Created
May 21, 2018 09:39
-
-
Save tmtmtmtm/28de60e167ddd658493d17548d573715 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/env ruby | |
require 'csv' | |
require 'rest-client' | |
#--------------------------------------------------------------------------- | |
# Find all Memberships of the 2016-20 with no P4100 qualifier and add it | |
# from data on the Wikipedia members list page: | |
# https://ro.wikipedia.org/wiki/Legislatura_2016-2020_(Camera_Deputaților) | |
# as scraped at | |
# https://morph.io/everypolitician-scrapers/romania-deputies-2016-wikipedia | |
# | |
# The output of this can then be passed to PositionStatements | |
# https://github.com/everypolitician/position_statements | |
#--------------------------------------------------------------------------- | |
WIKIDATA_SPARQL_URL = 'https://query.wikidata.org/sparql' | |
def sparql(query) | |
result = RestClient.get WIKIDATA_SPARQL_URL, accept: 'text/csv', params: { query: query } | |
CSV.parse(result.body, headers: true, header_converters: :symbol) | |
rescue RestClient::Exception => e | |
raise "Wikidata query #{query} failed: #{e.message}" | |
end | |
memberships_query = <<SPARQL | |
SELECT ?item ?ps | |
{ | |
?item p:P39 ?ps . | |
?ps ps:P39/wdt:P279* wd:Q17556530 ; pq:P2937 wd:Q28726607 . | |
FILTER NOT EXISTS { ?ps pq:P4100 wd:Q28726607 } | |
} | |
SPARQL | |
morph_data = CSV.table('MORPH.csv').group_by { |row| row[:id] } | |
sparql(memberships_query).map(&:to_h).each do |row| | |
id = row[:item].split('/').last | |
unless morph_data[id].to_a.count == 1 | |
warn "#{morph_data[id].to_a.count} rows for #{id}" | |
next | |
end | |
party = morph_data[id].first[:party_id] or next | |
puts [id, "P39", row[:ps].split('/').last, 'P4100', party].join("\t") | |
end | |
#!/bin/env ruby | |
require 'csv' | |
require 'rest-client' | |
#--------------------------------------------------------------------------- | |
# Find all Memberships of the 2016-20 with no P4100 qualifier and add it | |
# from data on the Wikipedia members list page: | |
# https://ro.wikipedia.org/wiki/Legislatura_2016-2020_(Camera_Deputaților) | |
# as scraped at | |
# https://morph.io/everypolitician-scrapers/romania-deputies-2016-wikipedia | |
# | |
# The output of this can then be passed to PositionStatements | |
# https://github.com/everypolitician/position_statements | |
#--------------------------------------------------------------------------- | |
WIKIDATA_SPARQL_URL = 'https://query.wikidata.org/sparql' | |
def sparql(query) | |
result = RestClient.get WIKIDATA_SPARQL_URL, accept: 'text/csv', params: { query: query } | |
CSV.parse(result.body, headers: true, header_converters: :symbol) | |
rescue RestClient::Exception => e | |
raise "Wikidata query #{query} failed: #{e.message}" | |
end | |
memberships_query = <<SPARQL | |
SELECT ?item ?ps | |
{ | |
?item p:P39 ?ps . | |
?ps ps:P39/wdt:P279* wd:Q17556530 ; pq:P2937 wd:Q28726607 . | |
FILTER NOT EXISTS { ?ps pq:P4100 wd:Q28726607 } | |
} | |
SPARQL | |
morph_data = CSV.table('MORPH.csv').group_by { |row| row[:id] } | |
sparql(memberships_query).map(&:to_h).each do |row| | |
id = row[:item].split('/').last | |
unless morph_data[id].to_a.count == 1 | |
warn "#{morph_data[id].to_a.count} rows for #{id}" | |
next | |
end | |
party = morph_data[id].first[:party_id] or next | |
puts [id, "P39", row[:ps].split('/').last, 'P4100', party].join("\t") | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment