#为什么质量的钻石更贵

ggplot(diamonds, aes(cut, price)) + geom_boxplot()

ggplot(diamonds, aes(color, price)) + geom_boxplot()

ggplot(diamonds, aes(clarity, price)) + geom_boxplot()

##注意，最差的钻石颜色是J(微黄)，最差的纯净度是I1（肉眼可见内含物）。 #价格与重量

ggplot(diamonds, aes(carat, price)) +
 geom_hex(bins = 50)

diamonds2 <- diamonds %>%
 filter(carat <= 2.5) %>%
 mutate(lprice = log2(price), lcarat = log2(carat))
ggplot(diamonds2, aes(lcarat, lprice)) +
 geom_hex(bins = 50)

mod_diamond <- lm(lprice ~ lcarat, data = diamonds2)
grid <- diamonds2 %>%
 data_grid(carat = seq_range(carat, 20)) %>%
 mutate(lcarat = log2(carat)) %>%
 add_predictions(mod_diamond, "lprice") %>%
 mutate(price = 2 ^ lprice)
ggplot(diamonds2, aes(carat, price)) +
 geom_hex(bins = 50) +
 geom_line(data = grid, color = "red", size = 1)

diamonds2 <- diamonds2 %>%
 add_residuals(mod_diamond, "lresid")
ggplot(diamonds2, aes(lcarat, lresid)) +
 geom_hex(bins = 50)

ggplot(diamonds2, aes(cut, lresid)) + geom_boxplot()

ggplot(diamonds2, aes(color, lresid)) + geom_boxplot()

ggplot(diamonds2, aes(clarity, lresid)) + geom_boxplot()

mod_diamond2 <- lm(
 lprice ~ lcarat + color + cut + clarity,
 data = diamonds2
)
grid <- diamonds2 %>%
 data_grid(cut, .model = mod_diamond2) %>%
 add_predictions(mod_diamond2)
grid
## # A tibble: 5 x 5
##   cut       lcarat color clarity  pred
##   <ord>      <dbl> <chr> <chr>   <dbl>
## 1 Fair      -0.515 G     VS2      11.2
## 2 Good      -0.515 G     VS2      11.3
## 3 Very Good -0.515 G     VS2      11.4
## 4 Premium   -0.515 G     VS2      11.4
## 5 Ideal     -0.515 G     VS2      11.4
ggplot(grid, aes(cut, pred)) +
 geom_point()

diamonds2 <- diamonds2 %>%
 add_residuals(mod_diamond2, "lresid2")
ggplot(diamonds2, aes(lcarat, lresid2)) +
 geom_hex(bins = 50)