<?phpclass Document{    protected $words;    protected $tf_matrix;    protected $tfidf_matrix;    public function __construct($string)    {        $this->tfidf_matrix = null;        if (isset($string))        {            $string = strtolower($string);            $this->words = preg_split(‘/((^\p{P}+)|(\p{P}*\s+\p{P}*)|(\p{P}+$))/‘, $string, -1, PREG_SPLIT_NO_EMPTY);            $this->build_tf();        }        else        {            $this->words = null;            $this->tf_matrix = null;        }    }    public function build_tf()    {        if (isset($this->tf_matrix) && $this->tf_matrix)            return ;        $this->tfidf_matrix = null;        $words_count = count($this->words);        $words_occ = array_count_values($this->words);        foreach ($words_occ as $word => $amount)            $this->tf_matrix[$word] = $amount / $words_count;        arsort($this->tf_matrix);    }    public function build_tfidf($idf)    {        if (isset($this->tfidf_matrix) && $this->tfidf_matrix)            return true;        if (!isset($this->tf_matrix) || !$this->tf_matrix)            return false;        if (!isset($idf) || !$idf)            return false;            if(is_array($idf)){            foreach ($this->tf_matrix as $word => $word_tf){                $this->tfidf_matrix[$word] = $word_tf * $idf[$word];            }        }else{            foreach ($this->tf_matrix as $word => $word_tf){                $this->tfidf_matrix[$word] = $word_tf * $idf;            }        }        arsort($this->tfidf_matrix);        return true;    }    public function getWords()    {        return ($this->words);    }    public function getTf()    {        return ($this->tf_matrix);    }    public function getTfidf()    {        return ($this->tfidf_matrix);    }}/*第一步，计算词频。考虑到文章有长短之分，为了便于不同文章的比较，进行"词频"标准化。第二步，计算逆文档频率。这时，需要一个语料库（corpus），用来模拟语言的使用环境。如果一个词越常见，那么分母就越大，逆文档频率就越小越接近0。分母之所以要加1，是为了避免分母为0（即所有文档都不包含该词）。log表示对得到的值取对数。第三步，计算TF-IDF。可以看到，TF-IDF与一个词在文档中的出现次数成正比，与该词在整个语言中的出现次数成反比。所以，自动提取关键词的算法就很清楚了，就是计算出文档的每个词的TF-IDF值，然后按降序排列，取排在最前面的几个词。*/$text = ‘i very good, ha , i very nice, i is good‘;$obj = new Document($text);$obj->build_tf();   //词频率TF，一般是词出现次数/总词数$idf = log(3 / 2);   //逆文档频率，总文档数/包含该词的文档数$obj->build_tfidf($idf);  //越高则频率高var_dump($obj->getWords(), 88, $obj->getTf(), 99, $obj->getTfidf());