entity_embed.benchmarks package

Submodules

entity_embed.benchmarks.abt_buy module

class entity_embed.benchmarks.abt_buy.AbtBuyBenchmark(data_dir_path)

Bases: entity_embed.benchmarks.base.DeepmatcherBenchmark

base_url: str = 'http://pages.cs.wisc.edu/~anhai/data1/deepmatcher_data/Textual/Abt-Buy/'

dataset_name: str = 'Abt-Buy'

file_name: str = 'abt_buy_exp_data.zip'

table_csv_paths: List[str] = ['tableA.csv', 'tableB.csv']

entity_embed.benchmarks.amazon_google module

class entity_embed.benchmarks.amazon_google.AmazonGoogleBenchmark(data_dir_path)

Bases: entity_embed.benchmarks.base.DeepmatcherBenchmark

base_csv_path: str = '.'

base_url: str = 'http://pages.cs.wisc.edu/~anhai/data1/deepmatcher_data/Structured/Amazon-Google/'

dataset_name: str = 'Amazon-Google'

file_name: str = 'amazon_google_exp_data.zip'

table_csv_paths: List[str] = ['tableA.csv', 'tableB.csv']

entity_embed.benchmarks.base module

class entity_embed.benchmarks.base.DeepmatcherBenchmark(data_dir_path)

Bases: abc.ABC

base_csv_path: str = 'exp_data'

base_url: str

csv_encoding: str = 'utf-8'

dataset_name: str

file_name: str

property local_dir_path

property local_file_path

table_csv_paths: List[str]

test_csv_path: str = 'test.csv'

train_csv_path: str = 'train.csv'

property url

valid_csv_path: str = 'valid.csv'

entity_embed.benchmarks.beer module

class entity_embed.benchmarks.beer.BeerBenchmark(data_dir_path)

Bases: entity_embed.benchmarks.base.DeepmatcherBenchmark

base_url: str = 'http://pages.cs.wisc.edu/~anhai/data1/deepmatcher_data/Structured/Beer/'

dataset_name: str = 'Beer'

file_name: str = 'beer_exp_data.zip'

table_csv_paths: List[str] = ['tableA.csv', 'tableB.csv']

entity_embed.benchmarks.company module

class entity_embed.benchmarks.company.CompanyBenchmark(data_dir_path)

Bases: entity_embed.benchmarks.base.DeepmatcherBenchmark

base_url: str = 'http://pages.cs.wisc.edu/~anhai/data1/deepmatcher_data/Textual/Company/'

dataset_name: str = 'Company'

file_name: str = 'company_exp_data.zip'

table_csv_paths: List[str] = ['tableA.csv', 'tableB.csv']

entity_embed.benchmarks.dblp_acm_structured module

class entity_embed.benchmarks.dblp_acm_structured.DBLP_ACM_StructuredBenchmark(data_dir_path)

Bases: entity_embed.benchmarks.base.DeepmatcherBenchmark

base_url: str = 'http://pages.cs.wisc.edu/~anhai/data1/deepmatcher_data/Structured/DBLP-ACM/'

dataset_name: str = 'DBLP-ACM-Structured'

file_name: str = 'dblp_acm_exp_data.zip'

table_csv_paths: List[str] = ['tableA.csv', 'tableB.csv']

entity_embed.benchmarks.dblp_scholar_structured module

class entity_embed.benchmarks.dblp_scholar_structured.DBLPScholarStructuredBenchmark(data_dir_path)

Bases: entity_embed.benchmarks.base.DeepmatcherBenchmark

base_url: str = 'http://pages.cs.wisc.edu/~anhai/data1/deepmatcher_data/Structured/DBLP-GoogleScholar/'

dataset_name: str = 'DBLP-Scholar-Structured'

file_name: str = 'dblp_scholar_exp_data.zip'

table_csv_paths: List[str] = ['tableA.csv', 'tableB.csv']

entity_embed.benchmarks.fodors_zagats module

class entity_embed.benchmarks.fodors_zagats.FodorsZagatsBenchmark(data_dir_path)

Bases: entity_embed.benchmarks.base.DeepmatcherBenchmark

base_url: str = 'http://pages.cs.wisc.edu/~anhai/data1/deepmatcher_data/Structured/Fodors-Zagats/'

dataset_name: str = 'Fodors-Zagats'

file_name: str = 'fodors_zagat_exp_data.zip'

table_csv_paths: List[str] = ['tableA.csv', 'tableB.csv']

entity_embed.benchmarks.itunes_amazon_structured module

class entity_embed.benchmarks.itunes_amazon_structured.ITunesAmazonStructuredBenchmark(data_dir_path)

Bases: entity_embed.benchmarks.base.DeepmatcherBenchmark

base_url: str = 'http://pages.cs.wisc.edu/~anhai/data1/deepmatcher_data/Structured/iTunes-Amazon/'

dataset_name: str = 'iTunes-Amazon-Structured'

file_name: str = 'itunes_amazon_exp_data.zip'

table_csv_paths: List[str] = ['tableA.csv', 'tableB.csv']

entity_embed.benchmarks.walmart_amazon_structured module

class entity_embed.benchmarks.walmart_amazon_structured.WalmartAmazonStructuredBenchmark(data_dir_path)

Bases: entity_embed.benchmarks.base.DeepmatcherBenchmark

base_url: str = 'http://pages.cs.wisc.edu/~anhai/data1/deepmatcher_data/Structured/Walmart-Amazon/'

dataset_name: str = 'Walmart-Amazon-Structured'

file_name: str = 'walmart_amazon_exp_data.zip'

table_csv_paths: List[str] = ['tableA.csv', 'tableB.csv']

Module contents