Create an rsumary relop operator node.

This is a non_sql_node, so please see non_sql_node for some of the issues for this node type.

rsummary_node(
  source,
  ...,
  quartiles = FALSE,
  tmp_name_source = wrapr::mk_tmp_name_source("sn"),
  temporary = TRUE
)

Arguments

source	incoming source (relop node or data.frame).
...	force later arguments to be by name
quartiles	logical, if TRUE add Q1 (25%), median (50%), Q3 (75%) quartiles.
tmp_name_source	wrapr::mk_tmp_name_source(), temporary name generator.
temporary	logical, if TRUE use temporary tables

Value

rsummary node

See also

quantile_node, non_sql_node

Examples

if (requireNamespace("DBI", quietly = TRUE) && requireNamespace("RSQLite", quietly = TRUE)) {
  d <- data.frame(p= c(TRUE, FALSE, NA),
                  s= NA,
                  w= 1:3,
                  x= c(NA,2,3),
                  y= factor(c(3,5,NA)),
                  z= c('a',NA,'a'),
                  stringsAsFactors=FALSE)
  db <- DBI::dbConnect(RSQLite::SQLite(), ":memory:")
  RSQLite::initExtension(db)
  rq_copy_to(db, "dRemote", d,
              overwrite = TRUE,
              temporary = TRUE)

  ops <- db_td(db, "dRemote") %.>%
    extend(., v %:=% ifelse(x>2, "x", "y")) %.>%
    rsummary_node(.)
  cat(format(ops))

  print(to_sql(ops, db))

  reshdl <- materialize(db, ops)
  print(DBI::dbGetQuery(db, to_sql(reshdl, db)))

  DBI::dbDisconnect(db)
}
#> mk_td("dRemote", c(
#>   "p",
#>   "s",
#>   "w",
#>   "x",
#>   "y",
#>   "z")) %.>%
#>  extend(.,
#>   v := ifelse(x > 2, "x", "y")) %.>%
#>  non_sql_node(., rsummary_node(.))
#> [[1]]
#> [1] "CREATE TEMPORARY TABLE `sn_78423848310883927581_0000000000`  AS  SELECT\n  `p`,\n  `s`,\n  `w`,\n  `x`,\n  `y`,\n  `z`,\n  ( CASE WHEN ( `x` > 2 ) THEN ( 'x' ) WHEN NOT ( `x` > 2 ) THEN ( 'y' ) ELSE NULL END )  AS `v`\n FROM (\n  SELECT\n   `p`,\n   `s`,\n   `w`,\n   `x`,\n   `y`,\n   `z`\n  FROM\n   `dRemote`\n  ) tsql_21419932143980659800_0000000000\n"
#> 
#> [[2]]
#> [1] "non SQL step:  rsummary_node(.)"
#> 
#> [[3]]
#> [1] " SELECT\n  `column`,\n  `index`,\n  `class`,\n  `nrows`,\n  `nna`,\n  `nunique`,\n  `min`,\n  `max`,\n  `mean`,\n  `sd`,\n  `lexmin`,\n  `lexmax`\n FROM\n  `sn_78423848310883927581_0000000001`\n"
#> 
#>   column index     class nrows nna nunique min max mean        sd lexmin lexmax
#> 1      p     1   integer     3   1      NA   0   1  0.5 0.7071068   <NA>   <NA>
#> 2      s     2   integer     3   3       0  NA  NA   NA        NA   <NA>   <NA>
#> 3      w     3   integer     3   0      NA   1   3  2.0 1.0000000   <NA>   <NA>
#> 4      x     4   numeric     3   1      NA   2   3  2.5 0.7071068   <NA>   <NA>
#> 5      y     5 character     3   1       2  NA  NA   NA        NA      3      5
#> 6      z     6 character     3   1       1  NA  NA   NA        NA      a      a
#> 7      v     7   logical     3   1       2   0   0  0.0 0.0000000  FALSE  FALSE