Conference paper Open Access

Code Duplication and Reuse in Jupyter Notebooks

Koenzen, Andreas P.; Ernst, Neil A.; Storey, Margaret-Anne D.


DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.3836691">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.3836691</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.3836691"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Koenzen, Andreas P.</foaf:name>
        <foaf:givenName>Andreas P.</foaf:givenName>
        <foaf:familyName>Koenzen</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Victoria</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Ernst, Neil A.</foaf:name>
        <foaf:givenName>Neil A.</foaf:givenName>
        <foaf:familyName>Ernst</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Victoria</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Storey, Margaret-Anne D.</foaf:name>
        <foaf:givenName>Margaret-Anne D.</foaf:givenName>
        <foaf:familyName>Storey</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Victoria</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Code Duplication and Reuse in Jupyter Notebooks</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2020</dct:issued>
    <dcat:keyword>Jupyter, computational notebooks, code duplication, code clones, code reuse, data analysis, data exploration, exploratory programming</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2020-05-29</dct:issued>
    <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/ENG"/>
    <owl:sameAs rdf:resource="https://zenodo.org/record/3836691"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/3836691</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.3836690"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/msr"/>
    <owl:versionInfo>3.0</owl:versionInfo>
    <dct:description>&lt;p&gt;This is a replication package for the paper: &amp;quot;Code Duplication and Reuse in Jupyter Notebooks&amp;quot;, which was accepted as a full paper at the&amp;nbsp;&lt;strong&gt;IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) 2020&lt;/strong&gt;.&lt;/p&gt; &lt;p&gt;The contents of this package are as follows:&lt;/p&gt; &lt;ul&gt; &lt;li&gt;&lt;strong&gt;code&lt;/strong&gt; folder: Contains all necessary code to reproduce the first study presented in the paper.&lt;/li&gt; &lt;li&gt;&lt;strong&gt;data&lt;/strong&gt; folder: Contains all data pertaining to the first study presented in the paper. &lt;ul&gt; &lt;li&gt;&lt;strong&gt;clones_1582405629.json.gz&lt;/strong&gt; file: JSON database with all detected clones and its&amp;nbsp;metadata for the used dataset.&lt;/li&gt; &lt;li&gt;&lt;strong&gt;commit_data_1589997765.pkl.gz&lt;/strong&gt; file: Pandas pickle file containing the table &amp;quot;commit_data&amp;quot; (See &lt;em&gt;database.sql&lt;/em&gt; file).&lt;/li&gt; &lt;li&gt;&lt;strong&gt;commits_1589997765.pkl.gz&lt;/strong&gt; file: Pandas pickle file containing the table &amp;quot;commit&amp;quot; (See &lt;em&gt;database.sql&lt;/em&gt; file).&lt;/li&gt; &lt;li&gt;&lt;strong&gt;counter_1582422799.json.gz&lt;/strong&gt; file: JSON database with statistics about all repositories in the used dataset.&lt;/li&gt; &lt;li&gt;&lt;strong&gt;notebooks_1589997765.pkl.gz&lt;/strong&gt; file: Pandas pickle file containing&amp;nbsp;the table &amp;quot;notebooks&amp;quot; (See &lt;em&gt;database.sql&lt;/em&gt; file).&lt;/li&gt; &lt;li&gt;&lt;strong&gt;parameter_tunning&lt;/strong&gt; folder: Folder with the results of the parameter tuning phase. Each TXT file corresponds to a different threshold.&lt;/li&gt; &lt;/ul&gt; &lt;/li&gt; &lt;/ul&gt; &lt;p&gt;In order to fully reproduce the code, a fully functional &lt;strong&gt;Python 3.7&lt;/strong&gt; environment is needed. The requirements can be found in the &lt;strong&gt;requirements.txt&lt;/strong&gt; file. If the starting scripts are to be used, a &lt;strong&gt;Python 3.7.7&lt;/strong&gt; version must be installed via &lt;strong&gt;pyenv&lt;/strong&gt;, but is NOT&amp;nbsp;necessary to run the notebooks,&amp;nbsp;the &lt;strong&gt;JupyterLab&lt;/strong&gt; environment can be launched manually issuing the&amp;nbsp;command: &lt;strong&gt;&amp;quot;jupyter lab notebooks&amp;quot;&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;Commands:&lt;/p&gt; &lt;ol&gt; &lt;li&gt;To install Python dependencies via Pip: &lt;strong&gt;&amp;quot;pip install -r requirements.txt&amp;quot;&lt;/strong&gt;&lt;/li&gt; &lt;li&gt;To launch Jupyter: &lt;strong&gt;&amp;quot;source start-jupyter.sh&amp;quot;&lt;/strong&gt;&lt;/li&gt; &lt;/ol&gt; &lt;p&gt;Optional:&lt;/p&gt; &lt;ol&gt; &lt;li&gt;To access environment variables from Jupyter, the file &lt;strong&gt;env_variables.py&lt;/strong&gt; can be edited to add new variables or modify current ones.&lt;/li&gt; &lt;/ol&gt; &lt;p&gt;&lt;strong&gt;SHA1SUM of ZIP file:&lt;/strong&gt;&amp;nbsp;c9b5d7e2dbe0574b73f2d2b67adb9e18fdcfb513&lt;/p&gt;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3836691"/>
        <dcat:byteSize>2453258443</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/3836691/files/VLHCC_2020_Paper_Reproducibility_Pkg.zip"/>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
83
10
views
downloads
All versions This version
Views 8383
Downloads 1010
Data volume 24.5 GB24.5 GB
Unique views 7676
Unique downloads 99

Share

Cite as