July 19, 2019 Software Open Access

Sebastian Raschka; James Bourbeau; Reiichiro Nakano; Zach Griffith; Kota Mori; Will McGinnis; JJLWHarrison; Guillaume Poirier-Morency; Daniel; Qiang Gu; Floris Hoogenboom; Colin; Vahid Mirjalili; selay01; Christos Aridas; Steve Harenberg; Pablo Fernandez; Oliver Tomic; Laurens Geffert; Janpreet Singh; Alejandro Correa Bahnsen; Benjamin Lee; Batuhan Bardak; Arfon Smith; Anton Loss; Anebi; Ajinkya Kale; Adam Erickson; Adam Cooper; Ackerley Tng

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.3343208</identifier>
  <creators>
    <creator>
      <creatorName>Sebastian Raschka</creatorName>
      <affiliation>UW-Madison</affiliation>
    </creator>
    <creator>
      <creatorName>James Bourbeau</creatorName>
      <affiliation>@Quansight</affiliation>
    </creator>
    <creator>
      <creatorName>Reiichiro Nakano</creatorName>
      <affiliation>@infostellarinc</affiliation>
    </creator>
    <creator>
      <creatorName>Zach Griffith</creatorName>
      <affiliation>@WIPACrepo</affiliation>
    </creator>
    <creator>
      <creatorName>Kota Mori</creatorName>
      <affiliation></affiliation>
    </creator>
    <creator>
      <creatorName>Will McGinnis</creatorName>
      <affiliation>Predikto Inc.</affiliation>
    </creator>
    <creator>
      <creatorName>JJLWHarrison</creatorName>
      <affiliation></affiliation>
    </creator>
    <creator>
      <creatorName>Guillaume Poirier-Morency</creatorName>
      <affiliation>IRIC @major-lab</affiliation>
    </creator>
    <creator>
      <creatorName>Daniel</creatorName>
      <affiliation></affiliation>
    </creator>
    <creator>
      <creatorName>Qiang Gu</creatorName>
      <affiliation></affiliation>
    </creator>
    <creator>
      <creatorName>Floris Hoogenboom</creatorName>
      <affiliation></affiliation>
    </creator>
    <creator>
      <creatorName>Colin</creatorName>
      <affiliation></affiliation>
    </creator>
    <creator>
      <creatorName>Vahid Mirjalili</creatorName>
      <affiliation>Michigan State University</affiliation>
    </creator>
    <creator>
      <creatorName>selay01</creatorName>
      <affiliation></affiliation>
    </creator>
    <creator>
      <creatorName>Christos Aridas</creatorName>
      <affiliation></affiliation>
    </creator>
    <creator>
      <creatorName>Steve Harenberg</creatorName>
      <affiliation></affiliation>
    </creator>
    <creator>
      <creatorName>Pablo Fernandez</creatorName>
      <affiliation>FANSI Motorsport</affiliation>
    </creator>
    <creator>
      <creatorName>Oliver Tomic</creatorName>
      <affiliation>Norwegian University of Life Sciences</affiliation>
    </creator>
    <creator>
      <creatorName>Laurens Geffert</creatorName>
      <affiliation></affiliation>
    </creator>
    <creator>
      <creatorName>Janpreet Singh</creatorName>
      <affiliation></affiliation>
    </creator>
    <creator>
      <creatorName>Alejandro Correa Bahnsen</creatorName>
      <affiliation>Easy Solutions</affiliation>
    </creator>
    <creator>
      <creatorName>Benjamin Lee</creatorName>
      <affiliation>@Lab41</affiliation>
    </creator>
    <creator>
      <creatorName>Batuhan Bardak</creatorName>
      <affiliation>STM</affiliation>
    </creator>
    <creator>
      <creatorName>Arfon Smith</creatorName>
      <affiliation>@spacetelescope</affiliation>
    </creator>
    <creator>
      <creatorName>Anton Loss</creatorName>
      <affiliation></affiliation>
    </creator>
    <creator>
      <creatorName>Anebi</creatorName>
      <affiliation></affiliation>
    </creator>
    <creator>
      <creatorName>Ajinkya Kale</creatorName>
      <affiliation></affiliation>
    </creator>
    <creator>
      <creatorName>Adam Erickson</creatorName>
      <affiliation></affiliation>
    </creator>
    <creator>
      <creatorName>Adam Cooper</creatorName>
      <affiliation>Tribal</affiliation>
    </creator>
    <creator>
      <creatorName>Ackerley Tng</creatorName>
      <affiliation>Centre for Strategic Infocomm Technologies</affiliation>
    </creator>
  </creators>
  <titles>
    <title>rasbt/mlxtend: Version 0.17.0</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2019</publicationYear>
  <dates>
    <date dateType="Issued">2019-07-19</date>
  </dates>
  <resourceType resourceTypeGeneral="Software"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3343208</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsSupplementTo">https://github.com/rasbt/mlxtend/tree/v0.17.0</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.594432</relatedIdentifier>
