PHP 中的关键字提取
Keyword extraction in PHP
我需要使用 php 从文本文件中提取关键字及其频率计数。我发现了一个只输出关键字的代码,例如。一些,文本,机器,自动售货机。我还需要频率计数以及这些关键字,例如。 some 3, text 2, machines 1, vending 1. 你能建议必要的修改吗?
function extractCommonWords($string)
{
$stopWords = array('i','a','about','an','and','are','as','at','be','by','com','de','en','for','from','how','in','is','it','la','of','on','or','that','the','this','to','was','what','when','where','who','will','with','und','the','www');
$string = preg_replace('/ss+/i', '', $string);
$string = trim($string); // trim the string
$string = preg_replace('/[^a-zA-Z0-9 -]/', '', $string); // only take alphanumerical characters, but keep the spaces and dashes too…
$string = strtolower($string); // make it lowercase
preg_match_all('/\b.*?\b/i', $string, $matchWords);
$matchWords = $matchWords[0];
$totalWords = count($matchWords[0]);
foreach ( $matchWords as $key=>$item )
{
if ( $item == '' || in_array(strtolower($item), $stopWords) || strlen($item) <= 3 )
{
unset($matchWords[$key]);
}
}
$wordCountArr = array();
if ( is_array($matchWords) )
{
foreach ( $matchWords as $key => $val )
{
$val = strtolower($val);
if ( !isset($wordCountArr[$val]))
{
$wordCountArr[$val] = array();
}
if ( isset($wordCountArr[$val]['count']) )
{
$wordCountArr[$val]['count']++;
}
else
{
$wordCountArr[$val]['count'] = 1;
}
}
arsort($wordCountArr);
$wordCountArr = array_slice($wordCountArr, 0, 10);
foreach ($wordCountArr as $key => $val)
{
$val['bytotal'] = $val['count'] / $totalWords;
}
}
return $wordCountArr;
}
$text = "This is some text. This is some text. Vending Machines are great.";
$words = extractCommonWords($text);
echo implode(',', array_keys($words));
function extractCommonWords($string)
{
$stopWords = array('i','a','about','an','and','are','as','at','be','by','com','de','en','for','from','how','in','is','it','la','of','on','or','that','the','this','to','was','what','when','where','who','will','with','und','the','www');
$string = preg_replace('/ss+/i', '', $string);
$string = trim($string);
$string = preg_replace('/[^a-zA-Z0-9 -]/', '', $string); // only take alphanumerical characters, but keep the spaces and dashes too…
$string = strtolower($string); // make it lowercase
echo $string."<br>";
preg_match_all('/\b.*?\b/i', $string, $matchWords);
$matchWords = $matchWords[0];
$totalWords = count($matchWords[0]);
foreach ( $matchWords as $key=>$item ){
if ( $item == '' || in_array(strtolower($item), $stopWords) || strlen($item) <= 3 ) {
unset($matchWords[$key]);
}
}
$wordCountArr = array();
if ( is_array($matchWords) ) {
foreach ( $matchWords as $key => $val ) {
$val = strtolower($val);
if (isset($wordCountArr[$val])){
$wordCountArr[$val] += 1;
} else {
$wordCountArr[$val] = 1;
}
}
arsort($wordCountArr);
}
}
$text = "This is some text. This is some text. Vending Machines are great.";
$words = extractCommonWords($text);
foreach ($words as $word => $count){
print ($word . " was found " . $count . " time(s)<br> ");
}
我需要使用 php 从文本文件中提取关键字及其频率计数。我发现了一个只输出关键字的代码,例如。一些,文本,机器,自动售货机。我还需要频率计数以及这些关键字,例如。 some 3, text 2, machines 1, vending 1. 你能建议必要的修改吗?
function extractCommonWords($string)
{
$stopWords = array('i','a','about','an','and','are','as','at','be','by','com','de','en','for','from','how','in','is','it','la','of','on','or','that','the','this','to','was','what','when','where','who','will','with','und','the','www');
$string = preg_replace('/ss+/i', '', $string);
$string = trim($string); // trim the string
$string = preg_replace('/[^a-zA-Z0-9 -]/', '', $string); // only take alphanumerical characters, but keep the spaces and dashes too…
$string = strtolower($string); // make it lowercase
preg_match_all('/\b.*?\b/i', $string, $matchWords);
$matchWords = $matchWords[0];
$totalWords = count($matchWords[0]);
foreach ( $matchWords as $key=>$item )
{
if ( $item == '' || in_array(strtolower($item), $stopWords) || strlen($item) <= 3 )
{
unset($matchWords[$key]);
}
}
$wordCountArr = array();
if ( is_array($matchWords) )
{
foreach ( $matchWords as $key => $val )
{
$val = strtolower($val);
if ( !isset($wordCountArr[$val]))
{
$wordCountArr[$val] = array();
}
if ( isset($wordCountArr[$val]['count']) )
{
$wordCountArr[$val]['count']++;
}
else
{
$wordCountArr[$val]['count'] = 1;
}
}
arsort($wordCountArr);
$wordCountArr = array_slice($wordCountArr, 0, 10);
foreach ($wordCountArr as $key => $val)
{
$val['bytotal'] = $val['count'] / $totalWords;
}
}
return $wordCountArr;
}
$text = "This is some text. This is some text. Vending Machines are great.";
$words = extractCommonWords($text);
echo implode(',', array_keys($words));
function extractCommonWords($string)
{
$stopWords = array('i','a','about','an','and','are','as','at','be','by','com','de','en','for','from','how','in','is','it','la','of','on','or','that','the','this','to','was','what','when','where','who','will','with','und','the','www');
$string = preg_replace('/ss+/i', '', $string);
$string = trim($string);
$string = preg_replace('/[^a-zA-Z0-9 -]/', '', $string); // only take alphanumerical characters, but keep the spaces and dashes too…
$string = strtolower($string); // make it lowercase
echo $string."<br>";
preg_match_all('/\b.*?\b/i', $string, $matchWords);
$matchWords = $matchWords[0];
$totalWords = count($matchWords[0]);
foreach ( $matchWords as $key=>$item ){
if ( $item == '' || in_array(strtolower($item), $stopWords) || strlen($item) <= 3 ) {
unset($matchWords[$key]);
}
}
$wordCountArr = array();
if ( is_array($matchWords) ) {
foreach ( $matchWords as $key => $val ) {
$val = strtolower($val);
if (isset($wordCountArr[$val])){
$wordCountArr[$val] += 1;
} else {
$wordCountArr[$val] = 1;
}
}
arsort($wordCountArr);
}
}
$text = "This is some text. This is some text. Vending Machines are great.";
$words = extractCommonWords($text);
foreach ($words as $word => $count){
print ($word . " was found " . $count . " time(s)<br> ");
}