matching_dependency/hpo/er_model_hpo.py

import json
from ConfigSpace import Categorical, Configuration, ConfigurationSpace, Integer, Float
from ConfigSpace.conditions import InCondition
from ConfigSpace.read_and_write import json as csj
import py_entitymatching.catalog.catalog_manager as cm
import pandas as pd
from smac import HyperparameterOptimizationFacade, Scenario
from settings import *
from ml_er.ml_entity_resolver import er_process


class Classifier:
    @property
    def configspace(self) -> ConfigurationSpace:
        # Build Configuration Space which defines all parameters and their ranges
        cs = ConfigurationSpace(seed=0)
        ltable = pd.read_csv(ltable_path, encoding='ISO-8859-1')
        selected_attrs = ltable.columns.values.tolist()
        block_attr_items = selected_attrs[:]
        block_attr_items.remove(ltable_id)

        block_attr = Categorical("block_attr", block_attr_items)
        ml_matcher = Categorical("ml_matcher", ["dt", "svm", "rf", "lg", "ln", "nb"], default="rf")
        ml_blocker = Categorical("ml_blocker", ["over_lap", "attr_equiv"], default="over_lap")
        similarity_thresh = Float("similarity_thresh", (0, 0.2), default=0.2)
        support_thresh = Integer("support_thresh", (1, 5), default=1)
        confidence_thresh = Float("confidence_thresh", (0.3, 0.7), default=0.4)

        cs.add_hyperparameters([block_attr, ml_matcher, ml_blocker, similarity_thresh,
                                support_thresh, confidence_thresh])
        return cs

    # train 就是整个函数 只需将返回结果由预测变成预测结果的评估
    def train(self, config: Configuration, seed: int = 0) -> float:
        cm.del_catalog()
        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 + "configspace.json", "w") as f:
        json.dump(dict_configspace, f, indent=4)

    scenario = Scenario(
        cs,
        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 + "incumbent.json", "w") as f:
        json.dump(dict(incumbent), f, indent=4)
    return incumbent


if __name__ == '__main__':
    ml_er_hpo()