1500字范文 > 0416-F · Global Mortality · ggplot2 地图热力图条形图 · R 语言数据可视化案例源码

0416-F · Global Mortality · ggplot2 地图热力图条形图 · R 语言数据可视化案例源码

时间：2020-06-08 06:04:14

所有作品合集传送门： Tidy Tuesday

年合集传送门：

Global Mortality

What do people die from?

在过去的几个世纪里，世界发生了很大的变化–这就是《我们的世界》的数据所显示的。然而，有一件事在这种转变中一直保持不变：我们都必须在某个时候死亡。然而，随着生活水平的提高、医疗保健的进步和生活方式的改变，死亡的原因正在发生变化。

在这篇博客中，我们试图回答 “人们死于什么？”，首先看一下全球死因的数据，然后选择国家层面的例子。

世界各地的主要死因仍有很大差异，因此，也可以选择了一些国家，以突出这种异质性。

本次示例通过一些可视化方式来展示这些信息。

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//-04-16_Global_Mortality/src-f'setwd(wkdir)

3. 加载 R 包

library(scales)library(tidyverse)library(glue)library(gridExtra)library(ggpubr)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/global_mortality.xlsx")# 简要查看数据内容glimpse(df_input)

## Rows: 6,156## Columns: 35## $ country<chr> "Afghanistan", "Afghanistan…## $ country_code <chr> "AFG", "AFG", "AFG", "AFG",…## $ year <dbl> 1990, 1991, 1992, 1993, 199…## $ `Cardiovascular albertes (%)` <dbl> 17.61040, 17.80181, 18.3868…## $ `Cancers (%)`<dbl> 4.025975, 4.054145, 4.17395…## $ `Respiratory diseases (%)` <dbl> 2.106626, 2.134176, 2.20829…## $ `Diabetes (%)` <dbl> 3.832555, 3.822228, 3.90012…## $ `Dementia (%)` <dbl> 0.5314287, 0.5324973, 0.540…## $ `Lower respiratory infections (%)` <dbl> 10.886362, 10.356968, 10.09…## $ `Neonatal deaths (%)` <dbl> 9.184653, 8.938897, 8.84138…## $ `Diarrheal diseases (%)` <dbl> 2.497141, 2.572228, 2.70774…## $ `Road accidents (%)` <dbl> 3.715944, 3.729142, 3.81635…## $ `Liver disease (%)` <dbl> 0.8369093, 0.8455159, 0.874…## $ `Tuberculosis (%)`<dbl> 5.877075, 5.891704, 6.03466…## $ `Kidney disease (%)` <dbl> 1.680611, 1.671115, 1.70098…## $ `Digestive diseases (%)` <dbl> 1.058771, 1.049322, 1.06288…## $ `HIV/AIDS (%)` <dbl> 0.01301948, 0.01451458, 0.0…## $ `Suicide (%)`<dbl> 0.4366105, 0.4422802, 0.456…## $ `Malaria (%)`<dbl> 0.4488863, 0.4550191, 0.460…## $ `Homicide (%)` <dbl> 1.287020, 1.290991, 1.32616…## $ `Nutritional deficiencies (%)` <dbl> 0.3505045, 0.3432123, 0.345…## $ `Meningitis (%)` <dbl> 3.037603, 2.903202, 2.84064…## $ `Protein-energy malnutrition (%)`<dbl> 0.3297599, 0.3221711, 0.323…## $ `Drowning (%)` <dbl> 0.9838624, 0.9545860, 0.951…## $ `Maternal albert (%)` <dbl> 1.769213, 1.749264, 1.76424…## $ `Parkinson disease (%)`<dbl> 0.02515859, 0.02545063, 0.0…## $ `Alcohol disorders (%)`<dbl> 0.02899828, 0.02917152, 0.0…## $ `Intestinal infectious diseases (%)` <dbl> 0.1833303, 0.1781074, 0.176…## $ `Drug disorders (%)` <dbl> 0.04120540, 0.04203340, 0.0…## $ `Hepatitis (%)` <dbl> 0.1387378, 0.1350081, 0.134…## $ `Fire (%)` <dbl> 0.1741567, 0.1706712, 0.171…## $ `Heat-related (hot and cold exposure) (%)` <dbl> 0.1378229, 0.1348266, 0.139…## $ `Natural disasters (%)`<dbl> 0.00000000, 0.79760256, 0.3…## $ `Conflict (%)` <dbl> 0.932, 2.044, 2.408, NA, 4.…## $ `Terrorism (%)` <dbl> 0.007, 0.040, 0.027, NA, 0.…

