T2D benchmark

[28]:

import logging as log
log.getLogger().setLevel(log.INFO)

import takco

dataset = takco.evaluate.dataset.T2D(
    name='t2d-v1', version=1, resourcedir='resources', datadir='data',
    download = [
    'http://webdatacommons.org/webtables/tables_instance.tar.gz',
    'http://webdatacommons.org/webtables/entities_instance.tar.gz',
    'http://webdatacommons.org/webtables/classes_instance.csv',
    'http://webdatacommons.org/webtables/attributes_instance.tar.gz',
]
)

# dataset = takco.evaluate.dataset.T2D(
#     resourcedir='resources',
#     datadir='data',
#     tabledir = 'data/taipan/TAIPAN-Datasets-master/T2DStar/tables',
# #     entitydir = 'data/t2d-v2/instance',
#     classfile = 'data/t2d-v2/classes_GS.csv',
# #     propdir = 'data/t2d-v2/property',
#     keycolfile = 'data/taipan/TAIPAN-Datasets-master/T2DStar/subject_column.csv',
#     propdir = 'data/taipan/TAIPAN-Datasets-master/T2DStar/properties_t2d_format',
# )


takco.preview(dataset.get_annotated_tables_as_predictions())

INFO:root:Downloading http://webdatacommons.org/webtables/tables_instance.tar.gz to data/t2d-v1/tables_instance.tar.gz
INFO:root:Unpacking data/t2d-v1/tables_instance.tar.gz to data/t2d-v1/tables_instance
INFO:root:Downloading http://webdatacommons.org/webtables/entities_instance.tar.gz to data/t2d-v1/entities_instance.tar.gz
INFO:root:Unpacking data/t2d-v1/entities_instance.tar.gz to data/t2d-v1/entities_instance
INFO:root:Downloading http://webdatacommons.org/webtables/classes_instance.csv to data/t2d-v1/classes_instance.csv
INFO:root:Downloading http://webdatacommons.org/webtables/attributes_instance.tar.gz to data/t2d-v1/attributes_instance.tar.gz
INFO:root:Unpacking data/t2d-v1/attributes_instance.tar.gz to data/t2d-v1/attributes_instance
INFO:root:Read 233 tables from data/t2d-v1/tables_instance
INFO:root:Read 233 key cols from data/t2d-v1/attributes_instance
INFO:root:Read 233 prop files from data/t2d-v1/attributes_instance
INFO:root:Read 233 class tables from data/t2d-v1/classes_instance.csv
INFO:root:Read 233 table headerrows from data/t2d-v1/entities_instance
INFO:root:Read 233 entity tables from data/t2d-v1/entities_instance

[28]:
? 0 1 2
∈ Book
0 author
title author source
adventures of huckleberry finn mark twain ala [11]
the adventures of super diaper baby dav pilkey ala [47]
the adventures of tom sawyer mark twain ala
alice series phyllis reynolds naylor ala [2]
all the king's men robert penn warren rad

(146 more rows)
? 0 1 2
∈ Newspaper
# media mix
1 dainik jagran 27.500
2 dainik bhaskar 14.000
3 aajtak tv 7.000
4 cnn editions (international) 6.000
5 dinakaran 5.000

(16 more rows)
? 0 1 2 3 4 5 6
∈ Building
2 location floorCount openingDate
# gebäude gebäude stadt etagen höhe jahr
1 NULL burj khalifa dubai 163 2.717 ft 2010
2 NULL makkah clock royal tower [abraj al bait] mekka 95 1.972 ft 2012
3 NULL taipei 101 taipei 101 1.671 ft 2004
4 NULL shanghai world financial center shanghai 101 1.614 ft 2008
5 NULL international commerce centre [union square] hong kong 118 1.588 ft 2010

(195 more rows)
? 0 1 2 3 4
∈ Company
1 industry
rank company industry temkin experience rating (ter) company ter vs industry ter
1 sam's club retailer 85% 13.0
2 publix grocery chain 81% 4.9
3 a credit union bank 80% 14.5
3 chick-fil-a fast food chain 80% 6.2
3 subway fast food chain 80% 6.4

(201 more rows)
? 0 1 2 3 4 5 6
∈ Mountain
0 elevation
peak ranking map guide grid ref alt (ft) alt (m)
allen crags 43 sw e ny 236 085 2572 784
angletarn pikes   143 ne fe ny 414 148 1857 566
ard crags 142 nw nw ny 207 197 1860 567
armboth fell 182 nw c ny 297 159 1570 479
arnison crag 194 ne e ny 394 150 1424 434

(210 more rows)
? 0 1 2 3 4
∈ Country
1 frenchName region capital timeZone
a nom en anglais endroit capitale heure
afghanistan afghanistan asie kabul +4.5
afrique du sud south afrique afrique pretoria +2
albanie albania europe tirane +1
alderney (uk) voir îles (...) alderney europe   0
algérie algeria afrique algiers +1

