def fetch_senate_committee_meetings(committees, options):
# Load any existing meetings file so we can recycle any GUIDs.
existing_meetings = []
output_file = output_for("senate")
if os.path.exists(output_file):
existing_meetings = json.load(open(output_file))
options = dict(options) # clone
options["binary"] = True #
options["force"] = True
meetings = []
dom = lxml.etree.fromstring(
utils.download(
"http://www.senate.gov/general/committee_schedules/hearings.xml",
"committee_schedule/senate.xml", options))
for node in dom.xpath("meeting"):
committee_id = str(node.xpath('string(cmte_code)'))
if committee_id.strip() == "":
continue # "No committee hearings scheduled" placeholder
occurs_at = str(node.xpath('string(date)'))
room = str(node.xpath('string(room)'))
topic = str(node.xpath('string(matter)'))
occurs_at = datetime.datetime.strptime(occurs_at, "%d-%b-%Y %I:%M %p")
topic = re.sub(r"\s+", " ", topic).strip()
# Validate committee code.
try:
committee_code, subcommittee_code = re.match(
r"(\D+)(\d+)$", committee_id).groups()
if committee_code not in committees:
raise ValueError(committee_code)
if subcommittee_code == "00":
subcommittee_code = None
if subcommittee_code and subcommittee_code not in committees[
committee_code]["subcommittees"]:
raise ValueError(subcommittee_code)
except:
print("Invalid committee code", committee_id)
continue
# See if this meeting already exists. If so, take its GUID.
# Assume meetings are the same if they are for the same committee/subcommittee and
# at the same time.
for mtg in existing_meetings:
if mtg["committee"] == committee_code and mtg.get(
"subcommittee", None) == subcommittee_code and mtg[
"occurs_at"] == occurs_at.isoformat():
if options.get("debug", False):
print("[%s] Reusing gUID." % mtg["guid"])
guid = mtg["guid"]
break
else:
# Not found, so create a new ID.
# TODO: Can we make this a human-readable ID?
guid = str(uuid.uuid4())
# Scrape the topic text for mentions of bill numbers.
congress = utils.congress_from_legislative_year(
utils.current_legislative_year(occurs_at))
bills = []
bill_number_re = re.compile(
r"(hr|s|hconres|sconres|hjres|sjres|hres|sres)\s?(\d+)", re.I)
for bill_match in bill_number_re.findall(topic.replace(".", "")):
bills.append(bill_match[0].lower() + bill_match[1] + "-" +
str(congress))
# Create the meeting event.
if options.get("debug", False):
print("[senate][%s][%s] Found meeting in room %s at %s." %
(committee_code, subcommittee_code, room,
occurs_at.isoformat()))
meetings.append({
"chamber": "senate",
"congress": congress,
"guid": guid,
"committee": committee_code,
"subcommittee": subcommittee_code,
"occurs_at": occurs_at.isoformat(),
"room": room,
"topic": topic,
"bill_ids": bills,
})
print("[senate] Found %i meetings." % len(meetings))
return meetings
def run():
# default to caching
cache = utils.flags().get('cache', True)
force = not cache
only_bioguide = utils.flags().get('bioguide', None)
congress = utils.flags().get('congress', None)
data_files = []
print("Loading %s..." % "legislators-current.yaml")
legislators = load_data("legislators-current.yaml")
data_files.append((legislators, "legislators-current.yaml"))
print("Loading %s..." % "legislators-historical.yaml")
legislators = load_data("legislators-historical.yaml")
data_files.append((legislators, "legislators-historical.yaml"))
#load roll call data. Will need to be updated (possibly) for 114th+ congresses, since it is unclear what the URl format will be
if congress == None:
raise Exception("the --congress flag is required")
elif congress == "113":
url_senate = "http://amypond.sscnet.ucla.edu/rollcall/static/S113.ord"
url_house = "http://amypond.sscnet.ucla.edu/rollcall/static/H113.ord"
elif int(congress) < 10 and int(congress) > 0:
url_senate = "ftp://voteview.com/dtaord/sen0%skh.ord" % congress
url_house = "ftp://voteview.com/dtaord/hou0%skh.ord" % congress
elif int(congress) < 113 and int(congress) >= 10:
url_senate = "ftp://voteview.com/dtaord/sen%skh.ord" % congress
url_house = "ftp://voteview.com/dtaord/hou%skh.ord" % congress
else:
raise Exception("no data for congress " + congress)
senate_destination = "icpsr/source/senate_rollcall%s.txt" % congress
senate_data = utils.download(url_senate, senate_destination, force)
house_destination = "icpsr/source/house_rollcall%s.txt" % congress
