def _standardized_filename(self, election, bits=None, **kwargs):
"""
Standardize a result filename for an election.
Arguments:
election - Dictionary containing election metadata as returned by
the elections API. Required.
bits - List of filename elements. These will be prepended to the
filename. List items will be separated by "__".
Keyword arguments:
reporting_level
jurisdiction
office
office_district
extension - Filename extension, including the leading '.'.
Defaults to extension of first file in elections
'direct-links'.
"""
reporting_level = kwargs.get('reporting_level')
jurisdiction = kwargs.get('jurisdiction')
office = kwargs.get('office')
office_district = kwargs.get('office_district')
extension = kwargs.get('extension')
if extension is None:
extension = self._filename_extension(election)
if bits is None:
bits = []
bits.extend([
election['start_date'].replace('-', ''),
self.state,
])
if election['special']:
bits.append('special')
bits.append(election['race_type'].replace('-', '_'))
if jurisdiction:
bits.append(slugify(jurisdiction))
if office:
bits.append(slugify(office))
if office_district:
bits.append(slugify(office_district))
if reporting_level:
bits.append(reporting_level)
return "__".join(bits) + extension
def _standardized_filename(self, election, bits=None, **kwargs):
"""
Standardize a result filename for an election.
Arguments:
election - Dictionary containing election metadata as returned by
the elections API. Required.
bits - List of filename elements. These will be prepended to the
filename. List items will be separated by "__".
Keyword arguments:
reporting_level
jurisdiction
office
office_district
extension - Filename extension, including the leading '.'.
Defaults to extension of first file in elections
'direct-links'.
"""
reporting_level = kwargs.get('reporting_level')
jurisdiction = kwargs.get('jurisdiction')
office = kwargs.get('office')
office_district = kwargs.get('office_district')
extension = kwargs.get('extension')
if extension is None:
extension = self._filename_extension(election)
if bits is None:
bits = []
bits.extend([
election['start_date'].replace('-', ''),
self.state,
])
if election['special']:
bits.append('special')
bits.append(election['race_type'].replace('-', '_'))
if jurisdiction:
bits.append(slugify(jurisdiction))
if office:
bits.append(slugify(office))
if office_district:
bits.append(slugify(office_district))
if reporting_level:
bits.append(reporting_level)
return "__".join(bits) + extension
def contest_slug(self):
"""
A slugified version of the raw contest information.
This will not neccesarily match the slug on canonical Contest records.
"""
slug = "%s" % slugify(self.office)
if self.district:
slug += "-%s" % slugify(self.district.lstrip('0'))
if self.primary_party:
slug += "-%s" % slugify(self.primary_party)
return slug
def contest_slug(self):
"""
A slugified version of the raw contest information.
This will not neccesarily match the slug on canonical Contest records.
"""
slug = "%s" % slugify(self.office)
if self.district:
slug += "-%s" % slugify(self.district.lstrip('0'))
if self.primary_party:
slug += "-%s" % slugify(self.primary_party)
return slug
def slug(self):
"""
Returns slugified office in format "name-district".
Example:
>>> office = Office(state="MD", name="House of Delegates", district="35B", chamber="lower")
>>> office.slug
u'house-of-delegates-35b'
"""
slug = slugify(self.name, '-')
if self.district:
slug += "-%s" % slugify(self.district, '-')
return slug
def slug(self):
"""
Returns slugified office in format "name-district".
