wink-nlp - npm Package Compare versions

Comparing version 1.13.1 to 1.14.0

.nyc_output/processinfo/index.json

@@ -1,1 +0,1 @@
-{"processes":{"447606eb-68d4-4bdc-894f-5ad8a7af4cf5":{"parent":null,"children":[]}},"files":{"/Users/neilsbohr/dev/winkjs/wink-nlp/src/wink-nlp.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/dd-wrapper.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/constants.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/doc-v2.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/contained-entities.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/locate.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/get-parent-item.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/search.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-get-item.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-get-item.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-each.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-each.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-filter.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-filter.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-token-out.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/its.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/sort4FT.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/allowed.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/as.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/contained-markings.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-tokens-out.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-tokens-out.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-entity-out.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-entities-out.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-entities-out.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-sentence-out.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-sentences-out.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-document-out.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/print-tokens.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/cache.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/tokenizer.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/recursive-tokenizer.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/compile-trex.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/tokens-mappers.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/examples-compiler.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/automaton.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/compose-patterns.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/identify-marked-area.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/helper.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/utilities/bm25-vectorizer.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/utilities/allowed.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"],"/Users/neilsbohr/dev/winkjs/wink-nlp/utilities/similarity.js":["447606eb-68d4-4bdc-894f-5ad8a7af4cf5"]},"externalIds":{}}
+{"processes":{"8906aaf5-b61e-498b-9a09-90d1440090a1":{"parent":null,"children":[]}},"files":{"/Users/neilsbohr/dev/winkjs/wink-nlp/src/wink-nlp.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/dd-wrapper.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/constants.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/doc-v2.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/contained-entities.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/locate.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/get-parent-item.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/search.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-get-item.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-get-item.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-each.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-each.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-filter.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-filter.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-token-out.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/its.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/sort4FT.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/sentence-wise-importance.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/allowed.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/as.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/contained-markings.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-tokens-out.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-tokens-out.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-entity-out.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-entities-out.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-entities-out.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-sentence-out.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-sentences-out.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-document-out.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/print-tokens.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/cache.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/tokenizer.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/recursive-tokenizer.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/compile-trex.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/tokens-mappers.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/examples-compiler.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/automaton.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/compose-patterns.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/identify-marked-area.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/helper.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/utilities/bm25-vectorizer.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/utilities/allowed.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"],"/Users/neilsbohr/dev/winkjs/wink-nlp/utilities/similarity.js":["8906aaf5-b61e-498b-9a09-90d1440090a1"]},"externalIds":{}}

CHANGELOG.md

@@ -0,1 +1,7 @@
+# [Introducing helper for extracting important sentences from a document](https://github.com/winkjs/wink-nlp/releases/tag/1.14.0)
+## Version 1.14.0 May 20, 2023
+
+### ✨ Features
+- You can now use `its.sentenceWiseImprotance` helper to obtain sentence wise importance (on a scale of 0 to 1) of a document, if it is supported by language model. 📚📊🤓
+
 # [Operational update](https://github.com/winkjs/wink-nlp/releases/tag/1.13.1)
@@ -2,0 +8,0 @@ ## Version 1.13.1 March 27, 2023

package.json

 {
   "name": "wink-nlp",
-  "version": "1.13.1",
+  "version": "1.14.0",
   "description": "Developer friendly Natural Language Processing ✨",
@@ -5,0 +5,0 @@ "keywords": [

README.md

@@ -10,5 +10,5 @@ # winkNLP
 
-It is built ground up with a lean code base that has [no external dependency](https://snyk.io/test/github/winkjs/wink-nlp?tab=dependencies). A test coverage of [~100%](https://coveralls.io/github/winkjs/wink-nlp?branch=master) and compliance with the [Open Source Security Foundation best practices](https://bestpractices.coreinfrastructure.org/en/projects/6035) make winkNLP the ideal tool for building production grade systems with confidence.
+It is built ground up with [no external dependency](https://snyk.io/test/github/winkjs/wink-nlp?tab=dependencies) and has a [lean code base of ~10Kb minified & gzipped](https://bundlephobia.com/package/wink-nlp). A test coverage of [~100%](https://coveralls.io/github/winkjs/wink-nlp?branch=master) and compliance with the [Open Source Security Foundation best practices](https://bestpractices.coreinfrastructure.org/en/projects/6035) make winkNLP the ideal tool for building production grade systems with confidence.
 
-WinkNLP with full [Typescript support](https://github.com/winkjs/wink-nlp/blob/master/types/index.d.ts), runs on Node.js and browsers.
+WinkNLP with full [Typescript support](https://github.com/winkjs/wink-nlp/blob/master/types/index.d.ts), runs on Node.js and [web browsers](https://github.com/winkjs/wink-nlp#how-to-install-for-web-browser).
 
@@ -38,3 +38,3 @@ ## Build amazing apps quickly
 <tr><td>♻️ Extensive text processing features</td><td>Remove and/or retain tokens with specific attributes such as part-of-speech, named entity type, token type, stop word, shape and many more; compute Flesch reading ease score; generate n-grams; normalize, lemmatise or stem. Checkout how with the right kind of text preprocessing, even <a href="https://github.com/winkjs/wink-naive-bayes-text-classifier#readme">Naive Bayes classifier</a> achieves <b>impressive (≥90%)</b> accuracy in sentiment analysis and chatbot intent classification tasks.</td></tr>
-<tr><td>🔠 Pre-trained <a href="https://winkjs.org/wink-nlp/language-models.html">language models</a></td><td>Compact sizes starting from <b>&lt;3MB</b> – reduced model loading time drastically.</td></tr>
+<tr><td>🔠 Pre-trained <a href="https://winkjs.org/wink-nlp/language-models.html">language models</a></td><td>Compact sizes starting from <a href="https://bundlephobia.com/package/wink-eng-lite-web-model">~1MB (minified & gzipped)</a> – reduce model loading time drastically down to ~1 second on a 4G network.</td></tr>
 <tr><td>💼 Host of <a href="https://winkjs.org/wink-nlp/its-as-helper.html">utilities & tools</a></td><td>BM25 vectorizer; Several similarity methods – Cosine, Tversky, Sørensen-Dice, Otsuka-Ochiai; Helpers to get bag of words, frequency table, lemma/stem, stop word removal and many more.</td></tr>
@@ -41,0 +41,0 @@ </table>