  </relatedIdentifiers>
  <version>v0.17.0</version>
  <rightsList>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">New Features
&lt;ul&gt;
&lt;li&gt;Added an enhancement to the existing &lt;code&gt;iris_data()&lt;/code&gt; such that both the UCI Repository version of the Iris dataset as well as the corrected, original
version of the dataset can be loaded, which has a slight difference in two data points (consistent with Fisher's paper; this is also the same as in R). (via &lt;a href="https://github.com/rasbt/mlxtend/pull/532"&gt;#539&lt;/a&gt; via &lt;a href="https://github.com/janismdhanbad"&gt;janismdhanbad&lt;/a&gt;)&lt;/li&gt;
&lt;li&gt;Added optional &lt;code&gt;groups&lt;/code&gt; parameter to &lt;code&gt;SequentialFeatureSelector&lt;/code&gt; and &lt;code&gt;ExhaustiveFeatureSelector&lt;/code&gt; &lt;code&gt;fit()&lt;/code&gt; methods for forwarding to sklearn CV (&lt;a href="https://github.com/rasbt/mlxtend/pull/537"&gt;#537&lt;/a&gt; via &lt;a href="https://github.com/qiaguhttps://github.com/arc12"&gt;arc12&lt;/a&gt;)&lt;/li&gt;
&lt;li&gt;Added a new &lt;code&gt;plot_pca_correlation_graph&lt;/code&gt; function to the &lt;code&gt;mlxtend.plotting&lt;/code&gt; submodule for plotting a PCA correlation graph. (&lt;a href="https://github.com/rasbt/mlxtend/pull/544"&gt;#544&lt;/a&gt; via &lt;a href="https://github.com/qiaguhttps://github.com/Gabriel-Azevedo-Ferreira"&gt;Gabriel-Azevedo-Ferreira&lt;/a&gt;)&lt;/li&gt;
&lt;li&gt;Added a &lt;code&gt;zoom_factor&lt;/code&gt; parameter to the &lt;code&gt;mlxten.plotting.plot_decision_region&lt;/code&gt; function that allows users to zoom in and out of the decision region plots. (&lt;a href="https://github.com/rasbt/mlxtend/pull/545"&gt;#545&lt;/a&gt;)&lt;/li&gt;
&lt;li&gt;Added a function &lt;code&gt;fpgrowth&lt;/code&gt; that implements the FP-Growth algorithm for mining frequent itemsets as a drop-in replacement for the existing &lt;code&gt;apriori&lt;/code&gt; algorithm. (&lt;a href="https://github.com/rasbt/mlxtend/pull/550"&gt;#550&lt;/a&gt; via &lt;a href="https://github.com/harenbergsd"&gt;Steve Harenberg&lt;/a&gt;)&lt;/li&gt;
&lt;li&gt;New &lt;code&gt;heatmap&lt;/code&gt; function in &lt;code&gt;mlxtend.plotting&lt;/code&gt;.  (&lt;a href="https://github.com/rasbt/mlxtend/pull/552"&gt;#552&lt;/a&gt;)&lt;/li&gt;
&lt;li&gt;Added a function &lt;code&gt;fpmax&lt;/code&gt; that implements the FP-Max algorithm for mining maximal itemsets as a drop-in replacement for the &lt;code&gt;fpgrowth&lt;/code&gt; algorithm. (&lt;a href="https://github.com/rasbt/mlxtend/pull/553"&gt;#553&lt;/a&gt; via &lt;a href="https://github.com/harenbergsd"&gt;Steve Harenberg&lt;/a&gt;)&lt;/li&gt;
&lt;li&gt;New &lt;code&gt;figsize&lt;/code&gt; parameter for the &lt;code&gt;plot_decision_regions&lt;/code&gt; function in &lt;code&gt;mlxtend.plotting&lt;/code&gt;. (&lt;a href="https://github.com/rasbt/mlxtend/pull/555"&gt;#555&lt;/a&gt; via &lt;a href="https://github.com/kazyka"&gt;Mirza Hasanbasic&lt;/a&gt;)&lt;/li&gt;
&lt;li&gt;New &lt;code&gt;low_memory&lt;/code&gt; option for the &lt;code&gt;apriori&lt;/code&gt; frequent itemset generating function. Setting &lt;code&gt;low_memory=False&lt;/code&gt; (default) uses a substantially optimized version of the algorithm that is 3-6x faster than the original implementation (&lt;code&gt;low_memory=True&lt;/code&gt;). (&lt;a href="https://github.com/rasbt/mlxtend/pull/567"&gt;#567&lt;/a&gt; via &lt;a href="https://github.com/jmayse"&gt;jmayse&lt;/a&gt;)&lt;/li&gt;
&lt;/ul&gt;
Changes
&lt;ul&gt;
&lt;li&gt;Now uses the latest joblib library under the hood for multiprocessing instead of &lt;code&gt;sklearn.externals.joblib&lt;/code&gt;. (&lt;a href="https://github.com/rasbt/mlxtend/pull/547"&gt;#547&lt;/a&gt;)&lt;/li&gt;
&lt;li&gt;Changes to &lt;code&gt;StackingCVClassifier&lt;/code&gt; and &lt;code&gt;StackingCVRegressor&lt;/code&gt; such that first-level models are allowed to generate output of non-numeric type. (&lt;a href="https://github.com/rasbt/mlxtend/pull/562"&gt;#562&lt;/a&gt;)&lt;/li&gt;
&lt;/ul&gt;
Bug Fixes
&lt;ul&gt;
&lt;li&gt;Fixed documentation of &lt;code&gt;iris_data()&lt;/code&gt; under &lt;code&gt;iris.py&lt;/code&gt; by adding a note about differences in the iris data in R and UCI machine learning repo.&lt;/li&gt;
&lt;li&gt;Make sure that if the &lt;code&gt;'svd'&lt;/code&gt; mode is used in PCA, the number of eigenvalues is the same as when using &lt;code&gt;'eigen'&lt;/code&gt; (append 0's zeros in that case) (&lt;a href="https://github.com/rasbt/mlxtend/pull/565"&gt;#565&lt;/a&gt;)&lt;/li&gt;
&lt;/ul&gt;</description>
  </descriptions>
</resource>