diff --git a/datasets/Amazon-Google/Amzon_GoogleProducts_perfectMapping.csv b/datasets/Amazon-Google/Mapping.csv similarity index 100% rename from datasets/Amazon-Google/Amzon_GoogleProducts_perfectMapping.csv rename to datasets/Amazon-Google/Mapping.csv diff --git a/hpo/er_model_hpo.py b/hpo/er_model_hpo.py index 8253146..5fb5d50 100644 --- a/hpo/er_model_hpo.py +++ b/hpo/er_model_hpo.py @@ -1,21 +1,12 @@ -import os - -import numpy as np -import torch 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 as em import py_entitymatching.catalog.catalog_manager as cm import pandas as pd - from smac import HyperparameterOptimizationFacade, Scenario - -from md_discovery.md_discover import md_discover from settings import * -from ml_er.ml_entity_resolver import evaluate_prediction, load_mds, is_explicable, build_col_pairs_sim_tensor_dict, \ - process_prediction_for_md_discovery, er_process +from ml_er.ml_entity_resolver import er_process class Classifier: @@ -29,17 +20,14 @@ class Classifier: block_attr_items.remove(ltable_id) block_attr = Categorical("block_attr", block_attr_items) - overlap_size = Integer("overlap_size", (1, 3), default=1) 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", (0.2, 0.21)) - support_thresh = Integer("support_thresh", (1, 1000)) - confidence_thresh = Float("confidence_thresh", (0.25, 0.5)) + 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) - use_overlap_size = InCondition(child=overlap_size, parent=ml_blocker, values=["over_lap"]) - cs.add_hyperparameters([block_attr, overlap_size, ml_matcher, ml_blocker, - similarity_thresh, support_thresh, confidence_thresh]) - cs.add_conditions([use_overlap_size]) + 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 @@ -48,183 +36,6 @@ class Classifier: indicators = er_process(config) return 1-indicators['performance'] - # # 数据在外部加载 - # ######################################################################################################################## - # ltable = pd.read_csv(ltable_path, encoding='ISO-8859-1') - # cm.set_key(ltable, ltable_id) - # # ltable.fillna("", inplace=True) - # rtable = pd.read_csv(rtable_path, encoding='ISO-8859-1') - # cm.set_key(rtable, rtable_id) - # # rtable.fillna("", inplace=True) - # mappings = pd.read_csv(mapping_path, encoding='ISO-8859-1') - # - # lid_mapping_list = [] - # rid_mapping_list = [] - # # 全部转为字符串 - # # ltable = ltable.astype(str) - # # rtable = rtable.astype(str) - # # mappings = mappings.astype(str) - # matching_number = len(mappings) # 所有阳性样本数，商品数据集应为1300 - # - # for index, row in mappings.iterrows(): - # lid_mapping_list.append(row[mapping_lid]) - # rid_mapping_list.append(row[mapping_rid]) - # # 仅保留两表中出现在映射表中的行，增大正样本比例 - # selected_ltable = ltable[ltable[ltable_id].isin(lid_mapping_list)] - # # if len(lr_attrs_map) > 0: - # # selected_ltable = selected_ltable.rename(columns=lr_attrs_map) # 参照右表，修改左表中与右表对应但不同名的字段 - # tables_id = rtable_id # 不论左表右表ID字段名是否一致，经上一行调整，统一以右表为准 - # selected_rtable = rtable[rtable[rtable_id].isin(rid_mapping_list)] - # selected_attrs = selected_ltable.columns.values.tolist() # 两张表中的字段名 - # ######################################################################################################################## - # - # attrs_with_l_prefix = ['ltable_' + i for i in selected_attrs] # 字段名加左前缀 - # attrs_with_r_prefix = ['rtable_' + i for i in selected_attrs] # 字段名加右前缀 - # cm.set_key(selected_ltable, tables_id) - # cm.set_key(selected_rtable, tables_id) - # - # if config["ml_blocker"] == "over_lap": - # blocker = em.OverlapBlocker() - # candidate = blocker.block_tables(selected_ltable, selected_rtable, config["block_attr"], config["block_attr"], - # l_output_attrs=selected_attrs, r_output_attrs=selected_attrs, - # overlap_size=config["overlap_size"], show_progress=False, - # allow_missing=True) - # elif