Dimaond

Dataset Description

dataset Structure

str(diamonds)

## tibble [53,940 × 10] (S3: tbl_df/tbl/data.frame)
##  $ carat  : num [1:53940] 0.23 0.21 0.23 0.29 0.31 0.24 0.24 0.26 0.22 0.23 ...
##  $ cut    : Ord.factor w/ 5 levels "Fair"<"Good"<..: 5 4 2 4 2 3 3 3 1 3 ...
##  $ color  : Ord.factor w/ 7 levels "D"<"E"<"F"<"G"<..: 2 2 2 6 7 7 6 5 2 5 ...
##  $ clarity: Ord.factor w/ 8 levels "I1"<"SI2"<"SI1"<..: 2 3 5 4 2 6 7 3 4 5 ...
##  $ depth  : num [1:53940] 61.5 59.8 56.9 62.4 63.3 62.8 62.3 61.9 65.1 59.4 ...
##  $ table  : num [1:53940] 55 61 65 58 58 57 57 55 61 61 ...
##  $ price  : int [1:53940] 326 326 327 334 335 336 336 337 337 338 ...
##  $ x      : num [1:53940] 3.95 3.89 4.05 4.2 4.34 3.94 3.95 4.07 3.87 4 ...
##  $ y      : num [1:53940] 3.98 3.84 4.07 4.23 4.35 3.96 3.98 4.11 3.78 4.05 ...
##  $ z      : num [1:53940] 2.43 2.31 2.31 2.63 2.75 2.48 2.47 2.53 2.49 2.39 ...

summary

summary(diamonds)

##      carat               cut        color        clarity          depth      
##  Min.   :0.2000   Fair     : 1610   D: 6775   SI1    :13065   Min.   :43.00  
##  1st Qu.:0.4000   Good     : 4906   E: 9797   VS2    :12258   1st Qu.:61.00  
##  Median :0.7000   Very Good:12082   F: 9542   SI2    : 9194   Median :61.80  
##  Mean   :0.7979   Premium  :13791   G:11292   VS1    : 8171   Mean   :61.75  
##  3rd Qu.:1.0400   Ideal    :21551   H: 8304   VVS2   : 5066   3rd Qu.:62.50  
##  Max.   :5.0100                     I: 5422   VVS1   : 3655   Max.   :79.00  
##                                     J: 2808   (Other): 2531                  
##      table           price             x                y         
##  Min.   :43.00   Min.   :  326   Min.   : 0.000   Min.   : 0.000  
##  1st Qu.:56.00   1st Qu.:  950   1st Qu.: 4.710   1st Qu.: 4.720  
##  Median :57.00   Median : 2401   Median : 5.700   Median : 5.710  
##  Mean   :57.46   Mean   : 3933   Mean   : 5.731   Mean   : 5.735  
##  3rd Qu.:59.00   3rd Qu.: 5324   3rd Qu.: 6.540   3rd Qu.: 6.540  
##  Max.   :95.00   Max.   :18823   Max.   :10.740   Max.   :58.900  
##                                                                   
##        z         
##  Min.   : 0.000  
##  1st Qu.: 2.910  
##  Median : 3.530  
##  Mean   : 3.539  
##  3rd Qu.: 4.040  
##  Max.   :31.800  
## 

univariate Analysis

Histogram of Carat

ggplot(diamonds ,aes(carat)) +
  geom_histogram( fill = "skyblue", color = "black") +
  geom_vline(xintercept = mean(carat), color = "red", linetype = "dashed") +
  geom_vline(xintercept = median(carat), color = "green", linetype = "dashed") +
  labs(title = "Histogram of Carat",
       x = "Carat Value",
       y = "Count")  

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Histogram for price

ggplot(diamonds ,aes(price)) +
  geom_histogram( fill = "skyblue", color = "black") +
  geom_vline(xintercept = mean(price), color = "red", linetype = "dashed") +
  geom_vline(xintercept = median(price), color = "green", linetype = "dashed") +
  labs(title = "Histogram for price",
       x = "Price",
       y = "Frequence")  +
  xlim(c(0,10000))  

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

## Warning: Removed 5222 rows containing non-finite outside the scale range
## (`stat_bin()`).

## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_bar()`).

cut Quality

ggplot(diamonds, aes(x = cut)) +
  geom_bar(fill = "skyblue", color = "black") +  # Basic barplot with color
  labs(title = "Count of Diamonds by Cut Quality",
       x = "Cut Quality",
       y = "Count")

Color

ggplot(diamonds, aes(x = color)) +
  geom_bar(fill = "skyblue", color = "black") +  # Basic barplot with color
  labs(title = "Count of Diamonds by COlor",
       x = "Color",
       y = "Count")

Clarity

ggplot(diamonds, aes(x = clarity)) +
  geom_bar(fill = "skyblue", color = "black") +  # Basic barplot with color
  labs(title = "Count of Diamonds by clarity",
       x = "clarity",
       y = "Count")

Carat vs. Price colored by Cut

ggplot(diamonds, aes(x = carat, y = price, color = cut)) +
  geom_point(alpha = 0.5) +
  labs(title = "Carat vs. Price colored by Cut")

Price distribution across Cuts and Colors

ggplot(diamonds, aes(x = cut, y = price, fill = color)) +
  geom_boxplot() +
  labs(title = "Price distribution across Cuts and Colors")

Price distribution across Clarity and Colors

ggplot(diamonds,aes(x=clarity,y=price,fill=color)) +
  geom_boxplot()+
  labs(title = "Price distribution across Clarity and Colors")

Boxplot of Diamond Prices by Color

ggplot(diamonds, aes(x = color, y = price)) +
  geom_boxplot() +  # Create the boxplot
  labs(title = "Boxplot of Diamond Prices by Color",
       x = "Cut Quality",
       y = "Price (in USD)")

Boxplot of Diamond Prices by Cut

ggplot(diamonds, aes(x = cut, y = price)) +
  geom_boxplot() +  # Create the boxplot
  labs(title = "Boxplot of Diamond Prices by Cut",
       x = "Cut Quality",
       y = "Price (in USD)")