house_data = utils.download(url_house, house_destination, force)
error_log = csv.writer(
open("cache/errors/mismatch/mismatch_%s.csv" % congress, "wb"))
error_log.writerow([
"error_type", "matches", "icpsr_name", "icpsr_state", "is_territory",
"old_id", "new_id"
])
read_files = [(senate_data, "sen"), (house_data, "rep")]
print("Running for congress " + congress)
for read_file in read_files:
for data_file in data_files:
for legislator in data_file[0]:
num_matches = 0
# # this can't run unless we've already collected a bioguide for this person
bioguide = legislator["id"].get("bioguide", None)
# if we've limited this to just one bioguide, skip over everyone else
if only_bioguide and (bioguide != only_bioguide):
continue
#if not in currently read chamber, skip
chamber = legislator['terms'][len(legislator['terms']) -
1]['type']
if chamber != read_file[1]:
continue
#only run for selected congress
latest_congress = utils.congress_from_legislative_year(
utils.legislative_year(
parse_date(
legislator['terms'][len(legislator['terms']) -
1]['start'])))
if chamber == "sen":
congresses = [
latest_congress, latest_congress + 1,
latest_congress + 2
]
else:
congresses = [latest_congress]
if int(congress) not in congresses:
continue
# pull data to match from yaml
last_name_unicode = legislator['name']['last'].upper().strip(
).replace('\'', '')
last_name = unicodedata.normalize(
'NFD', str(last_name_unicode)).encode('ascii', 'ignore')
state = utils.states[legislator['terms']
[len(legislator['terms']) -
1]['state']].upper()[:7].strip()
# select icpsr source data based on more recent chamber
write_id = ""
lines = read_file[0].split('\n')
for line in lines:
# parse source data
icpsr_state = line[12:20].strip()
icpsr_name = line[21:].strip().strip(string.digits).strip()
icpsr_id = line[3:8].strip()
#ensure unique match
if icpsr_name[:8] == last_name[:8] and state == icpsr_state:
num_matches += 1
write_id = icpsr_id
#skip if icpsr id is currently in data
if "icpsr" in legislator["id"]:
if write_id == legislator["id"]["icpsr"] or write_id == "":
continue
elif write_id != legislator["id"][
"icpsr"] and write_id != "":
error_log.writerow([
"Incorrect_ID", "NA", last_name[:8], state, "NA",
legislator["id"]["icpsr"], write_id
])
print("ID updated for %s" % last_name)
if num_matches == 1:
legislator['id']['icpsr'] = int(write_id)
else:
if state == 'GUAM' or state == 'PUERTO' or state == "VIRGIN" or state == "DISTRIC" or state == "AMERICA" or state == "NORTHER" or state == "PHILIPP":
error_log.writerow([
"Non_1_match_number",
str(num_matches), last_name[:8], state, "Y", "NA",
"NA"
])
else:
print(
str(num_matches) + " matches found for " +
last_name[:8] + ", " + state + " in congress " +
str(congress))
error_log.writerow([
"Non_1_match_number",
str(num_matches), last_name, state, "N", "NA", "NA"
])
save_data(data_file[0], data_file[1])
for data_file in data_files:
for legislator in data_file[0]:
num_matches = 0
# # this can't run unless we've already collected a bioguide for this person
bioguide = legislator["id"].get("bioguide", None)
# if we've limited this to just one bioguide, skip over everyone else
if only_bioguide and (bioguide != only_bioguide):
continue
# if not in currently read chamber, skip
chamber = legislator["terms"][len(legislator["terms"]) - 1]["type"]
if chamber != read_file[1]:
continue
# only run for selected congress
latest_congress = utils.congress_from_legislative_year(
utils.legislative_year(parse_date(legislator["terms"][len(legislator["terms"]) - 1]["start"]))
)
if chamber == "sen":
congresses = [latest_congress, latest_congress + 1, latest_congress + 2]
else:
congresses = [latest_congress]
if int(congress) not in congresses:
continue
# pull data to match from yaml
last_name_unicode = legislator["name"]["last"].upper().strip().replace("'", "")
last_name = unicodedata.normalize("NFD", unicode(last_name_unicode)).encode("ascii", "ignore")
state = utils.states[legislator["terms"][len(legislator["terms"]) - 1]["state"]].upper()[:7].strip()
# select icpsr source data based on more recent chamber
def run():
# default to caching
cache = utils.flags().get('cache', True)
force = not cache
only_bioguide = utils.flags().get('bioguide', None)
congress = utils.flags().get('congress', None)
data_files = []
print("Loading %s..." % "legislators-current.yaml")
legislators = load_data("legislators-current.yaml")
data_files.append((legislators, "legislators-current.yaml"))
print("Loading %s..." % "legislators-historical.yaml")
legislators = load_data("legislators-historical.yaml")
data_files.append((legislators, "legislators-historical.yaml"))
# load member data from vote view
if congress == None:
raise Exception("the --congress flag is required")
elif int(congress) < 10 and int(congress) > 0:
url_senate = "https://voteview.com/static/data/out/members/S00%s_members.csv" % congress
url_house = "https://voteview.com/static/data/out/members/H00%s_members.csv" % congress
elif int(congress) < 100 and int(congress) >= 10:
url_senate = "https://voteview.com/static/data/out/members/S0%s_members.csv" % congress
url_house = "https://voteview.com/static/data/out/members/H0%s_members.csv" % congress
elif int(congress) >= 100:
url_senate = "https://voteview.com/static/data/out/members/S%s_members.csv" % congress
url_house = "https://voteview.com/static/data/out/members/H%s_members.csv" % congress
else:
raise Exception("no data for congress " + congress)
senate_destination = "icpsr/source/senate_rollcall%s.txt" % congress
senate_data = utils.download(url_senate, senate_destination, force)
house_destination = "icpsr/source/house_rollcall%s.txt" % congress
house_data = utils.download(url_house, house_destination, force)
error_log = csv.writer(
open("cache/errors/mismatch/mismatch_%s.csv" % congress, "w"))
error_log.writerow([
"error_type", "matches", "icpsr_name", "icpsr_state", "is_territory",
"old_id", "new_id"
])
read_files = [("sen", senate_data), ("rep", house_data)]
print("Running for congress " + congress)
for read_file_chamber, read_file_content in read_files:
for data_file in data_files:
for legislator in data_file[0]:
num_matches = 0
write_id = ""
# this can't run unless we've already collected a bioguide for this person
bioguide = legislator["id"].get("bioguide", None)
# if we've limited this to just one bioguide, skip over everyone else
if only_bioguide and (bioguide != only_bioguide):
continue
#if not in currently read chamber, skip
chamber = legislator['terms'][len(legislator['terms']) -
1]['type']
if chamber != read_file_chamber:
continue
#only run for selected congress
latest_congress = utils.congress_from_legislative_year(
utils.legislative_year(
parse_date(
legislator['terms'][len(legislator['terms']) -
1]['start'])))
if chamber == "sen":
congresses = [
latest_congress, latest_congress + 1,
latest_congress + 2
]
else:
congresses = [latest_congress]
if int(congress) not in congresses:
continue
# pull data to match from yaml
last_name = legislator['name']['last'].upper()
state = utils.states[legislator['terms']
[len(legislator['terms']) -
1]['state']].upper()[:7].strip()
# convert read_file_content str to file object, then parse as csv file
content_as_file = StringIO(read_file_content)
content_parsed = csv.reader(content_as_file, delimiter=',')
# loop through congress members in read file, see if one matches the current legislator
for icpsr_member in content_parsed:
# ensure unique match bassed of bioguide id
if bioguide == icpsr_member[10]:
num_matches += 1
write_id = int(icpsr_member[2])
# skip if icpsr id is currently in data
if "icpsr" in legislator["id"]:
if write_id == legislator["id"]["icpsr"] or write_id == "":
continue
elif write_id != legislator["id"][
"icpsr"] and write_id != "":
error_log.writerow([
"Incorrect_ID", "NA", last_name[:8], state, "NA",
legislator["id"]["icpsr"], write_id
])
print("ID updated for %s" % last_name)
if num_matches == 1:
legislator['id']['icpsr'] = int(write_id)
else:
if state == 'GUAM' or state == 'PUERTO' or state == "VIRGIN" or state == "DISTRIC" or state == "AMERICA" or state == "NORTHER" or state == "PHILIPP":
print('error: non 1 match')
error_log.writerow([
"Non_1_match_number",
str(num_matches), last_name[:8], state, "Y", "NA",
"NA"
])
else:
print(
str(num_matches) + " matches found for " +
last_name[:8] + ", " + state + " in congress " +
str(congress))
error_log.writerow([
"Non_1_match_number",
str(num_matches), last_name, state, "N", "NA", "NA"
])
save_data(data_file[0], data_file[1])
def fetch_senate_committee_meetings(existing_meetings, committees, options):
