def maximum_number_of_pairs(self):
""" the maximum number of record pairs """
if self.deduplication:
return max_number_of_pairs(self.df_a)
else:
return max_number_of_pairs(self.df_a, self.df_b)
def _random_small_link(df_a, df_b, n):
n_max = max_number_of_pairs(df_a, df_b)
if not isinstance(n, int) or n <= 0 or n > n_max:
raise ValueError("n must be a integer satisfying 0<n<=%s" % n_max)
levels = [df_a.index.values, df_b.index.values]
names = [df_a.index.name, df_b.index.name]
# Initialize pandas MultiIndex
pairs = pandas.MultiIndex(levels=levels, labels=[[], []], names=names)
# Run as long as the number of pairs is less than the requested number
# of pairs n.
while len(pairs) < n:
# The number of pairs to sample (sample twice as much record pairs
# because the duplicates are dropped).
n_sample = (n - len(pairs)) * 2
sample_a = numpy.random.randint(len(df_a), size=n_sample)
sample_b = numpy.random.randint(len(df_b), size=n_sample)
# Make a pandas MultiIndex of the sample above
pairs_sample = pandas.MultiIndex(
levels=levels, labels=[sample_a, sample_b], names=names
)
pairs = pairs.append(pairs_sample).drop_duplicates()
return pairs[0:n]
def _random_large_link(df_a, df_b, n):
n_max = max_number_of_pairs(df_a, df_b)
if not isinstance(n, int) or n <= 0 or n > n_max:
raise ValueError("n must be a integer satisfying 0<n<=%s" % n_max)
full_index = _fullindex_link(df_a, df_b)
sample = numpy.random.choice(
numpy.arange(len(full_index)), n, replace=False
)
return full_index[sample]