R数据实训

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

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

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

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)

## geom_line: na.rm = FALSE, orientation = NA
## stat_identity: na.rm = FALSE
## position_identity

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)
ggplot(grid, aes(cut, pred)) +
 geom_point()

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