README

This ruby script takes in a TSV of type co-occurrence probabilities, 
does some simple filtering, and prints the output. 

The filtered text file is suitable for node-link diagram visualization.

freebase_implicit_types (filtered).txt

football_coach ->	person
family_member ->	person
building ->	structure
house ->	structure
house ->	project_focus
truck_trim_level ->	trim_level
usnris.nris_listing ->	usnris.topic
usnris.nris_listing ->	listed_site
notable_person_with_medical_condition ->	person
uspolitician.u_s_congressperson ->	person
adultentertainment.adult_media ->	adultentertainment.topic
thoroughbredracing.thoroughbred_racehorse_trainer ->	thoroughbredracing.topic
delete_task ->	task
thoroughbredracing.thoroughbred_racehorse_trainer ->	horsefacts.topic
merge_task ->	task
simple_merge_task ->	task
vancouver.city_street ->	vancouver.location_in_neighborhood
vancouver.city_street ->	vancouver.topic
vancouver.city_street ->	location
vancouver.city_street ->	road
thoroughbredracing.thoroughbred_racehorse ->	thoroughbredracing.topic
us_county ->	location
uk_civil_parish ->	statistical_region
uk_civil_parish ->	location
vancouver.location_in_neighborhood ->	vancouver.topic
neighborhood ->	location
jp_district ->	statistical_region
jp_district ->	dated_location
jp_city_town ->	statistical_region
jp_city_town ->	dated_location
in_district ->	statistical_region
in_district ->	location
in_district ->	dated_location
barbie.barbie_doll ->	barbie.topic
barbie.barbie_doll ->	consumer_product
barbie.barbie_doll ->	collectable_item
bioventurist.bv_therapeutic ->	bioventurist.product
bioventurist.bv_venture_investor ->	venture_investor
birdwatching.checklist_bird ->	organism_classification
australian_suburb ->	location
australian_local_government_area ->	statistical_region
australian_local_government_area ->	location
australian_local_government_area ->	dated_location
braziliangovt.politician ->	politician
braziliangovt.politician ->	person
britishpubs.pub ->	britishpubs.topic
britishpubs.pub ->	business_location
britishpubs.pub ->	employer
britishpubs.pub ->	drinking_establishment
sports_team_location ->	location
classiccars.classic_car ->	model
classiccars.classic_car ->	classiccars.topic
contractbridge.bridge_player ->	contractbridge.topic
contractbridge.bridge_player ->	person
crime.executed_person ->	crime.convicted_criminal
crime.executed_person ->	crime.topic
crime.lawyer ->	crime.topic
9202a8c04000641f800000000ae936d4 ->	moscratch.topic
engineering.engineering_person ->	engineering.topic
engineering.engineering_person ->	person
engineering.engineering_person ->	project_participant
fashionmodels.fashion_model ->	person
formula1.formula_1_driver ->	formula1.topic
wfilmbase.film ->	wfilmbase.topic
wfilmbase.topic ->	wfilmbase.film
gayporn.topic ->	gayporn.gay_porn
9202a8c04000641f8000000009e713a9 ->	zxspectrum.zx_spectrum_program
9202a8c04000641f8000000009e713a9 ->	zxspectrum.topic
golfcourses.golf_club ->	golfcourses.topic
golfcourses.golf_course ->	golfcourses.topic
horseracing.racehorse ->	horseracing.topic
horseracing.racehorse ->	thoroughbredracing.thoroughbred_racehorse
horseracing.racehorse ->	thoroughbredracing.topic
horseracing.racehorse ->	organism
indianelections2009.constituency ->	indianelections.topic
indianelections2009.constituency ->	indianelections2009.topic
indianelections2009.topic ->	indianelections.topic
infrastructure.power_station ->	structure
infrastructure.power_station ->	infrastructure.topic
juiced.topic ->	juiced.user_of_banned_substances
juiced.user_of_banned_substances ->	juiced.topic
litcentral.focal_taxa ->	litcentral.topic
losangelesbands.topic ->	artist
9202a8c04000641f80000000086e6204 ->	engineering.topic
marchmadness.ncaa_basketball_tournament_game ->	marchmadness.topic
