固定MD挖掘的阈值，使用训练集挖掘MD

使用GPU穷举后采样挖掘法

draw.py

@@ -1,55 +0,0 @@
-import os
-
-import pyecharts
-from pyecharts.charts import Line
-from pyecharts import options as opts
-from pyecharts.globals import ThemeType
-
-if __name__ == '__main__':
-    dir_path = r'E:\Data\Research\Outcome\Walmart-Amazon_dirty'
-    filename_list = os.listdir(dir_path)
-    iter_list = []
-    precision = []
-    recall = []
-    f1 = []
-    interpretability = []
-    performance = []
-    for _ in filename_list:
-        if _.startswith('eval_result'):
-            it = int(_[12:13])
-            iter_list.append(str(it))
-            with open(dir_path + '\\' + _, 'r') as f:
-                # 读取每一行的md，加入该文件的md列表
-                for line in f.readlines():
-                    if line.startswith('Precision'):
-                        lt = line.split(' ')
-                        value = float(lt[2].replace('%', ''))/100
-                        precision.append(value)
-                    elif line.startswith('Recall'):
-                        lt = line.split(' ')
-                        value = float(lt[2].replace('%', ''))/100
-                        recall.append(value)
-                    elif line.startswith('F1'):
-                        lt = line.split(' ')
-                        value = float(lt[2].replace('%', ''))/100
-                        f1.append(value)
-                    elif line.startswith('interpretability'):
-                        lt = line.split(':')
-                        value = float(lt[1])
-                        interpretability.append(value)
-                    elif line.startswith('performance'):
-                        lt = line.split(':')
-                        value = float(lt[1])
-                        performance.append(value)
-
-    line = (
-        Line(init_opts=opts.InitOpts(theme=ThemeType.LIGHT))
-        .add_xaxis(iter_list)
-        .add_yaxis('Precision', precision)
-        .add_yaxis('Recall', recall)
-        .add_yaxis('F1', f1)
-        .add_yaxis('Interpretability', interpretability)
-        .add_yaxis('Performance', performance)
-        .set_global_opts(title_opts=opts.TitleOpts(title=dir_path.split('\\')[-1]))
-    )
-    line.render(dir_path + '\\' + "line.html")

draw/draw_confidence_histogram.py

@@ -0,0 +1,54 @@
+import os
+import pandas as pd
+from pyecharts import options as opts
+from pyecharts.charts import Bar
+from pyecharts.faker import Faker
+from pyecharts.globals import ThemeType
+
+if __name__ == '__main__':
+    outcome_dir = r'E:\Data\Research\Outcome'
+    configs_dir = r'\Magellan+Smac+roberta-large-nli-stsb-mean-tokens'
+    datasets_list = os.listdir(outcome_dir)
+
+    for _ in datasets_list:
+        path = outcome_dir + rf'\{_}' + configs_dir
+        statistics_files = os.listdir(path)
+        length = 0
+        for file in statistics_files:
+            if file.startswith('predictions'):
+                preds = pd.read_csv(path + rf'\{file}', encoding='ISO-8859-1')
+                preds = preds[['predicted', 'confidence']]
+                preds = preds.astype(float)
+                preds = preds[preds['predicted'] == 1.0]
+                length = len(preds)
+                li = []
+                zeros = len(preds[preds['confidence'] == 0])
+                dot_02 = len(preds[(preds['confidence'] > 0) & (preds['confidence'] <= 0.2)])
+                dot_24 = len(preds[(preds['confidence'] > 0.2) & (preds['confidence'] <= 0.4)])
+                dot_46 = len(preds[(preds['confidence'] > 0.4) & (preds['confidence'] <= 0.6)])
+                dot_68 = len(preds[(preds['confidence'] > 0.6) & (preds['confidence'] <= 0.8)])
+                dot_80 = len(preds[(preds['confidence'] > 0.8) & (preds['confidence'] <= 1.0)])
+                for number in [zeros, dot_02, dot_24, dot_46, dot_68, dot_80]:
+                    li.append(round(number * 100 / length, ndigits=3))
+
+                c = (
+                    Bar(init_opts=opts.InitOpts(theme=ThemeType.WALDEN))
+                    .add_xaxis(['conf=0', '0<conf≤0.2', '0.2<conf≤0.4', '0.4<conf≤0.6', '0.6<conf≤0.8', '0.8<conf≤1'])
+                    .add_yaxis(_, li, category_gap=2)
+                    .set_global_opts(
+                        yaxis_opts=opts.AxisOpts(
+                            name="Proportion",
+                            type_="value",
+                            min_=0,
+                            max_=100,
+                            position="left",
+                            axisline_opts=opts.AxisLineOpts(
+                                linestyle_opts=opts.LineStyleOpts()
+                            ),
+                            axislabel_opts=opts.LabelOpts(formatter="{value}%"),
+                        ),
+                        title_opts=opts.TitleOpts(title="Confidence Histogram"),
+                        xaxis_opts=opts.AxisOpts(name="Intervals")
+                    )
+                    .render(path + r"\confidence_histogram.html")
+                )

