818 lines
38 KiB
HTML
Vendored
818 lines
38 KiB
HTML
Vendored
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
|
|
<!-- NewPage -->
|
|
<html lang="en">
|
|
<head>
|
|
<!-- Generated by javadoc (1.8.0_312) on Sun Dec 11 09:30:03 MST 2022 -->
|
|
<title>Modelling (tech.ml.dataset Documentation)</title>
|
|
<meta name="date" content="2022-12-11">
|
|
<link rel="stylesheet" type="text/css" href="../../../stylesheet.css" title="Style">
|
|
<script type="text/javascript" src="../../../script.js"></script>
|
|
</head>
|
|
<body>
|
|
<script type="text/javascript"><!--
|
|
try {
|
|
if (location.href.indexOf('is-external=true') == -1) {
|
|
parent.document.title="Modelling (tech.ml.dataset Documentation)";
|
|
}
|
|
}
|
|
catch(err) {
|
|
}
|
|
//-->
|
|
var methods = {"i0":9,"i1":9,"i2":9,"i3":9,"i4":9,"i5":9,"i6":9,"i7":9,"i8":9,"i9":9,"i10":9,"i11":9,"i12":9,"i13":9,"i14":9,"i15":9,"i16":9,"i17":9,"i18":9,"i19":9,"i20":9,"i21":9,"i22":9,"i23":9,"i24":9,"i25":9,"i26":9,"i27":9,"i28":9};
|
|
var tabs = {65535:["t0","All Methods"],1:["t1","Static Methods"],8:["t4","Concrete Methods"]};
|
|
var altColor = "altColor";
|
|
var rowColor = "rowColor";
|
|
var tableTab = "tableTab";
|
|
var activeTableTab = "activeTableTab";
|
|
</script>
|
|
<noscript>
|
|
<div>JavaScript is disabled on your browser.</div>
|
|
</noscript>
|
|
<!-- ========= START OF TOP NAVBAR ======= -->
|
|
<div class="topNav"><a name="navbar.top">
|
|
<!-- -->
|
|
</a>
|
|
<div class="skipNav"><a href="#skip.navbar.top" title="Skip navigation links">Skip navigation links</a></div>
|
|
<a name="navbar.top.firstrow">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="navList" title="Navigation">
|
|
<li><a href="../../../overview-summary.html">Overview</a></li>
|
|
<li><a href="package-summary.html">Package</a></li>
|
|
<li class="navBarCell1Rev">Class</li>
|
|
<li><a href="package-tree.html">Tree</a></li>
|
|
<li><a href="../../../deprecated-list.html">Deprecated</a></li>
|
|
<li><a href="../../../index-all.html">Index</a></li>
|
|
<li><a href="../../../help-doc.html">Help</a></li>
|
|
</ul>
|
|
<div class="aboutLanguage"><script async src="https://www.googletagmanager.com/gtag/js?id=G-RGTB4J7LGP"</script><script>window.dataLayer = window.dataLayer || [];\nfunction gtag(){dataLayer.push(arguments);}\ngtag('js', new Date());\ngtag('config', 'G-RGTB4J7LGP');</div>
|
|
</div>
|
|
<div class="subNav">
|
|
<ul class="navList">
|
|
<li>Prev Class</li>
|
|
<li><a href="../../../tech/v3/dataset/Reductions.html" title="class in tech.v3.dataset"><span class="typeNameLink">Next Class</span></a></li>
|
|
</ul>
|
|
<ul class="navList">
|
|
<li><a href="../../../index.html?tech/v3/dataset/Modelling.html" target="_top">Frames</a></li>
|
|
<li><a href="Modelling.html" target="_top">No Frames</a></li>
|
|
</ul>
|
|
<ul class="navList" id="allclasses_navbar_top">
|
|
<li><a href="../../../allclasses-noframe.html">All Classes</a></li>
|
|
</ul>
|
|
<div>
|
|
<script type="text/javascript"><!--
|
|
allClassesLink = document.getElementById("allclasses_navbar_top");
|
|
if(window==top) {
|
|
allClassesLink.style.display = "block";
|
|
}
|
|
else {
|
|
allClassesLink.style.display = "none";
|
|
}
|
|
//-->
|
|
</script>
|
|
</div>
|
|
<div>
|
|
<ul class="subNavList">
|
|
<li>Summary: </li>
|
|
<li>Nested | </li>
|
|
<li>Field | </li>
|
|
<li>Constr | </li>
|
|
<li><a href="#method.summary">Method</a></li>
|
|
</ul>
|
|
<ul class="subNavList">
|
|
<li>Detail: </li>
|
|
<li>Field | </li>
|
|
<li>Constr | </li>
|
|
<li><a href="#method.detail">Method</a></li>
|
|
</ul>
|
|
</div>
|
|
<a name="skip.navbar.top">
|
|
<!-- -->
|
|
</a></div>
|
|
<!-- ========= END OF TOP NAVBAR ========= -->
|
|
<!-- ======== START OF CLASS DATA ======== -->
|
|
<div class="header">
|
|
<div class="subTitle">tech.v3.dataset</div>
|
|
<h2 title="Class Modelling" class="title">Class Modelling</h2>
|
|
</div>
|
|
<div class="contentContainer">
|
|
<ul class="inheritance">
|
|
<li>java.lang.Object</li>
|
|
<li>
|
|
<ul class="inheritance">
|
|
<li>tech.v3.dataset.Modelling</li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
<div class="description">
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<hr>
|
|
<br>
|
|
<pre>public class <span class="typeNameLabel">Modelling</span>
|
|
extends java.lang.Object</pre>
|
|
