MCPcopy Create free account

hub / github.com/BIT-DataLab/LakeBench / functions

Functions1,080 in github.com/BIT-DataLab/LakeBench

⨍ Functions 1,080◇ Types & classes 68
Methodinsert
(self, key, *vals, **kwargs)
join/LSH/datasketch/storage.py:1034
Methodinsert
Insert a unique key to the index, together with a MinHash (or weighted MinHash) of the set referenced by the key. Ar
join/LSH/datasketch/lsh.py:368
Functioninverse1_pivot_based_mapping
(d, pivots)
join/Pexeso/Pivot_Metric.py:311
FunctioninverseSetFrequency
(freq)
join/Joise/online/common.py:14
Functioninverse_pivot_based_mapping
(d, pivots)
join/Pexeso/Pivot_Metric.py:102
Functioninverse_pivot_based_mapping1
(d, pivots)
join/Pexeso/Pivot_Metric.py:111
Methodis_empty
Returns: bool: If the current MinHash is empty - at the state of just initialized.
join/LSH/datasketch/minhash.py:230
Methodis_empty
Returns: bool: Check if the index is empty.
join/LSH/datasketch/lsh.py:287
Methoditemcounts
Returns a dict where the keys are the keys of the container. The values are the *lengths* of the value sequences stored in this contai
join/LSH/datasketch/storage.py:230
Methoditemcounts
Implement interface.
join/LSH/datasketch/storage.py:849
Methoditemcounts
(self)
join/LSH/datasketch/storage.py:1053
Methodkeys
(self)
join/LSH/datasketch/storage.py:211
Methodless
(self, i,j)
join/Joise/online/josie_util.py:78
Methodless
(self, other)
join/Joise/online/josie_util.py:96
Methodless
(self, other)
join/Joise/online/josie_util.py:112
FunctionloadDictionaryFromCsvFile
(filePath)
union/Santos/generalFunctions.py:133
FunctionloadDictionaryFromCsvFile
(filePath)
union/TUS/generalFunctions.py:133
FunctionloadDictionaryFromPickleFile
(dictionaryPath)
union/Santos/generalFunctions.py:119
FunctionloadDictionaryFromPickleFile
(dictionaryPath)
union/TUS/generalFunctions.py:119
Methodlsh_parameters
(self)
union/D3L/d3l/indexing/lsh/lsh_index.py:132
Functionmain
()
union/TUS/run_c_alignment.py:223
Functionmain
()
union/TUS/santos_annotation.py:113
Functionmatch_entity_from_yago
()
union/TUS/Usem.py:40
Functionmatch_yago_entity_from_yago_lsh_thread
(lsh)
union/TUS/Usem.py:157
Functionmerge_dicts
(dict1, path)
union/Santos/data_lake_processing_yago_mv.py:26
Functionmerge_dicts_list
(dict_list)
join&union/InfoGather/util.py:107
Functionminhash_Lsh_forest
(type='Uset', folder_path = 'benchmark', t = 0.7, n = 128)
union/TUS/Uset.py:73
Functionminhash_Lsh_forest
(type='Uset', folder_path = 'benchmark', t = 0.7, n = 128)
union/TUS/Uset_run.py:70
Functionminhash_Lsh_forest
(type='Uset', folder_path = 'benchmark', t = 0.7, n = 128)
union/TUS/query.py:73
Functionminhash_multi_process
(folder_path, file_list, q, spl, id, n, type, t)
union/TUS/Uset.py:121
Functionminhash_multi_process
(folder_path, file_list, q, spl, id, n, type, t)
union/TUS/query.py:121
Functionminhash_multi_process
(split_num, q, param_dic, id)
union/D3L/d3l/indexing/similarity_indexes/__init__.py:269
Functionminhash_multi_process
(file_list, q, param_dic, id)
join/LSH/LSH_benchmark_os.py:162
Functionminhash_multi_process
(file_list, q, param_dic, id)
join/LSH/LSH_benchmark_ws.py:161
Functionminhash_multi_process
(file_list, q, param_dic, id)
join/LSH/LSH_benchmark_ol.py:162
Functionminhash_multi_process
(file_list, q, param_dic, id)
join/LSH/LSH_benchmark_wl.py:167
Functionminhash_multi_process
(file_list, q, param_dic, id)
join/LSH/LSH_benchmark_wlq.py:166
Functionminhash_multi_process
(set_path, file_list, q, param_dic, id)
