小编SCD*_*DCE的帖子

很基本，但我认为我不太了解这种变化：

library(dplyr)
library(lubridate)

Lab_import_sql <- Lab_import %>%
    select_if(~sum(!is.na(.)) > 0) %>%
    mutate_if(is.factor, as.character) %>%
    mutate_if(is.character, funs(ifelse(is.character(.), trimws(.),.))) %>%
    mutate_at(.vars = Lab_import %>% select_if(grepl("'",.)) %>% colnames(),
                 .funs = gsub,
                 pattern = "'",
                 replacement = "''") %>%
    mutate_if(is.character, funs(ifelse(is.character(.), paste0("'", ., "'"),.))) %>%
    mutate_if(is.Date, funs(ifelse(is.Date(.), paste0("'", ., "'"),.)))

编辑：

感谢大家的投入，这里是可复制的代码和我的解决方案：

library(dplyr)
library(lubridate)

import <- data.frame(Test_Name = "Fir'st Last", 
                     Test_Date = "2019-01-01", 
                     Test_Number = 10)

import_sql <-import %>%
  select_if(~!all(is.na(.))) %>%
  mutate_if(is.factor, as.character) %>%
  mutate_if(is.character, trimws) %>%
  mutate_if(is.character, list(~gsub("'", "''",.))) %>% 
  mutate_if(is.character, list(~paste0("'", ., …

当我向期刊提交论文时，期刊要求我将字体大小设置为7.5，但是当我使用以下代码时，只有轴文本发生了变化，标签大小保持不变，

    library(ggplot2)
    library(FactoMineR)
    library(factoextra)

    irispca <- PCA(iris,quali.sup = 5)
    fviz_pca_var(irispca)+
   theme(text = element_text(size = 7.5),
         axis.title = element_text(size = 7.5),
         axis.text = element_text(size = 7.5)
         )

任何建议都可以告诉我应该使用什么代码来更改标签大小？

我geom_label用来绘制文本。默认情况下，标签（框）的宽度取决于文本的宽度。但是，我想要统一的标签尺寸。也就是说，我想要文本后面矩形的固定大小，而不管字符串的长度。

我当前标签的示例，根据字符串长度具有不同的大小：

我如何制作看起来像这样的标签：

我查看了geom_label github，它看起来不太好，我在想也许是某种修改unit() 的方法，但我什么也做不了。

对于一些可重现的代码：

library(ggplot2)
ggplot(mtcars, aes(wt, mpg, label = rownames(mtcars))) +
geom_text(check_overlap = TRUE) +
geom_label(aes(fill= factor(cyl)))

你将如何使所有标签的尺寸相同？

我正在尝试将一些标签部分斜体化，但仍然具有sum()功能，但我不知道该怎么做：

library(ggplot2)
library(reshape2)

iris_mean <- aggregate(iris[,1:4], by=list(Species=iris$Species), FUN=mean) 
iris_sd <- aggregate(iris[,1:4], by=list(Species=iris$Species), FUN=sd) 
df_mean <- melt(iris_mean, id.vars=c("Species"), variable.name = "Samples", value.name="Values")
df_sd <- melt(iris_sd, id.vars=c("Species"), variable.name = "Samples", value.name="Values")
limits <- aes(ymax = df_mean[,"Values"] + df_sd[,"Values"], ymin=df_mean[,"Values"] - df_sd[,"Values"])
df_mean$Species <- factor(df_mean$Species, levels=unique(df_mean$Species), ordered=TRUE)

ggplot(df_mean, aes(Samples, Values, fill = Species)) + 
  geom_bar(position="dodge", stat="identity") + coord_flip() + 
  theme(axis.text.y=element_text(angle=0, hjust=1)) +
  theme_minimal() +
  theme(
    legend.position = "bottom",
    plot.margin = unit(c(1,1,.5,0),"cm"),
    legend.key.size = unit(.5, "lines"),
    axis.text.y = element_text(face = "italic")
  ) …

相当简单的问题我似乎无法想出一个优雅的解决方案。

我想通过不同的降序排列一列数据：

library(dplyr)
test <- data.frame(ID=c(19000,19001,19002,1,2))

test %>% 
  arrange(desc(ID)) %>%
  mutate(ID = formatC(ID,width=5,format="d",flag="0"))

     ID
1 19002
2 19001
3 19000
4 00002
5 00001

我想要：

     ID
1 00002
2 00001
3 19002
4 19001
5 19000

这是用于管道，因此将添加更多 ID，例如 00003、00004....

这是我想出的东西：

test %>% 
  mutate(ID = formatC(ID,width=5,format="d",flag="0")) %>% 
  group_by(group=substr(ID,1,1)) %>% 
  arrange(desc(ID)) %>% 
  arrange(group) %>% 
  ungroup() %>% 
  select(ID)

还有比这更好的吗？

编辑 -

library(microbenchmark)

test <- data.frame(ID=c(1:29999))

microbenchmark(group = test %>% 
                 mutate(ID = formatC(ID,width=5,format="d",flag="0"),
                        group = substr(ID,1,1)) %>% 
                 arrange(group, desc(ID)) %>% 
                 select(ID),

               mod = test …

我看过这个答案：错误 in bind_rows_(x, .id) : Column can't be convert from factor to numeric but I can't mutate_all()a list。

library(rvest)
library(dplyr)
library(tidyr)

fips <- read_html("https://www.census.gov/geo/reference/ansi_statetables.html") %>% 
  html_nodes("table") %>% 
  html_table() %>% 
  bind_rows(.[[1]][1:3] %>% 
          transmute(name = `Name`,
                    fips = as.character(`FIPS State Numeric Code`),
                    abb = `Official USPS Code`),
        filter(.[[2]][1:3], !grepl("Status",c(`Area Name`))) %>% 
          transmute(name = `Area Name`,
                    fips = as.character(`FIPS State Numeric Code`),
                    abb = `Official USPS Code`))

Error in bind_rows_(list_or_dots(...), id = NULL) : 
  Column `FIPS State Numeric Code` can't be …

我的数据看起来像这样:

dat <- data.frame(SOURCES1 = c("123 Name, 123 Rd, City, State", 
                               "354 Name, 354 Rd, City, State",
                               NA,"",""),
                  SOURCES2 = c("","",
                               "321 Name, 321 Rd, City, State", 
                               "678 Name, 678 Rd, City, State",
                               ""),
                  SOURCES3 = c("","",NA,
                               "678 Name, 678 Rd, City, State", 
                               NA),
                  SOURCES4 = c("","","",NA,NA),
                  SOURCES5 = c("","","",NA,NA))

我正在寻找一个看起来像这样的列:

"123 Name, 123 Rd, City, State"
"354 Name, 354 Rd, City, State"
"321 Name, 321 Rd, City, State"
"678 Name, 678 Rd, City, State"
NA

我正在寻找一个更优雅的解决方案:

phone_number <- function(x) {
x <- gsub("[\\() -]", "", x) 
x <- gsub("^(.{3})(.{3})(.*)","\\1-\\2-\\3", x, perl = TRUE)
}

这将采用这样的数据:

(123) 123-1234
123-123-1234
123 123-1234

并产生这个:

123-123-1234
123-123-1234
123-123-1234