<div class="block"><p>Functions related to training and evaluating ML models. The functions are grouped into a few groups.</p>
|
|
<p>For the purpose of this system, categorical data means a column of data that is not numeric. it could be strings, keywords, or arbitrary objects.</p>
|
|
<p>Minimal example extra dependencies for PCA:</p>
|
|
<pre><code class="console">[uncomplicate/neanderthal "0.43.3"]
|
|
</code></pre>
|
|
<p>It is also important to note that you can serialize the fit results to nippy automatically as included in dtype-next are extensions to nippy that work with tensors.</p></div>
|
|
</li>
|
|
</ul>
|
|
</div>
|
|
<div class="summary">
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<!-- ========== METHOD SUMMARY =========== -->
|
|
<ul class="blockList">
|
|
<li class="blockList"><a name="method.summary">
|
|
<!-- -->
|
|
</a>
|
|
<h3>Method Summary</h3>
|
|
<table class="memberSummary" border="0" cellpadding="3" cellspacing="0" summary="Method Summary table, listing methods, and an explanation">
|
|
<caption><span id="t0" class="activeTableTab"><span>All Methods</span><span class="tabEnd"> </span></span><span id="t1" class="tableTab"><span><a href="javascript:show(1);">Static Methods</a></span><span class="tabEnd"> </span></span><span id="t4" class="tableTab"><span><a href="javascript:show(8);">Concrete Methods</a></span><span class="tabEnd"> </span></span></caption>
|
|
<tr>
|
|
<th class="colFirst" scope="col">Modifier and Type</th>
|
|
<th class="colLast" scope="col">Method and Description</th>
|
|
</tr>
|
|
<tr id="i0" class="altColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#correlationTable-java.lang.Object-">correlationTable</a></span>(java.lang.Object ds)</code>
|
|
<div class="block">Return a map of column to inversely sorted from greatest to least sequence of tuples of column name, pearson correlation coefficient.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i1" class="rowColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#correlationTable-java.lang.Object-java.lang.Object-">correlationTable</a></span>(java.lang.Object ds,
|
|
java.lang.Object options)</code>
|
|
<div class="block">Return a map of column to inversely sorted from greatest to least sequence of tuples of column name, coefficient.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i2" class="altColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#fillRangeReplace-java.lang.Object-java.lang.Object-double-java.lang.Object-">fillRangeReplace</a></span>(java.lang.Object ds,
|
|
java.lang.Object cname,
|
|
double maxSpan,
|
|
java.lang.Object missingStrategy)</code>
|
|
<div class="block">Expand a dataset ensuring that the difference between two successive values is less than <code>max-span</code>.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i3" class="rowColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#fitCategorical-java.lang.Object-java.lang.Object-">fitCategorical</a></span>(java.lang.Object ds,
|
|
java.lang.Object cname)</code>
|
|
<div class="block">Fit an object->integer transformation.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i4" class="altColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#fitCategorical-java.lang.Object-java.lang.Object-java.lang.Object-">fitCategorical</a></span>(java.lang.Object ds,
|
|
java.lang.Object cname,
|
|
java.lang.Object options)</code>
|
|
<div class="block">Fit an object->integer transform that takes each value and assigned an integer to it.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i5" class="rowColor">
|
|
<td class="colFirst"><code>static java.lang.Object</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#fitMinMax-java.lang.Object-">fitMinMax</a></span>(java.lang.Object ds)</code>
|
|
<div class="block">Fit a minmax transformation that will transform each column to a minimum of -0.5 and a maximum of 0.5.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i6" class="altColor">
|
|
<td class="colFirst"><code>static java.lang.Object</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#fitMinMax-java.lang.Object-java.lang.Object-">fitMinMax</a></span>(java.lang.Object ds,
|
|
java.lang.Object options)</code>
|
|
<div class="block">Fit a bias and scale the dataset that transforms each colum to a target min-max value.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i7" class="rowColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#fitOneHot-java.lang.Object-java.lang.Object-">fitOneHot</a></span>(java.lang.Object ds,
