namer

beauty_of_across.Rmd

@@ -5,7 +5,7 @@ dplyr 1.0版本增加了`across()`函数，这个函数集中体现了dplyr宏
 
 
 
-```{r message=FALSE, warning=FALSE}
+```{r beauty-of-across-1, message=FALSE, warning=FALSE}
 library(tidyverse)
 library(palmerpenguins)
 penguins
@@ -14,7 +14,7 @@ penguins
 ��唳獢���憭撩憭勗€潘��€閬�霈⊥�銝€�撩憭勗€潛��圈�嚗��批虜閫���
 
 
-```{r}
+```{r beauty-of-across-2}
 penguins %>%
   summarise(
     na_in_species = sum(is.na(species)),
@@ -29,7 +29,7 @@ penguins %>%
 ```
 撟訾��唳獢��銝�憭��芣�8��憒��唳獢������停���暑鈭��隞��憭蝎斐銋捆��€�瑟�嚗�隞祈�嗆�啁`summarise_all()`嚗�
 
-```{r}
+```{r beauty-of-across-3}
 penguins %>%
   summarise_all(
     ~ sum(is.na(.))
@@ -38,7 +38,7 @@ penguins %>%
 
 �箏末��€�Ｙ揣嚗�隞祆��隡�蝐餃���嚗��霈∪��敺�桃��€潘�餈葵憟質秩嚗�亙�隞��
 
-```{r}
+```{r beauty-of-across-4}
 penguins %>%
   group_by(species) %>%
   summarise(
@@ -52,7 +52,7 @@ penguins %>%
 �€`summarise_if()`�瑟�
 
 
-```{r}
+```{r beauty-of-across-5}
 d1 <- penguins %>%
   group_by(species) %>%
   summarise_if(is.numeric, mean, na.rm = TRUE)
@@ -63,7 +63,7 @@ d1
 �寞�銝�嚗�霂凋�銝�蝞�憟賜�閫�€� 雿�鈭��year`, ��灼summarise_if()`銝剔 `is.numeric & !year`�餅�`year`嚗瘝⊥��€犖蝐餌�甈脫��舀�蝛瑞�嚗�隞祈��€閬�霈⊥�蝏�隡��葵�堆��嗅��僎�唬�韏瑯€�甇歹��賑���
 
 
-```{r}
+```{r beauty-of-across-6}
 d2 <- penguins %>%
   group_by(species) %>%
   summarise(
@@ -73,7 +73,7 @@ d2
 ```
 
 �€��撟�
-```{r}
+```{r beauty-of-across-7}
 d1 %>% left_join(d2, by = "species")
 ```
 
@@ -85,12 +85,12 @@ d1 %>% left_join(d2, by = "species")
 
 `across()`��堆�霈抵�銝€��敺���皜嚗��Ｖ�甇亙����其�嚗�甇交�摰�
 
-```{r out.width = '75%', echo = FALSE}
+```{r beauty-of-across-8, out.width = '75%', echo = FALSE}
 knitr::include_graphics("images/across_cover.jpg")
 ```
 
 
-```{r}
+```{r beauty-of-across-9}
 penguins %>%
   group_by(species) %>%
   summarise(
@@ -103,7 +103,7 @@ penguins %>%
 ## across()�賣敶Ｗ�
 
 `across()`�賣嚗���銝芯蜓閬��嚗�
-```{r, eval = FALSE}
+```{r beauty-of-across-10, eval = FALSE}
 across(.cols = , .fns = , .names = )
 ```
 
@@ -153,7 +153,7 @@ across(.cols = , .fns = , .names = )
 ### 瘙�銝€��蝻箏仃�潭��
 
 撠望�祉�撘€憪��€瘙�
-```{r, eval=FALSE}
+```{r beauty-of-across-11, eval=FALSE}
 penguins %>%
   summarise(
     na_in_species = sum(is.na(species)),
@@ -168,7 +168,7 @@ penguins %>%
 ```
 
 
-```{r}
+```{r beauty-of-across-12}
 # using across()
 penguins %>%
   summarise(
@@ -189,7 +189,7 @@ penguins %>%
 
