Create modified data

Usage

create_modified_data(
  compare,
  base,
  by = NULL,
  by_col = NULL,
  cols = NULL,
  ignore_case = FALSE,
  trim_ws = FALSE
)

Arguments

compare: A 'current' or 'new' dataset (tibble or data.frame)
base: A 'previous' or 'old' dataset (tibble or data.frame)
by: A join column between the two datasets, or any combination of columns that constitute a unique row.
by_col: A new name for the joining column.
cols: Columns to be compared.
ignore_case, trim_ws: passed to compare_values() for character comparisons.

Value

a list with diffs (long format: Variable name, key column(s), Current Value, Previous Value), diffs_byvar (count of differing values per variable), and class_diffs (class mismatches by shared column)

Examples

# with local data
CurrentData <- dfdiffs::ChangedData
PreviousData <- dfdiffs::InitialData
create_modified_data(
           compare = CurrentData,
           base = PreviousData,
           by = c("subject_id", "record"),
           cols = c("text_value_a", "text_value_b", "updated_date"))
#> $diffs
#> # A tibble: 8 × 4
#>   `Variable name` join  `Current Value`                    `Previous Value`
#>   <chr>           <chr> <chr>                              <chr>           
#> 1 text_value_a    A-1   Issue resolved                     Issue unresolved
#> 2 text_value_a    A-2   Issue resolved                     Issue unresolved
#> 3 text_value_b    C-4   Joint pain, stiffness and swelling Joint pain      
#> 4 updated_date    A-1   2021-10-03                         2021-09-29      
#> 5 updated_date    A-2   2021-11-27                         2021-10-03      
#> 6 updated_date    B-3   2021-10-20                         2021-09-02      
#> 7 updated_date    C-4   2021-10-13                         2021-10-03      
#> 8 updated_date    C-5   2021-10-14                         2021-09-20      
#> 
#> $diffs_byvar
#> # A tibble: 3 × 2
#>   `Variable name` `Modified Values`
#>   <chr>                       <int>
#> 1 text_value_a                    2
#> 2 text_value_b                    1
#> 3 updated_date                    5
#> 
#> $class_diffs
#> # A tibble: 0 × 3
#> # ℹ 3 variables: variable <chr>, class_base <chr>, class_compare <chr>
#> 
create_modified_data(
           compare = CurrentData,
           base = PreviousData,
           by = c("subject_id", "record"))
#> $diffs
#> # A tibble: 13 × 4
#>    `Variable name` join  `Current Value`                    `Previous Value`
#>    <chr>           <chr> <chr>                              <chr>           
#>  1 text_value_a    A-1   Issue resolved                     Issue unresolved
#>  2 text_value_a    A-2   Issue resolved                     Issue unresolved
#>  3 text_value_b    C-4   Joint pain, stiffness and swelling Joint pain      
#>  4 updated_date    A-1   2021-10-03                         2021-09-29      
#>  5 updated_date    A-2   2021-11-27                         2021-10-03      
#>  6 updated_date    B-3   2021-10-20                         2021-09-02      
#>  7 updated_date    C-4   2021-10-13                         2021-10-03      
#>  8 updated_date    C-5   2021-10-14                         2021-09-20      
#>  9 entered_date    A-1   2021-11-30                         2021-09-29      
#> 10 entered_date    A-2   2021-11-30                         2021-10-29      
#> 11 entered_date    B-3   2021-11-21                         2021-08-18      
#> 12 entered_date    C-4   2021-11-11                         2021-10-03      
#> 13 entered_date    C-5   2021-11-16                         2021-10-20      
#> 
#> $diffs_byvar
#> # A tibble: 7 × 2
#>   `Variable name` `Modified Values`
#>   <chr>                       <int>
#> 1 subject_id                      0
#> 2 record                          0
#> 3 text_value_a                    2
#> 4 text_value_b                    1
#> 5 created_date                    0
#> 6 updated_date                    5
#> 7 entered_date                    5
#> 
#> $class_diffs
#> # A tibble: 0 × 3
#> # ℹ 3 variables: variable <chr>, class_base <chr>, class_compare <chr>
#>