所有作品合集传送门: Tidy Tuesday
2018 年合集传送门: 2018
US Tuition Costs
Average Tuition and Educational Attainment in the United States。
Tidy Tuesday 在 GitHub 上的传送地址:
Thomas Mock (2022). Tidy Tuesday: A weekly data project aimed at the R ecosystem. https://github.com/rfordatascience/tidytuesday
1. 一些环境设置
# 设置为国内镜像, 方便快速安装模块
options("repos" = c(CRAN = "https://mirrors.tuna.tsinghua.edu.cn/CRAN/"))
2. 设置工作路径
wkdir <- '/home/user/R_workdir/TidyTuesday/2018/2018-04-02_US_Tuition_Costs/src-a'
setwd(wkdir)
3. 加载 R 包
library(scales)
library(tidyverse)
library(extrafont)
library(gghighlight)
library(showtext)
# 在 Ubuntu 系统上测试的, 不加这个我画出来的汉字会乱码 ~
showtext_auto()
4. 加载数据
df_input <- readxl::read_excel("../data/us_avg_tuition.xlsx")
# 简要查看数据内容
glimpse(df_input)
## Rows: 50
## Columns: 13
## $ State <chr> "Alabama", "Alaska", "Arizona", "Arkansas", "California", "C…
## $ `2004-05` <dbl> 5682.838, 4328.281, 5138.495, 5772.302, 5285.921, 4703.777, …
## $ `2005-06` <dbl> 5840.550, 4632.623, 5415.516, 6082.379, 5527.881, 5406.967, …
## $ `2006-07` <dbl> 5753.496, 4918.501, 5481.419, 6231.977, 5334.826, 5596.348, …
## $ `2007-08` <dbl> 6008.169, 5069.822, 5681.638, 6414.900, 5672.472, 6227.002, …
## $ `2008-09` <dbl> 6475.092, 5075.482, 6058.464, 6416.503, 5897.888, 6284.137, …
## $ `2009-10` <dbl> 7188.954, 5454.607, 7263.204, 6627.092, 7258.771, 6948.473, …
## $ `2010-11` <dbl> 8071.134, 5759.153, 8839.605, 6900.912, 8193.739, 7748.201, …
## $ `2011-12` <dbl> 8451.902, 5762.421, 9966.716, 7028.991, 9436.426, 8315.632, …
## $ `2012-13` <dbl> 9098.069, 6026.143, 10133.503, 7286.580, 9360.574, 8792.856,…
## $ `2013-14` <dbl> 9358.929, 6012.445, 10296.200, 7408.495, 9274.193, 9292.954,…
## $ `2014-15` <dbl> 9496.084, 6148.808, 10413.844, 7606.410, 9186.824, 9298.599,…
## $ `2015-16` <dbl> 9751.101, 6571.340, 10646.278, 7867.297, 9269.844, 9748.188,…
# 检查数据的列名
colnames(df_input)
## [1] "State" "2004-05" "2005-06" "2006-07" "2007-08" "2008-09" "2009-10"
## [8] "2010-11" "2011-12" "2012-13" "2013-14" "2014-15" "2015-16"
5. 数据预处理
5.1 调整列名
# 将列名简化, 方便绘图展示
tuition <- df_input %>%
dplyr::rename(
"state" = "State",
"2004" = "2004-05",
"2005" = "2005-06",
"2006" = "2006-07",
"2007" = "2007-08",
"2008" = "2008-09",
"2009" = "2009-10",
"2010" = "2010-11",
"2011" = "2011-12",
"2012" = "2012-13",
"2013" = "2013-14",
"2014" = "2014-15",
"2015" = "2015-16")
5.2. 数据倒置
# 从宽数据透视到长数据转换
tuition <- pivot_longer(tuition,
cols = "2004":"2015",
names_to = "year",
values_to = "cost")
