nisaba 0.2.4

Data quality, reconciliation, and validation across different data stores
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

use nisaba::{
    AnalyzerConfig, DistanceType, EmbeddingModel, FileStoreType, SchemaAnalyzer, ScoringConfig,
    SimilarityConfig, Source,
};

#[tokio::main]
async fn main() {
    let config = AnalyzerConfig::builder()
        .sample_size(10)
        .scoring(ScoringConfig {
            type_weight: 0.65,
            structure_weight: 0.35,
        })
        .similarity(SimilarityConfig {
            threshold: 0.59,
            top_k: Some(7),
            algorithm: DistanceType::Cosine,
        })
        .build();

    // analyzer
    let analyzer = SchemaAnalyzer::builder()
        .name("nisaba")
        .config(config)
        .embedding_model(EmbeddingModel::MultilingualE5Small)
        .source(
            Source::files(FileStoreType::Csv)
                .path("./assets/csv")
                .num_rows(10)
                .has_header(true)
                .build()
                .unwrap(),
        )
        .sources(vec![
            Source::files(FileStoreType::Parquet)
                .path("./assets/parquet")
                .num_rows(10)
                .build()
                .unwrap(),
        ])
        .build()
        .await
        .unwrap();

    let _result = analyzer.analyze().await.unwrap();
}