rqdatatable (version 1.2.9)

rq_df_grouped_funciton_node: Helper to build data.table capable non-sql nodes.

Description

Helper to build data.table capable non-sql nodes.

Usage

rq_df_grouped_funciton_node(
  .,
  f,
  ...,
  f_db = NULL,
  columns_produced,
  group_col,
  display_form
)

Arguments

.

or data.frame input.

f

function that takes a data.table to a data.frame (or data.table).

...

force later arguments to bind by name.

f_db

implementation signature: f_db(db, incoming_table_name, outgoing_table_name) (db being a database handle). NULL defaults to using f.

columns_produced

character columns produces by f.

group_col

character, column to split by.

display_form

display form for node.

Value

relop non-sql node implementation.

See Also

ex_data_table_step.relop_non_sql, rq_df_funciton_node

Examples

# NOT RUN {
# a node generator is something an expert can
# write and part-time R users can use.
grouped_regression_node <- function(., group_col = "group", xvar = "x", yvar = "y") {
  force(group_col)
  formula_str <- paste(yvar, "~", xvar)
  f <- function(di) {
    mi <- lm(as.formula(formula_str), data = di)
    ci <- as.data.frame(summary(mi)$coefficients)
    ci$Variable <- rownames(ci)
    rownames(ci) <- NULL
    colnames(ci) <- c("Estimate", "Std_Error", "t_value", "p_value", "Variable")
    ci
  }
  columns_produced =
    c("Estimate", "Std_Error", "t_value", "p_value", "Variable", group_col)
  rq_df_grouped_funciton_node(
    ., f,
    columns_produced = columns_produced,
    group_col = group_col,
    display_form = paste0(yvar, "~", xvar, " grouped by ", group_col))
}

# work an example
set.seed(3265)
d <- data.frame(x = rnorm(1000),
                y = rnorm(1000),
                group = sample(letters[1:5], 1000, replace = TRUE),
                stringsAsFactors = FALSE)

rquery_pipeline <- local_td(d) %.>%
  grouped_regression_node(.)

cat(format(rquery_pipeline))

d %.>% rquery_pipeline


# }