用ggplot2绘制美观的柱状图

发表于

实习的时候看完了一本讲解ggplot2包的书，名字叫做《Guide to CreateBeautiful Graphics in R》。
老实说，这本书虽然有很多例子，但讲的很浅，也许这本书的定位就是参考手册吧。^^…看完了里面柱状图的内容，感觉配色不是很美观。
于是乎自己动手绘制了以下的两幅柱状图，其中配色方案来自The Pudding。感觉这个博客
图像的配色方案让人赏心悦目，自己就仿照着也画一画^^…

图1，单因子映射

1
2
library(janeaustenr)
library(tidyverse)
1
#> Warning: package 'tibble' was built under R version 3.4.1
1
#> Warning: package 'purrr' was built under R version 3.4.1
1
2
3
4
5
6
7
8
9
10
11
12
library(tidytext)
austen_books() %>%
  select(2, 1) %>%
  unnest_tokens(word, text, token = "ngrams", n = 2) %>%
  print() %>% 
  # A token is a meaningful unit of text, most often a word, 
  # that we are interested in using for further analysis, 
  # and tokenization is the process of splitting text into tokens.
  count(word, sort = TRUE) %>% 
  top_n(10) ->
  top_10_austen_bigrams
1
2
3
4
5
6
7
8
9
10
11
12
13
14
#> # A tibble: 725,049 x 2
#>                   book            word
#>                 <fctr>           <chr>
#>  1 Sense & Sensibility       sense and
#>  2 Sense & Sensibility and sensibility
#>  3 Sense & Sensibility  sensibility by
#>  4 Sense & Sensibility         by jane
#>  5 Sense & Sensibility     jane austen
#>  6 Sense & Sensibility     austen 1811
#>  7 Sense & Sensibility    1811 chapter
#>  8 Sense & Sensibility       chapter 1
#>  9 Sense & Sensibility           1 the
#> 10 Sense & Sensibility      the family
#> # ... with 725,039 more rows
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
library(ggthemes)
## 一元映射
top_10_austen_bigrams %>% 
  print() %>% 
  ggplot(aes(x = reorder(word, n), y = n)) +
  geom_bar(stat = "identity", fill = "#E7962A") +  # `柱子`填充色为“橘黄色”
  coord_flip() +
  theme_fivethirtyeight() +
  theme(panel.background = element_rect(fill = "#FCF0E1"), # 图片背景填充色为“土黄色”
        plot.background = element_rect(fill = "#FCF0E1")) +
  geom_text(aes(label = n), hjust = -0.3) + # hjust/vjust调整`标签`的位置
  # 标题
  labs(title = "Words Frequency Count",
       subtitle = "Made in 2017-08-25，by Leo Lee",
       caption = "Source: janeaustenr package",
       xlab = "", ylab = "")
1
2
3
4
5
6
7
8
9
10
11
12
13
#> # A tibble: 10 x 2
#>        word     n
#>       <chr> <int>
#>  1   of the  3017
#>  2    to be  2787
#>  3   in the  2368
#>  4   it was  1781
#>  5     i am  1545
#>  6  she had  1472
#>  7   of her  1445
#>  8   to the  1387
#>  9  she was  1377
#> 10 had been  1299

barplot1

图2，双因子映射

1
2
3
4
5
6
7
8
9
10
11
12
austen_books() %>%
  select(2, 1) %>%
  filter(book %in% c("Sense & Sensibility", "Pride & Prejudice")) %>% 
  unnest_tokens(word, text, token = "ngrams", n = 1) %>%
  anti_join(stop_words, by = "word") %>% 
  print() %>% 
  group_by(book) %>% 
  count(book, word, sort = TRUE) %>% 
  top_n(15) %>% 
  ungroup() %>% 
  mutate(n2 = if_else(book == "Sense & Sensibility", -n, n)) ->
  austen_2_books
1
2
3
4
5
6
7
8
9
10
11
12
13
14
#> # A tibble: 73,576 x 2
#>                   book    word
#>                 <fctr>   <chr>
#>  1 Sense & Sensibility   rival
#>  2 Sense & Sensibility   rival
#>  3   Pride & Prejudice   rival
#>  4   Pride & Prejudice  _near_
#>  5   Pride & Prejudice  _near_
#>  6 Sense & Sensibility growing
#>  7 Sense & Sensibility growing
#>  8 Sense & Sensibility growing
#>  9 Sense & Sensibility growing
#> 10 Sense & Sensibility growing
#> # ... with 73,566 more rows
1
print(austen_2_books)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
#> # A tibble: 30 x 4
#>                   book      word     n    n2
#>                 <fctr>     <chr> <int> <int>
#>  1 Sense & Sensibility    elinor   623  -623
#>  2   Pride & Prejudice elizabeth   597   597
#>  3 Sense & Sensibility  marianne   492  -492
#>  4   Pride & Prejudice     darcy   373   373
#>  5   Pride & Prejudice    bennet   294   294
#>  6   Pride & Prejudice      miss   283   283
#>  7   Pride & Prejudice      jane   264   264
#>  8   Pride & Prejudice   bingley   257   257
#>  9 Sense & Sensibility      time   239  -239
#> 10 Sense & Sensibility  dashwood   231  -231
#> # ... with 20 more rows
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
austen_2_books %>% 
  ggplot(aes(x = reorder(word, n2), y = n2, fill = book)) +
  geom_bar(stat = "identity") +
  theme_fivethirtyeight() +
  theme(panel.background = element_rect(fill = "#FCF0E1"), # 图片背景填充色为“土黄色”
        plot.background = element_rect(fill = "#FCF0E1"),
        legend.background = element_blank()) +
  # 标题
  labs(title = "Words Frequency Count 2",
       subtitle = "Made in 2017-08-25，by Leo Lee",
       caption = "Source: janeaustenr package",
       xlab = "", ylab = "",
       fill = "") +
  scale_fill_manual(values = c("#F26B68", "#0991DB")) +
  scale_y_continuous(position = "right") +
  coord_flip() +
  geom_text(data = filter(austen_2_books, book == "Sense & Sensibility"), 
            aes(x = , y = , label = n), hjust = 1.5) +
  geom_text(data = filter(austen_2_books, book != "Sense & Sensibility"), 
            aes(x = , y = , label = n), hjust = -0.5)

barplot2