|
| 1 | +/* |
| 2 | +* @license Apache-2.0 |
| 3 | +* |
| 4 | +* Copyright (c) 2021 The Stdlib Authors. |
| 5 | +* |
| 6 | +* Licensed under the Apache License, Version 2.0 (the "License"); |
| 7 | +* you may not use this file except in compliance with the License. |
| 8 | +* You may obtain a copy of the License at |
| 9 | +* |
| 10 | +* http://www.apache.org/licenses/LICENSE-2.0 |
| 11 | +* |
| 12 | +* Unless required by applicable law or agreed to in writing, software |
| 13 | +* distributed under the License is distributed on an "AS IS" BASIS, |
| 14 | +* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 15 | +* See the License for the specific language governing permissions and |
| 16 | +* limitations under the License. |
| 17 | +*/ |
| 18 | + |
| 19 | +// TypeScript Version: 2.0 |
| 20 | + |
| 21 | +/* tslint:disable:max-line-length */ |
| 22 | +/* tslint:disable:max-file-line-count */ |
| 23 | + |
| 24 | +import expandContractions = require( '@stdlib/nlp/expand-contractions' ); |
| 25 | +import lda = require( '@stdlib/nlp/lda' ); |
| 26 | +import porterStemmer = require( '@stdlib/nlp/porter-stemmer' ); |
| 27 | +import tokenize = require( '@stdlib/nlp/tokenize' ); |
| 28 | + |
| 29 | +/** |
| 30 | +* Interface describing the `nlp` namespace. |
| 31 | +*/ |
| 32 | +interface Namespace { |
| 33 | + /** |
| 34 | + * Expands all contractions to their formal equivalents. |
| 35 | + * |
| 36 | + * @param str - string to convert |
| 37 | + * @returns string with expanded contractions |
| 38 | + * |
| 39 | + * @example |
| 40 | + * var str = 'I won\'t be able to get y\'all out of this one.'; |
| 41 | + * var out = ns.expandContractions( str ); |
| 42 | + * // returns 'I will not be able to get you all out of this one.' |
| 43 | + * |
| 44 | + * @example |
| 45 | + * var str = 'It oughtn\'t to be my fault, because, you know, I didn\'t know'; |
| 46 | + * var out = ns.expandContractions( str ); |
| 47 | + * // returns 'It ought not to be my fault, because, you know, I did not know' |
| 48 | + */ |
| 49 | + expandContractions: typeof expandContractions; |
| 50 | + |
| 51 | + /** |
| 52 | + * Latent Dirichlet Allocation via collapsed Gibbs sampling. |
| 53 | + * |
| 54 | + * @param documents - document corpus |
| 55 | + * @param K - number of topics |
| 56 | + * @param options - options object |
| 57 | + * @param options.alpha - Dirichlet hyper-parameter of topic vector theta: |
| 58 | + * @param options.beta - Dirichlet hyper-parameter for word vector phi |
| 59 | + * @throws second argument must be a positive integer |
| 60 | + * @throws must provide valid options |
| 61 | + * @returns model object |
| 62 | + */ |
| 63 | + lda: typeof lda; |
| 64 | + |
| 65 | + /** |
| 66 | + * Extracts the stem of a given word. |
| 67 | + * |
| 68 | + * @param word - input word |
| 69 | + * @returns word stem |
| 70 | + * |
| 71 | + * @example |
| 72 | + * var out = ns.porterStemmer( 'walking' ); |
| 73 | + * // returns 'walk' |
| 74 | + * |
| 75 | + * @example |
| 76 | + * var out = ns.porterStemmer( 'walked' ); |
| 77 | + * // returns 'walk' |
| 78 | + * |
| 79 | + * @example |
| 80 | + * var out = ns.porterStemmer( 'walks' ); |
| 81 | + * // returns 'walk' |
| 82 | + * |
| 83 | + * @example |
| 84 | + * var out = ns.porterStemmer( 'worldwide' ); |
| 85 | + * // returns 'worldwid' |
| 86 | + * |
| 87 | + * @example |
| 88 | + * var out = ns.porterStemmer( '' ); |
| 89 | + * // returns '' |
| 90 | + */ |
| 91 | + porterStemmer: typeof porterStemmer; |
| 92 | + |
| 93 | + /** |
| 94 | + * Tokenize a string. |
| 95 | + * |
| 96 | + * @param str - input string |
| 97 | + * @param keepWhitespace - boolean indicating whether whitespace characters should be returned as part of the token array (default: false) |
| 98 | + * @returns array of tokens |
| 99 | + * |
| 100 | + * @example |
| 101 | + * var str = 'Hello World!'; |
| 102 | + * var out = ns.tokenize( str ); |
| 103 | + * // returns [ 'Hello', 'World', '!' ] |
| 104 | + * |
| 105 | + * @example |
| 106 | + * var str = ''; |
| 107 | + * var out = ns.tokenize( str ); |
| 108 | + * // returns [] |
| 109 | + * |
| 110 | + * @example |
| 111 | + * var str = 'Hello Mrs. Maple, could you call me back?'; |
| 112 | + * var out = ns.tokenize( str ); |
| 113 | + * // returns [ 'Hello', 'Mrs.', 'Maple', ',', 'could', 'you', 'call', 'me', 'back', '?' ] |
| 114 | + */ |
| 115 | + tokenize: typeof tokenize; |
| 116 | +} |
| 117 | + |
| 118 | +/** |
| 119 | +* Standard library natural language processing. |
| 120 | +*/ |
| 121 | +declare var ns: Namespace; |
| 122 | + |
| 123 | + |
| 124 | +// EXPORTS // |
| 125 | + |
| 126 | +export = ns; |
0 commit comments