# 检查数据的列名colnames(df_input)

## [1] "country" ## [2] "country_code" ## [3] "year"## [4] "Cardiovascular diseases (%)" ## [5] "Cancers (%)" ## [6] "Respiratory diseases (%)"## [7] "Diabetes (%)" ## [8] "Dementia (%)" ## [9] "Lower respiratory inalbertons (%)" ## [10] "Neonatal deaths (%)" ## [11] "Diarrheal diseases (%)" ## [12] "Road accidents (%)" ## [13] "Liver disease (%)" ## [14] "Tuberculosis (%)" ## [15] "Kidney disease (%)" ## [16] "Digestive diseases (%)" ## [17] "HIV/AIDS (%)" ## [18] "Suicide (%)" ## [19] "Malaria (%)" ## [20] "Homicide (%)" ## [21] "Nutritional deficiencies (%)" ## [22] "Meningitis (%)"## [23] "Protein-energy malnutrition (%)" ## [24] "Drowning (%)" ## [25] "Maternal deaths (%)" ## [26] "Parkinson disease (%)" ## [27] "Alcohol disorders (%)" ## [28] "Intestinal infectious diseases (%)"## [29] "Drug disorders (%)" ## [30] "Hepatitis (%)" ## [31] "Fire (%)" ## [32] "Heat-related (hot and cold exposure) (%)"## [33] "Natural disasters (%)" ## [34] "Conflict (%)" ## [35] "Terrorism (%)"

5. 数据预处理

df_tidy = df_input %>%# pivot_longer() 从宽数据透视到长数据转换pivot_longer(names_to = "Cause", cols = contains("%"), values_to = "Percent") %>%# 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(Percent = Percent/100,Cause = str_trim(str_to_title(sub(" [(]%[)]", "", Cause)))) # 删除缺失值的观测df_tidy <- na.omit(df_tidy)# 简要查看数据内容glimpse(df_tidy)

## Rows: 167,808## Columns: 5## $ country<chr> "Afghanistan", "Afghanistan", "Afghanistan", "Afghanistan…## $ country_code <chr> "AFG", "AFG", "AFG", "AFG", "AFG", "AFG", "AFG", "AFG", "…## $ year <dbl> 1990, 1990, 1990, 1990, 1990, 1990, 1990, 1990, 1990, 199…## $ Cause <chr> "Cardiovascular Diseases", "Cancers", "Respialbert Diseas…## $ Percent<dbl> 0.1761039712, 0.0402597540, 0.0210662613, 0.0383255475, 0…

6. 生成绘图所需数据

# 从中挑选一些需要关注的点Year <- Disease <- 'Cardiovascular Diseases'# 根据给定的年份和致死因素筛选数据df_plot <- df_tidy %>% filter(Cause == Disease, year == Year) # 获得各个国家的地图信息country.map <- df_plot %>% inner_join(maps::iso3166, by = c(country_code = "a3")) %>% inner_join(map_data("world"), by = c(mapname = "region"))# 获得给定的致死因素致死人数占各个国家死亡人口的百分比country_bar <- df_plot %>% slice_max(Percent, n = 15) %>% dplyr::mutate(country = fct_reorder(country, Percent))

7. 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(data = country.map, aes(long, lat, group = group, text = paste(round(Percent*100, 2) , "% of Deaths in", country, "were from", Disease)))# geom_polygon() 绘制的是多边形gg <- gg + geom_polygon(aes(fill = Percent))gg <- gg + borders("world")# coord_cartesian() 默认坐标系统是笛卡尔坐标系gg <- gg + coord_cartesian(ylim = c(-50, 90))# scale_fill_gradientn() 将颜色比例转换为概率转换颜色分布gg <- gg + scale_fill_gradientn(colours = c("#98FB98", "#FF4500", "#191970"), labels = percent_format())gg <- gg + labs(x = "", y = "")# theme_minimal() 去坐标轴边框的最小化主题gg <- gg + theme_minimal()gg <- gg + theme(# legend.position 设置图例位置, "bottom" 表示图例置于下方legend.position = "bottom", # legend.title 设置图例标题legend.title = element_blank(), # plot.margin 调整图像边距, 上-右-下-左plot.margin = unit(c(1, 1.5, .5, .5), "cm"))pal = colorRampPalette(colors = c("#98FB98", "#FF4500", "#191970"))hh <- ggplot(data = country_bar, aes(country, Percent, fill = country), alpha = 0.8)# geom_col() 绘制条形图hh <- hh + geom_col() # coord_flip() 倒置坐标系hh <- hh + coord_flip()# scale_y_continuous() 对连续变量设置坐标轴显示范围hh <- hh + scale_y_continuous(labels = percent_format())# scale_fill_manual() 采取的是手动赋值的方法, 也就是直接把颜色序列赋值给它的参数 valuehh <- hh + scale_fill_manual(values = rev(pal(15))) # guides() 设置图例信息, 4 列, 按行排序hh <- hh + guides(fill = guide_legend(nrow = 4, byrow = TRUE))hh <- hh + labs(x = "", y = "")# theme_minimal() 去坐标轴边框的最小化主题hh <- hh + theme_minimal()hh <- hh + theme(# legend.direction 设置图例的方向legend.direction = "horizontal",# legend.title 设置图例标题legend.title = element_blank(), # legend.position 设置图例位置, 这里指定精确的坐标legend.position = c(0.22, -0.25), # plot.margin 调整图像边距, 上-右-下-左plot.margin = unit(c(1, 1.5, 3.5, 0.5), "cm"),# panel.background 面板背景数据下面panel.background = element_rect(colour = "#CAEAFF", fill = "#CAEAFF"))

