Chapter 15

Introduction

# To create/see data summary.
skimr::skim(gss_cat)
Data summary
Name gss_cat
Number of rows 21483
Number of columns 9
_______________________
Column type frequency:
factor 6
numeric 3
________________________
Group variables None

Variable type: factor

skim_variable n_missing complete_rate ordered n_unique top_counts
marital 0 1 FALSE 6 Mar: 10117, Nev: 5416, Div: 3383, Wid: 1807
race 0 1 FALSE 3 Whi: 16395, Bla: 3129, Oth: 1959, Not: 0
rincome 0 1 FALSE 16 $25: 7363, Not: 7043, $20: 1283, $10: 1168
partyid 0 1 FALSE 10 Ind: 4119, Not: 3690, Str: 3490, Not: 3032
relig 0 1 FALSE 15 Pro: 10846, Cat: 5124, Non: 3523, Chr: 689
denom 0 1 FALSE 30 Not: 10072, Oth: 2534, No : 1683, Sou: 1536

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
year 0 1.00 2006.50 4.45 2000 2002 2006 2010 2014 ▇▃▇▂▆
age 76 1.00 47.18 17.29 18 33 46 59 89 ▇▇▇▅▂
tvhours 10146 0.53 2.98 2.59 0 1 2 4 24 ▇▂▁▁▁

Creating Factors

# Two strings are created to show the problem. 

x1 <- c("Dec", "Apr", "Jan", "Mar")

x2 <- c("Dec", "Apr", "Jam", "Mar")

# Create a list of the valid levels.

month_levels <- c(
  "Jan", "Feb", "Mar", "Apr", "May", "Jun", 
  "Jul", "Aug", "Sep", "Oct", "Nov", "Dec")

# Create factors for both strings.

y1 <- factor(x1, levels = month_levels)

y1
## [1] Dec Apr Jan Mar
## Levels: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
sort(y1)
## [1] Jan Mar Apr Dec
## Levels: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
y2 <- factor(x2, levels = month_levels)

# Typos are automatically converted to NA. 
y2
## [1] Dec  Apr  <NA> Mar 
## Levels: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
# Use parse_factor to receive a warning that there is a problem.


y2 <- parse_factor(x2, levels = month_levels)
## Warning: 1 parsing failure.
## row col           expected actual
##   3  -- value in level set    Jam

General Social Survey

gss_cat
## # A tibble: 21,483 × 9
##     year marital         age race  rincome        partyid    relig denom tvhours
##    <int> <fct>         <int> <fct> <fct>          <fct>      <fct> <fct>   <int>
##  1  2000 Never married    26 White $8000 to 9999  Ind,near … Prot… Sout…      12
##  2  2000 Divorced         48 White $8000 to 9999  Not str r… Prot… Bapt…      NA
##  3  2000 Widowed          67 White Not applicable Independe… Prot… No d…       2
##  4  2000 Never married    39 White Not applicable Ind,near … Orth… Not …       4
##  5  2000 Divorced         25 White Not applicable Not str d… None  Not …       1
##  6  2000 Married          25 White $20000 - 24999 Strong de… Prot… Sout…      NA
##  7  2000 Never married    36 White $25000 or more Not str r… Chri… Not …       3
##  8  2000 Divorced         44 White $7000 to 7999  Ind,near … Prot… Luth…      NA
##  9  2000 Married          44 White $25000 or more Not str d… Prot… Other       0
## 10  2000 Married          47 White $25000 or more Strong re… Prot… Sout…       3
## # ℹ 21,473 more rows