draw/draw_f1_inter_bars.py

@@ -0,0 +1,44 @@
+import os
+
+import pyecharts
+from pyecharts.charts import Line
+from pyecharts import options as opts
+from pyecharts.charts import Bar
+from pyecharts.globals import ThemeType
+
+if __name__ == '__main__':
+    outcome_dir = r'E:\Data\Research\Outcome'
+    configs_dir = r'\Magellan+Smac+roberta-large-nli-stsb-mean-tokens'
+    datasets_list = os.listdir(outcome_dir)
+    f1 = []
+    interpretability = []
+    for _ in datasets_list:
+        path = outcome_dir + rf'\{_}' + configs_dir
+        statistics_files = os.listdir(path)
+        for i in statistics_files:
+            if i.startswith('eval_result'):
+                with open(path + rf'\{i}', 'r') as f:
+                    # 读取每一行的md，加入该文件的md列表
+                    for line in f.readlines():
+                        if line.startswith('F1'):
+                            lt = line.split(' ')
+                            value = float(lt[2].replace('%', ''))/100
+                            f1.append(round(value, ndigits=3))
+                        elif line.startswith('interpretability'):
+                            lt = line.split(':')
+                            value = float(lt[1])
+                            interpretability.append(round(value, ndigits=3))
+
+    c = (
+        Bar()
+        .add_xaxis(
+            datasets_list
+        )
+        .add_yaxis('F1', f1)
+        .add_yaxis('Interpretability', interpretability)
+        .set_global_opts(
+            xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-15)),
+            title_opts=opts.TitleOpts(title="各数据集F1值与预测结果可解释比例", subtitle="可解释性比重：0.5"),
+        )
+        .render("output/F1_Inter_bars.html")
+    )

hpo/er_model_hpo.py

@@ -12,7 +12,6 @@ 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()
@@ -22,12 +21,8 @@ class Classifier:
         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", (0.25, 0.5), default=0.25)
 
-        cs.add_hyperparameters([block_attr, ml_matcher, ml_blocker, similarity_thresh,
-                                support_thresh, confidence_thresh])
+        cs.add_hyperparameters([block_attr, ml_matcher, ml_blocker])
         return cs
 
     def train(self, config: Configuration, seed: int = 0) -> float:
@@ -47,8 +42,7 @@ def ml_er_hpo():
     scenario = Scenario(
         cs,
         deterministic=True,
-        n_trials=50,  # We want to run max 50 trials (combination of config and seed)
-        walltime_limit=28800,  # Max time limit in seconds (14400s = 4h)
+        n_trials=12,  # We want to run max 50 trials (combination of config and seed)
         n_workers=1
     )
 

md_discovery/discovery_executor.py

@@ -6,7 +6,7 @@ import copy
 import torch
 from ConfigSpace import Configuration
 from tqdm import tqdm
-from settings import model
+from settings import model, similarity_threshold, support_threshold, confidence_threshold
 
 
 def is_minimal(md, md_list, target_col):
@@ -36,11 +36,7 @@ def is_minimal(md, md_list, target_col):
     return minimal
 
 
-def pairs_inference(path, target_col, conf: Configuration):
-    simt = conf["similarity_thresh"]
-    # simt = round(simt, ndigits=3)
-    supt = conf["support_thresh"]
-    cont = conf["confidence_thresh"]
+def pairs_inference(path, target_col):
     data = pd.read_csv(path, low_memory=False, encoding='ISO-8859-1')
     data.fillna("", inplace=True)
     data = data.astype(str)
@@ -109,12 +105,12 @@ def pairs_inference(path, target_col, conf: Configuration):
 
