require_once 'utils/BarPageBuilder.php';
/**
* Get some text from the internet
* we will grab tom sawyer from the gutenberg project
* http://www.gutenberg.org/cache/epub/74/pg74.txt
*
*/
/**
* @var string $book
*/
$book = file_get_contents('data/books/pg74.txt');
/**
* Create a tokenizer object to parse the book into a set of tokens
*
*/
$tokenizer = new \TextAnalysis\Tokenizers\GeneralTokenizer();
/**
* Get the set of tokens generated by the tokenize, see
*
*/
$tokens = $tokenizer->tokenize($book);
$freqDist = new \TextAnalysis\Analysis\FreqDist($tokens);
/**
* Get the top 10 most used words in Tom Sawyer
*/
$top10 = array_splice($freqDist->getKeyValuesByFrequency(), 0, 10);
/**
* Use High Charts to visualize the data
*/
$pageBuilder = new BarPageBuilder($top10);
$html = $pageBuilder->getHtmlPage();
* An example of creating a creating document collection
* Document Collections allow you to work with a group of documents easily
*/
require_once 'vendor/autoload.php';
//used to generate a chart from the output of PHP Text Analysis
require_once 'utils/BarPageBuilder.php';
/**
* @var string $book
*/
$tomSawyerBook = file_get_contents('data/books/pg74.txt');
$huckFinnBook = file_get_contents('data/books/pg76.txt');
/**
* Create a tokenizer object to parse the book into a set of tokens
*
*/
$tokenizer = new \TextAnalysis\Tokenizers\GeneralTokenizer();
/**
* Get the set of tokens generated by the tokenize and
* create a token document from the tokens
*
*/
$tomSawyerDocument = new \TextAnalysis\Documents\TokensDocument($tokenizer->tokenize($tomSawyerBook));
$huckFinnDocument = new \TextAnalysis\Documents\TokensDocument($tokenizer->tokenize($huckFinnBook));
/**
* create a document collection that can have filters or further analysis done
*/
$docCollection = new \TextAnalysis\Collections\DocumentArrayCollection(array($tomSawyerDocument, $huckFinnDocument));
/**
* Apply filters to the document collection
* lower case the documents, remove quotes and remove stop words
*/