 ### 瘥葵蝐餃���銝�憭�蝏�
 
-```{r}
+```{r beauty-of-across-13}
 penguins %>%
   summarise(
     distinct_species = n_distinct(species),
@@ -214,7 +214,7 @@ penguins %>%
 ### 憭�憭葵蝏恣�賣
 
 
-```{r}
+```{r beauty-of-across-14}
 penguins %>%
   group_by(species) %>%
   summarise(
@@ -246,7 +246,7 @@ penguins %>%
 鈭�銝�餈��畔across()`銝summarise()`�撩憭抒��絲��
 
 
-```{r}
+```{r beauty-of-across-15}
 penguins %>%
   group_by(species, island) %>%
   summarise(
@@ -283,7 +283,7 @@ penguins %>%
 
 ### 銝���銝憭���霈�
 
-```{r}
+```{r beauty-of-across-16}
 # using across()
 penguins %>%
   group_by(species) %>%
@@ -299,7 +299,7 @@ penguins %>%
 
 ### �唳������
 
-```{r}
+```{r beauty-of-across-17}
 std <- function(x) {
   (x - mean(x, na.rm = TRUE)) / sd(x, na.rm = TRUE)
 }
@@ -326,7 +326,7 @@ penguins %>%
 
 ### �唳撖寞����
 
-```{r}
+```{r beauty-of-across-18}
 # using across()
 penguins %>%
   drop_na() %>%
@@ -351,7 +351,7 @@ penguins %>%
 ### �典�蝏遣璅∩葉銝cur_data()`��雿輻
 
 
-```{r}
+```{r beauty-of-across-19}
 penguins %>%
   group_by(species) %>%
   summarise(
@@ -388,7 +388,7 @@ penguins %>%
 ### 銝cur_column()`��雿輻
 
 
-```{r}
+```{r beauty-of-across-20}
 # 瘥���隞亙��芰�蝟餅
 df   <- tibble(x = 1:3, y = 3:5, z = 5:7)
 mult <- list(x = 1, y = 10, z = 100)
@@ -427,7 +427,7 @@ df %>% mutate(
 
 ### 銝c_across()`��銋暺�
 
-```{r}
+```{r beauty-of-across-21}
 df <- tibble(x = 1:3, y = 3:5, z = 5:7)
 
 df %>%
@@ -450,13 +450,13 @@ df %>%
 - �唳獢葉���銵��雿�
 - 銝��扯捶��雿���臭誑銝€韏瑕��綽�銝�left_join()`
 
-```{r out.width = '90%', echo = FALSE, fig.cap = "across()函数总结图"}
+```{r beauty-of-across-22, out.width = '90%', echo = FALSE, fig.cap = "across()�賣�餌��<U+3E65>"}
 knitr::include_graphics("images/across.png")
 ```
 
 
 
-```{r, echo = F}
+```{r beauty-of-across-23, echo = F}
 # remove the objects
 # ls() %>% stringr::str_flatten(collapse = ", ")
 
@@ -465,7 +465,7 @@ rm(cutoffs, d1, d2, df, mult, std, weights)
 
 
 
-```{r, echo = F, message = F, warning = F, results = "hide"}
+```{r beauty-of-across-24, echo = F, message = F, warning = F, results = "hide"}
 pacman::p_unload(pacman::p_loaded(), character.only = TRUE)
 ```
 

broom.Rmd

@@ -5,7 +5,7 @@
 
 还是用第 \@ref(ggplot2-geom) 章的`gapminder`案例
 
-```{r}
+```{r broom-1}
 library(tidyverse)
 library(gapminder)
 gapminder
@@ -17,15 +17,15 @@ gapminder
 ### 可视化探索
 
 画个简单的图
-```{r}
+```{r broom-2}
 gapminder %>%
   ggplot(aes(x = log(gdpPercap), y = lifeExp)) +
   geom_point(alpha = 0.2)
 ```
 
 我们想用**不同的模型**拟合`log(gdpPercap)`与`lifeExp`的关联
 
-```{r}
+```{r broom-3}
 library(colorspace)
 
 model_colors <- colorspace::qualitative_hcl(4, palette = "dark 2")
@@ -58,7 +58,7 @@ ggplot(
 ### 简单模型
 
 还是回到我们今天的主题。我们建立一个简单的线性模型
-```{r}
+```{r broom-4}
 out <- lm(
   formula = lifeExp ~ gdpPercap + pop + continent,
   data = gapminder
@@ -67,12 +67,12 @@ out
 ```
 