             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:
+                if vio_md_support >= support_threshold:
                     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
+                            if sims[col] < similarity_threshold:
+                                spec_l_md[col] = similarity_threshold
                             else:
                                 if sims[col] + 0.01 <= 1.0:
                                     spec_l_md[col] = sims[col] + 0.01
@@ -134,7 +130,7 @@ def pairs_inference(path, target_col, conf: Configuration):
     if len(minimal_vio) > 0:
         for md in minimal_vio[:]:
             support, confidence = get_metrics(md, data, sim_tensor, target_col, target_index)
-            if support >= supt and confidence >= cont:
+            if support >= support_threshold and confidence >= confidence_threshold:
                 minimal_vio.append((md, support, confidence))
             minimal_vio.remove(md)
 
@@ -148,7 +144,7 @@ def pairs_inference(path, target_col, conf: Configuration):
         # 去除support小于阈值MD
         for _ in md_list[:]:
             support, confidence = get_metrics(_, data, sim_tensor, target_col, target_index)
-            if support >= supt and confidence >= cont:
+            if support >= support_threshold and confidence >= confidence_threshold:
                 md_list.append((_, support, confidence))
             md_list.remove(_)
         # 去除不minimal的MD
@@ -170,7 +166,6 @@ def pairs_inference(path, target_col, conf: Configuration):
     result.extend(minimal_vio)
     result.sort(key=operator.itemgetter(2), reverse=True)
     print(f'\033[33mList Length: {len(result)}\033[0m')
-    print(f'\033[33mSupport: {supt}\tConfidence: {cont}\033[0m')
     return result
 
 