# Parse the Senate committee meeting XML feed for meetings.
# To aid users of the data, attempt to assign GUIDs to meetings.
options = dict(options) # clone
options["binary"] = True
meetings = []
dom = lxml.etree.fromstring(utils.download(
"http://www.senate.gov/general/committee_schedules/hearings.xml",
"committee_schedule/senate.xml",
options))
for node in dom.xpath("meeting"):
committee_id = unicode(node.xpath('string(cmte_code)'))
if committee_id.strip() == "": continue # "No committee hearings scheduled" placeholder
occurs_at = unicode(node.xpath('string(date)'))
room = unicode(node.xpath('string(room)'))
topic = unicode(node.xpath('string(matter)'))
occurs_at = datetime.datetime.strptime(occurs_at, "%d-%b-%Y %I:%M %p")
topic = re.sub(r"\s+", " ", topic).strip()
# Validate committee code.
try:
committee_code, subcommittee_code = re.match(r"(\D+)(\d+)$", committee_id).groups()
if committee_code not in committees: raise ValueError(committee_code)
if subcommittee_code == "00": subcommittee_code = None
if subcommittee_code and subcommittee_code not in committees[committee_code]["subcommittees"]: raise ValueError(subcommittee_code)
except:
print "Invalid committee code", committee_id
continue
# See if this meeting already exists. If so, take its GUID.
# Assume meetings are the same if they are for the same committee/subcommittee and
# at the same time.
for mtg in existing_meetings:
if mtg["committee"] == committee_code and mtg.get("subcommittee", None) == subcommittee_code and mtg["occurs_at"] == occurs_at.isoformat():
guid = mtg["guid"]
break
else:
# Not found, so create a new ID.
guid = unicode(uuid.uuid4())
# Scrape the topic text for mentions of bill numbers.
congress = utils.congress_from_legislative_year(utils.current_legislative_year(occurs_at))
bills = []
bill_number_re = re.compile(r"(hr|s|hconres|sconres|hjres|sjres|hres|sres)\s?(\d+)", re.I)
for bill_match in bill_number_re.findall(topic.replace(".", "")):
bills.append( bill_match[0].lower() + bill_match[1] + "-" + str(congress) )
# Create the meeting event.
meetings.append({
"chamber": "senate",
"congress": congress,
"guid": guid,
"committee": committee_code,
"subcommittee": subcommittee_code,
"occurs_at": occurs_at.isoformat(),
"room": room,
"topic": topic,
"bills": bills,
})
return meetings
def fetch_senate_committee_meetings(existing_meetings, committees, options):
# Parse the Senate committee meeting XML feed for meetings.
# To aid users of the data, attempt to assign GUIDs to meetings.
options = dict(options) # clone
options["binary"] = True
meetings = []
dom = lxml.etree.fromstring(
utils.download(
"http://www.senate.gov/general/committee_schedules/hearings.xml",
"committee_schedule/senate.xml", options))
for node in dom.xpath("meeting"):
committee_id = unicode(node.xpath('string(cmte_code)'))
if committee_id.strip() == "":
continue # "No committee hearings scheduled" placeholder
occurs_at = unicode(node.xpath('string(date)'))
room = unicode(node.xpath('string(room)'))
topic = unicode(node.xpath('string(matter)'))
occurs_at = datetime.datetime.strptime(occurs_at, "%d-%b-%Y %I:%M %p")
topic = re.sub(r"\s+", " ", topic).strip()
# Validate committee code.
try:
committee_code, subcommittee_code = re.match(
r"(\D+)(\d+)$", committee_id).groups()
if committee_code not in committees:
raise ValueError(committee_code)
if subcommittee_code == "00": subcommittee_code = None
if subcommittee_code and subcommittee_code not in committees[
committee_code]["subcommittees"]:
raise ValueError(subcommittee_code)
except:
