main.py

import numpy as np
from bloom_filter import Bloom_Filter
from features import ext_feat, compute_feature_mut_inf,slt_feat
from evaluation import evaluate_queries, save_results_csv
from plots import plot_query_results, plot_bloom_metrics

if __name__ == "__main__":

    items = [
        "bloom filter implementation",
        "probabilistic data structure",
        "machine learning basics",
        "deep learning neural networks"
    ]
    labels = [1, 1, 0, 0]

    dataset = [ext_feat(i) for i in items]
    mi_scores = compute_feature_mut_inf(dataset, labels)

    bf = Bloom_Filter(n=100, fpr=0.01)
    for item in items[:2]:
        feats = ext_feat(item)
        selected = slt_feat(feats, mi_scores)
        bf.add(selected)

    queries = [
        "bloom filter structure",
        "probabilistic bloom filter",
        "deep neural network",
        "machine learning filter",
        "random text example"
    ]

    results = evaluate_queries(bf, queries, mi_scores)
    plot_query_results(results)
    save_results_csv(results)

    fpr_range = np.linspace(0.001, 0.5, 100)
    plot_bloom_metrics(fpr_range)