matching_dependency_pyJedAI/hpo/er_model_hpo.py

import pandas as pd
import json
from ConfigSpace import Categorical, Configuration, ConfigurationSpace, Integer, Float
from ConfigSpace import EqualsCondition
from ConfigSpace.read_and_write import json as csj
from smac import HyperparameterOptimizationFacade, Scenario
from settings import *
from ml_er.ml_entity_resolver import er_process
from settings import ltable_path, ltable_id


class Classifier:
    @property
    def configspace(self) -> ConfigurationSpace:
        cs = ConfigurationSpace(seed=0)
        ltable = pd.read_csv(ltable_path, encoding='ISO-8859-1', sep='|')
        selected_attrs = ltable.columns.values.tolist()
        block_attr_items = selected_attrs[:]
        block_attr_items.remove(ltable_id)

        jed_blocker = Categorical("jed_blocker",
                                  ["Standard", "QGrams", "ExtendedQG", "SuffixArrays", "ExtendedSA"])
        qgrams = Integer('qgrams', (3, 10), default=6)
        use_qgrams = EqualsCondition(child=qgrams, parent=jed_blocker, value="QGrams")
        block_attr = Categorical("block_attr", block_attr_items)

        block_filtering_ratio = Float("block_filtering_ratio", (0.7, 0.95), default=0.8)

        meta_blocker = Categorical("meta_blocker",
                                   ["WEP", "WNP", "CEP", "CNP", "BLAST", "RCNP", "RWNP", "CP"])
        weighting_scheme = Categorical("weighting_scheme",
                                       ['CN-CBS', 'CBS', 'SN-CBS', 'CNC', 'SNC', 'SND', 'CND', 'CNJ', 'SNJ',
                                        'COSINE', 'DICE', 'ECBS', 'JS', 'EJS', 'X2'])

        # todo other hyperparameters
        matching_metric = Categorical("matching_metric",
                                      ['cosine', 'euclidean'])
        matching_tokenizer = Categorical("matching_tokenizer",
                                         ['char_tokenizer', 'word_tokenizer', 'white_space_tokenizer'])
        matching_vectorizer = Categorical("matching_vectorizer",
                                          ['tfidf', 'tf', 'boolean'])
        matching_sim_thresh = Float("similarity_threshold", (0.05, 0.9))
        clusteror = Categorical("clusteror_name",
                                ["CCC", "UMC", "CenterC", "BMC", "MCC", "CC", "CTC", "MCL", "KMAC", "RSRC"])

        cs.add_hyperparameters([jed_blocker, block_attr, meta_blocker, weighting_scheme, matching_metric,
                                matching_tokenizer, matching_vectorizer, clusteror, qgrams, block_filtering_ratio,
                                matching_sim_thresh])
        cs.add_conditions([use_qgrams])
        return cs

    def train(self, config: Configuration, seed: int = 0) -> float:
        indicators = er_process(config)
        return 1-indicators['performance']


def ml_er_hpo():
    classifier = Classifier()
    cs = classifier.configspace
    str_configspace = csj.write(cs)
    dict_configspace = json.loads(str_configspace)
    with open(hpo_output_dir + r"\configspace.json", "w") as f:
        json.dump(dict_configspace, f, indent=4)

    scenario = Scenario(
        cs,
        crash_cost=1,
        deterministic=True,
        n_trials=50,  # We want to run max 50 trials (combination of config and seed)
        n_workers=1
    )

    initial_design = HyperparameterOptimizationFacade.get_initial_design(scenario, n_configs=5)

    smac = HyperparameterOptimizationFacade(
        scenario,
        classifier.train,
        initial_design=initial_design,
        overwrite=True,  # If the run exists, we overwrite it; alternatively, we can continue from last state
    )

    incumbent = smac.optimize()
    incumbent_cost = smac.validate(incumbent)
    default = cs.get_default_configuration()
    default_cost = smac.validate(default)
    print(f"Default Cost: {default_cost}")
    print(f"Incumbent Cost: {incumbent_cost}")

    if incumbent_cost > default_cost:
        incumbent = default
        print(f"Updated Incumbent Cost: {default_cost}")

    print(f"Optimized Configuration:{incumbent.values()}")

    with open(hpo_output_dir + r"\incumbent.json", "w") as f:
        json.dump(dict(incumbent), f, indent=4)
    return incumbent


if __name__ == '__main__':
    ml_er_hpo()