% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/dupe_detect.R
\name{dupe_detect}
\alias{dupe_detect}
\title{Get ids of duplicate documents that have a cosine similarity score higher than [threshold]}
\usage{
dupe_detect(row, grid, cutoff, es_pwd)
}
\arguments{
\item{row}{Row of grid to parse}

\item{grid}{A cross-table of all possible combinations of doctypes and dates}

\item{cutoff}{Cutoff value for cosine similarity above which documents are considered duplicates}

\item{es_pwd}{Password for Elasticsearch read access}
}
\value{
dupe_objects.json and data frame containing each id and all its duplicates. remove_ids.txt and character vector with list of ids to be removed. Files are in current working directory
}
\description{
Get ids of duplicate documents that have a cosine similarity score higher than [threshold]
}
\examples{
dupe_detect(1,grid,es_pwd)
}