md_discovery/discovery_executor_gpu.py

@@ -0,0 +1,138 @@
+import math
+import operator
+import random
+import time
+from tqdm import tqdm
+import numpy as np
+import pandas as pd
+import torch
+
+from settings import model, similarity_threshold, support_threshold, confidence_threshold, md_output_dir
+
+sample_number = 100000
+step_length = 0.01
+
+def get_metrics(md_tensor, data, sim_tensor, target_index):
+    length = data.shape[0]
+    width = data.shape[1]
+
+    # md_tensor = list(current_md.values())
+    # md_tensor = torch.tensor(md_tensor, device='cuda')
+    md_tensor_2d = md_tensor.unsqueeze(1)
+    md_tensor_3d = md_tensor_2d.unsqueeze(2)
+    md_tensor_3d = md_tensor_3d.repeat(1, length, length)
+
+    sim_tensor = torch.round(sim_tensor, decimals=4)
+
+    sup_tensor = torch.ge(sim_tensor, md_tensor_3d)
+    ini_slice = torch.ones((length, length), dtype=torch.bool, device='cuda')
+    for i in range(0, width):
+        if i != 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_Naumann = torch.count_nonzero(sup_tensor_int).item()
+    support_Naumann = (support_Naumann - length) / 2
+
+    conf_tensor = torch.logical_and(ini_slice, sup_tensor[target_index])
+    conf_tensor_int = conf_tensor.int()
+    support_Fan = torch.count_nonzero(conf_tensor_int).item()
+    support_Fan = (support_Fan - length) / 2
+    confidence = support_Fan / support_Naumann if support_Naumann > 0 else 0
+
+    return support_Fan, confidence
+
+
+def build_cartesian(width, target_index):
+    all_values_array = np.linspace(start=similarity_threshold, stop=1, endpoint=True,
+                                   num=math.ceil((1-similarity_threshold)/step_length) + 1)
+    all_values_array = np.round(all_values_array, 4)
+    all_values_tensor = torch.tensor(all_values_array, device='cuda')
+    all_values_tensor = all_values_tensor.float()
+    all_values_tensor = torch.round(all_values_tensor, decimals=4)
+    tensors_for_cartesian = []
+    for i in range(0, width):
+        if i == target_index:
+            t = torch.tensor([1.0], device='cuda')
+            tensors_for_cartesian.append(t)
+        else:
+            tensors_for_cartesian.append(all_values_tensor)
+    result = torch.cartesian_prod(*tensors_for_cartesian)
+    return result
+
+
+def get_metric_tensor(cartesian_product, data, sim_tensor, target_index):
+    length = data.shape[0]
+    width = data.shape[1]
+    cartesian_product = cartesian_product.unsqueeze(2)
+    cartesian_product = cartesian_product.unsqueeze(3)
+    cartesian_product = cartesian_product.repeat(1, 1, length, length)
+
+
+def discover(path, target_col):
+    data = pd.read_csv(path, low_memory=False, encoding='ISO-8859-1')
+    data.fillna("", inplace=True)
+    data = data.astype(str)
+    columns = data.columns.values.tolist()
+    target_index = columns.index(target_col)
+    cols_but_target = list(set(columns) - {target_col})
+    length = data.shape[0]
+    width = data.shape[1]
+    # 除了目标列外所有列的索引
+    columns_indices = [_ for _ in range(0, width) if _ != target_index]
+
+    sentences = []
+    for col in range(0, width):
+        for row in range(0, length):
+            cell_value = data.values[row, col]
+            sentences.append(cell_value)
+    embedding = model.encode(sentences, convert_to_tensor=True, device="cuda")
+    split_embedding = torch.split(embedding, length, dim=0)
+    table_tensor = torch.stack(split_embedding, dim=0, out=None)
+    norm_table_tensor = torch.nn.functional.normalize(table_tensor, dim=2)
+    sim_tensor = torch.matmul(norm_table_tensor, norm_table_tensor.transpose(1, 2))
+    sim_tensor = sim_tensor.float()
+    sim_tensor = torch.round(sim_tensor, decimals=4)
+
+    # 小于6列的可以尝试做笛卡尔积，大于6列可能指数爆炸
+    if width <= 6:
+        # 列出除目标列以外所有列的所有取值，做笛卡尔积，结果为所有可能MD取值
+        cartesian = build_cartesian(width, target_index)
+        # 抽取sample_number / (width - 1)条MD，不含-1
+        if cartesian.shape[0] > sample_number / (width - 1):
+            index = torch.tensor(random.sample(range(cartesian.shape[0]), math.ceil(sample_number / (width - 1))), device='cuda')
+            cartesian = torch.index_select(cartesian, 0, index)
+    else:
+        # 随机生成sample_number / (width - 1)条MD，使用randint先转化为int再除成小数，不含-1
+        cartesian = torch.randint(int(similarity_threshold * 100), 1 * 100,
+                                  (math.ceil(sample_number / (width - 1)), width - 1), device='cuda')
+        cartesian = cartesian / 100
+        # 生成一列相似度为1的目标列，插入目标列所在位置
+        ones = torch.ones((math.ceil(sample_number / (width - 1)), 1), device='cuda')
+        cartesian = torch.cat((cartesian[:, 0:target_index], ones, cartesian[:, target_index:]), 1)
+        cartesian = torch.round(cartesian, decimals=4)
+    # 此tensor将与其他置为-1的tensor拼接
+    joint_md_tensor = cartesian.clone()
+    # 随机将1列，2列……置为-1
+    for i in range(width - 2):
+        index_list_format = []
+        for j in range(cartesian.shape[0]):
+            # 对每条MD，随机选择将要置为-1的列索引
+            index_list_format.append(random.sample(columns_indices, i + 1))
+        index = torch.tensor(index_list_format, device='cuda')
+        # 随机调整为-1后的MD集合
+        modified_cartesian = cartesian.scatter(1, index, -1)
+        joint_md_tensor = torch.cat((joint_md_tensor, modified_cartesian), 0)
+
+    md_list = []
+    # get_metric_tensor(cartesian, data, sim_tensor, target_index)
+    for _ in tqdm(range(joint_md_tensor.shape[0])):
+        s, c = get_metrics(joint_md_tensor[_], data, sim_tensor, target_index)
+        if s >= support_threshold and c >= confidence_threshold:
+            md_list_format = [round(i, 4) for i in joint_md_tensor[_].tolist()]
+            md_dict_format = {}
+            for k in range(0, width):
+                md_dict_format[columns[k]] = md_list_format[k]
+            md_list.append((md_dict_format, s, c))
+    md_list.sort(key=operator.itemgetter(2), reverse=True)
+    return md_list

md_discovery/md_discover.py

@@ -1,6 +1,7 @@
 from ConfigSpace import Configuration
 
 from md_discovery.discovery_executor import pairs_inference
+from md_discovery.discovery_executor_gpu import discover
 from settings import *
 