5.3. 分组计算历年变化及百分比
df_plot <- tuition %>%
group_by(state) %>%
arrange(year) %>%
# 建议使用 dplyr::mutate 形式调用函数, 不然容易与 plyr 中的函数冲突 (因为我自己就报错了...)
dplyr::mutate(change = (dplyr::last(cost) - dplyr::first(cost)),
change_perc = change/dplyr::first(cost)*100) %>%
ungroup()
6. 利用 ggplot2 绘图
# PS: 方便讲解, 我这里进行了拆解, 具体使用时可以组合在一起
gg <- ggplot(df_plot, aes(x = as.numeric(year), y = cost, color = state))
gg <- gg + geom_line(size = 2)
gg <- gg + geom_point(size = 4)
gg <- gg + scale_colour_viridis_d()
# gghighlight 根据条件高亮其中符合条件的线图
gg <- gg + gghighlight(change_perc > 100, use_group_by = FALSE, unhighlighted_params = list(color = "grey", size = .5))
gg <- gg + scale_x_continuous(breaks = seq(2004, 2015, 1))
# 利用 scales::dollar_format() 函数展示美元符号
gg <- gg + scale_y_continuous(labels = scales::dollar_format())
gg <- gg + labs(title = "美国各个州的大学学费变化",
subtitle = "2004年至2015年,三个州的学费增长超过100%",
x = NULL,
y = NULL)
# theme_minimal() 去坐标轴边框的最小化主题
gg <- gg + theme_minimal()
# theme() 实现对非数据元素的调整, 对结果进行进一步渲染, 使之更加美观
gg <- gg + theme(
# panel.grid.major 主网格线, 这一步表示删除主要网格线
panel.grid.major = element_blank(),
# panel.grid.minor 次网格线, 这一步表示删除次要网格线
panel.grid.minor = element_blank(),
# axis.text 坐标轴刻度文本
axis.text = element_text(color = "black", size = 12),
# axis.title 坐标轴标题
axis.title = element_text(color = "black", size = 10),
# plot.title 主标题
plot.title = element_text(color = "black", size = 20, face = "bold"),
# plot.subtitle 次要标题
plot.subtitle = element_text(color = "red", size = 12),
# plot.background 图片背景
plot.background = element_rect(fill = "white"))
7. 保存图片到 PDF 和 PNG
gg
albert = '20180402-A-01'
ggsave(filename = paste0(albert, ".pdf"), width = 8.6, height = 5, device = cairo_pdf)
ggsave(filename = paste0(albert, ".png"), width = 8.6, height = 5, dpi = 100, device = "png")
8. session-info
sessionInfo()
## R version 4.2.1 (2022-06-23)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 20.04.4 LTS
##
## Matrix products: default
## BLAS: /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3
## LAPACK: /usr/lib/x86_64-linux-gnu/openblas-pthread/liblapack.so.3
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
## [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
## [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] showtext_0.9-5 showtextdb_3.0 sysfonts_0.8.8 gghighlight_0.3.3
## [5] extrafont_0.18 forcats_0.5.2 stringr_1.4.1 dplyr_1.0.10
## [9] purrr_0.3.4 readr_2.1.2 tidyr_1.2.1 tibble_3.1.8
## [13] ggplot2_3.3.6 tidyverse_1.3.2 scales_1.2.1
##
## loaded via a namespace (and not attached):
## [1] httr_1.4.4 sass_0.4.2 jsonlite_1.8.0
## [4] viridisLite_0.4.1 modelr_0.1.9 bslib_0.4.0
## [7] assertthat_0.2.1 highr_0.9 googlesheets4_1.0.1
## [10] cellranger_1.1.0 yaml_2.3.5 ggrepel_0.9.1
## [13] Rttf2pt1_1.3.10 pillar_1.8.1 backports_1.4.1
## [16] glue_1.6.2 extrafontdb_1.0 digest_0.6.29
## [19] rvest_1.0.3 colorspace_2.0-3 htmltools_0.5.3
## [22] pkgconfig_2.0.3 broom_1.0.1 haven_2.5.1
## [25] tzdb_0.3.0 googledrive_2.0.0 generics_0.1.3
## [28] farver_2.1.1 ellipsis_0.3.2 cachem_1.0.6
## [31] withr_2.5.0 cli_3.3.0 magrittr_2.0.3
## [34] crayon_1.5.1 readxl_1.4.1 evaluate_0.16
## [37] fs_1.5.2 fansi_1.0.3 xml2_1.3.3
## [40] textshaping_0.3.6 tools_4.2.1 hms_1.1.2
## [43] gargle_1.2.1 lifecycle_1.0.1 munsell_0.5.0
## [46] reprex_2.0.2 compiler_4.2.1 jquerylib_0.1.4
## [49] systemfonts_1.0.4 rlang_1.0.5 grid_4.2.1
## [52] rstudioapi_0.14 labeling_0.4.2 rmarkdown_2.16
## [55] gtable_0.3.1 DBI_1.1.3 R6_2.5.1
## [58] lubridate_1.8.0 knitr_1.40 fastmap_1.1.0
## [61] utf8_1.2.2 ragg_1.2.3 stringi_1.7.8
## [64] Rcpp_1.0.9 vctrs_0.4.1 dbplyr_2.2.1
## [67] tidyselect_1.1.2 xfun_0.32
测试数据
配套数据下载:us_avg_tuition.xlsx