|
|
java.lang.Object cname)</code>
|
|
<div class="block">Fit a mapping from a categorical column to a group of one-hot encoded columns.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i8" class="altColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#fitOneHot-java.lang.Object-java.lang.Object-java.lang.Object-">fitOneHot</a></span>(java.lang.Object ds,
|
|
java.lang.Object cname,
|
|
java.lang.Object options)</code>
|
|
<div class="block">Fit a transformation from a single column of categorical values to a <code>one-hot</code> encoded group of columns.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i9" class="rowColor">
|
|
<td class="colFirst"><code>static java.lang.Object</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#fitPCA-java.lang.Object-">fitPCA</a></span>(java.lang.Object ds)</code>
|
|
<div class="block">Fit a PCA transformation onto a dataset keeping 95% of the variance.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i10" class="altColor">
|
|
<td class="colFirst"><code>static java.lang.Object</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#fitPCA-java.lang.Object-java.lang.Object-">fitPCA</a></span>(java.lang.Object ds,
|
|
java.lang.Object options)</code>
|
|
<div class="block">Fit a PCA transformation on a dataset.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i11" class="rowColor">
|
|
<td class="colFirst"><code>static java.lang.Object</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#fitStdScale-java.lang.Object-">fitStdScale</a></span>(java.lang.Object ds)</code>
|
|
<div class="block">Calculate per-column mean, stddev.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i12" class="altColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#inferenceTargetLabelMap-java.lang.Object-">inferenceTargetLabelMap</a></span>(java.lang.Object ds)</code>
|
|
<div class="block">Return a map of val->idx for the inference target.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i13" class="rowColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#interpolateLOESS-java.lang.Object-java.lang.Object-java.lang.Object-">interpolateLOESS</a></span>(java.lang.Object ds,
|
|
java.lang.Object xColname,
|
|
java.lang.Object yColname)</code>
|
|
<div class="block">Perform a LOESS interpolation using the default parameters.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i14" class="altColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#interpolateLOESS-java.lang.Object-java.lang.Object-java.lang.Object-java.lang.Object-">interpolateLOESS</a></span>(java.lang.Object ds,
|
|
java.lang.Object xColname,
|
|
java.lang.Object yColname,
|
|
java.lang.Object options)</code>
|
|
<div class="block">Map a LOESS-interpolation transformation onto a dataset.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i15" class="rowColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#invertCategorical-java.lang.Object-java.lang.Object-">invertCategorical</a></span>(java.lang.Object ds,
|
|
java.lang.Object catFitData)</code>
|
|
<div class="block">Reverse a previously transformed categorical mapping.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i16" class="altColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#invertOneHot-java.lang.Object-java.lang.Object-">invertOneHot</a></span>(java.lang.Object ds,
|
|
java.lang.Object fitData)</code>
|
|
<div class="block">Reverse a previously transformed one-hot mapping.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i17" class="rowColor">
|
|
<td class="colFirst"><code>static java.lang.Iterable</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#kFold-java.lang.Object-long-">kFold</a></span>(java.lang.Object ds,
|
|
long k)</code>
|
|
<div class="block">Return k maps of the form <code>{:test-ds :train-ds}</code>.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i18" class="altColor">
|
|
<td class="colFirst"><code>static java.lang.Iterable</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#kFold-java.lang.Object-long-java.lang.Object-">kFold</a></span>(java.lang.Object ds,
|
|
long k,
|
|
java.lang.Object options)</code>
|
|
<div class="block">Produce 2*k datasets from 1 dataset using k-fold algorithm.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i19" class="rowColor">
