Description
Random walk sample (td_random_walk_sample_mle
) is a graph-sampling technique
to identify a subgraph that preserves graph properties as well as possible.
Usage
td_random_walk_sample_mle ( vertices.data = NULL, edges.data = NULL, target.key = NULL, sample.rate = 0.15, flyback.rate = 0.15, seed = 1000, accumulate = NULL, vertices.data.sequence.column = NULL, edges.data.sequence.column = NULL, vertices.data.partition.column = NULL, edges.data.partition.column = NULL )
Arguments
vertices.data |
Required Argument. |
vertices.data.partition.column |
Required Argument. |
edges.data |
Required Argument. |
edges.data.partition.column |
Required Argument. |
target.key |
Required Argument. |
sample.rate |
Optional Argument. |
flyback.rate |
Optional Argument. |
seed |
Optional Argument. |
accumulate |
Optional Argument. |
vertices.data.sequence.column |
Optional Argument. |
edges.data.sequence.column |
Optional Argument. |
Value
Function returns an object of class "td_random_walk_sample_mle" which is
a named list containing Teradata tbl objects.
Named list members can be referenced directly with the "$" operator
using following names:
output.vertex.table
-
output.edge.table
output
Examples
# Get the current context/connection con <- td_get_context()$connection # Load example data. loadExampleData("randomwalksample_example", "citvertices_2", "citedges_2") # Create remote tibble objects. citvertices_2 <- tbl(con, "citvertices_2") citedges_2 <- tbl(con, "citedges_2") # Example 1 - This function takes an input graph (which is typically large) and outputs # a sample graph that preserves graph properties as well as possible. td_random_walk_sample_out <- td_random_walk_sample_mle(vertices.data = citvertices_2, vertices.data.partition.column = c("id"), edges.data = citedges_2, edges.data.partition.column = c("from_id"), target.key = c("to_id"), sample.rate = 0.15, flyback.rate = 0.15, seed = 1000 )