reformatting and update documentation

.gitignore

@@ -1,7 +1,32 @@
+/node_modules
+/public/hot
+/public/storage
+/storage/*.key
+/storage/debugbar
+/vendor
+/.idea
+/.vagrant
+Homestead.json
+Homestead.yaml
+npm-debug.log
+yarn-error.log
+
 .DS_Store
-.idea/
-vendor/
-build/
-composer.lock
+coverage/
+bootstrap/cache/*.php
+storage/build/
+public/js/parts/*
+.env
+
+.docker/data/
+!.docker/data/*/*.gitkeep
+!.docker/data/*.gitkeep
+.docker/logs/
+!.docker/logs/*.gitkeep
+storage/installed
+docker-compose.yml
+._*.png
+dist.zip
+.php*.cache
 
-/.phpintel/
+playbook/recipe/downloaded/

README.md

@@ -65,6 +65,10 @@ Teach your classifier what `category` the `text` belongs to. The more you teach
 
 Returns the `category` it thinks `text` belongs to. Its judgement is based on what you have taught it with **.learn()**.
 
+### `$classifier->propabilities(text)`
+
+Extract the probabilities for each known category.
+
 ### `$classifier->toJson()`
 
 Returns the JSON representation of a classifier.
@@ -73,5 +77,33 @@ Returns the JSON representation of a classifier.
 
 Returns a classifier instance from the JSON representation. Use this with the JSON representation obtained from `$classifier->toJson()`
 
+## Stopwords
+
+You can pass in your own tokenizer function in the constructor.  Example:
+
+```
+// array containing stopwords
+$stopwords = array("der", "die", "das", "the");
+
+// escape the stopword array and implode with pipe
+$s = '~^\W*('.implode("|", array_map("preg_quote", $stopwords)).')\W+\b|\b\W+(?1)\W*$~i';
+
+$options['tokenizer'] = function($text) use ($s) {
+            // convert everything to lowercase
+            $text = mb_strtolower($text);
+
+            // remove stop words
+            $text = preg_replace($s, '', $text);
+
+            // split the words
+            preg_match_all('/[[:alpha:]]+/u', $text, $matches);
+
+            // first match list of words
+            return $matches[0];
+        };
+
+$classifier = new \niiknow\Bayes($options);
+```
+
 ## MIT