Modifying Factor Order

Unordered Factor Levels

# Transform data: Calculate average tv hours by religion.
tvhours_by_relig <- gss_cat %>%
    
    group_by(relig) %>%
    summarise(avg_tvhours = mean(tvhours, na.rm = TRUE))

tvhours_by_relig
## # A tibble: 15 × 2
##    relig                   avg_tvhours
##    <fct>                         <dbl>
##  1 No answer                      2.72
##  2 Don't know                     4.62
##  3 Inter-nondenominational        2.87
##  4 Native american                3.46
##  5 Christian                      2.79
##  6 Orthodox-christian             2.42
##  7 Moslem/islam                   2.44
##  8 Other eastern                  1.67
##  9 Hinduism                       1.89
## 10 Buddhism                       2.38
## 11 Other                          2.73
## 12 None                           2.71
## 13 Jewish                         2.52
## 14 Catholic                       2.96
## 15 Protestant                     3.15
# Plot
tvhours_by_relig %>% 
    
    ggplot(aes(x = avg_tvhours, y = relig)) +
    geom_point()

Ordered Factor Levels

tvhours_by_relig %>% 
    
    ggplot(aes(x = avg_tvhours, y = fct_reorder(.f = relig, .x = avg_tvhours))) +
    geom_point() +
    
    # Labeling
    labs(y = NULL, x = "Mean Daily TV Hours Watched")

Moving a Single Level to the Front

tvhours_by_relig %>% 
    
    ggplot(aes(x = avg_tvhours, 
               y = fct_reorder(.f = relig, .x = avg_tvhours) %>% fct_relevel("Don't know"))) + 
    geom_point() +
    
    # Labeling
    labs(y = NULL, x = "Mean Daily TV Hours Watched")

Modifying Factor Levels

gss_cat %>% distinct(partyid)
## # A tibble: 10 × 1
##    partyid           
##    <fct>             
##  1 Ind,near rep      
##  2 Not str republican
##  3 Independent       
##  4 Not str democrat  
##  5 Strong democrat   
##  6 Ind,near dem      
##  7 Strong republican 
##  8 Other party       
##  9 No answer         
## 10 Don't know
gss_cat %>% count(partyid)
## # A tibble: 10 × 2
##    partyid                n
##    <fct>              <int>
##  1 No answer            154
##  2 Don't know             1
##  3 Other party          393
##  4 Strong republican   2314
##  5 Not str republican  3032
##  6 Ind,near rep        1791
##  7 Independent         4119
##  8 Ind,near dem        2499
##  9 Not str democrat    3690
## 10 Strong democrat     3490
gss_cat %>% distinct(race)
## # A tibble: 3 × 1
##   race 
##   <fct>
## 1 White
## 2 Black
## 3 Other
# Recode
gss_cat %>%
    
    # Rename levels
    mutate(race_rev = fct_recode(race, "POC" = "Black")) %>%
    select(race, race_rev) %>%
    filter(race == "Black")
## # A tibble: 3,129 × 2
##    race  race_rev
##    <fct> <fct>   
##  1 Black POC     
##  2 Black POC     
##  3 Black POC     
##  4 Black POC     
##  5 Black POC     
##  6 Black POC     
##  7 Black POC     
##  8 Black POC     
##  9 Black POC     
## 10 Black POC     
## # ℹ 3,119 more rows
# Collapse multiple levels into one.
gss_cat %>% 
    
    mutate(race_col = fct_collapse(race, "Minority" = c("Black", "Other"))) %>%
    select(race, race_col) %>%
    filter(race != "White")
## # A tibble: 5,088 × 2
##    race  race_col
##    <fct> <fct>   
##  1 Black Minority
##  2 Black Minority
##  3 Black Minority
##  4 Other Minority
##  5 Black Minority
##  6 Other Minority
##  7 Black Minority
##  8 Other Minority
##  9 Black Minority
## 10 Black Minority
## # ℹ 5,078 more rows
# Lump small levels into other levels.
gss_cat %>% count(race)
## # A tibble: 3 × 2
##   race      n
##   <fct> <int>
## 1 Other  1959
## 2 Black  3129
## 3 White 16395
gss_cat %>% mutate(race_lump = fct_lump(race)) %>% distinct(race_lump)
## # A tibble: 2 × 1
##   race_lump
##   <fct>    
## 1 White    
## 2 Other

Chapter 16

Introduction

Creating Dates/Times

Date-Time Components

Time Spans