from open_elections.tools import StateDataFormat
def remove_invalid_vote_counts(dic: dict):
value = dic['votes']
if value in ['x', 'X', 'X ', ' ', 'X394', 'X.', 'X:', '"X"', '-', '`']:
dic['votes'] = None
national_precinct_dataformat = StateDataFormat(
row_cleaners=[remove_invalid_vote_counts])
from open_elections.tools import StateDataFormat
import pandas as pd
def remove_invalid_vote_counts(dic: dict):
value = dic['votes']
if value in ['Write-ins', 'ESTES R', 'I']:
dic['votes'] = None
def rename_vote_cols(df: pd.DataFrame) -> pd.DataFrame:
if 'Unnamed: 6'.lower() in df.columns:
return df.rename(columns={'Unnamed: 6'.lower(): 'votes'})
else:
return df
national_precinct_dataformat = StateDataFormat(
df_transformers=[rename_vote_cols],
row_cleaners=[remove_invalid_vote_counts])
from open_elections.tools import StateDataFormat
import pandas as pd
# need to exclude 20021105__wv__general__monongalia__precinct.csv
def remove_invalid_vote_counts(dic: dict):
value = dic['votes']
if type(value) == str and value == ' ':
dic['votes'] = None
def rename_total_to_votes(df: pd.DataFrame):
if 'total votes' in df.columns:
return df.rename(columns={'total votes': 'votes'})
else:
return df
national_precinct_dataformat = StateDataFormat(
excluded_files=['20021105__wv__general__monongalia__precinct.csv'],
df_transformers=[rename_total_to_votes],
row_cleaners=[remove_invalid_vote_counts])
from open_elections.tools import StateDataFormat
national_precinct_dataformat = StateDataFormat(df_transformers=[
lambda df: df.rename(columns={'election_district': 'precinct'})
])
from open_elections.tools import StateDataFormat, get_coerce_to_integer
import pandas as pd
def fix_vote_counts(df: pd.DataFrame) -> pd.DataFrame:
if 'total' in df.columns:
return df.rename(columns={'total': 'votes'})
else:
breakout_cols = [
col for col in ['poll', 'edr', 'abs'] if col in df.columns
]
if breakout_cols:
temp = df.copy()
for col in breakout_cols:
if col in temp.columns:
temp[col] = temp[col].apply(
get_coerce_to_integer([' - ']))
return temp.assign(votes=df[breakout_cols].sum(axis=1))
else:
return df
national_precinct_dataformat = StateDataFormat(
df_transformers=[fix_vote_counts])
from open_elections.tools import StateDataFormat
import pandas as pd
def rename_total_to_votes(df: pd.DataFrame):
if 'total_votes' in df.columns:
return df.rename(columns={'total_votes': 'votes'})
else:
return df
national_precinct_dataformat = StateDataFormat(
df_transformers=[rename_total_to_votes])
from open_elections.tools import StateDataFormat
import pandas as pd
INVALID_VOTES_VALUES = ['#REF!', 'REP', 'DEM', 'LIB', 'GRN', 'votes']
def remove_invalid_vote_counts(dic: dict):
value = dic['votes']
if value in INVALID_VOTES_VALUES:
dic['votes'] = None
elif type(value) == str and '*' in value:
dic['votes'] = int(value.lstrip().replace('*', ''))
def insert_missing_votes_column(df: pd.DataFrame) -> pd.DataFrame:
if 'early_voting' in df.columns and 'election_day' in df.columns and 'votes' not in df.columns:
return df.assign(votes=df['early_voting'] + df['election_day'])
national_precinct_dataformat = StateDataFormat(
df_transformers=[insert_missing_votes_column],
row_cleaners=[remove_invalid_vote_counts]
)
'20160830__az__primary__graham__precinct.csv',
'20160830__az__primary__santa_cruz__precinct.csv',
'20160830__az__primary__la_paz__precinct.csv',
'20160322__az__primary__president__la_paz__precinct.csv',
'20160322__az__primary__president__apache__precinct.csv',
'20160830__az__primary__apache__precinct.csv',
'20160322__az__primary__president__cochise__precinct.csv',
'20160830__az__primary__mohave__precinct.csv',
'20160322__az__primary__president__mohave__precinct.csv',
'20160830__az__primary__yuma__precinct.csv',
'20160322__az__primary__president__pinal__precinct.csv',
'20160322__az__primary__president__gila__precinct.csv',
'20160830__az__primary__gila__precinct.csv',
'20160322__az__primary__president__yuma__precinct.csv',
'20160830__az__primary__navajo__precinct.csv',
'20160830__az__primary__yavapai__precinct.csv',
'20160322__az__primary__president__coconino__precinct.csv',
'20160830__az__primary__pima__precinct.csv',
'20160322__az__primary__president__greenlee__precinct.csv',
'20160830__az__primary__pinal__precinct.csv',
'20160322__az__primary__president__maricopa__precinct.csv',
'20160322__az__primary__president__pima__precinct.csv',
'20160322__az__primary__president__santa_cruz__precinct.csv',
'20160830__az__primary__maricopa__precinct.csv',
'20160830__az__primary__cochise__precinct.csv',
'20160830__az__primary__coconino__precinct.csv',
'20160830__az__primary__greenlee__precinct.csv'
]
national_precinct_dataformat = StateDataFormat(excluded_files=INVALID_FILES)
from open_elections.tools import StateDataFormat
def remove_emtpy_string_vote_counts(dic: dict):
if dic['votes'] == ' ':
dic['votes'] = None
national_precinct_dataformat = StateDataFormat(
row_cleaners=[remove_emtpy_string_vote_counts])
from open_elections.tools import StateDataFormat
national_precinct_dataformat = StateDataFormat(
excluded_files=['20081104__hi__general__precinct.csv'])
