1 加载经常用的R包

library(pacman)
# 读数据
p_load(readxl,writexl,data.table,openxlsx,haven,rvest)

# 数据探索
p_load(tidyverse,DT,skimr,DataExplorer,explore,vtable,stringr,kableExtra,lubridate)

# 模型
p_load(grf,glmnet,caret,tidytext,fpp2,forecast,car,tseries,hdm,tidymodels,broom)

# 可视化
p_load(patchwork,ggrepel,ggcorrplot,gghighlight,ggthemes,shiny)

# 其它常用包
p_load(magrittr,listviewer,devtools,here,janitor,reticulate,jsonlite)

2 Variable labels

library(labelled)
var_label(iris$Petal.Length) <- "Length of sepal"

var_label(iris) <- list(Petal.Length = "Length of petal",
                        Petal.Width = "Width of Petal")

var_label(iris$Petal.Width)

## [1] "Width of Petal"

var_label(iris)

## $Sepal.Length
## NULL
## 
## $Sepal.Width
## NULL
## 
## $Petal.Length
## [1] "Length of petal"
## 
## $Petal.Width
## [1] "Width of Petal"
## 
## $Species
## NULL

To remove a variable label, use NULL.

var_label(iris$Sepal.Length) <- NULL

# View(iris)

可以通过 look for ()显示和搜索变量名和标签:

look_for(iris)

look_for(iris,"pet")

look_for(data = iris,details = TRUE)

look_for(mtcars,details = TRUE) %>% as_tibble()

3 Value labels

创建带标签的向量的第一种方法是使用标签函数。并不是必须为在矢量中观察到的每个值提供一个标签。您还可以为未观察到的值提供标签。

v <- labelled(c(1,2,2,2,3,9,1,3,2,NA), 
              c(yes = 1, no = 3, "don't know" = 8, refused = 9))
v

## <labelled<double>[10]>
##  [1]  1  2  2  2  3  9  1  3  2 NA
## 
## Labels:
##  value      label
##      1        yes
##      3         no
##      8 don't know
##      9    refused

val_labels(v)

##        yes         no don't know    refused 
##          1          3          8          9

val_label(v,8)

## [1] "don't know"

val_labels(v) <- c(yes = 1,nno = 3,bug = 5)
v

## <labelled<double>[10]>
##  [1]  1  2  2  2  3  9  1  3  2 NA
## 
## Labels:
##  value label
##      1   yes
##      3   nno
##      5   bug

val_label(v,3) <- "no"
val_label(v,5) <- "bugs"
v

## <labelled<double>[10]>
##  [1]  1  2  2  2  3  9  1  3  2 NA
## 
## Labels:
##  value label
##      1   yes
##      3    no
##      5  bugs

val_label(v,2) <- "maybe"
v

## <labelled<double>[10]>
##  [1]  1  2  2  2  3  9  1  3  2 NA
## 
## Labels:
##  value label
##      1   yes
##      3    no
##      5  bugs
##      2 maybe

val_labels(v) <- NULL
v

##  [1]  1  2  2  2  3  9  1  3  2 NA

val_label(v,1) <- "yes"
v

## <labelled<double>[10]>
##  [1]  1  2  2  2  3  9  1  3  2 NA
## 
## Labels:
##  value label
##      1   yes

Note that applying val_labels to a factor will have no effect!!

f <- factor(1:3,levels = 1:3)
f

## [1] 1 2 3
## Levels: 1 2 3

val_labels(f) <- c(yes = 1,no = 2,bug = 3)
f

## [1] 1 2 3
## Levels: 1 2 3

You could also apply value labels to several columns of a data frame.

df <- data.frame(v1 = 1:3, v2 = c(2, 3, 1), v3 = 3:1)
df

val_label(df, 1) <- "yes"
df

look_for(df,details = TRUE)

df$v1 <- haven::as_factor(df$v1)
df

df <- data.frame(v1 = 1:3, v2 = c(2, 3, 1), v3 = 3:1)

val_label(df, 1) <- "yes"
val_label(df[, c("v1", "v3")], 2) <- "maybe"
val_label(df[, c("v2", "v3")], 3) <- "no"
val_labels(df)

## $v1
##   yes maybe 
##     1     2 
## 
## $v2
## yes  no 
##   1   3 
## 
## $v3
##   yes maybe    no 
##     1     2     3