|
|
<td class="colFirst"><code>static java.lang.Object</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#labels-java.lang.Object-">labels</a></span>(java.lang.Object ds)</code>
|
|
<div class="block">Find the inference column.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i20" class="altColor">
|
|
<td class="colFirst"><code>static java.lang.Object</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#probabilityDistributionToLabels-java.lang.Object-">probabilityDistributionToLabels</a></span>(java.lang.Object ds)</code>
|
|
<div class="block">Given a dataset where the column names are labels and the each row is a probabilitly distribution across the labels, produce a Buffer of labels taking the highest probability for each row to choose the label.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i21" class="rowColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#setInferenceTarget-java.lang.Object-java.lang.Object-">setInferenceTarget</a></span>(java.lang.Object ds,
|
|
java.lang.Object cname)</code>
|
|
<div class="block">Set a column in the dataset as the inference target.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i22" class="altColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#trainTestSplit-java.lang.Object-">trainTestSplit</a></span>(java.lang.Object ds)</code>
|
|
<div class="block">Randomize then split dataset using 70% of the data for training and the rest for testing.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i23" class="rowColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#trainTestSplit-java.lang.Object-java.lang.Object-">trainTestSplit</a></span>(java.lang.Object ds,
|
|
java.lang.Object options)</code>
|
|
<div class="block">Split the dataset returning a map of <code>{:train-ds :test-ds}</code>.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i24" class="altColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#transformCategorical-java.lang.Object-java.lang.Object-">transformCategorical</a></span>(java.lang.Object ds,
|
|
java.lang.Object catFitData)</code>
|
|
<div class="block">Apply an object->integer transformation with data obtained from fitCategorical.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i25" class="rowColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#transformMinMax-java.lang.Object-java.lang.Object-">transformMinMax</a></span>(java.lang.Object ds,
|
|
java.lang.Object fitData)</code>
|
|
<div class="block">Transform a dataset using a previously fit minimax transformation.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i26" class="altColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#transformOneHot-java.lang.Object-java.lang.Object-">transformOneHot</a></span>(java.lang.Object ds,
|
|
java.lang.Object fitData)</code>
|
|
<div class="block">Transform a dataset using a fitted one-hot mapping.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i27" class="rowColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#transformPCA-java.lang.Object-java.lang.Object-">transformPCA</a></span>(java.lang.Object ds,
|
|
java.lang.Object fitData)</code>
|
|
<div class="block">Transform a dataset by the PCA fit data.</div>
|
|
</td>
|
|
</tr>
|
|
<tr id="i28" class="altColor">
|
|
<td class="colFirst"><code>static java.util.Map</code></td>
|
|
<td class="colLast"><code><span class="memberNameLink"><a href="../../../tech/v3/dataset/Modelling.html#transformStdScale-java.lang.Object-java.lang.Object-">transformStdScale</a></span>(java.lang.Object ds,
|
|
java.lang.Object fitData)</code>
|
|
<div class="block">Transform dataset to mean of zero and a standard deviation of 1.</div>
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
<ul class="blockList">
|
|
<li class="blockList"><a name="methods.inherited.from.class.java.lang.Object">
|
|
<!-- -->
|
|
</a>
|
|
<h3>Methods inherited from class java.lang.Object</h3>
|
|
<code>clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait</code></li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
</div>
|
|
<div class="details">
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<!-- ============ METHOD DETAIL ========== -->
|
|
<ul class="blockList">
|
|
<li class="blockList"><a name="method.detail">
|
|
<!-- -->
|
|
</a>
|
|
<h3>Method Detail</h3>
|
|
