example_honos_datasets.RmdThe package comes with a simulated dataset of HoNOS scores in “wide” format. A helper function can be used to transform this data into “long” format (pivot_honos_longer).
library(honos)
#> This is honos 0.1.1.9001
#> honos is currently in development - function names and arguments might change.
#> PLEASE REPORT ANY BUGS OR IDEAS!
honos_data
#> # A tibble: 18 x 24
#> id date team stage q1 q2 q3 q4 q5 q6 q7 q8
#> <chr> <date> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 id1 2020-01-01 team1 pre 3 3 3 2 0 0 1 2
#> 2 id1 2020-02-11 team1 pre 3 4 3 0 1 1 1 4
#> 3 id1 2020-03-04 team2 pre 2 0 2 1 3 3 2 2
#> 4 id1 2020-04-20 team2 pre 1 2 4 2 2 4 3 4
#> 5 id2 2020-01-14 team1 pre 0 0 2 4 1 0 2 2
#> 6 id2 2020-02-22 team2 pre 1 1 1 2 4 1 4 1
#> 7 id3 2019-05-19 team1 pre 2 2 0 4 4 0 2 4
#> 8 id4 2020-11-08 team1 pre 3 0 1 2 2 0 0 2
#> 9 id4 2021-01-04 team2 pre 4 1 0 0 2 1 1 2
#> 10 id4 2021-01-15 team2 pre 0 2 2 1 0 3 2 4
#> 11 id4 2021-02-14 team1 pre 3 5 1 2 4 1 3 4
#> 12 id4 2020-02-17 team1 pre 2 4 3 4 2 2 2 2
#> 13 id4 2020-02-18 team2 pre 1 3 2 2 0 2 3 1
#> 14 id5 2020-01-01 team1 pre 0 3 4 3 1 4 2 1
#> 15 id5 2020-02-13 team2 pre 1 1 0 2 0 2 1 2
#> 16 id5 2020-03-21 team3 pre 2 2 2 0 3 3 4 1
#> 17 id5 2020-04-08 team2 pre 3 2 2 2 2 0 2 1
#> 18 id5 2020-05-02 team1 pre 0 0 0 1 0 0 0 1
#> # … with 12 more variables: q8_prob <chr>, q8_spec <chr>, q9 <dbl>, q10 <dbl>,
#> # q11 <dbl>, q12 <dbl>, q13 <dbl>, qa <dbl>, qb <dbl>, qc <dbl>, qd <dbl>,
#> # qe <dbl>Although the original variable names in honos_data are somewhat self-explanatory, they are not good! Therefore this package also offers a function to rename the variables (rename_honos()) to be more consistent and allow for easier further data manipulation.
honos_data %>%
rename_honos(value_vars_current = c("q1", "q2", "q3", "q4", "q5", "q6", "q7",
"q8", "q9", "q10", "q11", "q12", "q13"),
prob_var_item8 = c("q8_prob"),
spec_var_item8 = c("q8_spec"),
value_vars_history = c("qa", "qb", "qc", "qd", "qe"))
#> # A tibble: 18 x 24
#> id date team stage honos_i1_value honos_i2_value honos_i3_value
#> <chr> <date> <chr> <chr> <dbl> <dbl> <dbl>
#> 1 id1 2020-01-01 team1 pre 3 3 3
#> 2 id1 2020-02-11 team1 pre 3 4 3
#> 3 id1 2020-03-04 team2 pre 2 0 2
#> 4 id1 2020-04-20 team2 pre 1 2 4
#> 5 id2 2020-01-14 team1 pre 0 0 2
#> 6 id2 2020-02-22 team2 pre 1 1 1
#> 7 id3 2019-05-19 team1 pre 2 2 0
#> 8 id4 2020-11-08 team1 pre 3 0 1
#> 9 id4 2021-01-04 team2 pre 4 1 0
#> 10 id4 2021-01-15 team2 pre 0 2 2
#> 11 id4 2021-02-14 team1 pre 3 5 1
#> 12 id4 2020-02-17 team1 pre 2 4 3
#> 13 id4 2020-02-18 team2 pre 1 3 2
