)",
    y = "Price (USD)"
  ) +
  theme(
    plot.title = element_text(face = "bold"),
    panel.grid.minor = element_blank()
  )

## `geom_smooth()` using formula = 'y ~ x'

Comment: Longer diamonds tend to have higher prices.