<a name="fitCategorical-java.lang.Object-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>fitCategorical</h4>
|
|
<pre>public static java.util.Map fitCategorical(java.lang.Object ds,
|
|
java.lang.Object cname,
|
|
java.lang.Object options)</pre>
|
|
<div class="block"><p>Fit an object->integer transform that takes each value and assigned an integer to it. The returned value can be used in transformCategorical to transform the dataset.</p>
|
|
<p>Options:</p>
|
|
<ul>
|
|
<li><code>:table-args</code> - Either a sequence of vectors [col-val, idx] or a sorted sequence of column values where integers will be assigned as per the sorted sequence. Any values found outside the the specified values will be auto-mapped to the next largest integer.</li>
|
|
<li><code>:res-dtype</code> - Datatype of result column. Defaults to <code>:float64</code>.</li>
|
|
</ul></div>
|
|
</li>
|
|
</ul>
|
|
<a name="fitCategorical-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>fitCategorical</h4>
|
|
<pre>public static java.util.Map fitCategorical(java.lang.Object ds,
|
|
java.lang.Object cname)</pre>
|
|
<div class="block"><p>Fit an object->integer transformation. Integers will be assigned in random order. For more control over the transform see the 3-arity version of the function.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="transformCategorical-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>transformCategorical</h4>
|
|
<pre>public static java.util.Map transformCategorical(java.lang.Object ds,
|
|
java.lang.Object catFitData)</pre>
|
|
<div class="block"><p>Apply an object->integer transformation with data obtained from fitCategorical.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="invertCategorical-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>invertCategorical</h4>
|
|
<pre>public static java.util.Map invertCategorical(java.lang.Object ds,
|
|
java.lang.Object catFitData)</pre>
|
|
<div class="block"><p>Reverse a previously transformed categorical mapping.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="fitOneHot-java.lang.Object-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>fitOneHot</h4>
|
|
<pre>public static java.util.Map fitOneHot(java.lang.Object ds,
|
|
java.lang.Object cname,
|
|
java.lang.Object options)</pre>
|
|
<div class="block"><p>Fit a transformation from a single column of categorical values to a <code>one-hot</code> encoded group of columns. .</p>
|
|
<p>Options:</p>
|
|
<ul>
|
|
<li><code>:table-args</code> - Either a sequence of vectors [col-val, idx] or a sorted sequence of column values where integers will be assigned as per the sorted sequence. Any values found outside the the specified values will be auto-mapped to the next largest integer.</li>
|
|
<li><code>:res-dtype</code> - Datatype of result column. Defaults to <code>:float64</code>.</li>
|
|
</ul></div>
|
|
</li>
|
|
</ul>
|
|
<a name="fitOneHot-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>fitOneHot</h4>
|
|
<pre>public static java.util.Map fitOneHot(java.lang.Object ds,
|
|
java.lang.Object cname)</pre>
|
|
<div class="block"><p>Fit a mapping from a categorical column to a group of one-hot encoded columns.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="transformOneHot-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>transformOneHot</h4>
|
|
<pre>public static java.util.Map transformOneHot(java.lang.Object ds,
|
|
java.lang.Object fitData)</pre>
|
|
<div class="block"><p>Transform a dataset using a fitted one-hot mapping.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="invertOneHot-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>invertOneHot</h4>
|
|
<pre>public static java.util.Map invertOneHot(java.lang.Object ds,
|
|
java.lang.Object fitData)</pre>
|
|
<div class="block"><p>Reverse a previously transformed one-hot mapping.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="correlationTable-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>correlationTable</h4>
|
|
<pre>public static java.util.Map correlationTable(java.lang.Object ds,
|
|
java.lang.Object options)</pre>
|
|
<div class="block"><p>Return a map of column to inversely sorted from greatest to least sequence of tuples of column name, coefficient.</p>
|
|
<p>Options:</p>
|
|
<ul>
|
|
<li><code>:correlation-type</code> One of <code>:pearson</code>, <code>:spearman</code>, or <code>:kendall</code>. Defaults to <code>:pearson</code>.</li>