print "Invalid committee code", committee_id
continue
# See if this meeting already exists. If so, take its GUID.
# Assume meetings are the same if they are for the same committee/subcommittee and
# at the same time.
for mtg in existing_meetings:
if mtg["committee"] == committee_code and mtg.get(
"subcommittee", None) == subcommittee_code and mtg[
"occurs_at"] == occurs_at.isoformat():
guid = mtg["guid"]
break
else:
# Not found, so create a new ID.
guid = unicode(uuid.uuid4())
# Scrape the topic text for mentions of bill numbers.
congress = utils.congress_from_legislative_year(
utils.current_legislative_year(occurs_at))
bills = []
bill_number_re = re.compile(
r"(hr|s|hconres|sconres|hjres|sjres|hres|sres)\s?(\d+)", re.I)
for bill_match in bill_number_re.findall(topic.replace(".", "")):
bills.append(bill_match[0].lower() + bill_match[1] + "-" +
str(congress))
# Create the meeting event.
meetings.append({
"chamber": "senate",
"congress": congress,
"guid": guid,
"committee": committee_code,
"subcommittee": subcommittee_code,
"occurs_at": occurs_at.isoformat(),
"room": room,
"topic": topic,
"bills": bills,
})
return meetings
def fetch_senate_committee_meetings(committees, options):
# Load any existing meetings file so we can recycle any GUIDs.
existing_meetings = []
output_file = output_for("senate")
if os.path.exists(output_file):
existing_meetings = json.load(open(output_file))
options = dict(options) # clone
options["binary"] = True #
options["force"] = True
meetings = []
dom = lxml.etree.fromstring(
utils.download(
"http://www.senate.gov/general/committee_schedules/hearings.xml", "committee_schedule/senate.xml", options
)
)
for node in dom.xpath("meeting"):
committee_id = unicode(node.xpath("string(cmte_code)"))
if committee_id.strip() == "":
continue # "No committee hearings scheduled" placeholder
occurs_at = unicode(node.xpath("string(date)"))
room = unicode(node.xpath("string(room)"))
topic = unicode(node.xpath("string(matter)"))
occurs_at = datetime.datetime.strptime(occurs_at, "%d-%b-%Y %I:%M %p")
topic = re.sub(r"\s+", " ", topic).strip()
# Validate committee code.
try:
committee_code, subcommittee_code = re.match(r"(\D+)(\d+)$", committee_id).groups()
if committee_code not in committees:
raise ValueError(committee_code)
if subcommittee_code == "00":
subcommittee_code = None
if subcommittee_code and subcommittee_code not in committees[committee_code]["subcommittees"]:
raise ValueError(subcommittee_code)
except:
print "Invalid committee code", committee_id
continue
# See if this meeting already exists. If so, take its GUID.
# Assume meetings are the same if they are for the same committee/subcommittee and
# at the same time.
for mtg in existing_meetings:
if (
mtg["committee"] == committee_code
and mtg.get("subcommittee", None) == subcommittee_code
and mtg["occurs_at"] == occurs_at.isoformat()
):
if options.get("debug", False):
print "[%s] Reusing gUID." % mtg["guid"]
guid = mtg["guid"]
break
else:
# Not found, so create a new ID.
# TODO: Can we make this a human-readable ID?
guid = unicode(uuid.uuid4())
# Scrape the topic text for mentions of bill numbers.
congress = utils.congress_from_legislative_year(utils.current_legislative_year(occurs_at))
bills = []
bill_number_re = re.compile(r"(hr|s|hconres|sconres|hjres|sjres|hres|sres)\s?(\d+)", re.I)
for bill_match in bill_number_re.findall(topic.replace(".", "")):
bills.append(bill_match[0].lower() + bill_match[1] + "-" + str(congress))
