Generate a Codebook of a Data Set
codebook.RdFunction codebook collects documentation about an item,
or the items in a data set or external data file. It returns
an object that, when shown, print this documentation
in a nicely formatted way.
Usage
codebook(x, weights = NULL, unweighted = TRUE, ...)
# S4 method for class 'item'
codebook(x, weights = NULL, unweighted = TRUE, ...)
# S4 method for class 'atomic'
codebook(x, weights = NULL, unweighted = TRUE, ...)
# S4 method for class 'factor'
codebook(x, weights = NULL, unweighted = TRUE, ...)
# S4 method for class 'data.set'
codebook(x, weights = NULL, unweighted = TRUE, ...)
# S4 method for class 'importer'
codebook(x, weights = NULL, unweighted = TRUE, ...)
# S4 method for class 'data.frame'
codebook(x, weights = NULL, unweighted = TRUE, ...)
# S4 method for class 'tbl_df'
codebook(x, weights = NULL, unweighted = TRUE, ...)Arguments
- x
an
item, numeric or character vector, factor,data.set,data.frameorimporterobject forcodebook()- weights
an optional vector of weights.
- unweighted
an optional logical vector; if weights are given, it determines of only summaries of weighted data are show or also summaries of unweighted data.
- ...
other arguments, currently ignored.
Value
An object of class "codebook", for which a show method exists that
produces a nicely formatted output.
Examples
Data <- data.set(
vote = sample(c(1,2,3,8,9,97,99),size=300,replace=TRUE),
region = sample(c(rep(1,3),rep(2,2),3,99),size=300,replace=TRUE),
income = exp(rnorm(300,sd=.7))*2000
)
Data <- within(Data,{
description(vote) <- "Vote intention"
description(region) <- "Region of residence"
description(income) <- "Household income"
wording(vote) <- "If a general election would take place next tuesday,
the candidate of which party would you vote for?"
wording(income) <- "All things taken into account, how much do all
household members earn in sum?"
foreach(x=c(vote,region),{
measurement(x) <- "nominal"
})
measurement(income) <- "ratio"
labels(vote) <- c(
Conservatives = 1,
Labour = 2,
"Liberal Democrats" = 3,
"Don't know" = 8,
"Answer refused" = 9,
"Not applicable" = 97,
"Not asked in survey" = 99)
labels(region) <- c(
England = 1,
Scotland = 2,
Wales = 3,
"Not applicable" = 97,
"Not asked in survey" = 99)
foreach(x=c(vote,region,income),{
annotation(x)["Remark"] <- "This is not a real survey item, of course ..."
})
missing.values(vote) <- c(8,9,97,99)
missing.values(region) <- c(97,99)
})
description(Data)
#>
#> vote 'Vote intention'
#> region 'Region of residence'
#> income 'Household income'
#>
codebook(Data)
#> ================================================================================
#>
#> vote 'Vote intention'
#>
#> "If a general election would take place next tuesday, the candidate of which
#> party would you vote for?"
#>
#> --------------------------------------------------------------------------------
#>
#> Storage mode: double
#> Measurement: nominal
#> Missing values: 8, 9, 97, 99
#>
#> Values and labels N Valid Total
#>
#> 1 'Conservatives' 33 28.0 11.0
#> 2 'Labour' 41 34.7 13.7
#> 3 'Liberal Democrats' 44 37.3 14.7
#> 8 M 'Don't know' 40 13.3
#> 9 M 'Answer refused' 37 12.3
#> 97 M 'Not applicable' 53 17.7
#> 99 M 'Not asked in survey' 52 17.3
#>
#> Remark:
#> This is not a real survey item, of course ...
#>
#> ================================================================================
#>
#> region 'Region of residence'
#>
#> --------------------------------------------------------------------------------
#>
#> Storage mode: double
#> Measurement: nominal
#> Missing values: 97, 99
#>
#> Values and labels N Valid Total
#>
#> 1 'England' 139 52.9 46.3
#> 2 'Scotland' 82 31.2 27.3
#> 3 'Wales' 42 16.0 14.0
#> 99 M 'Not asked in survey' 37 12.3
#>
#> Remark:
#> This is not a real survey item, of course ...
#>
#> ================================================================================
#>
#> income 'Household income'
#>
#> "All things taken into account, how much do all household members earn in
#> sum?"
#>
#> --------------------------------------------------------------------------------
#>
#> Storage mode: double
#> Measurement: ratio
#>
#> Min: 289.338
#> Max: 17629.525
#> Mean: 2460.252
#> Std.Dev.: 2073.515
#>
#> Remark:
#> This is not a real survey item, of course ...
#>
codebook(Data)$vote
#> ================================================================================
#>
#> vote 'Vote intention'
#>
#> "If a general election would take place next tuesday, the candidate of which
#> party would you vote for?"