Example:
>>> office = Office(state="MD", name="House of Delegates", district="35B", chamber="lower")
>>> office.slug
u'house-of-delegates-35b'
"""
slug = slugify(self.name, '-')
if self.district:
slug += "-%s" % slugify(self.district, '-')
return slug
def post_init(cls, sender, document, **kwargs):
if not document.slug:
if document.office:
document.slug = document.make_slug(
office=document.office,
primary_party=document.primary_party)
else:
document.slug = slugify(document.contest_name, '-')
def _build_candidate_kwargs(self, row):
full_name = row['choice'].strip()
slug = slugify(full_name, substitute='-')
kwargs = {
'full_name': full_name,
'name_slug': slug,
}
return kwargs
def _build_candidate_kwargs(self, row):
full_name = row['choice'].strip()
slug = slugify(full_name, substitute='-')
kwargs = {
'full_name': full_name,
'name_slug': slug,
}
return kwargs
def _build_candidate_kwargs(self, row):
full_name = row['Name'].strip()
slug = slugify(full_name, substitute='-')
kwargs = {
'full_name': full_name,
#TODO: QUESTION: Do we need this? if so, needs a matching model field on RawResult
'name_slug': slug,
}
return kwargs
def _build_candidate_kwargs(self, row):
full_name = row['Name'].strip()
slug = slugify(full_name, substitute='-')
kwargs = {
'full_name': full_name,
#TODO: QUESTION: Do we need this? if so, needs a matching model field on RawResult
'name_slug': slug,
}
return kwargs
def make_slug(cls, **kwargs):
bits = (
kwargs['election_id'],
kwargs['contest_slug'],
kwargs['candidate_slug'],
kwargs['reporting_level'],
slugify(kwargs['jurisdiction']),
)
return u'%s-%s-%s-%s-%s' % bits
def _build_contest_slug(self, row):
office = row['Office Name'].strip()
bits = [office]
district = row['Office District'].strip()
if district and 'pres' not in office.lower():
bits.append(district)
if 'primary' in self.source:
bits.append(row['Party'].lower())
return slugify(" ".join(bits), substitute='-')
def make_slug(cls, **kwargs):
bits = (
kwargs['election_id'],
kwargs['contest_slug'],
kwargs['candidate_slug'],
kwargs['reporting_level'],
slugify(kwargs['jurisdiction']),
)
return u'%s-%s-%s-%s-%s' % bits
def _build_candidate_kwargs(self, candidateName, partyName):
slug = slugify(candidateName, substitute='-')
kwargs = {
'party': partyName,
'full_name': candidateName,
#TODO: QUESTION: Do we need this? if so, needs a matching model field on RawResult
'name_slug': slug,
}
return kwargs
def _build_candidate_kwargs(self, candidate, party):
# check if party is in name, extract if so
full_name = candidate
slug = slugify(full_name, substitute='-')
kwargs = {
'full_name': full_name,
'name_slug': slug,
'party': party,
}
return kwargs
def _build_candidate_kwargs(self, candidate):
if ", " in candidate:
cand, party = candidate.split(", ")
party = party.upper()
else:
cand = candidate
party = None
slug = slugify(cand, substitute='-')
kwargs = {'full_name': cand, 'name_slug': slug, 'party': party}
if 'Scatter' in cand:
kwargs.update({'write_in': True})
return kwargs
def _build_candidate_kwargs(self, row):
try:
full_name = row['Candidate Name'].strip()
except KeyError:
# 2000 results use "Candidate" for the column name
full_name = row['Candidate'].strip()
slug = slugify(full_name, substitute='-')
kwargs = {
'full_name': full_name,
#TODO: QUESTION: Do we need this? if so, needs a matching model field on RawResult
'name_slug': slug,
}
return kwargs
def _build_candidate_kwargs(self, row):
try:
full_name = row['Candidate Name'].strip()
except KeyError:
# 2000 results use "Candidate" for the column name
full_name = row['Candidate'].strip()
slug = slugify(full_name, substitute='-')
kwargs = {
'full_name': full_name,
#TODO: QUESTION: Do we need this? if so, needs a matching model field on RawResult
'name_slug': slug,
}
return kwargs
def _build_candidate_kwargs(self, row):
if row['candidate'].strip() == 'UnderVotes':
row['candidate'] = 'Under Votes'
elif row['candidate'].strip() == 'OverVotes':
row['candidate'] = 'Over Votes'
elif row['candidate'].strip() == 'WriteinVotes':
row['candidate'] = 'Write-ins'
full_name = row['candidate'].strip()
slug = slugify(full_name, substitute='-')
kwargs = {
'full_name': full_name,
'name_slug': slug,
}
return kwargs
def _build_candidate_kwargs(self, row):
if row['candidate'].strip() == 'UnderVotes':
row['candidate'] = 'Under Votes'
elif row['candidate'].strip() == 'OverVotes':
row['candidate'] = 'Over Votes'
elif row['candidate'].strip() == 'WriteinVotes':
row['candidate'] = 'Write-ins'
full_name = row['candidate'].strip()
slug = slugify(full_name, substitute='-')
kwargs = {
'full_name': full_name,
'name_slug': slug,
}
return kwargs
def _build_candidate_kwargs(self, candidate):
if ", " in candidate:
cand, party = candidate.split(", ")
party = party.upper()
else:
cand = candidate
party = None
slug = slugify(cand, substitute='-')
kwargs = {
'full_name': cand,
'name_slug': slug,
'party': party
}
if 'Scatter' in cand:
kwargs.update({'write_in': True})
return kwargs
def candidate_slug(self):
"""
A slugified version of the raw candidate information.
