find_posterior_chunked: Like "find_posterior" but it uses less memory at any one time...

In csps-efpc/TokenLink: Joins two dataframes using tokens or like words

Like "find_posterior" but it uses less memory at any one time by iterating over chunks of the x dataset. When this is used the returned t_dat object will not have "positive_evidence_only" dataframe it will have the "all_evidence" dataframe

Description

Like "find_posterior" but it uses less memory at any one time by iterating over chunks of the x dataset. When this is used the returned t_dat object will not have "positive_evidence_only" dataframe it will have the "all_evidence" dataframe

Usage

find_posterior_chunked(
  t_dat,
  ...,
  min_posterior_all_evidence = MIN_POSTERIOR_ALL_EVIDENCE,
  min_posterior_positive_evidence_only = MIN_POSTERIOR_POSITIVE_EVIDENCE_ONLY,
  n_chunks = N_CHUNKS,
  return_all = TRUE
)

Arguments

t_dat	t_dat object
...	passed to find_posterior_subset
min_posterior_all_evidence	passed to find_posterior_subset. : Default MIN_POSTERIOR_ALL_EVIDENCE
min_posterior_positive_evidence_only	passed to find_posterior_subset. : Default MIN_POSTERIOR_POSITIVE_EVIDENCE_ONLY
n_chunks	How many chunks to break up the x dataset into : Default 100
return_all	return modified "t_dat" object if TRUE otherwise return the all_evidence dataframe : Default TRUE

csps-efpc/TokenLink documentation built on Feb. 10, 2023, 3:30 a.m.