Generate report from existing objects

Generate report from previously-created daiquiri_source_data and daiquiri_aggregated_data objects

Usage

report_data(
  source_data,
  aggregated_data,
  report_title = "daiquiri data quality report",
  save_directory = ".",
  save_filename = NULL,
  format = "html",
  show_progress = TRUE,
  ...
)

Arguments

source_data: A daiquiri_source_data object returned from prepare_data() function
aggregated_data: A daiquiri_aggregated_data object returned from aggregate_data() function
report_title: Title to appear on the report
save_directory: String specifying directory in which to save the report. Default is current directory.
save_filename: String specifying filename for the report, excluding any file extension. If no filename is supplied, one will be automatically generated with the format daiquiri_report_YYMMDD_HHMMSS.
format: File format of the report. Currently only "html" is supported
show_progress: Print progress to console. Default = TRUE
...: Further parameters to be passed to rmarkdown::render(). Cannot include any of input, output_dir, output_file, params, quiet.

Value

A string containing the name and path of the saved report

Examples

# \donttest{
# load example data into a data.frame
raw_data <- read_data(
  system.file("extdata", "example_prescriptions.csv", package = "daiquiri"),
  delim = ",",
  col_names = TRUE
)

# validate and prepare the data for aggregation
source_data <- prepare_data(
  raw_data,
  field_types = field_types(
    PrescriptionID = ft_uniqueidentifier(),
    PrescriptionDate = ft_timepoint(),
    AdmissionDate = ft_datetime(includes_time = FALSE),
    Drug = ft_freetext(),
    Dose = ft_numeric(),
    DoseUnit = ft_categorical(),
    PatientID = ft_ignore(),
    Location = ft_categorical(aggregate_by_each_category = TRUE)
  ),
  override_column_names = FALSE,
  na = c("", "NULL"),
  dataset_description = "Example data provided with package",
  show_progress = TRUE
)
#> field_types supplied:
#> PrescriptionID	<uniqueidentifier>
#> PrescriptionDate	<timepoint>	options: includes_time
#> AdmissionDate	<datetime>
#> Drug	<freetext>
#> Dose	<numeric>
#> DoseUnit	<categorical>
#> PatientID	<ignore>
#> Location	<categorical>	options: aggregate_by_each_category
#>  
#> Checking column names against field_types... 
#> Importing source data [Example data provided with package]... 
#> Removing column-specific na values... 
#> Checking data against field_types... 
#>   Selecting relevant warnings... 
#>   Identifying nonconformant values... 
#>   Checking and removing missing timepoints... 
#> Checking for duplicates... 
#>   Sorting data... 
#> Loading into source_data structure... 
#>   PrescriptionID 
#>   PrescriptionDate 
#>   AdmissionDate 
#>   Drug 
#>   Dose 
#>   DoseUnit 
#>   PatientID 
#>   Location 
#> Finished 

# aggregate the data
aggregated_data <- aggregate_data(
  source_data,
  aggregation_timeunit = "day",
  show_progress = TRUE
)
#> Aggregating [] by [day]... 
#> Aggregating overall dataset... 
#> Aggregating each data_field in turn... 
#> 1: PrescriptionID 
#> Preparing... 
#> Aggregating character field... 
#>   By n 
#>   By missing_n 
#>   By missing_perc 
#>   By min_length 
#>   By max_length 
#>   By mean_length 
#> Finished 
#> 2: PrescriptionDate 
#> Preparing... 
#> Aggregating double field... 
#>   By n 
#>   By midnight_n 
#>   By midnight_perc 
#> Finished 
#> 3: AdmissionDate 
#> Preparing... 
#> Aggregating double field... 
#>   By n 
#>   By missing_n 
#>   By missing_perc 
#>   By nonconformant_n 
#>   By nonconformant_perc 
#>   By min 
#>   By max 
#> Finished 
#> 4: Drug 
#> Preparing... 
#> Aggregating character field... 
#>   By n 
#>   By missing_n 
#>   By missing_perc 
#> Finished 
#> 5: Dose 
#> Preparing... 
#> Aggregating double field... 
#>   By n 
#>   By missing_n 
#>   By missing_perc 
#>   By nonconformant_n 
#>   By nonconformant_perc 
#>   By min 
#>   By max 
#>   By mean 
#>   By median 
#> Finished 
#> 6: DoseUnit 
#> Preparing... 
#> Aggregating character field... 
#>   By n 
#>   By missing_n 
#>   By missing_perc 
#>   By distinct 
#> Finished 
#> 7: Location 
#> Preparing... 
#> Aggregating character field... 
#>   By n 
#>   By missing_n 
#>   By missing_perc 
#>   By distinct 
#>   By subcat_n 
#>     4 categories found 
#>     1: SITE1 
#>     2: SITE2 
#>     3: SITE3 
#>     4: SITE4 
#>   By subcat_perc 
#>     4 categories found 
#>     1: SITE1 
#>     2: SITE2 
#>     3: SITE3 
#>     4: SITE4 
#> Finished 
#> Aggregating calculated fields... 
#> [DUPLICATES]: 
#> Preparing... 
#> Aggregating integer field... 
#>   By sum 
#>   By nonzero_perc 
#> Finished 
#> [ALL_FIELDS_COMBINED]: 
#> Finished 