config["ml_blocker"] == "attr_equiv": - # blocker = em.AttrEquivalenceBlocker() - # candidate = blocker.block_tables(selected_ltable, selected_rtable, config["block_attr"], config["block_attr"], - # l_output_attrs=selected_attrs, r_output_attrs=selected_attrs, - # allow_missing=True) - # - # candidate['gold'] = 0 - # candidate = candidate.reset_index(drop=True) - # candidate_match_rows = [] - # for line in candidate.itertuples(): - # l_id = getattr(line, 'ltable_' + tables_id) - # map_row = mappings[mappings[mapping_lid] == l_id] - # - # if map_row is not None: - # r_id = map_row[mapping_rid] - # for value in r_id: - # if value == getattr(line, 'rtable_' + tables_id): - # candidate_match_rows.append(line[0]) - # else: - # continue - # for _ in candidate_match_rows: - # candidate.loc[_, 'gold'] = 1 - # - # candidate.fillna("", inplace=True) - # - # # 裁剪负样本，保持正负样本数量一致 - # candidate_mismatch = candidate[candidate['gold'] == 0] - # candidate_match = candidate[candidate['gold'] == 1] - # if len(candidate_mismatch) > len(candidate_match): - # candidate_mismatch = candidate_mismatch.sample(n=len(candidate_match)) - # # 拼接正负样本 - # candidate_for_train_test = pd.concat([candidate_mismatch, candidate_match]) - # if len(candidate_for_train_test) == 0: - # return 1 - # candidate_for_train_test = candidate_for_train_test.reset_index(drop=True) - # cm.set_key(candidate_for_train_test, '_id') - # cm.set_fk_ltable(candidate_for_train_test, 'ltable_' + tables_id) - # cm.set_fk_rtable(candidate_for_train_test, 'rtable_' + tables_id) - # cm.set_ltable(candidate_for_train_test, selected_ltable) - # cm.set_rtable(candidate_for_train_test, selected_rtable) - # - # # 分为训练测试集 - # train_proportion = 0.7 - # test_proportion = 0.3 - # sets = em.split_train_test(candidate_for_train_test, train_proportion=train_proportion, random_state=0) - # train_set = sets['train'] - # test_set = sets['test'] - # - # cm.set_key(train_set, '_id') - # cm.set_fk_ltable(train_set, 'ltable_' + tables_id) - # cm.set_fk_rtable(train_set, 'rtable_' + tables_id) - # cm.set_ltable(train_set, selected_ltable) - # cm.set_rtable(train_set, selected_rtable) - # - # cm.set_key(test_set, '_id') - # cm.set_fk_ltable(test_set, 'ltable_' + tables_id) - # cm.set_fk_rtable(test_set, 'rtable_' + tables_id) - # cm.set_ltable(test_set, selected_ltable) - # cm.set_rtable(test_set, selected_rtable) - # - # if config["ml_matcher"] == "dt": - # matcher = em.DTMatcher(name='DecisionTree', random_state=0) - # elif config["ml_matcher"] == "svm": - # matcher = em.SVMMatcher(name='SVM', random_state=0) - # elif config["ml_matcher"] == "rf": - # matcher = em.RFMatcher(name='RF', random_state=0) - # elif config["ml_matcher"] == "lg": - # matcher = em.LogRegMatcher(name='LogReg', random_state=0) - # elif config["ml_matcher"] == "ln": - # matcher = em.LinRegMatcher(name='LinReg') - # elif config["ml_matcher"] == "nb": - # matcher = em.NBMatcher(name='NaiveBayes') - # feature_table = em.get_features_for_matching(selected_ltable, selected_rtable, validate_inferred_attr_types=False) - # - # train_feature_vecs = em.extract_feature_vecs(train_set, - # feature_table=feature_table, - # attrs_after=['gold'], - # show_progress=False) - # train_feature_vecs.fillna(value=0, inplace=True) - # test_feature_after = attrs_with_l_prefix[:] - # test_feature_after.extend(attrs_with_r_prefix) - # for _ in test_feature_after: - # if _.endswith(tables_id): - # test_feature_after.remove(_) - # test_feature_after.append('gold') - # test_feature_vecs = em.extract_feature_vecs(test_set, feature_table=feature_table, - # attrs_after=test_feature_after, show_progress=False) - # test_feature_vecs.fillna(value=0, inplace=True) - # fit_exclude = ['_id', 'ltable_' + tables_id, 'rtable_' + tables_id, 'gold'] - # matcher.fit(table=train_feature_vecs, exclude_attrs=fit_exclude, target_attr='gold') - # - # test_feature_after.extend(['_id', 'ltable_' + tables_id, 'rtable_' + tables_id]) - # predictions = matcher.predict(table=test_feature_vecs, exclude_attrs=test_feature_after, - # append=True, target_attr='predicted', inplace=False) - # eval_result = em.eval_matches(predictions, 'gold', 'predicted') - # em.print_eval_summary(eval_result) - # indicators = evaluate_prediction(predictions, 'gold', 'predicted', matching_number, candidate_for_train_test) - # print(indicators) - # - # # 计算可解释性 - # predictions_attrs = [] - # predictions_attrs.extend(attrs_with_l_prefix) - # predictions_attrs.extend(attrs_with_r_prefix) - # predictions_attrs.extend(['gold', 'predicted']) - # predictions = predictions[predictions_attrs] - # process_prediction_for_md_discovery(predictions) - # predictions = predictions.reset_index(drop=True) - # predictions = predictions.astype(str) - # sim_tensor_dict = build_col_pairs_sim_tensor_dict(predictions) - # - # # 默认路径为 "../md_discovery/output/xxx.txt" - # # mds/vio 共2个md文件 - # md_discover(config) - # md_paths = [md_output_dir + 'mds.txt', md_output_dir + 'vio.txt'] - # md_list = load_mds(md_paths) # 从全局变量中读取所有的md - # epl_match = 0 # 可解释，预测match - # if len(md_list) > 0: - # for line in predictions.itertuples(): - # if is_explicable(line, md_list, sim_tensor_dict) and str(getattr(line, 'predicted')) == str(1): - # epl_match += 1 - # - # ppre = predictions[predictions['predicted'] == str(1)] - # interpretability = epl_match / len(ppre) # 可解释性 - # - # if (indicators["block_recall"] < 0.8) and (indicators["block_recall"] < indicators["recall"]): - # f1 = (2.0 * indicators["precision"] * indicators["block_recall"]) / ( - # indicators["precision"] + indicators["block_recall"]) - # else: - # f1 = indicators["F1"] - # # if indicators["block_recall"] < 0.8: - # # return 1 - # # f1 = indicators["F1"] - # performance = interpre_weight * interpretability + (1 - interpre_weight) * f1 - # print('Interpretability: ', interpretability) - # return 1 - performance - def ml_er_hpo(): classifier = Classifier() @@ -234,7 +45,6 @@ def ml_er_hpo(): with open(hpo_output_dir + "configspace.json", "w") as f: json.dump(dict_configspace, f, indent=4) - # Next, we create an object, holding general information about the run scenario = Scenario( cs, deterministic=True, @@ -244,7 +54,6 @@ def ml_er_hpo(): initial_design = HyperparameterOptimizationFacade.get_initial_design(scenario, n_configs=5) - # Now we use SMAC to find the best hyperparameters smac = HyperparameterOptimizationFacade( scenario, classifier.train, diff --git a/md_discovery/tmp_discover.py b/md_discovery/discovery_executor.py similarity index 68% rename from md_discovery/tmp_discover.py rename to md_discovery/discovery_executor.py index 0421075..6f7fa71 100644 --- a/md_discovery/tmp_discover.py +++ b/md_discovery/discovery_executor.py @@ -1,16 +1,9 @@ -import multiprocessing -import time -from concurrent.futures import ProcessPoolExecutor -from multiprocessing.managers import SharedMemoryManager - import numpy as np import pandas as pd import copy - import torch from ConfigSpace import Configuration from tqdm import tqdm - from settings import model @@ -97,59 +90,58 @@ def pairs_inference(path, target_col, conf: Configuration): md_list.remove(md) violated_mds.append(md) - for vio_md in violated_mds: - # 特殊化左侧 - for col in cols_but_target: - if sims[col] + 0.01 <= 1: - spec_l_md = copy.deepcopy(vio_md) - spec_l_md[col] = simt if sims[col] < simt else sims[col] + 