pairs = self._link_index(*x)
names = self._make_index_names(x[0].index.name, x[1].index.name)
# deduplication
else:
pairs = self._dedup_index(*x)
names = self._make_index_names(x[0].index.name, x[0].index.name)
pairs.rename(names, inplace=True)
return pairs
BaseIndexator = DeprecationHelper(BaseIndexAlgorithm)
class BaseCompareFeature(object):
"""Base abstract class for compare feature engineering.
Parameters
----------
labels_left : list, str, int
The labels to use for comparing record pairs in the left
dataframe.
labels_right : list, str, int
The labels to use for comparing record pairs in the right
dataframe (linking) or left dataframe (deduplication).
args : tuple
Additional arguments to pass to the `_compare_vectorized`
# large dataframes
if n_max < 1e6:
pairs = random_pairs_without_replacement_small_frames(
self.n, shape, self.random_state)
# small dataframes
else:
pairs = random_pairs_without_replacement_large_frames(
self.n, shape, self.random_state)
levels = [df_a.index.values, df_a.index.values]
labels = pairs
return pandas.MultiIndex(levels=levels,
labels=labels,
verify_integrity=False)
FullIndex = DeprecationHelper(
Full, "class recordlinkage.FullIndex is renamed and moved, "
"use recordlinkage.index.Full")
BlockIndex = DeprecationHelper(
Block, "class recordlinkage.BlockIndex is renamed and moved, "
"use recordlinkage.index.Block")
SortedNeighbourhoodIndex = DeprecationHelper(
SortedNeighbourhood, "class recordlinkage.SortedNeighbourhoodIndex "
"is renamed and moved, use recordlinkage.index.SortedNeighbourhood")
RandomIndex = DeprecationHelper(
Random, "class recordlinkage.RandomIndex is renamed and moved, "
"use recordlinkage.index.Random")
"n must be a integer satisfying 0<n<=%s" % n_max)
# large dataframes
if n_max < 1e6:
pairs = random_pairs_without_replacement_small_frames(
self.n, shape, self.random_state)
# small dataframes
else:
pairs = random_pairs_without_replacement_large_frames(
self.n, shape, self.random_state)
levels = [df_a.index.values, df_a.index.values]
labels = pairs
return pandas.MultiIndex(
levels=levels,
labels=labels,
verify_integrity=False
)
FullIndex = DeprecationHelper(
Full, "This class is moved to recordlinkage.index.Full.")
BlockIndex = DeprecationHelper(
Block, "This class is moved to recordlinkage.index.Block.")
SortedNeighbourhoodIndex = DeprecationHelper(
SortedNeighbourhood,
"This class is moved to recordlinkage.index.SortedNeighbourhood.")
RandomIndex = DeprecationHelper(
Random, "This class is moved to recordlinkage.index.Random.")
if self.swap_months == 'default':
self.swap_months = [(6, 7, 0.5), (7, 6, 0.5), (9, 10, 0.5),
(10, 9, 0.5)]
else:
try:
if not all([len(x) == 3 for x in self.swap_months]):
raise Exception
except Exception:
raise ValueError(
'swap_months must be a list of (first month, \
second month, value) tuples or lists. ')
for month1, month2, value in self.swap_months:
c[(s1.dt.year == s2.dt.year) & (s1.dt.month == month1) &
(s2.dt.month == month2) & (s1.dt.day == s2.dt.day) &
(c != 1)] = value
c = pandas.Series(c)
c[s1.isnull() | s2.isnull()] = self.missing_value
return c
CompareExact = DeprecationHelper(Exact, "This class is renamed into Exact.")
CompareString = DeprecationHelper(String, "This class is renamed into String.")
CompareNumeric = DeprecationHelper(Numeric,
"This class is renamed into Numeric.")
CompareGeographic = DeprecationHelper(
Geographic, "This class is renamed into Geographic.")
CompareDate = DeprecationHelper(Date, "This class is renamed into Date.")