wink-naive-bayes-text-classifier - npm Package Compare versi...

+1

.nyc_output/bf700fc6-0a2e-4d1a-84ef-af1b3a7bb0d5.json

+1

.nyc_output/proces...700fc6-0a2e-4d1a-84ef-af1b3a7bb0d5.json

{"parent":null,"pid":3143,"argv":["/Users/neilsbohr/.nvm/versions/node/v18.10.0/bin/node","/Users/neilsbohr/dev/winkjs/wink-naive-bayes-text-classifier/node_modules/.bin/mocha","./test/"],"execArgv":[],"cwd":"/Users/neilsbohr/dev/winkjs/wink-naive-bayes-text-classifier","time":1667485485120,"ppid":3142,"coverageFilename":"/Users/neilsbohr/dev/winkjs/wink-naive-bayes-text-classifier/.nyc_output/bf700fc6-0a2e-4d1a-84ef-af1b3a7bb0d5.json","externalId":"","uuid":"bf700fc6-0a2e-4d1a-84ef-af1b3a7bb0d5","files":["/Users/neilsbohr/dev/winkjs/wink-naive-bayes-text-classifier/src/prep-text.js","/Users/neilsbohr/dev/winkjs/wink-naive-bayes-text-classifier/src/wink-naive-bayes-text-classifier.js"]}

chatbot-example/chatbot-training-data.json

Sorry, the diff of this file is too big to display

+37

chatbot-example/chatbot.js

		/* eslint-disable no-sync */
		const data = require( './chatbot-training-data.json' );
		const nbc = require( '../src/wink-naive-bayes-text-classifier' );
		const prepTask = require( './prep-task.js' );
		let count = 0;
		let validationExamples = 0;
		let trainingExamples = 0;

		const c = nbc();
		c.defineConfig( { considerOnlyPresence: false, smoothingFactor: 0.1 } );
		c.definePrepTasks( [ prepTask ] );


		for ( let i = 0; i < data.sentences.length; i += 1 ) {
		if ( data.sentences[ i ].training ) {
		c.learn( data.sentences[ i ].text, data.sentences[ i ].intent );
		trainingExamples += 1;
		}
		}

		console.log( `\nCompleted training using ${trainingExamples} examples labeled as 'training'.` );

		c.consolidate();

		for ( let i = 0; i < data.sentences.length; i += 1 ) {
		if ( !data.sentences[ i ].training ) {
		validationExamples += 1;
		const p = c.predict( data.sentences[ i ].text, data.sentences[ i ].intent );
		if ( p === data.sentences[ i ].intent ) {
		count += 1;
		}
		}
		}

		console.log( `\nCompleted intent classification using ${validationExamples} intents meant for validation.`)

		console.log( `\tAccuracy = ${+( ( count / validationExamples ) * 100 ).toFixed( 1 )}%` );

+22

chatbot-example/prep-task.js

		const model = require( 'wink-eng-lite-web-model' );
		const nlp = require( 'wink-nlp' )( model );
		const its = nlp.its;

		// POS and types to be preserved, rest is filtered out.
		const posSet = new Set( [ 'VERB', 'NOUN', 'ADP', 'DET', 'PART' ] );
		const typeSet = new Set( [ 'number' ] );

		// Text preprocessing for chatbot.
		module.exports = ( text ) => {
		const tokens = [];
		const doc = nlp.readDoc( text );
		doc.tokens()
		// Preserve only predefined pos & types.
		.filter( ( t ) => ( posSet.has( t.out( its.pos ) ) \|\| typeSet.has( t.out( its.type ) ) ) )
		// Handle numbers.
		.each( ( t ) => tokens.push(
		( t.out( its.type ) === 'number' ) ? '$number' : t.out( its.lemma ) )
		);

		return tokens;
		}; // prepTask()

+27

sentiment-analysis-example/amazon.js

		var trainingData = require( './shuffled-sentiment-training-data.json' );
		var trainingExamples = trainingData.slice( 0, 800 );
		var testingData = trainingData.slice( 800 );

		const nbc = require( '../src/wink-naive-bayes-text-classifier.js' );
		const prepTask = require( './prep-task.js' );
		var count = 0;
		var total = 0;

		const c = nbc();
		c.defineConfig( { considerOnlyPresence: false, smoothingFactor: 0.1 } );
		c.definePrepTasks( [ prepTask ] );

		console.log( '\nUsing 800 examples out of 1000 for training the classifier.' );
		trainingExamples.forEach( ( d ) => c.learn( d[ 0 ], d[ 1 ] ) );

		c.consolidate();

		console.log( '\nUsing balance 200 examples out of 1000 for validating the classifier.' );
		testingData.forEach( ( d ) => {
		total += 1;
		if ( c.predict( d[ 0 ] ) == d[ 1 ] ) {
		count += 1;
		}
		} );

		console.log( `\tAccuracy = ${( count * 100 / total ).toFixed( 2 )}%\n` );

