Parameter Table Helpers — partable

Helper functions to manipulate parameter tables. They are exported for advanced users.

Usage

combine_partables(object_list, drop_duplicated = TRUE)

setdiff_eq_partables(x, y)

setdiff_partables(x, y)

union_eq_partables(x, y)

intersect_eq_partables(x, y)

setequal_eq_partables(x, y)

setequal_partables(x, y)

is_element_eq_partables(el, set)

is_element_partables(el, set)

match_eq_partables(x, table, nomatch = NA_integer_)

match_partables(x, table, nomatch = NA_integer_)

x %pt_in% table

x %pt_notin% table

is_partable(object, colchk = c("id", "lhs", "op", "rhs"))

is_partables(object, colchk = c("id", "lhs", "op", "rhs"))

Arguments

object_list: A list of objects of the class partables or eq_partables.
drop_duplicated: Logical. Whether duplicated models will be removed.
x, y: List of parameter tables, such as eq_partables objects.
el: A parameter table.
set: A list of parameter tables.
table: A list of parameter tables.
nomatch: The same argument from match().
object: The object to be checked whether it is a parameter table.
colchk: The columns to be checked.

Value

The function combine_partables() always returns an object of the class eq_partables, which is a subclass of partables.

The function setdiff_eq_partables() returns a list of parameter tables, of the same class of x, with models present in y removed.

The function union_eq_partables() returns a list of parameter tables, of the class eq_partables.

The function intersect_eq_partables() returns a list of parameter tables, of the class eq_partables, common in both x and y.

The function setequal_eq_partables() returns TRUE or FALSE, based on the results of get_digest_partables() applied to x and y.

The function is_element_eq_partables() (and is_element_partables()) returns TRUE or FALSE, based on the results of is.element() applied to the hash values from get_digest() and get_digest_partables().

The function match_eq_partables() (and match_partables()) returns the results of match() applied to the hash values generated by get_digest().

%pt_in% returns a logical vector, the output of %in% applied to the has values of x and table.

%pt_notin% returns a logical vector, the output of %notin% applied to the has values of x and table.

The function is_partable() returns either TRUE or FALSE. It is TRUE if the two conditions mentioned in Details are met.

The function is_partables() returns either TRUE or FALSE. It is TRUE only if is_partable() returns TRUE for all its elements.

Details

The function combine_partables() combines a list of partables objects or eq_partables objects to one single object of the same type.

The function setdiff_eq_partables() (and setdiff_partables()) removes from x models that are also in y.

The function union_eq_partables() combines the models in x and y, with duplicated models removed.

The function intersect_eq_partables() finds the models common in x and y.

The function setequal_eq_partables() (and setequal_partables()) checks whether x and y has the same set of models. Orders are ignored.

The function is_element_eq_partables() checks whether el is one of the models in set.

The function match_eq_partables() (and match_partables()) is similar to match(), but check matches based on the results of get_digest() applied to the parameter tables.

%pt_in% is similar to %in%, but works on parameter tables using match_eq_partables().

%pt_notin% is similar to %notin%, but works on parameter tables using match_eq_partables().

The function is_partable() checks whether an object is probably a parameter table. It checks whether (a) the object is a data.frame-like object (by is.data.frame()) and (b) the columns in colchk exist. If both conditions are met, then the object is considered a parameter table.

The function is_partables() checks whether a list is likely a list of parameter tables. It simply calls is_partable() on all the elements.

Examples


library(lavaan)

# Model 1

mod1 <-
"
fx =~ x1 + x2 + x3
fm =~ m1 + m2 + m3
fy =~ y1 + y2 + y3
fm ~ fx
fy ~ fm + fx
"
fit1 <- sem(
          model = mod1,
          data = data_test_3_factor_3_item
        )
fit1_1_more <- drop_k(fit1)
fit1_1_more_1_less <- lapply(
  fit1_1_more,
  add_k
)

partables1 <- combine_partables(fit1_1_more_1_less)
partables1
#> 
#> Number of models: 4
#> 
#> The models:
#> 
#>   Model                  
#> 1 drop: fm~fx.add: fx~~fm
#> 2 drop: fm~fx.add: fx~fm 
#> 3 drop: fy~fm.add: fm~~fy
#> 4 drop: fy~fm.add: fm~fy  
#> 
#> NOTE: 'default' names are used. Call 'print()' and add 'names_to_use =
#> "long"' to use the long descriptive names, if available, for the
#> models.