1500字范文 > 0402-F · US Tuition Costs · pheatmap 绘制热图 · R 语言数据可视化案例源码

0402-F · US Tuition Costs · pheatmap 绘制热图 · R 语言数据可视化案例源码

时间：2020-05-13 12:56:06

所有作品合集传送门： Tidy Tuesday

年合集传送门：

US Tuition Costs

Average Tuition and Educational Attainment in the United States。

Tidy Tuesday 在 GitHub 上的传送地址：

Thomas Mock (). Tidy Tuesday: A weekly data project aimed at the R ecosystem./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./CRAN/"))

2. 设置工作路径

wkdir <- '/home/user/R_workdir/TidyTuesday//-04-02_US_Tuition_Costs/src-f'setwd(wkdir)

3. 加载 R 包

library(tidyverse)library(pheatmap)library(RColorBrewer)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> "Alalbert", "Alaska", "Arizona", "Arkansas", "California", "C…## $ `-05` <dbl> 5682.838, 4328.281, 5138.495, 5772.302, 5285.921, 4703.777, …## $ `-06` <dbl> 5840.550, 4632.623, 5415.516, 6082.379, 5527.881, 5406.967, …## $ `-07` <dbl> 5753.496, 4918.501, 5481.419, 6231.977, 5334.826, 5596.348, …## $ `-08` <dbl> 6008.169, 5069.822, 5681.638, 6414.900, 5672.472, 6227.002, …## $ `-09` <dbl> 6475.092, 5075.482, 6058.464, 6416.503, 5897.888, 6284.137, …## $ `-10` <dbl> 7188.954, 5454.607, 7263.204, 6627.092, 7258.771, 6948.473, …## $ `-11` <dbl> 8071.134, 5759.153, 8839.605, 6900.912, 8193.739, 7748.201, …## $ `-12` <dbl> 8451.902, 5762.421, 9966.716, 7028.991, 9436.426, 8315.632, …## $ `-13` <dbl> 9098.069, 6026.143, 10133.503, 7286.580, 9360.574, 8792.856,…## $ `-14` <dbl> 9358.929, 6012.445, 10296.200, 7408.495, 9274.193, 9292.954,…## $ `-15` <dbl> 9496.084, 6148.808, 10413.844, 7606.410, 9186.824, 9298.599,…## $ `-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" "-05" "-06" "-07" "-08" "-09" "-10"## [8] "-11" "-12" "-13" "-14" "-15" "-16"

5. 数据预处理

# 调整年份为 YYYY 格式, 方便绘图展示df_tidy <- df_input %>%dplyr::rename("" = "-05","" = "-06","" = "-07","" = "-08","" = "-09","" = "-10","" = "-11","" = "-12","" = "-13","" = "-14","" = "-15","" = "-16")# 将 State 转换为字符串格式df_tidy$State <- as.character(df_tidy$State)# 从美元值中去除 "$" 和 "," 符号indx <- sapply(df_tidy, is.factor)df_tidy[indx] <- lapply(df_tidy[indx], function(x) as.numeric(gsub("[,$]", "", x)))# 自定义一个函数, 用于创建矩阵但保留行名mat.convert <- function(i) {# tibble 转换为 data.frame 格式, 否则会报错i <- as.data.frame(i)mat <- as.matrix(i[, -1])rownames(mat) <- i[, 1]mat} df_plot <- mat.convert(df_tidy)# 简要查看数据内容glimpse(df_plot)

## num [1:50, 1:12] 5683 4328 5138 5772 5286 ...## - attr(*, "dimnames")=List of 2## ..$ : chr [1:50] "Alabama" "Alaska" "Arizona" "Arkansas" ...## ..$ : chr [1:12] "" "" "" "" ...

6. 用 pheatmap 绘制热图

# 自定义调色板palette <- colorRampPalette(c("blue", "red"))(100)# 使用 pheatmap() 函数绘制热图figure = pheatmap(df_plot, color = palette, cluster_cols = FALSE, border_color = NA, cellwidth = 30, cellheight = 10)

7 保存图片到 PDF 和 PNG

filename = '0402-F-01'ggsave(figure, filename = paste0(filename, ".pdf"), width = 10, height = 7.6, device = cairo_pdf)ggsave(figure, filename = paste0(filename, ".png"), width = 10, height = 7.6, dpi = 100, device = "png")

8. session-info

sessionInfo()

## R version 4.2.1 (-06-23)## Platform: x86_64-pc-linux-gnu (64-bit)## Running under: Ubuntu 20.04.5 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=CLC_TELEPHONE=C ## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C ## ## attached base packages:## [1] statsgraphics grDevices utilsdatasets methods base## ## other attached packages:## [1] showtext_0.9-5showtextdb_3.0sysfonts_0.8.8RColorBrewer_1.1-3## [5] pheatmap_1.0.12 forcats_0.5.2stringr_1.4.1dplyr_1.0.10## [9] purrr_0.3.4 readr_2.1.2 tidyr_1.2.1 tibble_3.1.8## [13] ggplot2_3.3.6tidyverse_1.3.2 ## ## loaded via a namespace (and not attached):## [1] lubridate_1.8.0assertthat_0.2.1 digest_0.6.29## [4] utf8_1.2.2R6_2.5.1 cellranger_1.1.0 ## [7] backports_1.4.1reprex_2.0.2 evaluate_0.16## [10] highr_0.9 httr_1.4.4pillar_1.8.1 ## [13] rlang_1.0.5 googlesheets4_1.0.1 readxl_1.4.1 ## [16] rstudioapi_0.14jquerylib_0.1.4rmarkdown_2.16## [19] textshaping_0.3.6 googledrive_2.0.0 munsell_0.5.0## [22] broom_1.0.1 compiler_4.2.1modelr_0.1.9 ## [25] xfun_0.32 systemfonts_1.0.4 pkgconfig_2.0.3 ## [28] htmltools_0.5.3tidyselect_1.1.2 fansi_1.0.3 ## [31] crayon_1.5.1 tzdb_0.3.0dbplyr_2.2.1 ## [34] withr_2.5.0 grid_4.2.1jsonlite_1.8.0## [37] gtable_0.3.1 lifecycle_1.0.1DBI_1.1.3## [40] magrittr_2.0.3scales_1.2.1 cli_3.3.0## [43] stringi_1.7.8 cachem_1.0.6 fs_1.5.2 ## [46] xml2_1.3.3bslib_0.4.0 ragg_1.2.3 ## [49] ellipsis_0.3.2generics_0.1.3vctrs_0.4.1 ## [52] tools_4.2.1 glue_1.6.2hms_1.1.2## [55] fastmap_1.1.0 yaml_2.3.5colorspace_2.0-3 ## [58] gargle_1.2.1 rvest_1.0.3 knitr_1.40 ## [61] haven_2.5.1 sass_0.4.2