+32

sentiment-analysis-example/prep-task.js

		const model = require( 'wink-eng-lite-web-model' );
		const nlp = require( 'wink-nlp' )(model);
		const its = nlp.its;

		// POS and types to be preserved, rest is filtered out.
		const posSet = new Set( [ 'ADJ', 'ADV', 'VERB', 'PROPN', 'INTJ' ] );
		const typeSet = new Set( [ 'number' ] );

		// Text preprocessing for sentiment analysis.
		module.exports = ( text ) => {
		const tokens = [];
		const doc = nlp.readDoc( text );
		doc.tokens()
		// Preserve only predefined pos & types.
		.filter( ( t ) => ( posSet.has( t.out( its.pos ) ) \|\| typeSet.has( t.out( its.type ) ) ) )
		// Handle negation & numbers.
		.each( ( t ) => tokens.push(
		( t.out( its.type ) === 'number' ) ? '$number' :
		( t.out( its.negationFlag ) ) ? '!' + t.out(its.lemma) : t.out(its.lemma) )
		);

		// Add bigrams!
		let i, imax;
		for ( i = 0, imax = tokens.length - 1; i < imax; i += 1 ) {
		tokens.push( tokens[ i ] + '_' + tokens[ i + 1 ] );
		}

		// Inject sentiment from winkNLP.
		if ( doc.out( its.sentiment ) > 0.05 ) tokens.push( '$pos' );
		if ( doc.out( its.sentiment ) < -0.05 ) tokens.push( '$neg' );
		return tokens;
		}; // prepTask()

sentiment-analysis...e/shuffled-sentiment-training-data.json

Sorry, the diff of this file is too big to display

+1

-1

.nyc_output/processinfo/index.json

		@@ -1,1 +0,1 @@
		{"processes":{"849141e9-ccfa-43f3-8915-e6670c872061":{"parent":null,"children":[]}},"files":{"/Users/neilsbohr/dev/winkjs/wink-naive-bayes-text-classifier/src/prep-text.js":["849141e9-ccfa-43f3-8915-e6670c872061"],"/Users/neilsbohr/dev/winkjs/wink-naive-bayes-text-classifier/src/wink-naive-bayes-text-classifier.js":["849141e9-ccfa-43f3-8915-e6670c872061"]},"externalIds":{}}
		{"processes":{"bf700fc6-0a2e-4d1a-84ef-af1b3a7bb0d5":{"parent":null,"children":[]}},"files":{"/Users/neilsbohr/dev/winkjs/wink-naive-bayes-text-classifier/src/prep-text.js":["bf700fc6-0a2e-4d1a-84ef-af1b3a7bb0d5"],"/Users/neilsbohr/dev/winkjs/wink-naive-bayes-text-classifier/src/wink-naive-bayes-text-classifier.js":["bf700fc6-0a2e-4d1a-84ef-af1b3a7bb0d5"]},"externalIds":{}}

+6

-5

package.json

		{
		"name": "wink-naive-bayes-text-classifier",
		"version": "2.1.0",
		"description": "Configurable Naive Bayes Classifier for text with cross-validation support",
		"version": "2.2.0",
		"description": "Naive Bayes Text Classifier",
		"keywords": [
		@@ -9,7 +9,8 @@ "Naive Bayes",
		"Machine Learning",
		"Cross-validation",
		"NLP",
		"Natural Language Processing",
		"AI",
		"wink"
		"Chatbot",
		"Sentiment Analysis",
		"winkNLP",
		"Text Classification"
		],
		@@ -16,0 +17,0 @@ "main": "src/wink-naive-bayes-text-classifier.js",

+15

-8

README.md


		# wink-naive-bayes-text-classifier

		Configurable [Naive Bayes](https://en.wikipedia.org/wiki/Naive_Bayes_classifier) Classifier for text with cross-validation support
		Naive Bayes Text Classifier

		@@ -10,11 +10,18 @@ ### [![Build Status](https://app.travis-ci.com/winkjs/wink-naive-bayes-text-classifier.svg?branch=master)](https://app.travis-ci.com/winkjs/wink-naive-bayes-text-classifier) [![Coverage Status](https://coveralls.io/repos/github/winkjs/wink-naive-bayes-text-classifier/badge.svg?branch=master)](https://coveralls.io/github/winkjs/wink-naive-bayes-text-classifier?branch=master) [![Gitter](https://img.shields.io/gitter/room/nwjs/nw.js.svg)](https://gitter.im/winkjs/Lobby)