#> 14 id5 2020-01-01 team1 pre 0 3 4
#> 15 id5 2020-02-13 team2 pre 1 1 0
#> 16 id5 2020-03-21 team3 pre 2 2 2
#> 17 id5 2020-04-08 team2 pre 3 2 2
#> 18 id5 2020-05-02 team1 pre 0 0 0
#> # … with 17 more variables: honos_i4_value <dbl>, honos_i5_value <dbl>,
#> # honos_i6_value <dbl>, honos_i7_value <dbl>, honos_i8_value <dbl>,
#> # honos_i8_prob <chr>, honos_i8_spec <chr>, honos_i9_value <dbl>,
#> # honos_i10_value <dbl>, honos_i11_value <dbl>, honos_i12_value <dbl>,
#> # honos_i13_value <dbl>, honos_i14_value <dbl>, honos_i15_value <dbl>,
#> # honos_i16_value <dbl>, honos_i17_value <dbl>, honos_i18_value <dbl>There are two options to create a long data set:
pivot = "all_items"
honos_long <- honos_data %>%
pivot_honos_longer(value_vars_current = c("q1", "q2", "q3", "q4", "q5", "q6", "q7",
"q8", "q9", "q10", "q11", "q12", "q13"),
prob_var_item8 = c("q8_prob"),
spec_var_item8 = c("q8_spec"),
value_vars_history = c("qa", "qb", "qc", "qd", "qe"),
pivot = "all_items")
honos_long
#> # A tibble: 360 x 8
#> id date team stage measure item type value
#> <chr> <chr> <chr> <chr> <chr> <dbl> <chr> <chr>
#> 1 id1 2020-04-20 team2 pre honos 1 value 1
#> 2 id1 2020-04-20 team2 pre honos 2 value 2
#> 3 id1 2020-04-20 team2 pre honos 3 value 4
#> 4 id1 2020-04-20 team2 pre honos 4 value 2
#> 5 id1 2020-04-20 team2 pre honos 5 value 2
#> 6 id1 2020-04-20 team2 pre honos 6 value 4
#> 7 id1 2020-04-20 team2 pre honos 7 value 3
#> 8 id1 2020-04-20 team2 pre honos 8 value 4
#> 9 id1 2020-04-20 team2 pre honos 8 prob A
#> 10 id1 2020-04-20 team2 pre honos 8 spec <NA>
#> # … with 350 more rowspivot = "item_scores"
honos_longish <- honos_data %>%
pivot_honos_longer(value_vars_current = c("q1", "q2", "q3", "q4", "q5", "q6", "q7",
"q8", "q9", "q10", "q11", "q12", "q13"),
prob_var_item8 = c("q8_prob"),
spec_var_item8 = c("q8_spec"),
value_vars_history = c("qa", "qb", "qc", "qd", "qe"),
pivot = "item_scores")
honos_longish
#> # A tibble: 324 x 9
#> id date team stage measure item value prob spec
#> <chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <chr> <chr>
#> 1 id1 2020-04-20 team2 pre honos 1 1 <NA> <NA>
#> 2 id1 2020-04-20 team2 pre honos 2 2 <NA> <NA>
#> 3 id1 2020-04-20 team2 pre honos 3 4 <NA> <NA>
#> 4 id1 2020-04-20 team2 pre honos 4 2 <NA> <NA>
#> 5 id1 2020-04-20 team2 pre honos 5 2 <NA> <NA>
#> 6 id1 2020-04-20 team2 pre honos 6 4 <NA> <NA>
#> 7 id1 2020-04-20 team2 pre honos 7 3 <NA> <NA>
#> 8 id1 2020-04-20 team2 pre honos 8 4 A <NA>
#> 9 id1 2020-04-20 team2 pre honos 9 2 <NA> <NA>
#> 10 id1 2020-04-20 team2 pre honos 10 3 <NA> <NA>
#> # … with 314 more rows