|
|
</ul></div>
|
|
</li>
|
|
</ul>
|
|
<a name="correlationTable-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>correlationTable</h4>
|
|
<pre>public static java.util.Map correlationTable(java.lang.Object ds)</pre>
|
|
<div class="block"><p>Return a map of column to inversely sorted from greatest to least sequence of tuples of column name, pearson correlation coefficient.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="fillRangeReplace-java.lang.Object-java.lang.Object-double-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>fillRangeReplace</h4>
|
|
<pre>public static java.util.Map fillRangeReplace(java.lang.Object ds,
|
|
java.lang.Object cname,
|
|
double maxSpan,
|
|
java.lang.Object missingStrategy)</pre>
|
|
<div class="block"><p>Expand a dataset ensuring that the difference between two successive values is less than <code>max-span</code>.</p></div>
|
|
<dl>
|
|
<dt><span class="paramLabel">Parameters:</span></dt>
|
|
<dd><code>maxSpan</code> - The minimal span value. For datetime types this is interpreted in millisecond or epoch-millisecond space.</dd>
|
|
<dd><code>missingStrategy</code> - Same missing strategy types from <code>TMD.replaceMissing</code>.</dd>
|
|
</dl>
|
|
</li>
|
|
</ul>
|
|
<a name="fitPCA-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>fitPCA</h4>
|
|
<pre>public static java.lang.Object fitPCA(java.lang.Object ds,
|
|
java.lang.Object options)</pre>
|
|
<div class="block"><p>Fit a PCA transformation on a dataset.</p></div>
|
|
<dl>
|
|
<dt><span class="returnLabel">Returns:</span></dt>
|
|
<dd>map of <code>{:means, :eigenvalues, :eigenvectors}</code>.</p>
|
|
<p>Options:</p>
|
|
<ul>
|
|
<li><code>:method</code> - either <code>:svd</code> or <code>:cov</code>. Use either SVD transformation or covariance-matrix base PCA. <code>:cov</code> method is somewhat slower but returns accurate variances and thus is the default.</li>
|
|
<li><code>:variance-amount</code> - Keep columns until variance is just less than variance-amount. Defaults to 0.95.</li>
|
|
<li><code>:n-components</code> - Return a fixed number of components. Overrides <code>:variance-amount</code> an returns a fixed number of components.</li>
|
|
<li><code>:covariance-bias</code> - When using <code>:cov</code> divide by <code>n-rows</code> if true and <code>n-rows - 1</code> if false. Defaults to false.</li>
|
|
</ul></dd>
|
|
</dl>
|
|
</li>
|
|
</ul>
|
|
<a name="fitPCA-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>fitPCA</h4>
|
|
<pre>public static java.lang.Object fitPCA(java.lang.Object ds)</pre>
|
|
<div class="block"><p>Fit a PCA transformation onto a dataset keeping 95% of the variance. See documentation for 2-arity form.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="transformPCA-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>transformPCA</h4>
|
|
<pre>public static java.util.Map transformPCA(java.lang.Object ds,
|
|
java.lang.Object fitData)</pre>
|
|
<div class="block"><p>Transform a dataset by the PCA fit data.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="fitStdScale-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>fitStdScale</h4>
|
|
<pre>public static java.lang.Object fitStdScale(java.lang.Object ds)</pre>
|
|
<div class="block"><p>Calculate per-column mean, stddev.</p>
|
|
<p>Options:</p>
|
|
<ul>
|
|
<li><code>:mean?</code> - Produce per-column means. Defaults to true.</li>
|
|
<li><code>:stddev?</code> - Produce per-column standard deviation. Defaults to true.</li>
|
|
</ul></div>
|
|
</li>
|
|
</ul>
|
|
<a name="transformStdScale-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>transformStdScale</h4>
|
|
<pre>public static java.util.Map transformStdScale(java.lang.Object ds,
|
|
java.lang.Object fitData)</pre>
|
|
<div class="block"><p>Transform dataset to mean of zero and a standard deviation of 1.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="fitMinMax-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>fitMinMax</h4>
|
|
<pre>public static java.lang.Object fitMinMax(java.lang.Object ds,
|
|
java.lang.Object options)</pre>
|
|
<div class="block"><p>Fit a bias and scale the dataset that transforms each colum to a target min-max value.</p>
|
|
<p>Options:</p>
|
|
<ul>
|
|
<li><code>:min</code> - Target minimum value. Defaults it -0.5.</li>