# save a report in the current directory using the previously-created objects
report_data(
  source_data,
  aggregated_data,
  report_title = "daiquiri data quality report",
  save_directory = ".",
  save_filename = "example_data_report",
  show_progress = TRUE
)
#> Generating html report... 
#> 
#> 
#> processing file: report_htmldoc.Rmd
#> 1/34                                            
#> 2/34 [daiquiri-setup]                           
#> 3/34                                            
#> 4/34 [daiquiri-styles]                          
#> 5/34                                            
#> 6/34 [daiquiri-strata-info]                     
#> 7/34                                            
#> 8/34 [daiquiri-source-data]                     
#> 9/34                                            
#> 10/34 [daiquiri-fields-imported]                 
#> 11/34                                            
#> 12/34 [daiquiri-fields-ignored]                  
#> 13/34                                            
#> 14/34 [daiquiri-validation-warnings]             
#> 15/34                                            
#> 16/34 [daiquiri-source-data-summary]             
#> 17/34                                            
#> 18/34 [daiquiri-aggregated-data]                 
#> 19/34                                            
#> 20/34 [daiquiri-overview-strata]                 
#> 21/34                                            
#> 22/34 [daiquiri-overview-presence]               
#> 23/34                                            
#> 24/34 [daiquiri-overview-missing]                
#> 25/34                                            
#> 26/34 [daiquiri-overview-nonconformant]          
#> 27/34                                            
#> 28/34 [daiquiri-overview-duplicates]             
#> 29/34                                            
#> 30/34 [daiquiri-aggregated-data-summary]         
#> 31/34                                            
#> 32/34 [daiquiri-individual-fields-set-fig-height]
#> 33/34                                            
#> 34/34 [daiquiri-individual-fields]               
#> output file: report_htmldoc.knit.md
#> "C:/Program Files/RStudio/resources/app/bin/quarto/bin/tools/pandoc" +RTS -K512m -RTS report_htmldoc.knit.md --to html4 --from markdown+autolink_bare_uris+tex_math_single_backslash --output pandoca0844433eec.html --lua-filter "C:\Users\pquan\Documents\Rworkspace\library\rmarkdown\rmarkdown\lua\pagebreak.lua" --lua-filter "C:\Users\pquan\Documents\Rworkspace\library\rmarkdown\rmarkdown\lua\latex-div.lua" --embed-resources --standalone --variable bs3=TRUE --section-divs --template "C:\Users\pquan\Documents\Rworkspace\library\rmarkdown\rmd\h\default.html" --no-highlight --variable highlightjs=1 --variable theme=bootstrap --mathjax --variable "mathjax-url=https://mathjax.rstudio.com/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML" --include-in-header "C:\Users\pquan\AppData\Local\Temp\RtmpuwDzBy\rmarkdown-stra08453623591.html" 
#> 
#> Output created: example_data_report.html
#> Report saved to: ./example_data_report.html 
#> [1] "./example_data_report.html"
file.remove("./example_data_report.html")
#> [1] TRUE
# }

Usage

Arguments

Value

See also

Examples