		Classify text, analyse sentiments, recognize user intents for chatbot using `wink-naive-bayes-text-classifier`. Its [API](http://winkjs.org/wink-naive-bayes-text-classifier/NaiveBayesTextClassifier.html) offers a rich set of features:
		Classify text, analyse sentiments, recognize user intents for chatbot using `wink-naive-bayes-text-classifier`. Its [API](http://winkjs.org/wink-naive-bayes-text-classifier/NaiveBayesTextClassifier.html) offers a rich set of features including cross validation to compute confusion matrix, precision, and recall. It delivers impressive accuracy levels with right text pre-processing using [wink-nlp](https://www.npmjs.com/package/wink-nlp):

		1. Preprocess text using [wink-nlp](https://www.npmjs.com/package/wink-nlp) — tokenize, stem, remove stop words, and handle negation. It also supports [Named Entity Recognition](https://winkjs.org/wink-nlp/getting-started.html) to further enhance preprocessing. A single winkNLP based helper function for preparing text is available that (a) tokenizes, (b) removes punctuations, symbols, numerals, URLs, stop words and (c) stems. It can be required from `wink-naive-bayes-text-classifier/src/prep-text.js`.
		2. Configure Lidstone or Laplace additive smoothing.
		3. Configure Multinomial or Binarized Multinomial Naive Bayes model.
		4. Export and import learnings in JSON format that can be easily saved on hard-disk.
		5. Evaluate learning to perform n-fold cross validation.
		6. Obtain comprehensive metrics including confusion matrix, precision, and recall.
		\| Dataset \| Accuracy \|
		\| --- \| --- \|
		\| Sentiment Analysis<br/>Amazon Product Review [Sentiment Labelled Sentences Data Set](https://archive.ics.uci.edu/ml/machine-learning-databases/00331/) at [UCI Machine Learning Repository](https://archive.ics.uci.edu/ml/index.php) \| 90% <br/> 800 training examples & 200 validation reviews<br/><br/>Refer to `sentiment-analysis-example` directory for the reference code \|
		\| Intent Classification<br/>Chatbot corpus from [NLU Evaluation Corpora](https://github.com/sebischair/NLU-Evaluation-Corpora) as mentioned in paper titled [Evaluating Natural Language Understanding Services for Conversational Question Answering Systems](https://aclanthology.org/W17-5522.pdf) \| 99% <br/>100 training examples & 106 validation<br/><br/>Refer to `chatbot-example` directory for the reference code \|

		#### Text Pre-processing
		A [winkNLP](https://github.com/winkjs/wink-nlp) based helper function for general purpose text pre-processing is available that (a) tokenizes, (b) removes punctuations, symbols, numerals, URLs, stop words, (c) stems each token and (d) handles negations. It can be required from `wink-naive-bayes-text-classifier/src/prep-text.js`. WinkNLP's [Named Entity Recognition](https://winkjs.org/wink-nlp/getting-started.html) may be used to further enhance the pre-processing.

		#### Hyperparameters
		These include smoothing factor to control [additive smoothing](https://winkjs.org/wink-naive-bayes-text-classifier/NaiveBayesTextClassifier.html#defineConfig) and a [consider presence only flag](https://winkjs.org/wink-naive-bayes-text-classifier/NaiveBayesTextClassifier.html#defineConfig) to choose from Multinomial/Binarized naive bayes.

		The trained model can be [exported](https://winkjs.org/wink-naive-bayes-text-classifier/NaiveBayesTextClassifier.html#exportJSON) as JSON and can be [reloaded](https://winkjs.org/wink-naive-bayes-text-classifier/NaiveBayesTextClassifier.html#importJSON) later for predictions.


		### Installation
		@@ -21,0 +28,0 @@ Use [npm](https://www.npmjs.com/package/wink-naive-bayes-text-classifier) to install:

-1

.nyc_output/849141e9-ccfa-43f3-8915-e6670c872061.json

-1

.nyc_output/proces...9141e9-ccfa-43f3-8915-e6670c872061.json

{"parent":null,"pid":4770,"argv":["/Users/neilsbohr/.nvm/versions/node/v18.10.0/bin/node","/Users/neilsbohr/dev/winkjs/wink-naive-bayes-text-classifier/node_modules/.bin/mocha","./test/"],"execArgv":[],"cwd":"/Users/neilsbohr/dev/winkjs/wink-naive-bayes-text-classifier","time":1667057197304,"ppid":4769,"coverageFilename":"/Users/neilsbohr/dev/winkjs/wink-naive-bayes-text-classifier/.nyc_output/849141e9-ccfa-43f3-8915-e6670c872061.json","externalId":"","uuid":"849141e9-ccfa-43f3-8915-e6670c872061","files":["/Users/neilsbohr/dev/winkjs/wink-naive-bayes-text-classifier/src/prep-text.js","/Users/neilsbohr/dev/winkjs/wink-naive-bayes-text-classifier/src/wink-naive-bayes-text-classifier.js"]}

wink-naive-bayes-text-classifier - npm Package Compare versions

New alerts

Improved metrics

Worsened metrics