(228 more rows)
? 0 1 2 3 4 5 6
∈ Country
1 populationTotal area populationDensity
NULL country name: population area (sq. km.) population density (sq. km.) area (sq. mi.) population density (sq. mi.)
36 china 1339190000 9596960.00 139.54 3705405.45 361.42
77 india 1184639000 3287590.00 360.34 1269345.07 933.27
183 united states of america 309975000 9629091.00 32.19 3717811.29 83.38
78 indonesia 234181400 1919440.00 122.01 741099.62 315.99
24 brazil 193364000 8511965.00 22.72 3286486.71 58.84

(188 more rows)
? 0 1 2 3 4 5
∈ VideoGame
0 publisher releaseDate releaseDate
title publisher eu release date au release date pegi acb
donkey kong country nintendo 2006-12-08 2006-12-07 7 g
f-zero nintendo 2006-12-08 2006-12-07 3 g
simcity nintendo 2006-12-29 2006-12-29 3 g
super castlevania iv konami 2006-12-29 2006-12-29 3 pg
street fighter ii: the world warrior capcom 2007-01-19 2007-01-19 12 pg

(60 more rows)
? 0 1 2 3 4
∈ RadioStation
1 programmeFormat
dial location call letters format address telephone
am 790 kabc (abc radio networks) news/talk 3321 s la cienega blvd los angeles 90016 (310) 840-4900
am 900 kali am spanish news/talk 747 e green st pasadena 91101 (626) 844-8882
am 1300 kazn(asian radio) chinese variety 747 e green st pasadena 91101 (626) 568-1300
am 1580 kbla spanish news/talk 123 figueroa st #101a los angeles 90012 (213) 628-8700
am 740 kbrt(k-bright) religious talk 3183-d airway ave costa mesa 92626 (714) 754-4450

(25 more rows)
? 0 1 2
∈ Hospital
local health boards hospital name link surgeons
abertawe bro morgannwg university lhb morriston hospital (swansea) roger morgan
  singleton hospital (swansea) roger morgan
  princess of wales hospital (bridgend) roger morgan
aneurin bevan lhb neville hall hospital (abergavenny) richard blackett
  royal gwent hospital (newport) ahmed shandall

(11 more rows)

 
[39]:

searcher = takco.config.build('dbpedia_t2ksubset_es', load='resources/pipelines/t2d-v2-baseline.toml')
print(searcher)

# Test
with searcher:
    for rs in searcher.search_entities([('USA',{})]):
        print([r.uri for r in rs])

ElasticSearcher(index='dbpediasub-7', baseuri='http://dbpedia.org/resource/', propbaseuri='http://dbpedia.org/ontology/', es_kwargs={'hosts': ['bricks07'], 'timeout': 60}, parts=True, prop_uri={'type': 'http://www.w3.org/1999/02/22-rdf-syntax-ns#type'}, prop_baseuri={'type': 'http://dbpedia.org/ontology/'}, typer=SimpleTyper(use_dateparser='dateutil'), stringmatch='jaccard')
['http://dbpedia.org/resource/United_States']

[30]:

%%capture --no-display
from dask.distributed import Client
client = Client(address = 'tcp://192.168.62.207:8686')
client

[30]:

Client

Cluster

  • Workers: 10
  • Cores: 20
  • Memory: 673.47 GB
 
[43]:

%%time

baseline = takco.config.build('linker', load='resources/pipelines/t2d-v2-baseline.toml')

pred = takco.TableSet.link(
#     takco.DaskHashBag(takco.TableSet.dataset(dataset), client=client),
    takco.TableSet(list(takco.TableSet.dataset(dataset))[:10]),
    usecols = "keycol",
    linker = baseline,
)
pred.tables.persist()

report = pred.report(keycol_only=True, curve = True )

import pandas as pd
pd.DataFrame.from_dict( report.get('scores'), orient='index' )

CPU times: user 641 ms, sys: 33.6 ms, total: 675 ms
Wall time: 1.44 s

[43]:
precision recall f1-score support predictions
entities 0.27907 0.433735 0.339623 166 258 
[44]:

from takco.evaluate import pr_plot
pr_plot(report['curves'])

[44]:
../_images/tutorials_t2d_5_0.png 
[45]:

takco.preview( pred, nrows=None, ntables=25, hide_correct_rows=True )

