keyword_extraction 1.5.0

Collection of algorithms for keyword extraction from text
Documentation
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
// Copyright (C) 2023 Afonso Barracha
//
// Rust Keyword Extraction is free software: you can redistribute it and/or modify
// it under the terms of the GNU Lesser General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// Rust Keyword Extraction is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
// GNU Lesser General Public License for more details.
//
// You should have received a copy of the GNU Lesser General Public License
// along with Rust Keyword Extraction. If not, see <http://www.gnu.org/licenses/>.

use std::collections::HashSet;

use stop_words::{get, LANGUAGE};

use crate::*;

const TEXT: &str = r#"
Title: Junior Rust Developer

Job Description:

We are seeking a talented and motivated Junior Rust Developer to join our growing team. The ideal candidate will have a passion for programming, a strong foundation in Rust, and a desire to learn and grow in a dynamic work environment.

Responsibilities:

Assist in the development and maintenance of our core Rust applications
Write clean, efficient, and well-documented code
Collaborate with the development team to design and implement new features
Actively participate in code reviews and provide constructive feedback
Continuously learn and stay up-to-date with the latest Rust ecosystem trends and technologies

Requirements:

Bachelor's degree in Computer Science or related field, or equivalent experience
Proficiency in Rust programming language
Familiarity with version control systems, preferably Git
Strong problem-solving and debugging skills
Excellent written and verbal communication skills
Ability to work well in a team-oriented environment

Nice-to-Haves:

Experience with other programming languages, such as Python, JavaScript, or C++
Knowledge of database systems, like PostgreSQL or MongoDB
Familiarity with web development frameworks, such as Actix or Rocket

What We Offer:

Competitive salary and benefits package
Opportunity for growth and career advancement
Supportive and collaborative work environment
Chance to work on cutting-edge projects using Rust

If you are passionate about Rust development and looking to kickstart your career in a supportive and dynamic environment, we encourage you to apply!
"#;

fn get_cs_hashset() -> HashSet<String> {
    HashSet::from_iter(vec!["c", "computer"].iter().map(|s| s.to_string()))
}

fn get_stop_words() -> Vec<String> {
    let cs_hashset = get_cs_hashset();
    get(LANGUAGE::English)
        .iter()
        .filter_map(|w| {
            let word = w.replace("\"", "");
            if !cs_hashset.contains(&word) {
                Some(word)
            } else {
                None
            }
        })
        .collect()
}

fn is_percent_in_hashset(vector: &[String], hashset: &HashSet<String>, percent: f64) -> bool {
    let mut count = 0;

    for item in vector {
        if hashset.contains(item) {
            count += 1;
        }
    }

    let percentage = (count as f64 / vector.len() as f64) * 100.0;
    percentage >= percent
}

fn contains_all(strings: &[String], substrings: &[&str]) -> bool {
    substrings
        .iter()
        .all(|substr| strings.contains(&substr.to_string()))
}

#[test]
fn test_tokenize() {
    let tokenizer = tokenizer::Tokenizer::new(TEXT, &get_stop_words(), None);
    let sentence_tokens = tokenizer.split_into_sentences();
    let expected_sentences = vec![
        "title junior rust developer",
        "job description",
        "seeking talented motivated junior rust developer growing team",
        "ideal candidate passion programming strong foundation rust desire learn grow dynamic environment",
        "responsibilities",
        "assist development maintenance core rust applications",
        "write clean efficient documented code",
        "collaborate development team design implement features",
        "actively participate code reviews provide constructive feedback",
        "continuously learn stay rust ecosystem trends technologies",
        "requirements",
        "bachelor degree computer science field equivalent experience",
        "proficiency rust programming language",
        "familiarity version control systems preferably git",
        "strong solving debugging skills",
        "excellent written verbal communication skills",
        "ability team oriented environment",
        "nice haves",
        "experience programming languages python javascript c",
        "knowledge database systems postgresql mongodb",
        "familiarity development frameworks actix rocket",
        "offer",
        "competitive salary benefits package",
        "opportunity growth career advancement",
        "supportive collaborative environment",
        "chance cutting edge projects rust",
        "passionate rust development kickstart career supportive dynamic environment encourage apply",
    ].iter().map(|s| s.to_string()).collect::<HashSet<String>>();