join/LSH/new copy.py:141
Functionminhash_multi_process_dis
(split_num, q, param_dic, id)
union/D3L/d3l/indexing/similarity_indexes/__init__.py:809
Functionminhash_multi_process_name
(split_num, q, param_dic, id)
union/D3L/d3l/indexing/similarity_indexes/__init__.py:86
Functionmulti
(file_ls,queue,query_result,query_folder_path, query_label_folder_path, fnames, can_label_second_column, can
join&union/Frt12/online_process/all_schema_com10.py:362
Functionmulti
(file_ls,queue,query_result,max_k)
join&union/Frt12/online_process/test1.py:298
Functionmulti
(file_ls,queue,query_result,query_folder_path, query_label_folder_path, fnames, can_label_second_column, can
join&union/Frt12/online_process/t2_paral.py:360
Functionmulti
(file_ls,queue,query_result,query_folder_path, query_label_folder_path, fnames, can_label_second_column, can
join&union/Frt12/online_process/all_schema_com25.py:362
Functionmulti
(file_ls,queue,query_result,query_folder_path, query_label_folder_path, fnames, can_label_second_column, can
join&union/Frt12/online_process/all_schema_com30.py:362
Functionmulti
(file_ls,queue,query_result,query_folder_path, query_label_folder_path, fnames, can_label_second_column, can
join&union/Frt12/online_process/all_schema_com5.py:362
Functionmulti
(file_ls,queue,query_result,query_folder_path, query_label_folder_path, fnames, can_label_second_column, can
join&union/Frt12/online_process/all_schema_com20.py:362
Functionmulti
(file_ls,queue,query_result,query_folder_path, query_label_folder_path, fnames, can_label_second_column, can
join&union/Frt12/online_process/all_schema_com15.py:362
Methodnormals
(self)
union/D3L/d3l/indexing/hashing/hash_generators.py:239
Methodnormals_csr
(self)
union/D3L/d3l/indexing/hashing/hash_generators.py:243
Methodnum_bins
(self)
union/D3L/d3l/indexing/feature_extraction/values/distribution_transformer.py:22
Functiononline_query
(file_ls,queue,query_result,max_k)
join&union/Frt12/online_process/all_entity_com5.py:144
Functiononline_query
(file_ls,queue,query_result,max_k)
join&union/Frt12/online_process/all_entity_com15.py:144
Functiononline_query
(file_ls,queue,query_result,max_k)
join&union/Frt12/online_process/test.py:144
Functiononline_query
(file_ls,queue,query_result,max_k)
join&union/Frt12/online_process/all_entity_com10.py:144
Functiononline_query
(file_ls,queue,query_result,max_k)
join&union/Frt12/online_process/all_entity_com20.py:144
Functiononline_query
(file_ls,queue,query_result,max_k)
join&union/Frt12/online_process/all_entity_com25.py:144
Functiononline_query
(file_ls,queue,query_result,max_k)
join&union/Frt12/online_process/all_entity_com30.py:144
FunctionorderedResults
(h)
join/Joise/online/heap.py:61
Functionordered_storage
Return ordered storage system based on the specified config. The canonical example of such a storage container is ``defaultdict(list)``. Thus
join/LSH/datasketch/storage.py:27
Functionoverlap_and_update_counts
(set_tokens, query_tokens, counts)
join/Joise/online/common.py:52
Functionpartition_files
(file_paths, m)
join/Deepjoin/dataprocess/process_table_tosentence.py:71
Methodpermutations
(self)
union/D3L/d3l/indexing/hashing/hash_generators.py:145
Methodpermutations
(self)
union/D3L/d3l/indexing/hashing/hash_generators.py:247
Functionpersonalized_pagerank
(graph, walk_length, num_walks)
join&union/InfoGather/util.py:45
Functionpivot_filtering
Fasle:在同一方格中 True：可以被过滤
join/Pexeso/Pivot_Metric.py:125
Functionpivot_validation
true：可以匹配