8. 保存图片到 PDF 和 PNG

filename = '0416-F-01'png(paste0(filename, ".png"), width = 920, height = 500)grid.arrange(gg, hh, ncol = 2, widths = c(3, 2), top = text_grob(label = glue("全世界每个国家由心血管疾病造成的死亡百分比·{Year}年"),hjust = .5, vjust = 1.0, size = 20, face = "bold" ))dev.off()

9. 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_0.9-5 showtextdb_3.0 sysfonts_0.8.8 ggpubr_0.4.0 ## [5] gridExtra_2.3 plotly_4.10.0 maps_3.4.0glue_1.6.2## [9] extrafont_0.18 tidytext_0.3.4 ggthemes_4.2.4 forcats_0.5.2 ## [13] stringr_1.4.1 dplyr_1.0.10 purrr_0.3.4readr_2.1.2 ## [17] tidyr_1.2.1tibble_3.1.8 ggplot2_3.3.6 tidyverse_1.3.2## [21] ggbump_0.1.0 scales_1.2.1 ## ## loaded via a namespace (and not attached):## [1] fs_1.5.2 lubridate_1.8.0httr_1.4.4 ## [4] SnowballC_0.7.0tools_4.2.1 backports_1.4.1 ## [7] bslib_0.4.0 utf8_1.2.2R6_2.5.1 ## [10] DBI_1.1.3 lazyeval_0.2.2colorspace_2.0-3 ## [13] withr_2.5.0 tidyselect_1.1.2 compiler_4.2.1## [16] extrafontdb_1.0cli_3.3.0 rvest_1.0.3 ## [19] xml2_1.3.3labeling_0.4.2sass_0.4.2 ## [22] digest_0.6.29 rmarkdown_2.16pkgconfig_2.0.3 ## [25] htmltools_0.5.3dbplyr_2.2.1 fastmap_1.1.0## [28] htmlwidgets_1.5.4 rlang_1.0.5 readxl_1.4.1 ## [31] rstudioapi_0.14farver_2.1.1 jquerylib_0.1.4 ## [34] generics_0.1.3jsonlite_1.8.0tokenizers_0.2.3 ## [37] car_3.1-0 googlesheets4_1.0.1 magrittr_2.0.3## [40] Matrix_1.5-1 Rcpp_1.0.9munsell_0.5.0## [43] fansi_1.0.3 abind_1.4-5 lifecycle_1.0.1 ## [46] stringi_1.7.8 yaml_2.3.5carData_3.0-5## [49] grid_4.2.1crayon_1.5.1 lattice_0.20-45 ## [52] haven_2.5.1 hms_1.1.2 knitr_1.40 ## [55] pillar_1.8.1 ggsignif_0.6.3reprex_2.0.2 ## [58] evaluate_0.16 data.table_1.14.2 modelr_0.1.9 ## [61] vctrs_0.4.1 tzdb_0.3.0Rttf2pt1_1.3.10 ## [64] cellranger_1.1.0 gtable_0.3.1 assertthat_0.2.1 ## [67] cachem_1.0.6 xfun_0.32 broom_1.0.1 ## [70] rstatix_0.7.0 janeaustenr_1.0.0 googledrive_2.0.0 ## [73] viridisLite_0.4.1 gargle_1.2.1 ellipsis_0.3.2