# Machine Learning Challenge — Data

来源：https://www.kaggle.com/competitions/final22202/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<h2>File descriptions</h2>
<ul>
<li><strong>training.csv</strong> - Training set of 250000 events, with an ID column, 30 feature columns, a weight column and a label column.</li>
<li><strong>test.csv</strong> - Test set of 550000 events with an ID column and 30 feature columns.</li>
<li><strong>random_submission</strong> - Sample submission file in the correct format. File format is described on the <a href="https://www.kaggle.com/c/higgs-boson/details/evaluation">Evaluation</a> page.</li>
<li><strong>HiggsBosonCompetition_AMSMetric</strong> - Python script to calculate the competition evaluation metric.</li>
</ul>
<p>For detailed information on the semantics of the features, labels, and weights, see the <a href="http://higgsml.lal.in2p3.fr/documentation">technical documentation</a> from the <a href="https://higgsml.lal.in2p3.fr/">LAL website</a> on the task.</p>
<p>Some details to get started:</p>
<ul>
<li>all variables are floating point, except <strong style="font-size: 1em;">PRI_jet_num</strong><span style="font-size: 1em;"> which is integer</span></li>
<li>variables prefixed with <strong style="font-size: 1em;">PRI</strong><span style="font-size: 1em;"> (for PRImitives) are “raw” quantities about the bunch collision as measured by the detector.</span></li>
<li>variables prefixed with <strong style="font-size: 1em;">DER</strong><span style="font-size: 1em;"> (for DERived) are quantities computed from the primitive features, which were selected by the physicists of ATLAS</span></li>
<li>it can happen that for some entries some variables are meaningless or cannot be computed; in this case, their value is −999.0, which is outside the normal range of all variables</li>
</ul>