join/Pexeso/Pivot_Metric.py:136
FunctionpprMtrix2
(similiar_matrix,main_node,docnum)
join&union/InfoGather/changeParamiter_PPR_opendata.py:12
FunctionpprMtrix2
(similiar_matrix,main_node,docnum)
join&union/InfoGather/changeParamiter_PPR_webtable.py:12
Functionpre_multi_process
(file_list, q, id)
join/LSH/LSH_benchmark_os.py:143
Functionpre_multi_process
(file_list, q, id)
join/LSH/LSH_benchmark_ws.py:142
Functionpre_multi_process
(file_list, q, id)
join/LSH/LSH_benchmark_ol.py:143
Functionpre_multi_process
(file_list, q, id)
join/LSH/LSH_benchmark_wl.py:148
Functionpre_multi_process
(file_list, q, id)
join/LSH/LSH_benchmark_wlq.py:147
Functionpre_multi_process
(set_path, file_list, q, id)
join/LSH/union wl.py:52
Functionpre_multi_process
(set_path, file_list, q, id)
join/LSH/union ws.py:52
Functionpre_multi_process
(set_path, file_list, q, id)
join/LSH/union ol.py:52
Functionpre_multi_process
(set_path, file_list, q, id)
join/LSH/union os.py:52
Functionpre_multi_process
(set_path, file_list, q, id)
join/LSH/new copy.py:122
FunctionpreprocessString
(string)
union/Santos/generalFunctions.py:43
FunctionpreprocessString
(string)
union/TUS/generalFunctions.py:43
Functionprocess_bucket
(bucket_idx, bucket_content)
union/TUS/Unl.py:314
Functionprocess_csv
Args: file_path (): Returns: 是一个字典，key为quary column value 为 join 的lake table columns list
join&union/InfoGather/util.py:122
Functionprocess_dict
(data)
union/Santos/data_lake_processing_synthesized_kb.py:326
Functionprocess_subset
(file_list)
union/TUS/Usem.py:164
Functionprocess_table
(table, label_dict, type_dict, class_dict, save_file_path)
union/TUS/santos_annotation.py:67
Functionprocess_task4
(i,input_values,queue,queue_inforgather,file_dic_path)
join/Deepjoin/dataprocess/process_table_tosentence.py:132
Functionprocess_task4
(input_values,queue,queue_inforgather_train,queue_inforgather_evluate,file_train_path)
join/Deepjoin/dataprocess/multi_preocess_csv.py:79
Functionprocess_value
(value)
union/TUS/Unl.py:148
Functionproduce_data
(args, queue, filepaths, dataset_indices)
join/Deepjoin/all-mpnet-base-v2/train_script.py:168
Functionpruning_power_ub
(freq, k)
join/Joise/online/common.py:10
FunctionpuncRemove
(stringList)
union/Santos/expandSearch.py:9
Methodpush
(self, x)
join/Joise/online/heap.py:19
Methodqgram_size
(self)
union/D3L/d3l/indexing/feature_extraction/schema/qgram_transformer.py:17
Methodquery
Search for the nearest neighbours of the given query. Parameters ---------- query : Any The query that c
union/D3L/d3l/indexing/similarity_indexes/__init__.py:63
Methodquery
Search for the nearest neighbours of the given query. Parameters ---------- query : Iterable[Any] A col
union/D3L/d3l/indexing/similarity_indexes/__init__.py:430
Methodquery
Search for the nearest neighbours of the given query. Parameters ---------- query : Iterable[Any] A col
union/D3L/d3l/indexing/similarity_indexes/__init__.py:593
Methodquery
Search for the nearest neighbours of the given query. Parameters ---------- query : Iterable[Any] A col
union/D3L/d3l/indexing/similarity_indexes/__init__.py:774
Methodquery
Search for the nearest neighbours of the given query. Parameters ---------- query : Iterable[Any] A col
union/D3L/d3l/indexing/similarity_indexes/__init__.py:986
Methodquery
给出查询集的MinHash和大小，检索出与查询集containment大于阈值的查询集。 Args: minhash (datasketch.MinHash): 查询集合的minhash. size (int): 查
join/LSH/datasketch/lshensemble.py:227
← previousnext →901–1,000 of 1,080, ranked by callers