Published July 4, 2019 | Version v1
Dataset Open

Datasets for Non-Parametric Class Completeness Estimators for Collaborative Knowledge Graphs

  • 1. University of Fribourg

Description

Non-Parametric Class Completeness Estimators for Collaborative Knowledge Graphs

This are intermediary datasets used for the calculation of the Class Completeness Estimators on Wikidata. For more information see: https://github.com/eXascaleInfolab/cardinal/

edits_wikidatawiki-20181001-pages.csv

This is an extract from wikidatawiki-20181001-pages-meta-history (All pages with complete page edit history (.bz2)) found at https://dumps.wikimedia.org/wikidatawiki/.

The extract was created by the following SQL query:

    SELECT
        page_title,
        rev_comment,
        rev_user_text,
        rev_timestamp 
    FROM
        revisions 
    WHERE
        rev_comment LIKE '%[[Property:%]]%[[Q%'
    ORDER BY
        rev_id 
    INTO
        OUTFILE 'edits_wikidatawiki-20181001-pages.csv';

 

wikidata-20180813-all.json.bz2.universe.noattr.gt.bz2

This is a graph-tool representation of the WikiData graph. Output of https://github.com/eXascaleInfolab/cardinal/blob/master/1_create_inmemory_graph.py.

observations_wikidatawiki-20181001-pages.pickle

Extracted observations. Output of https://github.com/eXascaleInfolab/cardinal/blob/master/2_extract_observations.py.

 

estimates_wikidatawiki-20181001-pages.pickle

Extracted estimates. Output of https://github.com/eXascaleInfolab/cardinal/blob/master/3_calculate_estimates.py

 

results_wikidatawiki-20181001-pages.pickle 

Results. Output of https://github.com/eXascaleInfolab/cardinal/blob/master/4_draw_graphs.py

Files

edits_wikidatawiki-20181001-pages.csv

Files (37.2 GB)

Name Size Download all
md5:93333f0d940603b3a05ace37726a3d07
17.0 GB Preview Download
md5:e11acb02625742de2702330d0ece08e8
6.9 MB Download
md5:fbdd1bc64ba24fc6eb6a82dbe72c6667
18.7 GB Download
md5:37b80479e7ca71a81b30c9a086e46507
164.6 kB Download
md5:58c0ba7bc0a222b42e0f60e469460cf4
1.5 GB Download

Additional details

Related works

Is supplement to
10.1007/978-3-030-30793-6_26 (DOI)
References
10.5281/zenodo.3268725 (DOI)

Funding

European Commission
GraphInt - Principles of Graph Data Integration 683253