- Load the diamonds dataset, which is included with the ggplot2 package. Identify which variables in the diamond set are numeric, and which are catgorical (factors).
library(ggplot2)
str(diamonds)
## Classes 'tbl_df', 'tbl' and 'data.frame': 53940 obs. of 10 variables:
## $ carat : num 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 61.5 59.8 56.9 62.4 63.3 62.8 62.3 61.9 65.1 59.4 ...
## $ table : num 55 61 65 58 58 57 57 55 61 61 ...
## $ price : int 326 326 327 334 335 336 336 337 337 338 ...
## $ x : num 3.95 3.89 4.05 4.2 4.34 3.94 3.95 4.07 3.87 4 ...
## $ y : num 3.98 3.84 4.07 4.23 4.35 3.96 3.98 4.11 3.78 4.05 ...
## $ z : num 2.43 2.31 2.31 2.63 2.75 2.48 2.47 2.53 2.49 2.39 ...
- Generate summary level descriptive statistics: Show the mean, median, 25th and 75th quartiles, min, and max for each of the applicable variables in diamonds.
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
##
summary(diamonds$carat)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.2000 0.4000 0.7000 0.7979 1.0400 5.0100
quantile(diamonds$carat)
## 0% 25% 50% 75% 100%
## 0.20 0.40 0.70 1.04 5.01
- Determine the frequency for each of the diamond colors.
table(diamonds$color )
##
## D E F G H I J
## 6775 9797 9542 11292 8304 5422 2808
with (diamonds, table(color))
## color
## D E F G H I J
## 6775 9797 9542 11292 8304 5422 2808
- Determine the frequency for each of the diamond cuts, by color
table(diamonds$cut, diamonds$color )
##
## D E F G H I J
## Fair 163 224 312 314 303 175 119
## Good 662 933 909 871 702 522 307
## Very Good 1513 2400 2164 2299 1824 1204 678
## Premium 1603 2337 2331 2924 2360 1428 808
## Ideal 2834 3903 3826 4884 3115 2093 896
with (diamonds, table(cut, color))
## color
## cut D E F G H I J
## Fair 163 224 312 314 303 175 119
## Good 662 933 909 871 702 522 307
## Very Good 1513 2400 2164 2299 1824 1204 678
## Premium 1603 2337 2331 2924 2360 1428 808
## Ideal 2834 3903 3826 4884 3115 2093 896
- Create a graph for a single numeric variable.
hist(diamonds$carat , main = 'Diamonds Carat Data' )
boxplot(diamonds$carat , main = 'Diamonds Carat Data')
table(diamonds$cut )
##
## Fair Good Very Good Premium Ideal
## 1610 4906 12082 13791 21551
pie(table(diamonds$cut ))
- Create a scatterplot of two numeric variables.
scatter.smooth(x=diamonds$carat, y=diamonds$price)
plot(diamonds$price ~ diamonds$carat)
qplot(carat, price, data=diamonds)
ggplot(diamonds, aes(x=carat, y=price) ) + geom_point()