def test_datasets_existance(self):
# Load all datasets
load_febrl1()
load_febrl2()
load_febrl3()
load_febrl4()
def test_febrl3(self):
df = load_febrl3()
self.assertIsInstance(df, pandas.DataFrame)
self.assertEqual(len(df), 5000)
df, links = load_febrl3(return_links=True)
self.assertIsInstance(df, pandas.DataFrame)
self.assertEqual(len(df), 5000)
self.assertIsInstance(links, pandas.MultiIndex)
'''
from __future__ import print_function
import recordlinkage as rl
from recordlinkage.index import Block
from recordlinkage.compare import Exact, String
from recordlinkage.datasets import load_febrl3
# set logging
rl.logging.set_verbosity(rl.logging.INFO)
# load dataset
print('Loading data...')
dfA, true_links = load_febrl3(return_links=True)
print(len(dfA), 'records in dataset A')
print(len(true_links), 'links in dataset A')
# start indexing
print('Build index...')
indexer = rl.Index()
indexer.add(Block('given_name'))
indexer.add(Block('surname'))
indexer.add(Block('soc_sec_id'))
candidate_links = indexer.index(dfA)
# start comparing
print('Start comparing...')
comparer = rl.Compare()
comparer.add(Exact('given_name', 'given_name', label='given_name'))