    let word_tokens = tokenizer.split_into_words();
    let expected_words = vec![
        "title",
        "junior",
        "rust",
        "developer",
        "job",
        "description",
        "seeking",
        "talented",
        "motivated",
        "junior",
        "rust",
        "developer",
        "growing",
        "team",
        "ideal",
        "candidate",
        "passion",
        "programming",
        "strong",
        "foundation",
        "rust",
        "desire",
        "learn",
        "grow",
        "dynamic",
        "environment",
        "responsibilities",
        "assist",
        "development",
        "maintenance",
        "core",
        "rust",
        "applications",
        "write",
        "clean",
        "efficient",
        "documented",
        "code",
        "collaborate",
        "development",
        "team",
        "design",
        "implement",
        "features",
        "actively",
        "participate",
        "code",
        "reviews",
        "provide",
        "constructive",
        "feedback",
        "continuously",
        "learn",
        "stay",
        "rust",
        "ecosystem",
        "trends",
        "technologies",
        "requirements",
        "bachelor",
        "degree",
        "computer",
        "science",
        "field",
        "equivalent",
        "experience",
        "proficiency",
        "rust",
        "programming",
        "language",
        "familiarity",
        "version",
        "control",
        "systems",
        "preferably",
        "git",
        "strong",
        "solving",
        "debugging",
        "skills",
        "excellent",
        "written",
        "verbal",
        "communication",
        "skills",
        "ability",
        "team",
        "oriented",
        "environment",
        "nice",
        "haves",
        "experience",
        "programming",
        "languages",
        "python",
        "javascript",
        "c",
        "knowledge",
        "database",
        "systems",
        "postgresql",
        "mongodb",
        "familiarity",
        "development",
        "frameworks",
        "actix",
        "rocket",
        "offer",
        "competitive",
        "salary",
        "benefits",
        "package",
        "opportunity",
        "growth",
        "career",
        "advancement",
        "supportive",
        "collaborative",
        "environment",
        "chance",
        "cutting",
        "edge",
        "projects",
        "rust",
        "passionate",
        "rust",
        "development",
        "kickstart",
        "career",
        "supportive",
        "dynamic",
        "environment",
        "encourage",
        "apply",
    ]
    .iter()
    .map(|s| s.to_string())
    .collect::<HashSet<String>>();

    let paragraph_tokens = tokenizer.split_into_paragraphs();
    let expected_paragraphs = vec![
        "title junior rust developer",
        "job description",
        "seeking talented motivated junior rust developer growing team ideal candidate passion programming strong foundation rust desire learn grow dynamic environment",
        "responsibilities",
        "assist development maintenance core rust applications",
        "write clean efficient documented code",
        "collaborate development team design implement features",
        "actively participate code reviews provide constructive feedback",
        "continuously learn stay rust ecosystem trends technologies",
        "requirements",
        "bachelor degree computer science field equivalent experience",
        "proficiency rust programming language",
        "familiarity version control systems preferably git",
        "strong solving debugging skills",
        "excellent written verbal communication skills",
        "ability team oriented environment",
        "nice haves",
        "experience programming languages python javascript c",
        "knowledge database systems postgresql mongodb",
        "familiarity development frameworks actix rocket",
        "offer", "competitive salary benefits package",
        "opportunity growth career advancement",
        "supportive collaborative environment",
        "chance cutting edge projects rust",
        "passionate rust development kickstart career supportive dynamic environment encourage apply",
    ].iter().map(|s| s.to_string()).collect::<HashSet<String>>();

    assert!(is_percent_in_hashset(
        &sentence_tokens,
        &expected_sentences,
        90.0
    ));
    assert!(is_percent_in_hashset(&word_tokens, &expected_words, 95.0));
    assert!(is_percent_in_hashset(
        &paragraph_tokens,
        &expected_paragraphs,
        95.0
    ));
}

#[test]
fn test_tf_idf() {
    let tf_idf = tf_idf::TfIdf::new(tf_idf::TfIdfParams::TextBlock(
        TEXT,
        &get_stop_words(),
        None,
        tf_idf::TextSplit::Paragraphs,
    ));
    let words_result = tf_idf.get_ranked_words(100);
    let expected_words = vec![
        "rust",
        "development",
        "environment",
        "work",
        "programming",
        "team",
        "career",
        "code",
        "developer",
        "dynamic",
        "experience",
        "familiarity",
        "junior",
        "learn",
        "skills",
        "strong",
        "supportive",
        "systems",
        "to",
        "well",
        "ability",
        "actively",
        "actix",
        "advancement",
        "applications",
        "apply",
        "assist",
        "bachelor",
        "benefits",
        "candidate",
        "chance",
        "clean",
        "collaborate",
        "collaborative",
        "communication",
        "competitive",
        "computer",
        "constructive",
        "continuously",
        "control",
        "core",
        "cutting",
        "database",
        "date",
        "debugging",
        "degree",
        "description",
        "design",
        "desire",
        "documented",
        "ecosystem",
        "edge",
        "efficient",
        "encourage",
        "equivalent",
        "excellent",
        "features",
        "feedback",
        "field",
        "foundation",
        "frameworks",
        "git",
        "grow",
        "growing",
        "growth",
        "haves",
        "ideal",
        "implement",
        "javascript",
        "job",
        "join",
        "kickstart",
        "knowledge",
        "language",
        "languages",
        "latest",
        "like",
        "looking",
        "maintenance",
        "mongodb",
        "motivated",
        "new",
        "nice",
        "offer",
        "opportunity",
        "oriented",
        "package",
        "participate",
        "passion",
        "passionate",
        "postgresql",
        "preferably",
        "problem",
        "proficiency",
        "projects",
        "provide",
        "python",
        "related",
        "requirements",
        "responsibilities",
    ]
    .iter()
    .map(|x| x.to_string())
    .collect::<HashSet<String>>();
    assert!(is_percent_in_hashset(&words_result, &expected_words, 85.0));
}