|
|
<li><code>:max</code> - Target maximum value. Defaults to 0.5.</li>
|
|
</ul></div>
|
|
</li>
|
|
</ul>
|
|
<a name="fitMinMax-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>fitMinMax</h4>
|
|
<pre>public static java.lang.Object fitMinMax(java.lang.Object ds)</pre>
|
|
<div class="block"><p>Fit a minmax transformation that will transform each column to a minimum of -0.5 and a maximum of 0.5.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="transformMinMax-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>transformMinMax</h4>
|
|
<pre>public static java.util.Map transformMinMax(java.lang.Object ds,
|
|
java.lang.Object fitData)</pre>
|
|
<div class="block"><p>Transform a dataset using a previously fit minimax transformation.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="interpolateLOESS-java.lang.Object-java.lang.Object-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>interpolateLOESS</h4>
|
|
<pre>public static java.util.Map interpolateLOESS(java.lang.Object ds,
|
|
java.lang.Object xColname,
|
|
java.lang.Object yColname,
|
|
java.lang.Object options)</pre>
|
|
<div class="block"><p>Map a LOESS-interpolation transformation onto a dataset. This can be used to, among other things, smooth out a column before graphing. For the meaning of the options, see documentation on the org.apache.commons.math3.analysis.interpolationLoessInterpolator.</p>
|
|
<p>Option defaults have been chosen to map somewhat closely to the R defaults.</p>
|
|
<p>Options:</p>
|
|
<ul>
|
|
<li><code>:bandwidth</code> - Defaults to 0.75.</li>
|
|
<li><code>:iterations</code> - Defaults to 4.</li>
|
|
<li><code>:accuracy</code> - Defaults to LoessInterpolator/DEFAULT_ACCURACY.</li>
|
|
<li><code>:result-name</code> - Result column name. Defaults to <code>yColname.toString + "-loess"</code>.</li>
|
|
</ul></div>
|
|
</li>
|
|
</ul>
|
|
<a name="interpolateLOESS-java.lang.Object-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>interpolateLOESS</h4>
|
|
<pre>public static java.util.Map interpolateLOESS(java.lang.Object ds,
|
|
java.lang.Object xColname,
|
|
java.lang.Object yColname)</pre>
|
|
<div class="block"><p>Perform a LOESS interpolation using the default parameters. For options see 4-arity form of function.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="kFold-java.lang.Object-long-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>kFold</h4>
|
|
<pre>public static java.lang.Iterable kFold(java.lang.Object ds,
|
|
long k,
|
|
java.lang.Object options)</pre>
|
|
<div class="block"><p>Produce 2*k datasets from 1 dataset using k-fold algorithm. Returns a k maps of the form `{:test-ds :train-ds}.</p>
|
|
<p>Options:</p>
|
|
<ul>
|
|
<li><code>:randomize-dataset?</code> - When true, shuffle dataset. Defaults to true.</li>
|
|
<li><code>:seed</code> - When randomizing dataset, seed may be either an integer or an implementation of <code>java.util.Random</code>.</li>
|
|
</ul></div>
|
|
</li>
|
|
</ul>
|
|
<a name="kFold-java.lang.Object-long-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>kFold</h4>
|
|
<pre>public static java.lang.Iterable kFold(java.lang.Object ds,
|
|
long k)</pre>
|
|
<div class="block"><p>Return k maps of the form <code>{:test-ds :train-ds}</code>. For options see 3-arity form.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="trainTestSplit-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>trainTestSplit</h4>
|
|
<pre>public static java.util.Map trainTestSplit(java.lang.Object ds,
|
|
java.lang.Object options)</pre>
|
|
<div class="block"><p>Split the dataset returning a map of <code>{:train-ds :test-ds}</code>.</p>
|
|
<p>Options:</p>
|
|
<ul>
|
|
<li><code>:randomize-dataset?</code> - Defaults to true.</li>
|
|
<li><code>:seed</code> - When provided must be an integer or an implementation <code>java.util.Random</code>.</li>
|
|
<li><code>:train-fraction</code> - Fraction of dataset to use as training set. Defaults to 0.7.</li>
|
|
</ul></div>
|
|
</li>
|
|
</ul>
|
|
<a name="trainTestSplit-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>trainTestSplit</h4>
|
|
<pre>public static java.util.Map trainTestSplit(java.lang.Object ds)</pre>
|
|
<div class="block"><p>Randomize then split dataset using 70% of the data for training and the rest for testing.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="setInferenceTarget-java.lang.Object-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>setInferenceTarget</h4>