[45]:
? 0 1 2 3
∈ OfficeHolder ❓
Brian Mulroney 💡
Joe Clark ❌ 💡
John George Diefenbaker 💡
John Sparrow David Thompson ❌ 💡
Lester Bowles Pearson 💡
Louis Stephen St . Laurent 💡
Paul Martin ❌ 💡
Richard Bedford Bennett 💡
? 0 1 2 3 4
∈ EducationalInstitution ❓ Settlement ❓
0 city ❓
1 isPartOf ❓
Ontario College of Art & Design ❌ 💡 Toronto ❓
? 0 1 2
∈ Animal ❓ Animal ❓
0 genus ❓
1 genus ❓
Greater Yellowlegs ❓ Tringa melanoleuca
Lesser Yellowlegs ❓ Tringa flavipes
Willet ❓ Catoptrophorus semipalmatus
Wandering Tattler ❓ Heteroscelus incanus
Spotted Sandpiper ❓ Actitis macularia ❓
Upland Sandpiper ❓ Bartramia longicauda
Ruddy Turnstone ❓ Arenaria interpres
Black Turnstone ❓ Arenaria melanocephala ❓
Surfbird ❓ Aphriza virgata
Sanderling ❓ Calidris alba
Red - necked Stint ❓ Calidris ruficollis
Little Stint ❌ 💡 Calidris minuta
Least Sandpiper ❓ Calidris minutilla ❓
Baird's Sandpiper ❓ Calidris bairdii
Pectoral Sandpiper ❓ Calidris melanotos
Sharp - tailed Sandpiper ❓ Calidris acuminata ❓
Dunlin ❓ Calidris alpina
Curlew Sandpiper ❓ Calidris ferruginea
Spoonbilleded Sandpiper Eurynorhynchus pygmaeus
Buff - breasted Sandpiper ❓ Tryngites subruficollis ❓
Ruff ❓ Philomachus pugnax
Long - billed Dowitcher ❓ Limnodromus scolopaceus ❓
Wilson's Snipe ❓ Gallinago delicata ❓
American Woodcock ❓ Scolopax minor ❓
Wilson's Phalarope ❓ Phalaropus tricolor ❓
Red - necked Phalarope ❌ 💡 Phalaropus lobatus ❓
Red Phalarope ❓ Phalaropus fulicarius
? 0 1 2 3 4 5
∈ Artist ❓
3 occupation ❓
Lisa's Rival 💡 Mike Scully ❓
Bart of Darkness 💡 Dan McGrath
Another Simpsons Clip Show 💡 Penny Wise
Itchy & Scratchy Land 💡 John Swartzwelder ❓
Sideshow Bob Roberts 💡 Bill Oakley & Josh Weinstein
Nightmare Cafeteria 💡 David S . Cohen ❓
Bart's Girlfriend John Collier ❓
Lisa on Ice 💡 Mike Scully ❓
Homer : Bad Man ❌ 💡 Greg Daniels ❓
Grampa vs . Sexual Inadequacy 💡 Bill Oakley & Josh Weinstein
Fear of Flying ❌ 💡 David Sacks
Homer the Great 💡 John Swartzwelder ❓
A Star is Burns 💡 Ken Keeler ❓
And Maggie Makes Three 💡 Jennifer Crittenden
Bart's Comet John Swartzwelder ❓
Homie the Clown 💡 John Swartzwelder ❓
Bart vs . Australia 💡 Bill Oakley & Josh Weinstein
Homer vs . Patty & Selma 💡 Brent Forrester
Lisa's Wedding Greg Daniels ❓
Two Dozen and One Greyhounds Mike Scully ❓
The PTA Disbands 💡 Jennifer Crittenden
'Round Springfield 💡 Joshua Sternin & Jeff Ventimilia
The Springfield Connection 💡 John Collier ❓
Lemon of Troy 💡 Brent Forrester
Who Shot Mr . Burns ? ( Part One ) ❓ Bill Oakley & Josh Weinstein
? 0 1 2 3
∈ Settlement ❓ Settlement ❓
0 location ❓
Venta silurum 💡 Caerwent ❓
Moridunum Carmarthen ❓
Camulodonum 💡 Colchester ❓
Noviomagus ❌ 💡 Chichester ❓
Deva ❓ Chester ❓
Durnovaria 💡 Dorchester ❓
Glevum Gloucester ❓
Ratae Coritanorum 💡 Leicester ❓
Mamucium ❓ Manchester ❓
Verulamium 💡 St Albans ❓
Venta Belgarum 💡 Winchester ❓
Eboracum ❌ 💡 York ❓
? 0 1 2
1 The Secret of the Old Clock 💡 1959
2 The Hidden Staircase 💡 1959
3 The Bungalow Mystery 💡 1960
4 The Mystery at Lilac Inn 💡 1961
5 The Secret at Shadow Ranch 💡 1931
6 The Secret of Red Gate Farm 💡 1961
7 The Clue in the Diary 💡 1962
