Merge branch 'PUB'

* PUB:
  minor update
  第9次课
  update

SD/20240328_9_课后作业/第8次课后作业_模板.qmd

@@ -7,18 +7,112 @@ format: html
 # 下载airquality.xlsx，并读取数据
 
 ```{r}
+#| eval: false
+#| execute: false
 # 下载至临时文件
 tmpxlsxpath <- file.path(tempdir(), "airquality.xlsx")
 download.file("https://drwater.rcees.ac.cn/git/course/RWEP/raw/branch/PUB/data/airquality.xlsx",
   destfile = tmpxlsxpath)
-airqualitydf <- readxl::read_xlsx(tmpxlsxpath, sheet = 1)
-metadf <- readxl::read_xlsx(tmpxlsxpath, sheet = 2)
+airqualitydf <- readxl::read_xlsx(tmpxlsxpath, sheet = 2)
+metadf <- readxl::read_xlsx(tmpxlsxpath, sheet = 1)
 ```
 
 # 根据`airqualitydf.xlsx`，按采样点统计白天（8:00-20:00）与夜晚（20:00-8:00）中空气质量指数（AQI）中位数，按城市统计低于所有采样点AQI30%分位值的采样点占比，列出上述占比最高的10个城市（不考虑采样点数低于5个的城市）。
 
+```{r}
+#| eval: false
+#| execute: false
+require(tidyverse)
+airqualitydf |>
+  select(datetime, site, AQI) |>
+  filter(!is.na(AQI)) |>
+  group_by(site) |>
+  summarize(AQI.median = median(AQI, na.rm = TRUE)) |>
+  left_join(metadf |> select(site, city = Area)) |>
+  group_by(city) |>
+  filter(n() > 5) |>
+  summarize(p = sum(AQI.median < quantile(airqualitydf$AQI, probs = 0.5, na.rm = TRUE)) / n()) |>
+  top_n(10, p)
 
 
+airqualitydf |>
+  select(datetime, site, AQI) |>
+  filter(!is.na(AQI)) |>
+  group_by(site) |>
+  summarize(AQI.median = median(AQI, na.rm = TRUE))
+
+airqualitydf |>
+  select(datetime, site, AQI) |>
+  filter(!is.na(AQI)) |>
+  left_join(metadf |> select(site, city = Area)) |>
+  group_by(city) |>
+  filter(length(unique(site)) >= 5) |>
+  summarize(p = sum(AQI < quantile(airqualitydf$AQI, probs = 0.2,
+    na.rm = TRUE)) / n()) |>
+  slice_max(p, n = 10)
+```
 
 
 # 按照不同城市分组，统计白天与夜晚AQI中位数是否具有显著差异。
+
+```{r}
+#| eval: false
+
+if (FALSE) {
+
+require(infer)
+testdf <- airqualitydf |>
+  select(datetime, site, AQI) |>
+  filter(!is.na(AQI)) |>
+  left_join(metadf |> select(site, city = Area)) |>
+  group_by(city) |>
+  filter(length(unique(site)) >= 5) |>
+  mutate(dayornight = factor(ifelse(between(hour(datetime), 8, 20), "day", "night"),
+    levels = c("day", "night"))
+  ) |>
+  group_by(city) |>
+  nest(citydf = -city) |>
+  mutate(median_diff = purrr::map_dbl(citydf, ~
+    .x |>
+      specify(AQI ~ dayornight) |>
+      calculate(stat = "diff in medians", order = c("day", "night")) |>
+      pull(stat)
+)) |>
+  ungroup() |>
+#  slice_sample(n = 12) |>
+  mutate(null_dist = purrr::map(citydf, ~
+    .x |>
+      specify(AQI ~ dayornight) |>
+   hypothesize(null = "independence") |>
+   generate(reps = 1000, type = "permute") |>
+      calculate(stat = "diff in medians", order = c("day", "night"))
+)) |>
+  mutate(fig = purrr::pmap(list(null_dist, median_diff, city),
+    ~ visualize(..1) +
+  shade_p_value(obs_stat = ..2, direction = "both") +
+      ggtitle(..3)
+  )) |>
+  mutate(p_value = purrr::map2_dbl(null_dist, median_diff, 
+    ~  get_p_value(.x, obs_stat = .y, direction = "both") |>
+      pull(p_value)
+  )) |>
+  arrange(p_value) |>
+  mutate(sigdiff = ifelse(p_value < 0.01, "显著差异", "无显著差异"))
+
+testdf |>
+  select(city, sigdiff) |>
+knitr::kable()
+
+  lang <- "cn"
+(testdf |>
+  slice_sample(n = 9) |>
+  pull(fig)) |>
+patchwork::wrap_plots(ncol = 3) +
+dwfun::theme_sci(5, 5)
+
+dwfun::ggsavep("./testdf.pdf")
+
+}
+
+```
+

