PHP 领域中缺少了一个功能强大的工具：基于语言的数学库。在这个由两部分组成的系列文章中，Paul Meagher 希望通过提供一个如何开发分析模型库的示例来启发 PHP 开发人员去开发和实现基于 PHP 的数学库。在第 1 部分中，他演示了如何使用 PHP 作为实现语言来开发和实现简单线性回归（Simple Linear Regression）算法包的核心部分。在第 2 部分中，作者在该包中添加了一些功能：针对中小规模数据集的有用的数据分析工具。

<?php 

// Copyright 2003, Paul Meagher 
// Distributed under GPL   

class SimpleLinearRegression { 

  var $n; 
  var $X = array();
  var $Y = array();  
  var $ConfInt;  
  var $Alpha;
  var $XMean;
  var $YMean;
  var $SumXX;
  var $SumXY;
  var $SumYY;  
  var $Slope;
  var $YInt;  
  var $PredictedY   = array();
  var $Error        = array();
  var $SquaredError = array();
  var $TotalError;  
  var $SumError;
  var $SumSquaredError;  
  var $ErrorVariance;
  var $StdErr;
  var $SlopeStdErr;  
  var $SlopeVal;   // T value of Slope 
  var $YIntStdErr;    
  var $YIntTVal;   // T value for Y Intercept
  var $R;
  var $RSquared;    
  var $DF;         // Degrees of Freedom
  var $SlopeProb;  // Probability of Slope Estimate
  var $YIntProb;   // Probability of Y Intercept Estimate
  var $AlphaTVal;  // T Value for given alpha setting
  var $ConfIntOfSlope;        
  
  var $RPath  = "/usr/local/bin/R";  // Your path here
  
  var $format = "%01.2f"; // Used for formatting output 
  
}
?>

<?php 

// Copyright 2003, Paul Meagher 
// Distributed under GPL   

function SimpleLinearRegression($X, $Y, $ConfidenceInterval="95") {

  $numX = count($X);
  $numY = count($Y);

  if ($numX != $numY) {
    die("Error: Size of X and Y vectors must be the same.");

  } 
  if ($numX <= 1) { 
    die("Error: Size of input array must be at least 2.");
  }
  
  $this->n               = $numX;
  $this->X               = $X;
  $this->Y               = $Y;  
  
  $this->ConfInt         = $ConfidenceInterval; 
  $this->Alpha           = (1 + ($this->ConfInt / 100) ) / 2;

  $this->XMean           = $this->getMean($this->X);
  $this->YMean           = $this->getMean($this->Y);
  $this->SumXX           = $this->getSumXX();
  $this->SumYY           = $this->getSumYY();
  $this->SumXY           = $this->getSumXY();    
  $this->Slope           = $this->getSlope();
  $this->YInt            = $this->getYInt();
  $this->PredictedY      = $this->getPredictedY();
  $this->Error           = $this->getError();
  $this->SquaredError    = $this->getSquaredError();
  $this->SumError        = $this->getSumError();
  $this->TotalError      = $this->getTotalError();    
  $this->SumSquaredError = $this->getSumSquaredError();
  $this->ErrorVariance   = $this->getErrorVariance();
  $this->StdErr          = $this->getStdErr();  
  $this->SlopeStdErr     = $this->getSlopeStdErr();     
  $this->YIntStdErr      = $this->getYIntStdErr();         
  $this->SlopeTVal       = $this->getSlopeTVal();            
  $this->YIntTVal        = $this->getYIntTVal();                
  $this->R               = $this->getR();   
  $this->RSquared        = $this->getRSquared();
  $this->DF              = $this->getDF();          
  $this->SlopeProb       = $this->getStudentProb($this->SlopeTVal, $this->DF);
  $this->YIntProb        = $this->getStudentProb($this->YIntTVal, $this->DF);
  $this->AlphaTVal       = $this->getInverseStudentProb($this->Alpha, $this->DF);
  $this->ConfIntOfSlope  = $this->getConfIntOfSlope(); 

  return true;
}

?>

$PredictedY[$i] = $YIntercept + $Slope * $X[$i]

<?php 

// Copyright 2003, Paul Meagher 
// Distributed under GPL   

class SimpleLinearRegression { 
   
  var $RPath  = "/usr/local/bin/R";  // Your path here

  function getStudentProb($T, $df) {    
    $Probability = 0.0;   
    $cmd = "echo 'dt($T, $df)' | $this->RPath --slave"; 
    $result = shell_exec($cmd);    
    list($LineNumber, $Probability) = explode(" ", trim($result)); 
    return $Probability;
  }

  function getInverseStudentProb($alpha, $df) {  
    $InverseProbability = 0.0; 
    $cmd = "echo 'qt($alpha, $df)' | $this->RPath --slave"; 
    $result = shell_exec($cmd);  
    list($LineNumber, $InverseProbability) = explode(" ", trim($result)); 
    return $InverseProbability;
  }

}

?>

<?php 

// BurnoutStudy.php

// Copyright 2003, Paul Meagher 
// Distributed under GPL   

include "SimpleLinearRegression.php"; 

// Load data from burnout study 

$Concentration   = array(20,60,38,88,79,87, 
                         68,12,35,70,80,92, 
                         77,86,83,79,75,81, 
                         75,77,77,77,17,85,96);  
                          
$ExhaustionIndex = array(100,525,300,980,310,900, 
                         410,296,120,501,920,810, 
                         506,493,892,527,600,855, 
                         709,791,718,684,141,400,970);  
                          
$slr = new SimpleLinearRegression($Concentration, $ExhaustionIndex);  

$YInt      = sprintf($slr->format, $slr->YInt);
$Slope     = sprintf($slr->format, $slr->Slope);    
$SlopeTVal = sprintf($slr->format, $slr->SlopeTVal);    
$SlopeProb = sprintf("%01.6f", $slr->SlopeProb);    

?>

<table border='1' cellpadding='5'>
  <tr>
    <th align='right'>Equation:</th>
    <td></td>
  </tr>
  <tr>
    <th align='right'>T:</th>
    <td></td>
  </tr>
  <tr>
    <th align='right'>Prob > T:</th>
    <td><td>
  </tr>
</table>