#>
#> --------------------------------------------------------------------------------
#>
#> Storage mode: double
#> Measurement: nominal
#> Missing values: 8, 9, 97, 99
#>
#> Values and labels N Valid Total
#>
#> 1 'Conservatives' 33 28.0 11.0
#> 2 'Labour' 41 34.7 13.7
#> 3 'Liberal Democrats' 44 37.3 14.7
#> 8 M 'Don't know' 40 13.3
#> 9 M 'Answer refused' 37 12.3
#> 97 M 'Not applicable' 53 17.7
#> 99 M 'Not asked in survey' 52 17.3
#>
#> Remark:
#> This is not a real survey item, of course ...
#>
codebook(Data)[2]
#> ================================================================================
#>
#> region 'Region of residence'
#>
#> --------------------------------------------------------------------------------
#>
#> Storage mode: double
#> Measurement: nominal
#> Missing values: 97, 99
#>
#> Values and labels N Valid Total
#>
#> 1 'England' 139 52.9 46.3
#> 2 'Scotland' 82 31.2 27.3
#> 3 'Wales' 42 16.0 14.0
#> 99 M 'Not asked in survey' 37 12.3
#>
#> Remark:
#> This is not a real survey item, of course ...
#>
codebook(Data[2])
#> ================================================================================
#>
#> region 'Region of residence'
#>
#> --------------------------------------------------------------------------------
#>
#> Storage mode: double
#> Measurement: nominal
#> Missing values: 97, 99
#>
#> Values and labels N Valid Total
#>
#> 1 'England' 139 52.9 46.3
#> 2 'Scotland' 82 31.2 27.3
#> 3 'Wales' 42 16.0 14.0
#> 99 M 'Not asked in survey' 37 12.3
#>
#> Remark:
#> This is not a real survey item, of course ...
#>
DataFr <- as.data.frame(Data)
DataHv <- as_haven(Data,user_na=TRUE)
codebook(DataFr)
#> ================================================================================
#>
#> vote 'Vote intention'
#>
#> --------------------------------------------------------------------------------
#>
#> Storage mode: integer
#> Factor with 3 levels
#>
#> Levels and labels N Valid Total
#>
#> 1 'Conservatives' 33 28.0 11.0
#> 2 'Labour' 41 34.7 13.7
#> 3 'Liberal Democrats' 44 37.3 14.7
#> NA 182 60.7
#>
#> ================================================================================
#>
#> region 'Region of residence'
#>
#> --------------------------------------------------------------------------------
#>
#> Storage mode: integer
#> Factor with 3 levels
#>
#> Levels and labels N Valid Total
#>
#> 1 'England' 139 52.9 46.3
#> 2 'Scotland' 82 31.2 27.3
#> 3 'Wales' 42 16.0 14.0
#> NA 37 12.3
#>
#> ================================================================================
#>
#> income 'Household income'
#>
#> --------------------------------------------------------------------------------
#>
#> Storage mode: double
#>
#> Min: 289.3379
#> Max: 17629.5251
#> Mean: 2460.2518
#> Std.Dev.: 2073.5155
#>
codebook(DataHv)
#> ================================================================================
#>
#> vote 'Vote intention'
#>
#> --------------------------------------------------------------------------------
#>
#> Storage mode: integer
#> Measurement: undefined
#> Missing values: 8, 9, 97, 99
#>
#> Values and labels N Valid Total
#>
#> 1 'Conservatives' 33 28.0 11.0
#> 2 'Labour' 41 34.7 13.7
#> 3 'Liberal Democrats' 44 37.3 14.7
#> 8 M 'Don't know' 40 13.3
#> 9 M 'Answer refused' 37 12.3
#> 97 M 'Not applicable' 53 17.7
#> 99 M 'Not asked in survey' 52 17.3
#>
#> ================================================================================
#>
#> region 'Region of residence'
#>
#> --------------------------------------------------------------------------------
#>
#> Storage mode: integer
#> Measurement: undefined
#> Missing values: 97, 99
#>
#> Values and labels N Valid Total
#>
#> 1 'England' 139 52.9 46.3
#> 2 'Scotland' 82 31.2 27.3
#> 3 'Wales' 42 16.0 14.0
#> 99 M 'Not asked in survey' 37 12.3
#>
#> ================================================================================
#>
#> income 'Household income'
#>
#> --------------------------------------------------------------------------------
#>
#> Storage mode: double
#>
#> Min: 289.3379
#> Max: 17629.5251
#> Mean: 2460.2518
#> Std.Dev.: 2073.5155
#>
if (FALSE) { # \dontrun{
Write(description(Data),
file="Data-desc.txt")
Write(codebook(Data),
file="Data-cdbk.txt")
} # }