SD/20240402_4_实践部分/index.qmd

@@ -97,3 +97,8 @@ geom_bar(position = "fill")
 ## 综合实践：三维荧光数据处理
 
 
+## 欢迎讨论！{.center}
+
+
+`r rmdify::slideend(wechat = FALSE, type = "public", tel = FALSE, thislink = "https://drwater.rcees.ac.cn/course/public/RWEP/@PUB/SD/")`
+

SD/20240402_9_课后作业/_extensions

@@ -0,0 +1 @@
+../../_extensions

SD/20240402_9_课后作业/index.qmd

@@ -0,0 +1,49 @@
+---
+title: "课后作业9"
+subtitle: 《区域水环境污染数据分析实践》<br>Data analysis practice of regional water environment pollution
+author: 苏命、王为东<br>中国科学院大学资源与环境学院<br>中国科学院生态环境研究中心
+date: today
+lang: zh
+format:
+  revealjs:
+    theme: dark
+    slide-number: true
+    chalkboard:
+      buttons: true
+    preview-links: auto
+    lang: zh
+    toc: true
+    toc-depth: 1
+    toc-title: 大纲
+    logo: ./_extensions/inst/img/ucaslogo.png
+    css: ./_extensions/inst/css/revealjs.css
+    pointer:
+      key: "p"
+      color: "#32cd32"
+      pointerSize: 18
+revealjs-plugins:
+  - pointer
+filters:
+  - d2
+---
+
+```{r}
+#| include: false
+#| cache: false
+lang <- "cn"
+require(tidyverse)
+require(learnr)
+```
+
+## 第9次课后作业
+
+自选数据集，使用R语言开展不同因子（如年份、季节、处理方式等）间某指标的差异分析，采用图表方式形成简要报告。
+
+作业模板：[第9次课后作业_模板.qmd](https://drwater.rcees.ac.cn/git/course/RWEP/raw/branch/main/SD/20240402_9_课后作业/第9次课后作业_模板.qmd)
+
+
+## 欢迎讨论！{.center}
+
+
+`r rmdify::slideend(wechat = FALSE, type = "public", tel = FALSE, thislink = "https://drwater.rcees.ac.cn/course/public/RWEP/@PUB/SD/")`
+

SD/20240402_9_课后作业/第9次课后作业_模板.qmd

@@ -0,0 +1,8 @@
+---
+title: 课后作业9
+author: 姓名
+format: html
+---
+
+要求：自选数据集，使用R语言开展不同因子间（如年份、季节、处理方式等）某指标的差异分析，采用图表+文字说明等方式形成简要报告。
+

index.qmd

@@ -19,4 +19,4 @@ subtitle: "课程简介"
 
 - 网页公开：[https://drwater.rcees.ac.cn/course/public/RWEP/\@PUB/index.html](https://drwater.rcees.ac.cn/course/public/RWEP/@PUB/index.html)
 - 课件代码：[https://drwater.rcees.ac.cn/git/course/RWEP.git](https://drwater.rcees.ac.cn/git/course/RWEP.git)
-- 代码web界面：[https://on.tty-share.com/s/KHxahtDKk7EIIMFFA60dQfh4-YgnWkkXRjzkaFV_7pSj96kDw_VxTC6Qa76UpG4Yee8/](https://on.tty-share.com/s/KHxahtDKk7EIIMFFA60dQfh4-YgnWkkXRjzkaFV_7pSj96kDw_VxTC6Qa76UpG4Yee8/)
+- 代码web界面：[https://on.tty-share.com/s/2YElKFjzniilfg3vH-d1PUqqmz_MQzNki5dyxWWL7QONCX_77GzsdP9EEAgBQu3ONwM/](https://on.tty-share.com/s/2YElKFjzniilfg3vH-d1PUqqmz_MQzNki5dyxWWL7QONCX_77GzsdP9EEAgBQu3ONwM/)