ROADMAP.md

@@ -6,5 +6,5 @@ # Roadmap 🧭
 |---|---|---|---|
-|01.|**Extractive Summarization**:<br/> Add `its.summary` helper to produce extractive summary of text via `doc.out( its.summary )`. While it should be language agnostic, but it should leverage loaded language model's capability to improve summarization.| Simple | WIP |
+|01.|**Extractive Summarization**:<br/> Add `its.summary` helper to produce extractive summary of text via `doc.out( its.summary )`. While it should be language agnostic, but it should leverage loaded language model's capability to improve summarization.| Simple | [WIP](https://observablehq.com/@winkjs/how-to-visualize-key-sentences-in-a-document) |
 |02.|**Text Pre-processor**:<br/>Add a text preprocessing utility that provides options to (a) filter specific tokens based on their properties such as `pos`, `isStopWordFlag`, and `type`; (b) map entity type with a definable keyword; (c) add bigrams & trigrams and (d) inject sentiment. The API should follow winkNLP style and standards.|Medium|YTS|
-|03.|**Word Vectors Integration**:<br/>Add integration with various word vectors starting with GloVe. This should include compression/decompression for fast loading, helpers for token, sentence and document vector computation. |High|YTS|
+|03.|**Word Vectors Integration**:<br/>Add integration with various word vectors starting with GloVe. This should include compression/decompression for fast loading, helpers for token, sentence and document vector computation. |High|WIP|
 |04.|**Sub-word Tokenizer**:<br/>Add sub-word tokenization feature using techniques like Byte Pair Encoding (BPE) and/or WordPiece. The processing pipeline should allow choice of tokenizer.|Very High|YTS|
@@ -11,0 +11,0 @@ |05.|**Compose Corpus**:<br/>Add a utility to produce training corpus using patterns and cartesian product.|Simple|YTS|

src/allowed.js

@@ -118,3 +118,4 @@ //     wink-nlp
   its.stem,
-  its.readabilityStats
+  its.readabilityStats,
+  its.sentenceWiseImportance
 ] );
@@ -121,0 +122,0 @@

src/api/itm-document-out.js

@@ -70,2 +70,6 @@ //     wink-nlp
 
+  if ( itsfn === its.sentenceWiseImportance ) {
+    return itsfn( rdd );
+  }
+
   // Setup the correct `as.fn` becuase the current markedup text would have
@@ -72,0 +76,0 @@ // returned the `value`. Refer to `its.markedUpText`.

src/its.js

@@ -36,2 +36,3 @@ //     wink-nlp
 var caseMap = [ 'other', 'lowerCase', 'upperCase', 'titleCase' ];
+var swi = require( './sentence-wise-importance.js' );
 
@@ -166,2 +167,6 @@ // Size of a single token.
 
+its.sentenceWiseImportance = function ( rdd ) {
+  return swi( rdd );
+}; // sentenceWiseImportance()
+
 /* ------ utilities ------ */
@@ -168,0 +173,0 @@

src/sort4FT.js

@@ -0,1 +1,33 @@
+//     wink-nlp
+//
+//     Copyright (C) GRAYPE Systems Private Limited
+//
+//     This file is part of “wink-nlp”.
+//
+//     Permission is hereby granted, free of charge, to any
+//     person obtaining a copy of this software and
+//     associated documentation files (the "Software"), to
+//     deal in the Software without restriction, including
+//     without limitation the rights to use, copy, modify,
+//     merge, publish, distribute, sublicense, and/or sell
+//     copies of the Software, and to permit persons to
+//     whom the Software is furnished to do so, subject to
+//     the following conditions:
+//
+//     The above copyright notice and this permission notice
+//     shall be included in all copies or substantial
+//     portions of the Software.
+//
+//     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF
+//     ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED
+//     TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
+//     PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+//     THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+//     DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF
+//     CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+//     CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+//     DEALINGS IN THE SOFTWARE.
+
+//
+
 /**
@@ -2,0 +34,0 @@ * Stable sort function for frequency table i.e. `[ [ term, frequency ] ... ]`.

types/index.d.ts

@@ -94,2 +94,7 @@ // Minimum TypeScript Version: 4.0
 
+  export interface SentenceImportance {
+    index: number;
+    importance: number;
+  }
+
   export type ModelTermFrequencies = Bow;
@@ -125,2 +130,3 @@ export type ModelInverseDocumentFrequencies = Bow;
     span(spanItem: number[]): number[];
+    sentenceWiseImportance(rdd: RawDocumentData): SentenceImportance[];
     sentiment(spanItem: number[]): number;
@@ -127,0 +133,0 @@ readabilityStats(rdd: RawDocumentData, addons: ModelAddons): ReadabilityStats;

No alert changes

Improved metrics

Total package byte prevSize

602787

increased by2.95%

Number of package files

62

increased by1.64%

Lines of code

6234

increased by2.6%

No dependency changes