0.01 - if is_minimal(spec_l_md, md_list, target_col): - md_list.append(spec_l_md) - if vio_md not in minimal_vio: - minimal_vio.append(vio_md) # for vio_md in violated_mds: # # 特殊化左侧 # for col in cols_but_target: - # if sims[col] < 1: + # if sims[col] + 0.01 <= 1: # spec_l_md = copy.deepcopy(vio_md) - # if sims[col] < threshold: - # spec_l_md[col] = threshold - # else: - # if sims[col] + 0.01 <= 1: - # spec_l_md[col] = sims[col] + 0.01 - # else: - # spec_l_md[col] = 1 + # spec_l_md[col] = simt if sims[col] < simt else sims[col] + 0.01 # if is_minimal(spec_l_md, md_list, target_col): # md_list.append(spec_l_md) # if vio_md not in minimal_vio: # minimal_vio.append(vio_md) + + for vio_md in violated_mds: + vio_md_support, vio_md_confidence = get_metrics(vio_md, data, sim_tensor, target_col, target_index) + if vio_md_support >= supt: + for col in cols_but_target: + if sims[col] < 1.0: + spec_l_md = copy.deepcopy(vio_md) + if sims[col] < simt: + spec_l_md[col] = simt + else: + if sims[col] + 0.01 <= 1.0: + spec_l_md[col] = sims[col] + 0.01 + else: + spec_l_md[col] = 1.0 + if is_minimal(spec_l_md, md_list, target_col): + md_list.append(spec_l_md) + if vio_md not in minimal_vio: + minimal_vio.append(vio_md) + if len(md_list) == 0: terminate = True break if terminate: break - tmp = [] - for _ in md_list: - if _ not in tmp: - tmp.append(_) - md_list = tmp - if len(md_list) > 0: - for vio in minimal_vio[:]: - if not is_minimal(vio, md_list, target_col): - minimal_vio.remove(vio) - for _ in md_list[:]: - if not is_minimal(_, md_list, target_col): - md_list.remove(_) - - print('mds_list\t', len(md_list), '\n') - print('vio_list\t', len(minimal_vio), '\n') - - if len(minimal_vio) == 0: - return md_list, [] + if len(minimal_vio) > 0: + remove_list = [] + for md in minimal_vio: + support, confidence = get_metrics(md, data, sim_tensor, target_col, target_index) + if confidence < cont: + remove_list.append(md) + for _ in remove_list: + minimal_vio.remove(_) - remove_list = [] if len(md_list) > 0: + # 去除重复MD + tmp = [] + for _ in md_list: + if _ not in tmp: + tmp.append(_) + md_list = tmp + # 去除support小于阈值MD md_rm_list = [] for _ in md_list: support, confidence = get_metrics(_, data, sim_tensor, target_col, target_index) @@ -157,23 +149,23 @@ def pairs_inference(path, target_col, conf: Configuration): md_rm_list.append(_) for _ in md_rm_list: md_list.remove(_) - for md in minimal_vio: - support, confidence = get_metrics(md, data, sim_tensor, target_col, target_index) - # fuck.append((support, confidence)) - if support < supt: - remove_list.append(md) - if confidence < cont and md not in remove_list: - remove_list.append(md) - # fuck_me = sorted(fuck, key=lambda x: x[1], reverse=True) - for _ in remove_list: - minimal_vio.remove(_) - - for _ in minimal_vio[:]: - if not is_minimal(_, minimal_vio, target_col): - minimal_vio.remove(_) + # 去除不minimal的MD + for _ in md_list[:]: + if not is_minimal(_, md_list, target_col): + md_list.remove(_) + if len(minimal_vio) > 0: + for vio in minimal_vio[:]: + if not is_minimal(vio, md_list, target_col): + minimal_vio.remove(vio) + + if len(minimal_vio) > 0: + for _ in minimal_vio[:]: + if not is_minimal(_, minimal_vio, target_col): + minimal_vio.remove(_) - print('\033[31m' + 'vio_length\t' + str(len(minimal_vio)) + '\033[0m') - print(f"Support: {supt}\tConfidence: {cont}") + print(f'\033[33mList Length: {len(md_list)}\033[0m') + print(f'\033[33mVio Length: {len(minimal_vio)}\033[0m') + print(f'\033[33mSupport: {supt}\tConfidence: {cont}\033[0m') return md_list, minimal_vio @@ -196,11 +188,11 @@ def get_metrics(current_md, data, sim_tensor, target_col, target_index): sup_tensor_slice = sup_tensor[i] ini_slice = torch.logical_and(ini_slice, sup_tensor_slice) sup_tensor_int = ini_slice.int() - support = torch.count_nonzero(sup_tensor_int).item() + support_Naumann = torch.count_nonzero(sup_tensor_int).item() ini_slice = torch.logical_and(ini_slice, sup_tensor[target_index]) conf_tensor_int = ini_slice.int() - confidence_numerator = torch.count_nonzero(conf_tensor_int).item() - confidence = confidence_numerator / support + support_Fan = torch.count_nonzero(conf_tensor_int).item() + confidence = support_Fan / support_Naumann - return support, confidence + return support_Fan, confidence diff --git a/md_discovery/md_discover.py b/md_discovery/md_discover.py index 102b497..731b1f6 100644 --- a/md_discovery/md_discover.py +++ b/md_discovery/md_discover.py @@ -1,6 +1,6 @@ from ConfigSpace import Configuration -from md_discovery import tmp_discover +from md_discovery.discovery_executor import pairs_inference from settings import * # # 若不输出support和confidence，使用以下两块代码 @@ -21,7 +21,7 @@ def md_discover(config: Configuration): t_single_tuple_path = er_output_dir + "t_single_tuple.csv" # 输入：csv文件路径，md左侧相似度阈值，md右侧目标字段 # 输出：2个md列表，列表1中md无violation,列表2中md有violation但confidence满足阈值 - mds_list, vio_list = tmp_discover.pairs_inference(t_single_tuple_path, target_attr, config) + mds_list, vio_list = pairs_inference(t_single_tuple_path, target_attr, config) # 将列表1写入本地，路径需自己修改 mds_path = md_output_dir + "mds.txt" diff --git a/ml_er/ml_entity_resolver.py b/ml_er/ml_entity_resolver.py index 848656b..af31283 100644 --- a/ml_er/ml_entity_resolver.py +++ b/ml_er/ml_entity_resolver.py @@ -184,7 +184,7 @@ def er_process(config: Configuration): candidate = blocker.block_tables(selected_ltable, selected_rtable, config["block_attr"], config["block_attr"], allow_missing=True, l_output_attrs=selected_attrs, r_output_attrs=selected_attrs, - overlap_size=config["overlap_size"], show_progress=False) + overlap_size=1, show_progress=False) elif config["ml_blocker"] == "attr_equiv": blocker = em.AttrEquivalenceBlocker() candidate = blocker.block_tables(selected_ltable, selected_rtable, config["block_attr"], @@ -336,7 +336,6 @@ def ml_er(config: Configuration = None): f.write('performance:' + str(indicators['performance']) + '\n') - if __name__ == '__main__': if os.path.isfile(hpo_output_dir + "incumbent.json"): with open(hpo_output_dir + "configspace.json", 'r') as f: diff --git a/settings.py b/settings.py index ff43696..7f629b3 100644 --- a/settings.py +++ b/settings.py @@ -1,11 +1,10 @@ from sentence_transformers import SentenceTransformer -import numpy as np -ltable_path = r'E:\Data\Research\Projects\matching_dependency\datasets\Abt-Buy\tableA.csv' -rtable_path = r'E:\Data\Research\Projects\matching_dependency\datasets\Abt-Buy\tableB.csv' -mapping_path = r'E:\Data\Research\Projects\matching_dependency\datasets\Abt-Buy\matches.csv' -mapping_lid = 'idAbt' # mapping表中左表id名 -mapping_rid = 'idBuy' # mapping表中右表id名 +ltable_path = r'E:\Data\Research\Projects\matching_dependency\datasets\Fodors-Zagats\tableA.csv' +rtable_path = r'E:\Data\Research\Projects\matching_dependency\datasets\Fodors-Zagats\tableB.csv' +mapping_path = r'E:\Data\Research\Projects\matching_dependency\datasets\Fodors-Zagats\matches.csv' +mapping_lid = 'ltable_id' # mapping表中左表id名 +mapping_rid = 'rtable_id' # mapping表中右表id名 ltable_id = 'id' # 左表id字段名称 rtable_id = 'id' # 右表id字段名称 target_attr = 'id' # 进行md挖掘时的目标字段 diff --git a/tfile.py b/tfile.py index 63d77ee..4857ddb 100644 --- a/tfile.py +++ b/tfile.py @@ -9,7 +9,7 @@ import pandas as pd import torch from tqdm import tqdm from ConfigSpace.read_and_write import json as csj -from md_discovery import tmp_discover +from md_discovery import discovery_executor from settings import er_output_dir, hpo_output_dir