def semi_join(left, right=None, on=None):
if isinstance(on, Mapping):
# coerce colnames to list, to avoid indexing with tuples
on_cols, right_on = map(list, zip(*on.items()))
right = right[right_on].rename(dict(zip(right_on, on_cols)))
elif on is None:
on_cols = set(left.columns).intersection(set(right.columns))
if not len(on_cols):
raise Exception(
"No joining column specified, and no shared column names")
elif isinstance(on, str):
on_cols = [on]
else:
on_cols = on
# get our semi join on ----
if len(on_cols) == 1:
col_name = on_cols[0]
indx = left[col_name].isin(right[col_name])
return left.loc[indx]
# Not a super efficient approach. Effectively, an inner join with what would
# be duplicate rows removed.
merger = _MergeOperation(left, right, left_on=on_cols, right_on=on_cols)
_, l_indx, _ = merger._get_join_info()
range_indx = pd.RangeIndex(len(left))
return left.loc[range_indx.isin(l_indx)]
def anti_join(left, right=None, on=None):
"""Return the left table with every row that would *not* be kept in an inner join.
"""
# copied from semi_join
if isinstance(on, Mapping):
left_on, right_on = zip(*on.items())
# manually perform merge, up to getting pieces need for indexing
merger = _MergeOperation(left, right, left_on=left_on, right_on=right_on)
_, l_indx, _ = merger._get_join_info()
# use the left table's indexer to exclude those rows
range_indx = pd.RangeIndex(len(left))
return left.iloc[range_indx.difference(l_indx), :]
