php实现朴素贝叶斯算法

1.源码实现

<?php

class Type {
    const POSITIVE = 'positive';
    const NEGATIVE = 'negative';
}

class Classifier {
    public $types = array(Type::POSITIVE, Type::NEGATIVE);
    public $words = array();
    public $documents = array();

    public function learn($statement, $type)
    {
        $words = $this->getWords($statement);

        foreach($words as $word)
        {
            if(!isset($this->words[$type][$word]))
            {
                $this->words[$type][$word] = 0;
            }

            $this->words[$type][$word]++;
        }

        $this->documents[$type]++;
    }

    private function totalP($type)
    {
        return ($this->documents[$type]+1) / (array_sum($this->documents) + 1);
    }

    private function p($word, $type)
    {
        $count = isset($this->words[$type][$word]) ? $this->words[$type][$word] : 0;
 
        return ($count + 1) / (array_sum($this->words[$type]) + 1);
    }

    private function getWords($string)
    {
        return preg_split('/\s+/', preg_replace('/[^A-Za-z0-9\s]/', '', strtolower($string)));
    }

    public function guess($statement)
    {
        $words = $this->getWords($statement); // 得到单词
        $best_likelihood = 0;
        $best_type = null;
 
        foreach($this->types as $type)
        {
            $likelihood = $this->totalP($type); //计算 P(Type)
 
            foreach($words as $word)
            {
                $likelihood *= $this->p($word, $type); // 计算 P(word, Type)
                //echo $word."\n";
            }
 
            if($likelihood > $best_likelihood)
            {
                $best_likelihood = $likelihood;
                $best_type = $type;
            }
        }
 
        return $best_type;
    }
}


$classifier = new Classifier();
$classifier->learn('Symfony is the best', Type::POSITIVE);
$classifier->learn('PhpStorm is great', Type::POSITIVE);
$classifier->learn('Iltar complains a lot', Type::NEGATIVE);
$classifier->learn('No Symfony is bad', Type::NEGATIVE);
 
var_dump($classifier->guess('Symfony is great')); // string(8) "positive"
var_dump($classifier->guess('I complain a lot')); // string(8) "negative"

?>

2.运行及其结果

$ php example.php
string(8) "positive"
string(8) "negative"