This will not neccesarily match the slug on canonical Candidate records.
"""
if self.full_name:
name = self.full_name
else:
name = self.family_name
if self.given_name:
name += " %s" % self.given_name
if self.additional_name:
name += " %s" % self.additional_name
if self.suffix:
name += " %s" % self.suffix
return slugify(name)
def candidate_slug(self):
"""
A slugified version of the raw candidate information.
This will not neccesarily match the slug on canonical Candidate records.
"""
if self.full_name:
name = self.full_name
else:
name = self.given_name
if self.additional_name:
name += " %s" % self.additional_name
if self.family_name:
name += " %s" % self.family_name
if self.suffix:
name += " %s" % self.suffix
return slugify(name)
def _key(self, rawresult):
"""
Returns a string that uniquely identifies a raw result from a particular
source.
"""
bits = [rawresult.contest_slug, rawresult.candidate_slug,
slugify(rawresult.jurisdiction)]
if rawresult.district:
bits.append(rawresult.district)
try:
bits.append(rawresult.reporting_district)
except AttributeError:
pass
return '-'.join(bits)
def _key(self, rawresult):
"""
Returns a string that uniquely identifies a raw result from a particular
source.
"""
bits = [rawresult.contest_slug, rawresult.candidate_slug,
slugify(rawresult.jurisdiction)]
if rawresult.district:
bits.append(rawresult.district)
try:
bits.append(rawresult.reporting_district)
except AttributeError:
pass
return '-'.join(bits)
def load(self):
workbook = xlrd.open_workbook(self._xls_file_path)
results = []
# workbook = xlrd.open_workbook(xlsfile)
worksheet = workbook.sheet_by_name('Master')
raw_offices = [c.value.strip() for c in worksheet.row(0)[5:]]
last_office_column = self._get_last_office_column(raw_offices)
offices = self._get_offices(raw_offices, last_office_column)
candidates = [
c.value for c in worksheet.row(1)[5:last_office_column + 7]
]
combined = list(zip(offices, candidates))
for i in range(4, worksheet.nrows):
row = [c.value for c in worksheet.row(i)[:last_office_column + 5]]
county = row[0]
county_ocd_id = [
c for c in self.datasource._jurisdictions()
if c['county'].upper() == county.upper()
][0]['ocd_id']
results = row[5:last_office_column + 5]
for result in zip(combined, results):
if result[1] == 0.0:
continue
office, candidate = result[0]
cand, party = candidate.split(' (')
party = party.replace(')', '')
votes = result[1]
kwargs = self._base_kwargs(row)
slug = slugify(cand, substitute='-')
kwargs.update({
'office': office,
'district': district,
'full_name': cand,
'slug': slug,
'party': party,
'votes': votes,
'reporting_level': 'county',
'jurisdiction': county,
'ocd_id': county_ocd_id,
})
results.append(kwargs)
RawResult.objects.insert(results)
def _get_or_create_candidate(self, row, contest):
raw_full_name = row['Candidate Name'].strip()
slug = slugify(raw_full_name, substitute='-')
key = (self.election_id, contest.slug, slug)
try:
candidate = self.cand_lkup[key]
except KeyError:
cand_kwargs = {
'source': self.source,
'election_id': self.election_id,
'contest': contest,
'contest_slug': contest.slug,
'state': self.state.upper(),
'raw_full_name': raw_full_name,
'slug': slug,
}
candidate = Candidate.objects.create(**cand_kwargs)
candidate.save()
self.cand_lkup[key] = candidate
return candidate
def load(self):
workbook = xlrd.open_workbook(self._xls_file_path)
results = []
# workbook = xlrd.open_workbook(xlsfile)
worksheet = workbook.sheet_by_name('Master')
