{"repo":"imperial-aisp/CorrectMatch.jl","free":true,"listed":false,"github":"https://github.com/imperial-aisp/CorrectMatch.jl","clone":"git clone https://github.com/imperial-aisp/CorrectMatch.jl.git","description":"Source code for https://nature.com/articles/s41467-019-10933-3","language":"Julia","stars":21,"topics":["privacy","privacy-protection","julia","statistics"],"license":"GPL-3.0","category":"self-hosted-apps","readme_excerpt":"CorrectMatch Installation CorrectMatch requires gfortran to precompile the mvndst routines. On macOS, using Homebrew, run: On GNU/Linux, install the gfortran package with your preferred package manager: Usage CorrectMatch works directly with DataFrames, automatically handling categorical variables: Individual uniqueness and correctness can be computed for any record: Working with integer matrices The codebase also supports working directly with integer matrices, where each column represents a categorical variable encoded as integers starting from 1. This allows for using the exact marginal=false option for better fitting distributions in small sparse datasets. See the examples folder to learn how to load a CSV file and estimate the metrics from a small sample. License GNU General Public License v3.0 See LICENSE to see the full text. Patent-pending code. Additional support and details are available for commercial uses.","default_branch":null,"files":null,"tree":[],"storefront":"/r/imperial-aisp","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/imperial-aisp/CorrectMatch.jl/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}