talfco

    def __calculate_name_matching(self, row):
        name = row['lastName']+' '+row['firstName']+' '+row['middleName']
        norm_name = sort_words(normalize_unicode_to_ascii(name))
        tp = double_metaphone(norm_name)
        row['col_match1'] = norm_name
        row['col_match2'] = tp[0]
        row['col_match3'] = tp[1]
        return row

talfco

    def create_politican_from_govapi_table(self):
        self.load_government_members()
        df = DataFrame.from_records(self._members)
        df = df.apply(self.__calculate_name_matching, axis=1)
        return df

talfco

# -*- coding: utf-8 -*-
import re
import unicodedata

def normalize_unicode_to_ascii(data):
    normal = unicodedata.normalize('NFKD', data).encode('ASCII', 'ignore')
    val = normal.decode("utf-8")
    val = val.lower()
    # remove special characters
    val = re.sub('[^A-Za-z0-9 ]+', ' ', val)

talfco

talfco

# -*- coding: utf-8 -*-
import pytest
from name_matching import double_metaphone,double_metaphone_compare, Threshold

class TestClass(object):

    def test_double_metaphone(self):
        tp1 = double_metaphone(u'LilianeMauryPasquier')
        tp2 = double_metaphone(u'liliane Maury Pasquier')
        assert True == double_metaphone_compare(tp1,tp2,Threshold.STRONG)

talfco

# -*- coding: utf-8 -*-
from metaphone import doublemetaphone
from enum import Enum

class Threshold(Enum):
    WEAK = 0
    NORMAL = 1
    STRONG = 2

def double_metaphone(value):

talfco

talfco

    def __calculate_name_matching(self, row):
        name = row['Name']
        for clean in self.__cfg['twitterNameCleaner']:
            name = name.replace(clean ,'')
        for expand in self.__cfg['twitterNamesExpander']:
            name = name.replace(expand.get('abbreviation'), expand.get('name'))

talfco

twitterNameCleaner: ["Dr.","Zürich"]
twitterNamesExpander:
  - abbreviation: "Chr."
    name: "Christophe"

talfco