# Create the meeting event.
if options.get("debug", False):
print "[senate][%s][%s] Found meeting in room %s at %s." % (
committee_code,
subcommittee_code,
room,
occurs_at.isoformat(),
)
meetings.append(
{
"chamber": "senate",
"congress": congress,
"guid": guid,
"committee": committee_code,
"subcommittee": subcommittee_code,
"occurs_at": occurs_at.isoformat(),
"room": room,
"topic": topic,
"bill_ids": bills,
}
)
print "[senate] Found %i meetings." % len(meetings)
return meetings
def run():
# default to caching
cache = utils.flags().get('cache', True)
force = not cache
only_bioguide = utils.flags().get('bioguide', None)
congress = utils.flags().get('congress',None)
data_files = []
print("Loading %s..." % "legislators-current.yaml")
legislators = load_data("legislators-current.yaml")
data_files.append((legislators,"legislators-current.yaml"))
print("Loading %s..." % "legislators-historical.yaml")
legislators = load_data("legislators-historical.yaml")
data_files.append((legislators,"legislators-historical.yaml"))
#load roll call data. Will need to be updated (possibly) for 114th+ congresses, since it is unclear what the URl format will be
if congress == None:
raise Exception("the --congress flag is required")
elif congress == "113":
url_senate = "http://amypond.sscnet.ucla.edu/rollcall/static/S113.ord"
url_house = "http://amypond.sscnet.ucla.edu/rollcall/static/H113.ord"
elif int(congress) <10 and int(congress) >0:
url_senate = "ftp://voteview.com/dtaord/sen0%skh.ord" % congress
url_house = "ftp://voteview.com/dtaord/hou0%skh.ord" % congress
elif int(congress) < 113 and int(congress) >= 10:
url_senate = "ftp://voteview.com/dtaord/sen%skh.ord" % congress
url_house = "ftp://voteview.com/dtaord/hou%skh.ord" % congress
else:
raise Exception("no data for congress " + congress)
senate_destination = "icpsr/source/senate_rollcall%s.txt" % congress
senate_data = utils.download(url_senate, senate_destination, force)
house_destination = "icpsr/source/house_rollcall%s.txt" % congress
house_data = utils.download(url_house, house_destination, force)
error_log = csv.writer(open("cache/errors/mismatch/mismatch_%s.csv" % congress, "wb"))
error_log.writerow(["error_type","matches","icpsr_name","icpsr_state","is_territory","old_id","new_id"])
read_files = [(senate_data,"sen"),(house_data,"rep")]
print("Running for congress " + congress)
for read_file in read_files:
for data_file in data_files:
for legislator in data_file[0]:
num_matches = 0
# # this can't run unless we've already collected a bioguide for this person
bioguide = legislator["id"].get("bioguide", None)
# if we've limited this to just one bioguide, skip over everyone else
if only_bioguide and (bioguide != only_bioguide):
continue
#if not in currently read chamber, skip
chamber = legislator['terms'][len(legislator['terms'])-1]['type']
if chamber != read_file[1]:
continue
#only run for selected congress
latest_congress = utils.congress_from_legislative_year(utils.legislative_year(parse_date(legislator['terms'][len(legislator['terms'])-1]['start'])))
if chamber == "sen":
congresses = [latest_congress,latest_congress+1,latest_congress+2]
else:
congresses =[latest_congress]
if int(congress) not in congresses:
continue
# pull data to match from yaml
last_name_unicode = legislator['name']['last'].upper().strip().replace('\'','')
last_name = unicodedata.normalize('NFD', str(last_name_unicode)).encode('ascii', 'ignore')
state = utils.states[legislator['terms'][len(legislator['terms'])-1]['state']].upper()[:7].strip()
# select icpsr source data based on more recent chamber
write_id = ""
lines = read_file[0].split('\n')
for line in lines:
# parse source data
icpsr_state = line[12:20].strip()
icpsr_name = line[21:].strip().strip(string.digits).strip()
icpsr_id = line[3:8].strip()
#ensure unique match
if icpsr_name[:8] == last_name[:8] and state == icpsr_state:
num_matches += 1
write_id = icpsr_id
#skip if icpsr id is currently in data
if "icpsr" in legislator["id"]:
if write_id == legislator["id"]["icpsr"] or write_id == "":
continue
elif write_id != legislator["id"]["icpsr"] and write_id != "":
error_log.writerow(["Incorrect_ID","NA",last_name[:8],state,"NA",legislator["id"]["icpsr"],write_id])
print("ID updated for %s" % last_name)
if num_matches == 1:
legislator['id']['icpsr'] = int(write_id)
else:
if state == 'GUAM' or state == 'PUERTO' or state == "VIRGIN" or state == "DISTRIC" or state == "AMERICA" or state == "NORTHER" or state == "PHILIPP":
error_log.writerow(["Non_1_match_number",str(num_matches),last_name[:8],state,"Y","NA","NA"])
else:
print(str(num_matches) + " matches found for "+ last_name[:8] + ", " + state + " in congress " + str(congress))
error_log.writerow(["Non_1_match_number",str(num_matches),last_name,state,"N","NA","NA"])
save_data(data_file[0], data_file[1])