 # # 若不输出support和confidence，使用以下两块代码
@@ -17,16 +18,12 @@ from settings import *
 #         f.write(str(_) + '\n')
 
 
-def md_discover(config: Configuration):
-    t_single_tuple_path = er_output_dir + "t_single_tuple.csv"
+def md_discover(config: Configuration, source_path, target_path):
     # 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 = 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"
-    
-    with open(mds_path, 'w') as f:
+    # mds_list = pairs_inference(source_path, target_attr)
+    mds_list = discover(source_path, target_attr)
+    with open(target_path, 'w') as f:
         for _ in mds_list:
             f.write('Target:'+str(target_attr) + '\t')
             f.write(str(_))

ml_er/ml_entity_resolver.py

@@ -1,6 +1,7 @@
 import json
 import os
 import sys
+import time
 
 import ConfigSpace
 import pandas
@@ -12,28 +13,24 @@ import py_entitymatching.catalog.catalog_manager as cm
 import pandas as pd
 import six
 from ConfigSpace import Configuration
+from tqdm import tqdm
 
 from md_discovery.md_discover import md_discover
 from settings import *
 
 
-def process_prediction_for_md_discovery(pred: pd.DataFrame,
-                                        t_single_tuple_path: str = er_output_dir + "t_single_tuple.csv"):
-    # 提取预测表中真阳和假阴部分
-    tp = pred[(pred['gold'] == 1) & (pred['predicted'] == 1)]
-    fn = pred[(pred['gold'] == 1) & (pred['predicted'] == 0)]
-    # 拼成一张表
-    df = pd.concat([tp, fn])
-    # 将真阳/假阴表中左右ID调整一致
+def prepare_file_for_md_discovery(train, t_single_tuple_path=er_output_dir + "t_single_tuple.csv"):
+    df = train[train['gold'] == 1]
+    # 元组对左右ID调整一致
     for index, row in df.iterrows():
         df.loc[index, "rtable_" + rtable_id] = row["ltable_" + rtable_id]
 
-    pred_columns = pred.columns.values.tolist()
+    train_columns = train.columns.values.tolist()
     l_columns = []
     r_columns = []
     cols = []
-    # 将预测表中左表和右表字段名分别加入两个列表
-    for _ in pred_columns:
+    # 左表和右表字段名分别加入两个列表
+    for _ in train_columns:
         if _.startswith('ltable'):
             l_columns.append(_)
         elif _.startswith('rtable'):
@@ -47,6 +44,7 @@ def process_prediction_for_md_discovery(pred: pd.DataFrame,
     ldf.columns = cols
     rdf.columns = cols
     t_single_tuple = pd.concat([ldf, rdf])
+    t_single_tuple = t_single_tuple.reset_index(drop=True)
 
     t_single_tuple.to_csv(t_single_tuple_path, sep=',', index=False, header=True, quoting=1)
 
@@ -148,6 +146,7 @@ def build_col_pairs_sim_tensor_dict(predictions: pandas.DataFrame):
 
 
 def er_process(config: Configuration):
+    start = time.time()
     ltable = pd.read_csv(ltable_path, encoding='ISO-8859-1')
     cm.set_key(ltable, ltable_id)
     # ltable.fillna("", inplace=True)
@@ -295,27 +294,42 @@ def er_process(config: Configuration):
     predictions_attrs.extend(attrs_with_r_prefix)
     predictions_attrs.extend(['gold', 'predicted'])
     predictions = predictions[predictions_attrs]
-    process_prediction_for_md_discovery(predictions)
+    train_attrs = predictions_attrs[:]
+    train_attrs.remove('predicted')
+    train_set = train_set[train_attrs]
+    prepare_file_for_md_discovery(train_set)
     predictions = predictions.reset_index(drop=True)
     predictions = predictions.astype(str)
     sim_tensor_dict = build_col_pairs_sim_tensor_dict(predictions)
     predictions['confidence'] = 0
 