 
-```{r, eval=FALSE}
+```{r broom-5, eval=FALSE}
 str(out)
 ```
 
 
-```{r}
+```{r broom-6}
 summary(out)
 ```
 
@@ -83,7 +83,7 @@ knitr::include_graphics("images/lm-object-schematic.png")
 ```
 
 我们发现`out`对象包含了很多元素，比如系数、残差、模型残差自由度等等，用读取列表的方法可以直接读取
-```{r, eval=FALSE}
+```{r broom-7, eval=FALSE}
 out$coefficients
 out$residuals
 out$fitted.values
@@ -100,7 +100,7 @@ out$fitted.values
 为规整模型结果，这里我们推荐用[David Robinson](http://varianceexplained.org/about/) 开发的`broom`宏包。
 
 
-```{r message = FALSE, warning = FALSE}
+```{r broom-8, message = FALSE, warning = FALSE}
 library(broom)
 ```
 
@@ -118,13 +118,13 @@ library(broom)
 
 ### tidy
 
-```{r}
+```{r broom-9}
 tidy(out)
 ```
 
 
 
-```{r}
+```{r broom-10}
 out %>%
   tidy() %>%
   ggplot(mapping = aes(
@@ -137,14 +137,14 @@ out %>%
 
 
 可以很方便的获取系数的置信区间
-```{r}
+```{r broom-11}
 out %>%
   tidy(conf.int = TRUE)
 ```
 
 
 
-```{r}
+```{r broom-12}
 out %>%
   tidy(conf.int = TRUE) %>%
   filter(!term %in% c("(Intercept)")) %>%
@@ -166,12 +166,12 @@ out %>%
 `augment()`会返回一个数据框，这个数据框是在原始数据框的基础上，增加了模型的拟合值（`.fitted`）, 拟合值的标准误（`.se.fit`）, 残差（`.resid`）等列。
 
 
-```{r}
+```{r broom-13}
 augment(out)
 ```
 
 
-```{r}
+```{r broom-14}
 out %>%
   augment() %>%
   ggplot(mapping = aes(x = lifeExp, y = .fitted)) +
@@ -185,7 +185,7 @@ out %>%
 `glance()` 函数也会返回数据框，但这个数据框只有一行，内容实际上是`summary()`输出结果的最底下一行。
 
 
-```{r}
+```{r broom-15}
 glance(out)
 ```
 
@@ -195,15 +195,15 @@ glance(out)
 
 broom的三个主要函数在分组统计建模时，格外方便。
 
-```{r}
+```{r broom-16}
 penguins <-
   palmerpenguins::penguins %>%
   drop_na()
 ```
 
 
 
-```{r}
+```{r broom-17}
 penguins %>%
   group_nest(species) %>%
   mutate(model = purrr::map(data, ~ lm(bill_depth_mm ~ bill_length_mm, data = .))) %>%
@@ -213,7 +213,7 @@ penguins %>%
 
 
 
-```{r}
+```{r broom-18}
 fit_ols <- function(df) {
   lm(body_mass_g ~ bill_depth_mm + bill_length_mm, data = df)
 }
@@ -231,7 +231,7 @@ out_tidy
 
 
 
-```{r}
+```{r broom-19}
 out_tidy %>%
   ggplot(aes(
     x = species, y = estimate,
@@ -246,13 +246,13 @@ out_tidy %>%
 
 
 
-```{r, echo = F}
+```{r broom-20, echo = F}
 # remove the objects
 # rm(list=ls())
 rm(out, out_tidy, penguins, model_colors, fit_ols)
 ```
 
 
-```{r, echo = F, message = F, warning = F, results = "hide"}
+```{r broom-21, echo = F, message = F, warning = F, results = "hide"}
 pacman::p_unload(pacman::p_loaded(), character.only = TRUE)
 ```