marchmadness.ncaa_basketball_tournament_game ->	event
marchmadness.ncaa_basketball_tournament_stage ->	marchmadness.topic
marchmadness.ncaa_basketball_tournament_stage ->	event
theater_actor ->	person
moscratch.shce021709 ->	moscratch.topic
nobelprizes.nobel_prize_winner ->	award_winner
nobelprizes.nobel_prize_winner ->	nobelprizes.topic
yalebase.person ->	yalebase.topic
passpm.project_management_concept ->	passpm.topic
waterfall ->	location
waterfall ->	body_of_water
mountain_range ->	location
written_by ->	attribution
saturdaynightlive.snl_episode ->	tv_series_episode
petbreeds.dog_breed ->	animal_breed
football_player ->	person
zxspectrum.zx_spectrum_program ->	zxspectrum.topic
popstra.company ->	popstra.sww_base
popstra.company ->	popstra.topic
popstra.organization ->	popstra.sww_base
popstra.organization ->	popstra.topic
popstra.party ->	popstra.sww_base
popstra.party ->	popstra.topic
popstra.party_attendance_person ->	popstra.sww_base
popstra.product ->	popstra.topic
popstra.product_choice ->	popstra.sww_base
popstra.restaurant ->	popstra.sww_base
popstra.restaurant ->	popstra.topic
popstra.restaurant_choice ->	popstra.sww_base
popstra.support ->	popstra.sww_base
provenance ->	attribution
rugby.views.rugby_player ->	rugby.rugby_player
golfer ->	person
cricket_player ->	person
baseball_player ->	person
basketball_coach ->	person
cricket_bowler ->	person
cricket_bowler ->	cricket_player
gene_group ->	gene_ontology_group
gene_group_membership_evidence ->	gene_ontology_group_membership_evidence
gene_ontology_group_membership_evidence ->	gene_group_membership_evidence
cyclist ->	person
company_advisor ->	person
australian_rules_footballer ->	person
tv_station ->	broadcast
podcast_feed ->	broadcast
internet_stream ->	broadcast
boxer ->	person
release_component ->	creative_work
multipart_release ->	creative_work
multipart_release ->	release
gene_ontology_group ->	gene_group
release_component ->	release
release ->	creative_work
football_team ->	sports_team
chivalric_order_member ->	person
pro_athlete ->	person
pro_athlete ->	measured_person
uk_civil_parish ->	dated_location
academic ->	person
user_profile ->	user
measured_person ->	person
user_profile ->	namespace
soundtrack ->	album
basketball_player ->	person
songwriter ->	composer
crime.lawyer ->	person
user ->	namespace
skyscraper ->	structure
statistical_region ->	dated_location
orbital_relationship ->	celestial_object
lake ->	body_of_water
football_player ->	person
uk_civil_parish ->	administrative_division
noble_person ->	person
us_county ->	dated_location
us_county ->	statistical_region
skyscraper ->	project_focus
domain_profile ->	domain
lake ->	location
9202a8c04000641f8000000008fe7278 ->	tv_program
givennames.topic ->	givennames.given_name
military_person ->	person
vancouver.location_in_neighborhood ->	location
birdconservation.bird_taxa ->	birdconservation.topic
deceased_person ->	person
politician ->	person
gayporn.gay_porn ->	gayporn.topic
us_county ->	administrative_division
skyscraper ->	building
place_of_interment ->	location
user ->	user_profile
tennis_player ->	person
amusementparks.ride ->	amusementparks.topic
songwriter ->	lyricist
venture_funded_company ->	employer
tv_actor ->	person
prison.prisoner ->	person
nobelprizes.topic ->	nobelprizes.nobel_prize_winner
nobelprizes.topic ->	award_winner
citytown ->	location
bangladeshipeople.topic ->	person
litcentral.focal_taxa ->	book_subject
vineyard ->	location
9202a8c04000641f800000000ae936d4 ->	moscratch.shce021709
frameline.topic ->	film
playboyplaymates.playmate ->	playboyplaymates.topic
playboyplaymates.playmate ->	person
venture_funded_company ->	company
star ->	celestial_object
in_district ->	administrative_division
greatfilms.ranking ->	greatfilms.topic
book ->	written_work
geometry ->	content