raw_offices = [c.value.strip() for c in worksheet.row(0)[5:]]
last_office_column = self._get_last_office_column(raw_offices)
offices = self._get_offices(raw_offices, last_office_column)
candidates = [c.value for c in worksheet.row(1)[5:last_office_column+7]]
combined = list(zip(offices, candidates))
for i in range(4, worksheet.nrows):
row = [c.value for c in worksheet.row(i)[:last_office_column+5]]
county = row[0]
county_ocd_id = [c for c in self.datasource._jurisdictions() if c['county'].upper() == county.upper()][0]['ocd_id']
results = row[5:last_office_column+5]
for result in zip(combined, results):
if result[1] == 0.0:
continue
office, candidate = result[0]
cand, party = candidate.split(' (')
party = party.replace(')','')
votes = result[1]
kwargs = self._base_kwargs(row)
slug = slugify(cand, substitute='-')
kwargs.update(
{'office': office,
'district': district,
'full_name': cand,
'slug': slug,
'party': party,
'votes': votes,
'reporting_level': 'county',
'jurisdiction': county,
'ocd_id': county_ocd_id,
})
results.append(kwargs)
RawResult.objects.insert(results)
def _standardized_filename(self, election, bits=None, **kwargs):
"""
Standardize a result filename for an election.
For more on filename standardization conventsions, see
http://docs.openelections.net/archive-standardization/.
Args:
election: Dictionary containing election metadata as returned by
the elections API. Required.
bits: List of filename elements. These will be prepended to the
filename. List items will be separated by "__".
reporting_level: Slug string representing the reporting level of
the data file. This could be something like 'county' or
'precinct'.
jurisdiction: String representing the jurisdiction of the data
covered in the file.
office: String representing the office if results are for a single
office.
office_district: String representing the office district numver if
the results in the file are for a single office.
extension: Filename extension, including the leading '.'.
Defaults to extension of first file in election's
``direct_links``.
Returns:
A string representing the standardized filename for
an election's data file.
"""
# TODO([email protected]) Delegate to
# openelex.lib.standardized_filename()
reporting_level = kwargs.get('reporting_level')
jurisdiction = kwargs.get('jurisdiction')
office = kwargs.get('office')
office_district = kwargs.get('office_district')
extension = kwargs.get('extension')
if extension is None:
extension = self._filename_extension(election['direct_links'][0])
if bits is None:
bits = []
bits.extend([
election['start_date'].replace('-', ''),
self.state,
])
if election['special']:
bits.append('special')
bits.append(election['race_type'].replace('-', '_'))
if jurisdiction:
bits.append(slugify(jurisdiction))
if office:
bits.append(slugify(office))
if office_district:
bits.append(slugify(office_district))
if reporting_level:
bits.append(reporting_level)
return "__".join(bits) + extension
def make_slug(cls, **kwargs):
return slugify(kwargs.get('full_name'), '-')
def slug(self):
return slugify(self.abbrev)
def standardized_filename(state, start_date, extension,
party=None, special=False, race_type=None, reporting_level=None,
jurisdiction=None, office=None, office_district=None,
prefix_bits=[], suffix_bits=[], sep="__"):
"""
Standardize an election-related filename.
For more on filename standardization conventions, see
http://docs.openelections.net/archive-standardization/.
