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

// Copyright (C) 2024 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::{cmp::min, collections::HashMap};

mod candidate_selection_and_context_builder;
mod feature_extraction;
mod levenshtein;
mod sentences_builder;
mod text_pre_processor;
mod yake_logic;
pub mod yake_params;
pub use yake_params::YakeParams;

use crate::common::{get_ranked_scores, get_ranked_strings, sort_ranked_map, PUNCTUATION};

use levenshtein::Levenshtein;
use yake_logic::YakeLogic;

fn build_ranked_keywords(vec: &mut Vec<String>, word: &str, threshold: f32) {
    if vec
        .iter()
        .any(|w| Levenshtein::new(w, word).ratio() >= threshold)
    {
        return;
    }
    vec.push(word.to_string());
}

fn build_ranked_scores(vec: &mut Vec<(String, f32)>, word: &str, score: f32, threshold: f32) {
    if vec
        .iter()
        .any(|(w, _)| Levenshtein::new(w, word).ratio() >= threshold)
    {
        return;
    }
    vec.push((word.to_string(), score));
}

pub struct Yake {
    keyword_rank: HashMap<String, f32>,
    term_rank: HashMap<String, f32>,
    size: usize,
    threshold: f32,
}

impl Yake {
    /// Create a new YAKE instance.
    pub fn new(params: YakeParams) -> Self {
        let (text, stop_words, puctuation, threshold, ngram, window_size) = params.get_params();
        let (keyword_rank, term_rank) = YakeLogic::build_yake(
            text,
            stop_words.iter().map(|s| s.as_str()).collect(),
            match puctuation {
                Some(p) => p.iter().map(|s| s.as_str()).collect(),
                None => PUNCTUATION.iter().copied().collect(),
            },
            ngram,
            window_size,
        );
        Self {
            size: keyword_rank.len(),
            keyword_rank,
            term_rank,
            threshold,
        }
    }

    /// Gets the score of a (n-gram terms) keyword.
    pub fn get_keyword_score(&self, keyword: &str) -> f32 {
        *self.keyword_rank.get(keyword).unwrap_or(&0.0)
    }

    /// Gets the score of a single term.
    pub fn get_word_score(&self, word: &str) -> f32 {
        *self.term_rank.get(word).unwrap_or(&0.0)
    }

    /// Get the top n (n-gram terms) keywords with the highest score.
    pub fn get_ranked_keywords(&self, n: usize) -> Vec<String> {
        let capacity = min(self.size, n);
        let result = sort_ranked_map(&self.keyword_rank).into_iter().try_fold(
            Vec::<String>::with_capacity(capacity),
            |mut acc, (word, _)| {
                if acc.len() == capacity {
                    return Err(acc);
                }
                build_ranked_keywords(&mut acc, word, self.threshold);
                Ok(acc)
            },
        );

        match result {
            Ok(v) => v,
            Err(v) => v,
        }
    }

    /// Gets the top n (n-gram terms) keywords with the highest score and their scores.
    pub fn get_ranked_keyword_scores(&self, n: usize) -> Vec<(String, f32)> {
        let capacity = min(self.size, n);
        let result = sort_ranked_map(&self.keyword_rank).into_iter().try_fold(
            Vec::<(String, f32)>::with_capacity(capacity),
            |mut acc, (word, score)| {
                if acc.len() == capacity {
                    return Err(acc);
                }
                build_ranked_scores(&mut acc, word, *score, self.threshold);
                Ok(acc)
            },
        );

        match result {
            Ok(v) => v,
            Err(v) => v,
        }
    }

    /// Gets the top n terms with the highest score.
    pub fn get_ranked_terms(&self, n: usize) -> Vec<String> {
        get_ranked_strings(&self.term_rank, n)
    }

    /// Gets the top n terms with the highest score and their scores.
    pub fn get_ranked_term_scores(&self, n: usize) -> Vec<(String, f32)> {
        get_ranked_scores(&self.term_rank, n)
    }

    /// Gets the (n-gram terms) keyword scores map
    pub fn get_keyword_scores_map(&self) -> &HashMap<String, f32> {
        &self.keyword_rank
    }

    /// Gets the term scores map
    pub fn get_term_scores_map(&self) -> &HashMap<String, f32> {
        &self.term_rank
    }
}