-    md_discover(config)
+    md_discover(config, er_output_dir + "t_single_tuple.csv", md_output_dir + "mds.txt")
     md_paths = [md_output_dir + 'mds.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
+
+    unexplainable = pd.DataFrame()
+
     if len(md_list) > 0:
-        for row in predictions.itertuples():
+        for row in tqdm(predictions.itertuples()):
             x = is_explicable(row, md_list, sim_tensor_dict)
             if x > 0 and str(getattr(row, 'predicted')) == str(1):
                 predictions.loc[row[0], 'confidence'] = x
                 epl_match += 1
+        #     else:
+        #         series = pd.Series(row)
+        #         unexplainable = unexplainable._append(series, ignore_index=True)
+        # unexplainable.drop(columns=unexplainable.columns[[-1, 0]], inplace=True)
+        # unexplainable.columns = predictions_attrs
+        # unexplainable = unexplainable[train_attrs]
+        # if len(unexplainable[unexplainable['gold'] == str(1)]) > 0:
+        #     prepare_file_for_md_discovery(unexplainable, t_single_tuple_path=er_output_dir + 'unexplainable_tst.csv')
+        #     md_discover(config, er_output_dir + 'unexplainable_tst.csv', md_output_dir + "from_unexplainable.txt")
 
     df = predictions[predictions['predicted'] == str(1)]
     interpretability = epl_match / len(df)  # 可解释性
     indicators['interpretability'] = interpretability
-    if (indicators["block_recall"] < 0.8) and (indicators["block_recall"] < indicators["recall"]):
+    if indicators["block_recall"] < indicators["recall"]:
         f1 = (2.0 * indicators["precision"] * indicators["block_recall"]) / (
                     indicators["precision"] + indicators["block_recall"])
     else:
@@ -326,6 +340,7 @@ def er_process(config: Configuration):
     print(indicators)
     predictions.to_csv(er_output_dir + 'predictions.csv', sep=',', index=False, header=True)
     ################################################################################################################
+    print(f'\033[33mTime consumed by ML-ER in seconds: {time.time() - start}\033[0m')
     return indicators
 
 

settings.py

@@ -1,10 +1,10 @@
 from sentence_transformers import SentenceTransformer
 
-ltable_path = r'E:\Data\Research\Projects\matching_dependency\datasets\Amazon-Google\Amazon.csv'
-rtable_path = r'E:\Data\Research\Projects\matching_dependency\datasets\Amazon-Google\GoogleProducts.csv'
-mapping_path = r'E:\Data\Research\Projects\matching_dependency\datasets\Amazon-Google\Mapping.csv'
-mapping_lid = 'idAmazon'  # mapping表中左表id名
-mapping_rid = 'idGoogleBase'  # mapping表中右表id名
+ltable_path = r'E:\Data\Research\Projects\matching_dependency\datasets\DBLP-GoogleScholar\tableA.csv'
+rtable_path = r'E:\Data\Research\Projects\matching_dependency\datasets\DBLP-GoogleScholar\tableB.csv'
+mapping_path = r'E:\Data\Research\Projects\matching_dependency\datasets\DBLP-GoogleScholar\matches.csv'
+mapping_lid = 'idDBLP'  # mapping表中左表id名
+mapping_rid = 'idScholar'  # 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
@@ -12,9 +12,9 @@ target_attr = 'id'  # 进行md挖掘时的目标字段
 
 model = SentenceTransformer('E:\\Data\\Research\\Models\\roberta-large-nli-stsb-mean-tokens')
 interpre_weight = 0.5  # 可解释性权重
-# similarity_threshold = 0.2
-# support_threshold = 100
-# confidence_threshold = 0.4
+similarity_threshold = 0.1
+support_threshold = 1
+confidence_threshold = 0.25
 
 er_output_dir = 'E:\\Data\\Research\\Projects\\matching_dependency\\ml_er\\output\\'
 md_output_dir = 'E:\\Data\\Research\\Projects\\matching_dependency\\md_discovery\\output\\'

tfile.py

@@ -147,3 +147,13 @@ def test12():
         dic = json.load(f)
     for _ in dic.keys():
         print(f'Key:{_}\tValue:{dic[_]}\tType:{type(dic[_])}')
+
+
+def test13():
+    outcome_dir = r'E:\Data\Research\Outcome'
+    configs_dir = r'\Magellan+Smac+roberta-large-nli-stsb-mean-tokens'
+    datasets_list = os.listdir(outcome_dir)
+    f = []
+    for _ in datasets_list:
+        f.append(outcome_dir + rf'\{_}' + configs_dir)
+    print(f)