Args:
state (string): State abbreviation, for example "md".
start_date (string): String representing the election's start date
in YYYY-MM-DD format.
extension (string): Filename extension, including the leading '.'. For
example, ".csv".
party (string, optional): Slug representing the political party of
information in the file.
special (boolean, optional): Whether the file contains data related to a
special election. Default is False.
race_type (string, optional): Slug representing the type of election
contest. For example, "general", "primary", etc.
reporting_level (string, optional): Slug representing the reporting level of
the data file. This could be something like 'county' or
'precinct'.
jurisdiction (string, optional): The jurisdiction of the data
covered in the file.
office (string, optional): Office if results are for a single office.
office_district (string, optional): Office district number if
the data in the file are for a single office.
prefix_bits (list, optional): List of strings that will be prepended to
the generated filename and separated by the value of ``sep``.
suffix_bits (list, optional): List of strings that will be appended
to the generated filename and separated by the value of ``sep``.
sep (string, optional): Separator between filename elements. Default
is "__".
Returns:
A string representing the standardized filename for
election-related data.
"""
# Store filename components in a list that we'll eventually join together
bits = []
# Filename starts with the prefix bits, if any
bits.extend(prefix_bits)
# All filenames need a date and a state
bits.extend([
start_date.replace('-', ''),
state.lower(),
])
if special:
bits.append('special')
if party:
bits.append(slugify(party))
if race_type:
bits.append(race_type.replace('-', '_'))
if jurisdiction:
bits.append(slugify(jurisdiction))
if office:
bits.append(slugify(office))
if office_district:
bits.append(slugify(office_district))
if reporting_level:
bits.append(reporting_level)
bits.extend(suffix_bits)
return sep.join(bits) + extension
def slug(self):
return slugify(self.raw_full_name, '-')
def slug(self):
return slugify(self.abbrev)
def slug(self):
return slugify(self.raw_office, "-")
def slug(self):
return slugify(self.raw_full_name, '-')
def standardized_filename(state, start_date, extension,
party=None, special=False, race_type=None, reporting_level=None,
jurisdiction=None, office=None, office_district=None,
prefix_bits=[], suffix_bits=[], sep="__"):
"""
Standardize an election-related filename.
For more on filename standardization conventions, see
http://docs.openelections.net/archive-standardization/.
Args:
state (string): State abbreviation, for example "md".
start_date (string): String representing the election's start date
in YYYY-MM-DD format.
extension (string): Filename extension, including the leading '.'. For
example, ".csv".
party (string, optional): Slug representing the political party of
information in the file.
special (boolean, optional): Whether the file contains data related to a
special election. Default is False.
race_type (string, optional): Slug representing the type of election
contest. For example, "general", "primary", etc.
reporting_level (string, optional): Slug representing the reporting level of
the data file. This could be something like 'county' or
'precinct'.
jurisdiction (string, optional): The jurisdiction of the data
covered in the file.
office (string, optional): Office if results are for a single office.
office_district (string, optional): Office district number if
the data in the file are for a single office.
prefix_bits (list, optional): List of strings that will be prepended to
the generated filename and separated by the value of ``sep``.
suffix_bits (list, optional): List of strings that will be appended
to the generated filename and separated by the value of ``sep``.
sep (string, optional): Separator between filename elements. Default
is "__".
Returns:
A string representing the standardized filename for
election-related data.
"""
# Store filename components in a list that we'll eventually join together
bits = []
# Filename starts with the prefix bits, if any
bits.extend(prefix_bits)
# All filenames need a date and a state
bits.extend([
start_date.replace('-', ''),
state.lower(),
])
if special:
bits.append('special')
if party:
bits.append(slugify(party))
if race_type:
bits.append(race_type.replace('-', '_'))
if jurisdiction:
bits.append(slugify(jurisdiction))
if office:
bits.append(slugify(office))
if office_district:
bits.append(slugify(office_district))
if reporting_level:
bits.append(reporting_level)
bits.extend(suffix_bits)
return sep.join(bits) + extension
def make_slug(cls, **kwargs):
return slugify(kwargs.get('full_name'), '-')
def slug(self):
return slugify(self.raw_office, "-")
