control_hnsw

Controls for HNSW algorithm used in the package (see <code>RcppHNSW::hnsw_build()</code> and <code>RcppHNSW::hnsw_search()</code> for details).

The goal of 'blocking' is to provide blocking methods for record linkage and deduplication using approximate nearest neighbour (ANN) algorithms and graph techniques. It supports multiple ANN implementations via 'rnndescent', 'RcppHNSW', 'RcppAnnoy', and 'mlpack' packages, and provides integration with the 'reclin2' package. The package generates shingles from character strings and similarity vectors for record comparison, and includes evaluation metrics for assessing blocking performance including false positive rate (FPR) and false negative rate (FNR) estimates. For details see: Papadakis et al. (2020) <doi:10.1145/3377455>, Steorts et al. (2014) <doi:10.1007/978-3-319-11257-2_20>, Dasylva and Goussanou (2021) <https://www150.statcan.gc.ca/n1/en/catalogue/12-001-X202100200002>, Dasylva and Goussanou (2022) <doi:10.1007/s42081-022-00153-3>.

Maciej Ber<c4><99>sewicz

blocking

Various Blocking Methods for Entity Resolution

Maciej Beręsewicz

Adam Struzik

control_hnsw function

<dl><dt>M</dt>
<dd>Controls the number of bi-directional links created for each element during index construction.</dd>
<dt>ef_c</dt>
<dd>Size of the dynamic list used during construction.</dd>
<dt>ef_s</dt>
<dd>Size of the dynamic list used during search.</dd>
<dt>grain_size</dt>
<dd>Minimum amount of work to do (rows in the dataset to add) per thread.</dd>
<dt>byrow</dt>
<dd>If <code>TRUE</code> (the default), this indicates that the items in the dataset to be indexed are stored in each row.
Otherwise, the items are stored in the columns of the dataset.</dd>
<dt>...</dt>
<dd>Additional arguments.</dd></dl>

Arguments

Controls for the HNSW algorithm — control_hnsw

<dl>

<dt>M</dt>
<dd>Controls the number of bi-directional links created for each element during index construction.</dd>


<dt>ef_c</dt>
<dd>Size of the dynamic list used during construction.</dd>


<dt>ef_s</dt>
<dd>Size of the dynamic list used during search.</dd>


<dt>grain_size</dt>
<dd>Minimum amount of work to do (rows in the dataset to add) per thread.</dd>


<dt>byrow</dt>
<dd>If <code>TRUE</code> (the default), this indicates that the items in the dataset to be indexed are stored in each row.
Otherwise, the items are stored in the columns of the dataset.</dd>


<dt>...</dt>
<dd>Additional arguments.</dd>

</dl>

control_hnsw: Controls for the HNSW algorithm

Description

Usage

Value

Arguments