8 Nancy's Mysterious Letter 💡 1932
9 The Sign of the Twisted Candles 💡 1933
10 The Password to Larkspur Lane 💡 1933
11 The Clue of the Broken Locket 💡 1934
12 The Message in the Hollow Oak 💡 1935
13 The Mystery of the Ivory Charm 💡 1936
14 The Whispering Statue 💡 1937
15 The Haunted Bridge 💡 1937
16 The Clue of the Tapping Heels 💡 1939
17 The Mystery of the Brass - Bound Trunk 💡 1940
18 The Mystery at the Moss - Covered Mansion 💡 1941
19 The Quest of the Missing Map 💡 1942
20 The Clue in the Jewel Box 💡 1943
21 The Secret in the Old Attic 💡 1944
22 The Clue in the Crumbling Wall 💡 1945
23 The Mystery of the Tolling Bell 💡 1946
24 The Clue in the Old Album 💡 1947
25 The Ghost of Blackwood Hall 💡 1948
26 The Clue of the Leaning Chimney 💡 1949
27 The Secret of the Wooden lady 💡 1950
28 The Clue of the Black Keys 💡 1951
29 The Mystery at the Ski Jump 1952
30 The Clue of the Velvet Mask 1953
31 The Ringmaster's Secret 1953
32 The Scarlet Slipper Mystery 1954
? 0 1 2 3
∈ TelevisionShow ❓ FictionalCharacter ❓ FictionalCharacter ❓
1 portrayer ❓
2 portrayer ❓
Martin Sheen 💡 Josiah "Jed" Bartlet ❓ President ❓
Bradley Whitford 💡 Josh Lyman ❓
Richard Schiff 💡 Tobias Zachary "Toby" Ziegler
John Spencer ❌ 💡 Leo McGarry ❓
Dule Hill 💡 Charlie Young ❓
Stockard Channing ❌ 💡 Abigail "Abbey" Bartlet
Jimmy Smits 💡 Matt Santos [ eps 114 - ] ❓
? 0 1
∈ Film ❓
Snow White and the Seven Dwarfs ❓ 1937
Pinocchio ❌ 💡 1940
Fantasia ❓ 1940
The Reluctant Dragon ❓ 1941
The Adventures of Ichabod and Mr . Toad ❓ 1949
Cinderella ❌ 💡 1950
Alice in Wonderland ❓ 1951
Peter Pan ❌ 💡 1953
20 , 000 Leagues Under the Sea ❓ 1954
Sleeping Beauty ❓ 1959
101 Dalmatians ❓ 1961
Mary Poppins ❓ 1964
The Aristocats ❌ 💡 1970
Bedknobs and Broomsticks ❓ 1971
Robin Hood ❓ 1973
The Rescuers ❓ 1977
The Fox and the Hound ❓ 1981
Who Framed Roger Rabbit ❓ 1988
Oliver & Company ❓ 1988
The Little Mermaid ❌ 💡 1989
Beauty and the Beast ❌ 💡 1991
The Nightmare Before Christmas ❓ 1993
The Return of Jafar ❓ 1994
A Goofy Movie ❓ 1995
Pocahontas ❓ 1995
Toy Story ❓ 1995
James and the Giant Peach ❓ 1996
The Hunchback of Notre Dame ❌ 💡 1996
Hercules ❓ 1997
Mulan ❌ 💡 1998
A Bug's Life ❓ 1998
Tarzan ❌ 💡 1999
Toy Story 2 ❓ 1999
Fantasia / 2000 ❓ 2000
The Tigger Movie ❓ 2000
Recess : School's Out ❓ 2001
Atlantis : The Lost Empire ❓ 2001
Monsters , Inc . ❓ 2001
Return to Never Land ❓ 2002
Lilo & Stitch ❓ 2002
The Jungle Book 2 ❓ 2003
Piglet's Big Movie ❓ 2003
Finding Nemo ❓ 2003
Teacher's Pet ❓ 2004
The Lion King 3 : Hakuna Matata ❓ 2004
Home on the Range ❌ 💡 2004
The Incredibles ❓ 2004
Chicken Little ❓ 2005
? 0 1 2 3
∈ EducationalInstitution ❓ Settlement ❓
0 city ❓
1 leaderName ❓
Grant MacEwan College ❌ 💡 Edmonton ❓
Lethbridge Community College 💡 Lethbridge ❓
Maskwachees Cultural College ❓ Hobbema ❓
Medicine Hat College 💡 Medicine Hat ❓
Mount Royal College ❌ 💡 Calgary ❓
Northern Alberta Institute of Technology ❓ Edmonton ❓
? 0 1 2 3 4
1831 - 1865 Leopold I ❌ 💡
1865 - 1909 Leopold II ❌ 💡
1909 - 1934 Albert I ❌ 💡
1934 - 1951 Leopold III ❌ 💡
1951 - 1993 Baudouin I ❌ 💡
1993 Albert II ❌ 💡 
[ ]: