R數(shù)據(jù)科學(xué)第五章

library(tidyverse)

變量的分布進(jìn)行可視化

ggplot(data = diamonds) +
  geom_bar(mapping = aes(x = cut))

圖片.png

• 觀測(cè)值可以使用dplyr::count()計(jì)算統(tǒng)計(jì)

diamonds %>%
  count(cut)

圖片.png

連續(xù)變量，用直方圖

ggplot(data = diamonds) +
  geom_histogram(mapping = aes(x = carat), binwidth = 0.5)

圖片.png

• 當(dāng)然也可以用dplry::count和ggplot::cut_width進(jìn)行手動(dòng)統(tǒng)計(jì)
  diamonds %>% count(cut_width(carat, 0.5))
  

  圖片.png

• 根據(jù)自己的目的選擇直方圖的寬度矮锈，如果選擇小于3克拉的鉆石

smaller <- diamonds %>%
  filter(carat < 3)
ggplot(data = smaller, mapping = aes(x = carat)) +
  geom_histogram(binwidth = 0.1)

圖片.png

• 如果使用疊加的條形圖則用geom_freqpoly代替geom_histogram,但前者是折線圖統(tǒng)計(jì)

ggplot(data = smaller, mapping = aes(x = carat, color = cut)) +
  geom_histogram(binwidth = 0.1)
ggplot(data = smaller, mapping = aes(x = carat, color = cut)) +
  geom_freqpoly(binwidth = 0.1)

ggplot(data = smaller, mapping = aes(x = carat)) +
        geom_histogram(binwidth = 0.1)
ggplot(data = faithful, mapping = aes(x = eruptions)) +
  geom_histogram(binwidth = 0.25)

圖片.png

圖片.png

5.3異常值

ggplot(diamonds) +
  geom_histogram(mapping = aes(x = y), binwidth = 0.5)

圖片.png

• coord_cartesian（）放到靠近0的數(shù)值

ggplot(diamonds) +
  geom_histogram(mapping = aes(x = y), binwidth =0.5) +
  coord_cartesian(ylim = c(0,50))

圖片.png

• 可以看到有三個(gè)異常的數(shù)值,利用dplry中的filter將他們 找到

unusual <- diamonds %>%
  filter(y < 3 | y > 20) %>%
  arrange(y)
unusual

圖片.png

ggplot(unusual) +
  geom_histogram(mapping = aes(x = y), binwidth =0.5) +
  coord_cartesian(ylim = c(0,50))

圖片.png

鉆石為0.99克拉和1克拉的數(shù)量如失，為什么出現(xiàn)這樣的結(jié)果

m0.99 <- diamonds %>%
  filter(carat == 0.99)
m0.99
m1 <- diamonds %>%
  filter(carat == 1)
m1

圖片.png

• 缺失值

diamonds2 <- diamonds %>% 
  filter(between(y, 3, 20)) %>%
  arrange(y)
diamonds2

• 利用缺失值NA代替異常值,mutate()

diamonds3 <- diamonds %>%
  mutate(y = ifelse(y < 3|y >20, NA, y))
diamonds3

• ggplot2中遵循無視缺失值的原則鸠踪，忽略缺失值

ggplot(data = diamonds3, mapping = aes(x = x, y = y)) +
  geom_point()
###Warning message:
Removed 9 rows containing missing values (geom_point).

• 警告忽略缺失值，可用na.rn = TURE,消除警告
  ggplot(data = diamonds3, mapping = aes(x = x, y = y)) + geom_point(na.rm = TRUE)

圖片.png

• 下邊這個(gè)沒看懂 原文是：弄清楚造成缺失值的觀測(cè)和沒有缺失值的觀測(cè)間的區(qū)別的原因，例如：在nycflights13::flights 中跟压，dep_time變量中的缺失值表示 航班取消了，因子架忌，應(yīng)該比較一下 已取消的航班和未取消航班的計(jì)劃出發(fā)時(shí)間愧沟，利用is.na()函數(shù)創(chuàng)建一個(gè)新變量來完成這個(gè)操作

nycflights13::flights %>% 
  mutate(
    cancelled = is.na(dep_time),
    sched_hour = sched_dep_time %/% 100,
    sched_min = sched_dep_time %% 100,
    sched_dep_time = sched_hour + sched_min / 60 
  ) %>%
  ggplot(mapping = aes(sched_dep_time)) + 
  geom_freqpoly(
    mapping = aes(color = cancelled),
    binwidth = 1/4)

圖片.png

相關(guān)變動(dòng)是兩個(gè)或者多個(gè)變量以相關(guān)的方式共同變化所表現(xiàn)出的趨勢(shì)

• ** 分類變量和連續(xù)變量**

ggplot(data = diamonds, mapping = aes(x = price)) +
  geom_freqpoly(mapping = aes(color = cut), binwidth = 500)

圖片.png

• 注：應(yīng)為數(shù)量差別很大和難看出差距
• 將縱坐標(biāo)改成密度 density，相當(dāng)于對(duì)計(jì)數(shù)進(jìn)行了標(biāo)準(zhǔn)化粤咪，這樣每個(gè)頻率多邊形下面的面積都是1

ggplot(data = diamonds, mapping = aes(x = price, y = ..density..)) +
  geom_freqpoly(mapping = aes(color = cut), binwidth = 500)

圖片.png

箱線圖可以將分類變量進(jìn)行可視化

• geom_boxplot函數(shù)查看切割質(zhì)量和價(jià)格分布

ggplot(data = diamonds, mapping = aes(x = cut, y = price)) +
  geom_boxplot(mapping = aes(color = cut)
)

圖片.png

• 利用reorder()函數(shù)進(jìn)行排列

ggplot(data = mpg, mapping = aes(x = class, y = hwy)) +
  geom_boxplot()
ggplot(data = mpg, mapping = aes(x = reorder(class, hwy, FUN = median), y = hwy)) +
  geom_boxplot() 

圖片.png

圖片.png

• 利用coord_flip將函數(shù)圖形旋轉(zhuǎn)90度

ggplot(data = mpg, mapping = aes(x = reorder(class, hwy, FUN = median), y = hwy)) +
  geom_boxplot() +
  coord_flip()

圖片.png