Implemented toJsonObject and allowed fromJson to accept JSON objects

.gitignore

@@ -0,0 +1,2 @@
+/node_modules/
+/nbproject/private/

lib/naive_bayes.js

@@ -15,16 +15,21 @@ var STATE_KEYS = module.exports.STATE_KEYS = [
  * Initializes a NaiveBayes instance from a JSON state representation.
  * Use this with classifier.toJson().
  *
- * @param  {String} jsonStr   state representation obtained by classifier.toJson()
+ * @param  {String} jsonStr   state representation obtained by classifier.toJson() or classifier.toJsonObject()
  * @return {NaiveBayes}       Classifier
  */
 module.exports.fromJson = function (jsonStr) {
   var parsed;
-  try {
-    parsed = JSON.parse(jsonStr)
-  } catch (e) {
-    throw new Error('Naivebayes.fromJson expects a valid JSON string.')
+  if(typeof jsonStr === 'string') {
+    try {
+      parsed = JSON.parse(jsonStr)
+    } catch (e) {
+      throw new Error('Naivebayes.fromJson expects a valid JSON string.')
+    }
+  } else if(typeof jsonStr === 'object') {
+    parsed = jsonStr // if it's an object try use it directly
   }
+
   // init a new classifier
   var classifier = new Naivebayes(parsed.options)
 
@@ -167,52 +172,60 @@ Naivebayes.prototype.learn = function (text, category) {
 }
 
 /**
- * Determine what category `text` belongs to.
- *
- * @param  {String} text
- * @return {String} category
+ * Returns the probability the given text matches each category, sorted in order from most likely to least likely. This
+ * method allows you to check the differences between the category probabilities.
+ * 
+ * @param {string} text the text to categorize
+ * @returns {Array} an array of objects in the form {category, probability}
  */
-Naivebayes.prototype.categorize = function (text) {
+Naivebayes.prototype.probabilities = function (text) {
   var self = this
-    , maxProbability = -Infinity
-    , chosenCategory = null
 
   var tokens = self.tokenizer(text)
   var frequencyTable = self.frequencyTable(tokens)
 
   //iterate thru our categories to find the one with max probability for this text
-  Object
-  .keys(self.categories)
-  .forEach(function (category) {
+  var categoryProbabilities = Object
+      .keys(self.categories)
+      .map(function (category) {
 
-    //start by calculating the overall probability of this category
-    //=>  out of all documents we've ever looked at, how many were
-    //    mapped to this category
-    var categoryProbability = self.docCount[category] / self.totalDocuments
+        //start by calculating the overall probability of this category
+        //=>  out of all documents we've ever looked at, how many were
+        //    mapped to this category
+        var categoryProbability = self.docCount[category] / self.totalDocuments
 
-    //take the log to avoid underflow
-    var logProbability = Math.log(categoryProbability)
+        //take the log to avoid underflow
+        var logProbability = Math.log(categoryProbability)
 
-    //now determine P( w | c ) for each word `w` in the text
-    Object
-    .keys(frequencyTable)
-    .forEach(function (token) {
-      var frequencyInText = frequencyTable[token]
-      var tokenProbability = self.tokenProbability(token, category)
+        //now determine P( w | c ) for each word `w` in the text
+        Object
+            .keys(frequencyTable)
+            .forEach(function (token) {
+              var frequencyInText = frequencyTable[token]
+              var tokenProbability = self.tokenProbability(token, category)
 
-      // console.log('token: %s category: `%s` tokenProbability: %d', token, category, tokenProbability)
+              // console.log('token: %s category: `%s` tokenProbability: %d', token, category, tokenProbability)
 
-      //determine the log of the P( w | c ) for this word
-      logProbability += frequencyInText * Math.log(tokenProbability)
-    })
+              //determine the log of the P( w | c ) for this word
+              logProbability += frequencyInText * Math.log(tokenProbability)
+            })
 
-    if (logProbability > maxProbability) {
-      maxProbability = logProbability
-      chosenCategory = category
-    }
-  })
+        return {category: category, probability: logProbability}
+      });
+
+  categoryProbabilities.sort(function(c1, c2) {return c2.probability - c1.probability})
+
+  return categoryProbabilities
+}
 
-  return chosenCategory
+/**
+ * Determine what category `text` belongs to.
+ *
+ * @param  {String} text
+ * @return {String} category
+ */
+Naivebayes.prototype.categorize = function(text) {
+  return this.probabilities(text)[0].category
 }
 
 /**
@@ -255,18 +268,25 @@ Naivebayes.prototype.frequencyTable = function (tokens) {
 }
 
 /**
- * Dump the classifier's state as a JSON string.
- * @return {String} Representation of the classifier.
+ * Dump the classifier's state as a simple object, suitable for embedding within a JSON document or another object.
+ * @return {Object} Representation of the classifier.
  */
-Naivebayes.prototype.toJson = function () {
+Naivebayes.prototype.toJsonObject = function () {
   var state = {}
   var self = this
   STATE_KEYS.forEach(function (k) {
     state[k] = self[k]
   })
+
+  return state
+}
 
-  var jsonStr = JSON.stringify(state)
-
+/**
+ * Dump the classifier's state as a JSON string.
+ * @return {String} Representation of the classifier.
+ */
+Naivebayes.prototype.toJson = function () {
+  var jsonStr = JSON.stringify(this.toJsonObject())
   return jsonStr
 }
 

readme.md

@@ -72,11 +72,15 @@ Returns the `category` it thinks `text` belongs to. Its judgement is based on wh
 
 ###`classifier.toJson()`
 
-Returns the JSON representation of a classifier.
+Returns the JSON representation of a classifier. This is the same as `JSON.stringify(classifier.toJsonObject())`.
+
+###`classifier.toJsonObject()`
+
+Returns a JSON-friendly representation of the classifier as an `object`.
 
 ###`var classifier = bayes.fromJson(jsonStr)`
 
-Returns a classifier instance from the JSON representation. Use this with the JSON representation obtained from `classifier.toJson()`
+Returns a classifier instance from the JSON representation. Use this with the JSON representation obtained from `classifier.toJson()` or `classifier.toJsonObject()`
 
 ## License
 

test/naive_bayes.js

@@ -72,6 +72,24 @@ describe('bayes serializing/deserializing its state', function () {
         assert.deepEqual(revivedClassifier[k], classifier[k])
       })
 
+      done()
+    })
+
+  it('serializes/deserializes its state as an Object correctly.', function (done) {
+      var classifier = bayes()
+
+      classifier.learn('Fun times were had by all', 'positive')
+      classifier.learn('sad dark rainy day in the cave', 'negative')
+
+      var jsonRepr = classifier.toJsonObject()
+
+      var revivedClassifier = bayes.fromJson(jsonRepr)
+
+      // ensure the revived classifier's state is same as original state
+      bayes.STATE_KEYS.forEach(function (k) {
+        assert.deepEqual(revivedClassifier[k], classifier[k])
+      })
+
       done()
     })
 })