#[cfg(feature = "co_occurrence")]
#[test]
fn test_co_occurrence() {
    let documents =
        tokenizer::Tokenizer::new(TEXT, &get_stop_words(), None).split_into_paragraphs();
    let word_vec = vec![
        "rust",
        "development",
        "environment",
        "work",
        "programming",
        "team",
        "career",
        "code",
        "developer",
        "dynamic",
    ]
    .iter()
    .map(|x| x.to_string())
    .collect::<Vec<String>>();
    let co_occurrence = co_occurrence::CoOccurrence::new(&documents, &word_vec, 10);
    assert_eq!(
        co_occurrence.get_matrix_row("rust").unwrap(),
        [0.6666667, 0.6666667, 0.6666667, 0.0, 1.0, 0.6666667, 0.33333334, 0.0, 1.0, 0.6666667]
    );
    assert_eq!(
        co_occurrence.get_matrix_row("development").unwrap(),
        [0.6666667, 0.0, 0.33333334, 0.0, 0.0, 0.33333334, 0.33333334, 0.0, 0.0, 0.33333334]
    );
    assert_eq!(
        co_occurrence.get_matrix_row("developer").unwrap(),
        [1.0, 0.0, 0.0, 0.0, 0.33333334, 0.33333334, 0.0, 0.0, 0.0, 0.0]
    );
    assert_eq!(
        co_occurrence.get_matrix_row("dynamic").unwrap(),
        [0.6666667, 0.33333334, 0.6666667, 0.0, 0.33333334, 0.0, 0.33333334, 0.0, 0.0, 0.0]
    );
}

#[test]
fn test_rake() {
    let rake_result = [
        "core rust applications write clean efficient",
        "version control systems preferably git strong",
        "title junior rust developer job description",
        "provide constructive feedback continuously learn",
        "motivated junior rust developer",
        "debugging skills excellent written",
        "technologies requirements bachelor degree",
        "verbal communication skills ability",
        "team oriented environment nice",
        "rust programming language familiarity",
    ];
    let rake_struct = rake::Rake::new(rake::RakeParams::WithDefaults(TEXT, &get_stop_words()));
    assert!(is_percent_in_hashset(
        &rake_struct.get_ranked_phrases(10),
        &rake_result
            .iter()
            .map(|x| x.to_string())
            .collect::<HashSet<String>>(),
        90.0
    ));

    let limited_rake_struct = rake::Rake::new(rake::RakeParams::WithDefaultsAndPhraseLength(
        TEXT,
        &get_stop_words(),
        Some(3),
    ));
    for phrase in limited_rake_struct.get_ranked_phrases(10) {
        assert!(phrase.split_whitespace().count() <= 3);
    }
}

#[test]
fn test_text_rank() {
    let expected_words = [
        "rust",
        "environment",
        "development",
        "team",
        "programming",
        "code",
        "systems",
        "skills",
        "experience",
        "familiarity",
    ];
    let text_rank = text_rank::TextRank::new(text_rank::TextRankParams::WithDefaults(
        TEXT,
        &get_stop_words(),
    ));
    assert!(is_percent_in_hashset(
        &text_rank.get_ranked_words(10),
        &expected_words
            .iter()
            .map(|x| x.to_string())
            .collect::<HashSet<String>>(),
        90.0
    ));
    assert!(is_percent_in_hashset(
        &text_rank
            .get_ranked_phrases(5)
            .iter()
            .flat_map(|phrases| phrases.split_whitespace().map(|w| w.to_string()))
            .collect::<Vec<String>>(),
        &text_rank
            .get_ranked_words(10)
            .iter()
            .map(|x| x.to_string())
            .collect::<HashSet<String>>(),
        90.0
    ));

    let limited_text_rank = text_rank::TextRank::new(
        text_rank::TextRankParams::WithDefaultsAndPhraseLength(TEXT, &get_stop_words(), Some(3)),
    );
    for phrase in limited_text_rank.get_ranked_phrases(10) {
        assert!(phrase.split_whitespace().count() <= 3);
    }
}

#[cfg(feature = "yake")]
#[test]
fn test_yake() {
    let yake = yake::Yake::new(yake::YakeParams::WithDefaults(TEXT, &get_stop_words()));
    let yake_result = [
        "motivated junior rust",
        "motivated junior",
        "job description",
        "developer job description",
        "rust developer",
        "developer job",
        "junior rust developer",
        "rust developer job",
        "junior rust",
        "rust programming language",
    ];

    let ranked_keywords = yake.get_ranked_keywords(10);
    let expected_terms = ranked_keywords
        .iter()
        .flat_map(|s| s.split_whitespace())
        .collect::<Vec<&str>>();
    let ranked_terms = yake.get_ranked_terms(
        ranked_keywords
            .iter()
            .fold(0, |acc, s| acc + s.split_whitespace().count()),
    );

    assert!(is_percent_in_hashset(
        &ranked_keywords,
        &yake_result
            .iter()
            .map(|x| x.to_string())
            .collect::<HashSet<String>>(),
        90.0
    ));
    assert!(contains_all(&ranked_terms, &expected_terms));
}