1500字范文 > 0416-E · Global Mortality · ggplot2 plotly 动态折线图 · R 语言数据可视化案例源码

0416-E · Global Mortality · ggplot2 plotly 动态折线图 · R 语言数据可视化案例源码

时间：2024-03-25 01:57:21

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。

plotly包是一个基于浏览器的交互式图表库，建立在开源的 JavaScript 图表库 plotly.js 上。

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-e'setwd(wkdir)

3. 加载 R 包

library(scales)library(tidyverse)library(glue)library(plotly)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 diseases (%)` <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 deficialbert (%)` <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 deaths (%)` <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 albertious 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 infections (%)" ## [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 malalberton (%)" ## [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", "Respiratory Albert…## $ Percent<dbl> 0.1761039712, 0.0402597540, 0.0210662613, 0.0383255475, 0…

6. 利用 ggplot2 绘图

# 以中国地区的数据为例画图# 从中挑选一些需要关注的点Country = "China"Diseases = c('Cardiovascular Diseases', 'Cancers', 'Diabetes', 'Suicide', 'Homicide', 'Neonatal Deaths', 'Tuberculosis')line.plot = df_tidy %>% filter(Cause %in% Diseases, country == Country)gg <- line.plot %>% ggplot(aes(year, Percent, col = Cause,text = paste("年份:", year, "\n致死因素: ", Cause, "\n百分比:", round(Percent, 4)*100, "%")))# geom_line() 添加折线图gg <- gg + geom_line(aes(lty = Cause, group = 1), lwd = 0.8)gg <- gg + scale_x_continuous(breaks = seq(1990, , by = 5), limits = c(1989, ))gg <- gg + scale_y_continuous(labels = percent_format())gg <- gg + labs(title = glue("死亡因素致死变化情况中国 {Country}"),subtitle = "历年死亡变化情况",x ='年份',y = '百分比 (%)')# theme_classic2() 经典白色背景, L坐标系主体gg <- gg + theme_classic2()# 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(),# plot.title 主标题plot.title = element_text(hjust = 0.1, color = "black", size = 20, face = "bold"),# axis.text 坐标轴刻度文本axis.text = element_text(hjust = 0.1, size = 12),# plot.caption 说明文字plot.caption = element_text(hjust = -0.85),# legend.direction 设置图例的方向legend.direction = "vertical", # legend.position 设置图例位置legend.position = "right")

7. 保存图片到 HTML

ggplotly(gg, tooltip = c("text"))

原图：0416-E-01.html

filename = '0416-E-01'htmlwidgets::saveWidget(ggplotly(gg, tooltip = c("text")), paste0(filename, ".html"))

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_0.9-5 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_1.8.0crosstalk_1.2.0 ## [37] tokenizers_0.2.3 car_3.1-0 googlesheets4_1.0.1## [40] magrittr_2.0.3Matrix_1.5-1 Rcpp_1.0.9 ## [43] munsell_0.5.0 fansi_1.0.3 abind_1.4-5 ## [46] lifecycle_1.0.1stringi_1.7.8 yaml_2.3.5 ## [49] carData_3.0-5 grid_4.2.1crayon_1.5.1 ## [52] lattice_0.20-45haven_2.5.1 hms_1.1.2## [55] knitr_1.40pillar_1.8.1 ggsignif_0.6.3## [58] reprex_2.0.2 evaluate_0.16 data.table_1.14.2 ## [61] modelr_0.1.9 vctrs_0.4.1 tzdb_0.3.0 ## [64] Rttf2pt1_1.3.10cellranger_1.1.0 gtable_0.3.1 ## [67] assertthat_0.2.1 cachem_1.0.6 xfun_0.32## [70] broom_1.0.1 rstatix_0.7.0 janeaustenr_1.0.0 ## [73] googledrive_2.0.0 viridisLite_0.4.1 gargle_1.2.1 ## [76] ellipsis_0.3.2