4 Sorting value labels

v <- c(1,2,2,2,3,9,1,3,2,NA)
v

##  [1]  1  2  2  2  3  9  1  3  2 NA

val_label(v,1) <- "yes"
val_label(v,3) <- "no"
val_label(v,9) <- "refused"
val_label(v,2) <- "maybe"
val_label(v,8) <- "don't know"
v

## <labelled<double>[10]>
##  [1]  1  2  2  2  3  9  1  3  2 NA
## 
## Labels:
##  value      label
##      1        yes
##      3         no
##      9    refused
##      2      maybe
##      8 don't know

It could be useful to reorder the value labels according to their attached values.

sort_val_labels(v)

## <labelled<double>[10]>
##  [1]  1  2  2  2  3  9  1  3  2 NA
## 
## Labels:
##  value      label
##      1        yes
##      2      maybe
##      3         no
##      8 don't know
##      9    refused

sort_val_labels(v,decreasing = TRUE)

## <labelled<double>[10]>
##  [1]  1  2  2  2  3  9  1  3  2 NA
## 
## Labels:
##  value      label
##      9    refused
##      8 don't know
##      3         no
##      2      maybe
##      1        yes

sort_val_labels(v,according_to = "l")

## <labelled<double>[10]>
##  [1]  1  2  2  2  3  9  1  3  2 NA
## 
## Labels:
##  value      label
##      8 don't know
##      2      maybe
##      3         no
##      9    refused
##      1        yes

5 User defined missing values (SPSS’s style)

v <- labelled(c(1,2,2,2,3,9,1,3,2,NA),
              labels = c(yes = 1,no = 3,"don't know" = 9))
v

## <labelled<double>[10]>
##  [1]  1  2  2  2  3  9  1  3  2 NA
## 
## Labels:
##  value      label
##      1        yes
##      3         no
##      9 don't know

na_values(v) <- 100
na_values(v)

## [1] 100

## <labelled_spss<double>[10]>
##  [1]  1  2  2  2  3  9  1  3  2 NA
## Missing values: 100
## 
## Labels:
##  value      label
##      1        yes
##      3         no
##      9 don't know

is.na(v)

##  [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE

6 Converting to factor

v <- labelled(c(1,2,2,2,3,9,1,3,2,NA),
              c(yes = 1, no = 3, "don't know" = 8, refused = 9))
v

## <labelled<double>[10]>
##  [1]  1  2  2  2  3  9  1  3  2 NA
## 
## Labels:
##  value      label
##      1        yes
##      3         no
##      8 don't know
##      9    refused

v %>% to_factor()

##  [1] yes     2       2       2       no      refused yes     no      2      
## [10] <NA>   
## Levels: yes 2 no don't know refused

to_factor(v,levels = "v")

##  [1] 1    2    2    2    3    9    1    3    2    <NA>
## Levels: 1 2 3 8 9

to_factor(v,levels = "p")

##  [1] [1] yes     [2] 2       [2] 2       [2] 2       [3] no      [9] refused
##  [7] [1] yes     [3] no      [2] 2       <NA>       
## Levels: [1] yes [2] 2 [3] no [8] don't know [9] refused

7 Other type of conversions

## <labelled<double>[10]>
##  [1]  1  2  2  2  3  9  1  3  2 NA
## 
## Labels:
##  value      label
##      1        yes
##      3         no
##      8 don't know
##      9    refused

to_character(v)

##  [1] "yes"     "2"       "2"       "2"       "no"      "refused" "yes"    
##  [8] "no"      "2"       NA

8 Conditionnal conversion to factors(重要)

library(tidyverse)
df <- data.frame(
  a = labelled(c(1, 1, 2, 3), labels = c(No = 1, Yes = 2)),
  b = labelled(c(1, 1, 2, 3), labels = c(No = 1, Yes = 2, DK = 3)),
  c = labelled(c(1, 1, 2, 2), labels = c(No = 1, Yes = 2, DK = 3)),
  d = labelled(c("a", "a", "b", "c"), labels = c(No = "a", Yes = "b")),
  e = labelled_spss(
    c(1, 9, 1, 2), 
    labels = c(No = 1, Yes = 2),
    na_values = 9
    )
)
df %>% glimpse()

