In edunford/qualify: qualify

knitr::opts_chunk$set(
  warning = FALSE, # show warnings during codebook generation
  message = FALSE, # show messages during codebook generation
  error = TRUE, # do not interrupt codebook generation in case of errors,
                # usually better for debugging
  echo = FALSE,  # show R code
  comment=NA #to remove all hashes from output
)
ggplot2::theme_set(ggplot2::theme_bw())
pander::panderOptions("table.split.table", Inf)

library(codebook)
codebook_data<-read.csv(("https://raw.githubusercontent.com/edunford/qualify/master/Data/example_pull_data_w_2users.csv"), header=TRUE)



#Code on lines 39:60 are intended to create sample data for exhibition purposes only. They should be removed prior to relase of the package. 
codebook_data$code<- rpois(n = 24, lambda = 10)
codebook_data$count<-runif(n = 24, min = 25, max = 3000)
rdate <- function(x,
                  min = paste0(format(Sys.Date(), '%Y'), '-01-01'),
                  max = paste0(format(Sys.Date(), '%Y'), '-12-31'),
                  sort = TRUE) {

  dates <- sample(seq(as.Date(min), as.Date(max), by = "day"), x, replace = TRUE)
  if (sort == TRUE) {
    sort(dates)
  } else {
    dates
  }

}
codebook_data$date<-rdate(24)


codebook_data$evid<-sample(x = c("aa", "ba", "bb", "ac", "cc", "bc"), 
       prob = c(.1, .1, .2, .05, .25, .3),
       size = 24, 
       replace = TRUE)

# omit the following lines, if your missing values are already properly labelled
codebook_data <- detect_missing(codebook_data,
    only_labelled = TRUE, # only labelled values are autodetected as
                                   # missing
    negative_values_are_missing = FALSE, # negative values are missing values
    ninety_nine_problems = TRUE   # 99/999 are missing values, if they
                                   # are more than 5 MAD from the median
    )

# If you are not using formr, the codebook package needs to guess which items
# form a scale. The following line finds item aggregates with names like this:
# scale = scale_1 + scale_2R + scale_3R
# identifying these aggregates allows the codebook function to
# automatically compute reliabilities.
# However, it will not reverse items automatically.
codebook_data <- detect_scales(codebook_data)

codebook(codebook_data)

Inter Coder Reliability

The data coded is assumed to be categorical. Different reliability tests would be more appropriate for ordinal/interval/ratio data.

#This code formats the ICR dataset a MxK dataframe where m is number of coders, and K is are unique unit of analysis/variable pairs. 
library("irr")
library("tidyverse")
irc_variables<-c(".user", "variableID", "code")
codebook_dataunite<- unite(codebook_data, variable, .unit, col="variableID")
trunc_codebook_data<-codebook_dataunite[irc_variables]
icr_data<-spread(trunc_codebook_data, variableID,code, fill=NA, convert=FALSE, drop=TRUE, sep=NULL)
#flipping the table to KxM
icr_transpose <- as.data.frame(t(as.matrix(icr_data)))
icr_trans<- icr_transpose[-1,]

Fleiss' Kappa for categorical data

#These tests were selected because data was assumed to be categorical and non-ordinal
print(kappam.fleiss(icr_trans, exact=TRUE, detail=TRUE))

Light's Kappa for categorical data

print(kappam.light(icr_trans))

Coefficient of Rater Bias for categorical data, between two raters

rater.bias(icr_trans)

```r

Posterior Functions -- Pulled from qualify.r --------------------------------------------------

Pull data out of the data base.

(Only optimized for a single coder at the moment)

' pull_timeline

'

' Pull in timeline information about the coding timeline.

'

' @param .project_path

'

' @return

' @export

'

' @examples

pull_timeline = function(.project_path,round_date = "minute"){ if(dir.exists(.project_path) & check_db_exists(.project_path)){ con = sql_instance(.project_path) all_tbls = grep("v", dplyr::src_tbls(con),value = T) data_summary = c()

for (t in all_tbls){
  # Get the variable name
  var_name =  dplyr::tbl(con,".input_state") %>% 
    dplyr::filter(.id == t) %>% 
    dplyr::collect() %>% .$var_name

  # Extract the data state
  data_summary <-
    dplyr::tbl(con,t) %>% 
    dplyr::collect() %>% 
    dplyr::mutate(timestamp = lubridate::round_date(lubridate::ymd_hms(timestamp),unit = round_date),
                  variable = var_name) %>% 
    dplyr::group_by(timestamp,.unit,variable) %>% 
    tidyr::nest() %>% 
    dplyr::mutate(is_entry = purrr::map(data,function(x) (apply(x,1,function(x) as.numeric(sum(x=="") < length(x)))) )) %>%
    tidyr::unnest() %>% 
    dplyr::filter(is_entry==1) %>% 
    dplyr::group_by(timestamp,variable) %>% 
    dplyr::count() %>% 
    dplyr::ungroup() %>% 
    dplyr::bind_rows(data_summary,.)
}
return(data_summary)

} else{ cat("\nNo qualify database located in the provide path.\n") } }

' pull_data

'

' Posterior function that call from the data base to make a distinct data frame

' that contains all fields from all coded variables from the application. The

' function allows users to draw the most recent state of the coding task to

' convert into a usable data frame for analysis

'

' @param .project_path

'

' @return

' @export

'

' @examples

'

' # Must point to the project path created by qualify()

' pull_data(.project_path = "~/Desktop/test_project/")

'

pull_data = function(.project_path = ""){ if(dir.exists(.project_path) & check_db_exists(.project_path)){ con = sql_instance(.project_path) all_tbls = grep("v", dplyr::src_tbls(con),value = T) data_summary = c()

for (t in all_tbls){
  # Get the variable name
  var_name =  dplyr::tbl(con,".input_state") %>% 
    dplyr::filter(.id == t) %>% 
    dplyr::collect() %>% .$var_name

  # Extract the data state
  data_summary <-
    dplyr::tbl(con,t) %>% 
    dplyr::collect() %>% 
    dplyr::group_by(.unit) %>% 
    dplyr::arrange(desc(timestamp)) %>% 
    dplyr::slice(1) %>% 
    dplyr::ungroup() %>% 
    dplyr::mutate(variable = var_name) %>% 
    select(variable,.unit,timestamp,dplyr::everything()) %>% 
    dplyr::bind_rows(data_summary,.) 
}
return(data_summary)

} else{ cat("\nNo qualify database located in the provide path.\n") }

}

' check_db_exists

'

' [Aux.] Check if a data base file exist

'

' @param path

'

' @return

'

' @examples

'

' check_db_exists()

'

check_db_exists = function(.project_path = ""){ set_path = paste0(path,"/.qualify_data.sqlite") file.exists(set_path) }

````

edunford/qualify documentation built on Aug. 27, 2019, 9:58 p.m.