def max_pairs(shape):
"""[DEPRECATED] Compute the maximum number of record pairs possible."""
if not isinstance(shape, (tuple, list)):
x = get_length(shape)
n = int(x * (x - 1) / 2)
elif (isinstance(shape, (tuple, list)) and len(shape) == 1):
x = get_length(shape[0])
n = int(x * (x - 1) / 2)
else:
n = numpy.prod([get_length(xi) for xi in shape], dtype=numpy.uint64)
return n
def full_index_size(*args):
"""Compute the number of records in a full index.
Compute the number of records in a full index without building the index
itself. The result is the maximum number of record pairs possible. This
function is especially useful in measures like the `reduction_ratio`.
Deduplication: Given a DataFrame A with length N, the full index size is
N*(N-1)/2. Linking: Given a DataFrame A with length N and a DataFrame B
with length M, the full index size is N*M.
Parameters
----------
*args: int, pandas.MultiIndex, pandas.Series, pandas.DataFrame
A pandas object or a int representing the length of a dataset to link.
When there is one argument, it is assumed that the record linkage is
a deduplication process.
Examples
--------
Use integers:
>>> full_index_size(10) # deduplication: 45 pairs
>>> full_index_size(10, 10) # linking: 100 pairs
or pandas objects
>>> full_index_size(DF) # deduplication: len(DF)*(len(DF)-1)/2 pairs
>>> full_index_size(DF, DF) # linking: len(DF)*len(DF) pairs
"""
# check if a list or tuple is passed as argument
if len(args) == 1 and isinstance(args[0], (list, tuple)):
args = tuple(args[0])
if len(args) == 1:
n = get_length(args[0])
size = int(n * (n - 1) / 2)
else:
size = numpy.prod([get_length(arg) for arg in args],
dtype=numpy.unit64)
return size