## Rows: 4
## Columns: 5
## $ a <dbl+lbl> 1, 1, 2, 3
## $ b <dbl+lbl> 1, 1, 2, 3
## $ c <dbl+lbl> 1, 1, 2, 2
## $ d <chr+lbl> "a", "a", "b", "c"
## $ e <dbl+lbl> 1, 9, 1, 2

unlabelled(df)

df %>% haven::as_factor(levels = "l")

unlabelled(df,drop_unused_label = TRUE)

p_load(questionr)
data(fertility)
glimpse(women)

## Rows: 2,000
## Columns: 17
## $ id_woman          <dbl> 391, 1643, 85, 881, 1981, 1072, 1978, 1607, 738, ...
## $ id_household      <dbl> 381, 1515, 85, 844, 1797, 1015, 1794, 1486, 711, ...
## $ weight            <dbl> 1.803150, 1.803150, 1.803150, 1.803150, 1.803150,...
## $ interview_date    <date> 2012-05-05, 2012-01-23, 2012-01-21, 2012-01-06, ...
## $ date_of_birth     <date> 1997-03-07, 1982-01-06, 1979-01-01, 1968-03-29, ...
## $ age               <dbl> 15, 30, 33, 43, 25, 18, 45, 23, 49, 31, 26, 45, 2...
## $ residency         <dbl+lbl> 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, ...
## $ region            <dbl+lbl> 4, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 3, 2, 2, 2, ...
## $ instruction       <dbl+lbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 2, 1, ...
## $ employed          <dbl+lbl> 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, ...
## $ matri             <dbl+lbl> 0, 2, 2, 2, 1, 0, 1, 1, 2, 5, 2, 3, 0, 2, 1, ...
## $ religion          <dbl+lbl> 1, 3, 2, 3, 2, 2, 3, 1, 3, 3, 2, 3, 2, 2, 2, ...
## $ newspaper         <dbl+lbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, ...
## $ radio             <dbl+lbl> 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, ...
## $ tv                <dbl+lbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, ...
## $ ideal_nb_children <dbl+lbl>  4,  4,  4,  4,  4,  5, 10,  5,  4,  5,  6, 1...
## $ test              <dbl+lbl> 0, 9, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 1, 1, ...

women$residency %>% sample(10)

## <labelled<double>[10]>: Urban / rural residency
##  [1] 1 2 2 2 2 1 2 2 1 2
## 
## Labels:
##  value label
##      1 urban
##      2 rural

women

women %>% unlabelled()

glimpse(women %>% mutate(across(is.labelled %>% where(), to_factor)))

## Rows: 2,000
## Columns: 17
## $ id_woman          <dbl> 391, 1643, 85, 881, 1981, 1072, 1978, 1607, 738, ...
## $ id_household      <dbl> 381, 1515, 85, 844, 1797, 1015, 1794, 1486, 711, ...
## $ weight            <dbl> 1.803150, 1.803150, 1.803150, 1.803150, 1.803150,...
## $ interview_date    <date> 2012-05-05, 2012-01-23, 2012-01-21, 2012-01-06, ...
## $ date_of_birth     <date> 1997-03-07, 1982-01-06, 1979-01-01, 1968-03-29, ...
## $ age               <dbl> 15, 30, 33, 43, 25, 18, 45, 23, 49, 31, 26, 45, 2...
## $ residency         <fct> rural, rural, rural, rural, rural, rural, rural, ...
## $ region            <fct> West, West, West, West, West, South, South, South...
## $ instruction       <fct> none, none, none, none, primary, none, none, none...
## $ employed          <fct> yes, yes, no, yes, yes, no, yes, no, yes, yes, ye...
## $ matri             <fct> single, living together, living together, living ...
## $ religion          <fct> Muslim, Protestant, Christian, Protestant, Christ...
## $ newspaper         <fct> no, no, no, no, no, no, no, no, no, no, no, no, n...
## $ radio             <fct> no, yes, yes, no, no, yes, yes, no, no, no, yes, ...
## $ tv                <fct> no, no, no, no, no, yes, no, no, no, no, yes, yes...
## $ ideal_nb_children <fct> 4, 4, 4, 4, 4, 5, 10, 5, 4, 5, 6, 10, 2, 6, 6, 6,...
## $ test              <fct> no, missing, no, no, yes, no, no, no, no, yes, ye...

women %>% mutate(across(employed:religion,to_factor))

Introduction to labelled

Studennt. LI Junjie

2020-07-15