|
|
<pre>public static java.util.Map setInferenceTarget(java.lang.Object ds,
|
|
java.lang.Object cname)</pre>
|
|
<div class="block"><p>Set a column in the dataset as the inference target. This information is stored in the column metadata. This function is short form for:</p>
|
|
<pre><code class="java"> Object col = column(ds, cname);
|
|
return assoc(ds, cname, varyMeta(col, assocFn, kw("inference-target?"), true));
|
|
</code></pre></div>
|
|
</li>
|
|
</ul>
|
|
<a name="labels-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>labels</h4>
|
|
<pre>public static java.lang.Object labels(java.lang.Object ds)</pre>
|
|
<div class="block"><p>Find the inference column. If column was the result of a categorical mapping, reverse that mapping. Return data in a form that can be efficiently converted to a Buffer.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="probabilityDistributionToLabels-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockList">
|
|
<li class="blockList">
|
|
<h4>probabilityDistributionToLabels</h4>
|
|
<pre>public static java.lang.Object probabilityDistributionToLabels(java.lang.Object ds)</pre>
|
|
<div class="block"><p>Given a dataset where the column names are labels and the each row is a probabilitly distribution across the labels, produce a Buffer of labels taking the highest probability for each row to choose the label.</p></div>
|
|
</li>
|
|
</ul>
|
|
<a name="inferenceTargetLabelMap-java.lang.Object-">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="blockListLast">
|
|
<li class="blockList">
|
|
<h4>inferenceTargetLabelMap</h4>
|
|
<pre>public static java.util.Map inferenceTargetLabelMap(java.lang.Object ds)</pre>
|
|
<div class="block"><p>Return a map of val->idx for the inference target.</p></div>
|
|
</li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
</div>
|
|
</div>
|
|
<!-- ========= END OF CLASS DATA ========= -->
|
|
<!-- ======= START OF BOTTOM NAVBAR ====== -->
|
|
<div class="bottomNav"><a name="navbar.bottom">
|
|
<!-- -->
|
|
</a>
|
|
<div class="skipNav"><a href="#skip.navbar.bottom" title="Skip navigation links">Skip navigation links</a></div>
|
|
<a name="navbar.bottom.firstrow">
|
|
<!-- -->
|
|
</a>
|
|
<ul class="navList" title="Navigation">
|
|
<li><a href="../../../overview-summary.html">Overview</a></li>
|
|
<li><a href="package-summary.html">Package</a></li>
|
|
<li class="navBarCell1Rev">Class</li>
|
|
<li><a href="package-tree.html">Tree</a></li>
|
|
<li><a href="../../../deprecated-list.html">Deprecated</a></li>
|
|
<li><a href="../../../index-all.html">Index</a></li>
|
|
<li><a href="../../../help-doc.html">Help</a></li>
|
|
</ul>
|
|
<div class="aboutLanguage"><script type="text/javascript" src="../../../highlight.pack.js"></script>
|
|
<script type="text/javascript"><!--
|
|
hljs.initHighlightingOnLoad();
|
|
//--></script></div>
|
|
</div>
|
|
<div class="subNav">
|
|
<ul class="navList">
|
|
<li>Prev Class</li>
|
|
<li><a href="../../../tech/v3/dataset/Reductions.html" title="class in tech.v3.dataset"><span class="typeNameLink">Next Class</span></a></li>
|
|
</ul>
|
|
<ul class="navList">
|
|
<li><a href="../../../index.html?tech/v3/dataset/Modelling.html" target="_top">Frames</a></li>
|
|
<li><a href="Modelling.html" target="_top">No Frames</a></li>
|
|
</ul>
|
|
<ul class="navList" id="allclasses_navbar_bottom">
|
|
<li><a href="../../../allclasses-noframe.html">All Classes</a></li>
|
|
</ul>
|
|
<div>
|
|
<script type="text/javascript"><!--
|
|
allClassesLink = document.getElementById("allclasses_navbar_bottom");
|
|
if(window==top) {
|
|
allClassesLink.style.display = "block";
|
|
}
|
|
else {
|
|
allClassesLink.style.display = "none";
|
|
}
|
|
//-->
|
|
</script>
|
|
</div>
|
|
<div>
|
|
<ul class="subNavList">
|
|
<li>Summary: </li>
|
|
<li>Nested | </li>
|
|
<li>Field | </li>
|
|
<li>Constr | </li>
|
|
<li><a href="#method.summary">Method</a></li>
|
|
</ul>
|
|
<ul class="subNavList">
|
|
<li>Detail: </li>
|
|
<li>Field | </li>
|
|
<li>Constr | </li>
|
|
<li><a href="#method.detail">Method</a></li>
|
|
</ul>
|
|
</div>
|
|
<a name="skip.navbar.bottom">
|
|
<!-- -->
|
|
</a></div>
|
|
<!-- ======== END OF BOTTOM NAVBAR ======= -->
|
|
</body>
|
|
</html>
|