classiccars.topic ->	model
popstra.fashion_choice ->	popstra.sww_base
popstra.fashion_choice ->	popstra.topic
popstra.topic ->	popstra.sww_base
olympic_event_competition ->	event
guitarist ->	artist
bioventurist.science_or_technology_company ->	company
bioventurist.science_or_technology_company ->	employer
sports_championship_event ->	event
computer_scientist ->	person
political_party ->	organization
writer ->	person
australian_suburb ->	dated_location
australian_suburb ->	statistical_region
author ->	person
visual_artist ->	person
board_member ->	person
hockey_player ->	person
moscratch.shce021709 ->	9202a8c04000641f800000000ae936d4
school ->	educational_institution
zxspectrum.zx_spectrum_program ->	computer_videogame
birdconservation.bird_taxa ->	organism_classification
adultentertainment.adult_entertainer ->	person
director ->	person
golfcourses.golf_club ->	location
9202a8c04000641f8000000009e713a9 ->	computer_videogame
dated_location ->	location
actor ->	person
amusementparks.roller_coaster ->	amusementparks.ride
physician ->	person
statistical_region ->	location
tv_director ->	person
editor ->	person
cinematographer ->	person
filmcameras.camera_lens ->	filmcameras.topic
political_district ->	location
wfilmbase.topic ->	film
wfilmbase.film ->	film
journal ->	periodical
formula1.formula_1_grand_prix ->	formula1.topic
monarch ->	person
chess_player ->	person
school_district ->	location
tropical_cyclone ->	disaster2.topic
astronaut ->	person
9202a8c04000641f80000000086e612d ->	engineering.topic
architect ->	person
cemetery ->	place_of_interment
cemetery ->	dated_location
cemetery ->	location
film_character ->	fictional_character
fashionmodels.fashion_model ->	fashionmodels.topic
guitarist ->	person
amusementparks.roller_coaster ->	amusementparks.topic
crime.convicted_criminal ->	crime.topic
olympic_athlete ->	person
musical_group ->	artist
university ->	educational_institution
litcentral.focal_taxa ->	organism_classification
company_founder ->	person
drinking_establishment ->	business_location
drinking_establishment ->	employer
yalebase.person ->	person
activism.activist ->	person
disaster2.death_causing_event ->	event
mountain ->	location
play ->	written_work
apps.application ->	domain
administrative_division ->	location
9202a8c04000641f80000000086e6204 ->	project_participant
popstra.product ->	popstra.sww_base
governmental_jurisdiction ->	location
moscratch.topic ->	moscratch.shce021709
restaurant ->	employer
cricket_bowler ->	measured_person
cricket_bowler ->	pro_athlete
producer ->	person
sports_league_season ->	event
horseracing.topic ->	organism
horseracing.topic ->	thoroughbredracing.topic
horseracing.topic ->	thoroughbredracing.thoroughbred_racehorse
engineering.engineering_person ->	9202a8c04000641f80000000086e6204
americancomedy.comedian ->	americancomedy.topic
nascar.nascar_driver ->	person
horseracing.topic ->	horseracing.racehorse
moscratch.topic ->	9202a8c04000641f800000000ae936d4
short_story ->	written_work
apps.acre_app ->	domain
poem ->	written_work
inventor ->	person
celebrity ->	popstra.celebrity
rugby.views.rugby_player ->	person
juiced.topic ->	person
juiced.user_of_banned_substances ->	person
usnris.topic ->	listed_site
usnris.nris_listing ->	location
adultentertainment.adult_entertainer ->	adultentertainment.topic
tv_writer ->	person
group_member ->	artist
celebrity ->	popstra.sww_base
celebrity ->	popstra.topic
astronomer ->	person
formula1.formula_1_driver ->	person
prison.prisoner ->	prison.topic

yar.rb

#!/usr/bin/env ruby

x = IO.readlines('cotype2009_07_10sans_user_types.txt')
z = x.sort_by { |ya| ya.split("\t")[5].to_f }.reverse.select do |ya| 
  arr = ya.split("\t")
  (arr[5].to_f > 0.99) && (arr[2].to_i > 500) && (arr[3].to_i > 500) && (arr[2].to_i + arr[3].to_i > 2000)
end

puts z