def _dedup_index(self, df_a):
shape = (len(df_a),)
# with replacement
if self.replace:
pairs = random_pairs_with_replacement(
self.n, shape, self.random_state)
# without replacement
else:
n_max = full_index_size(shape)
if not isinstance(self.n, int) or self.n <= 0 or self.n > n_max:
raise ValueError(
"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
)
def _link_index(self, df_a, df_b):
shape = (len(df_a), len(df_b))
n_max = full_index_size(shape)
if not isinstance(self.n, int):
raise ValueError('n must be an integer')
# with replacement
if self.replace:
if n_max == 0:
raise ValueError(
"one of the dataframes is empty")
pairs = random_pairs_with_replacement(
self.n, shape, self.random_state)
# without replacement
else:
if self.n <= 0 or self.n > n_max:
raise ValueError(
"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_b.index.values]
labels = pairs
names = [df_a.index.name, df_b.index.name]
return pandas.MultiIndex(
levels=levels,
labels=labels,
names=names,
verify_integrity=False
)
def _link_index(self, df_a, df_b):
shape = (len(df_a), len(df_b))
n_max = full_index_size(shape)
if not isinstance(self.n, int):
raise ValueError('n must be an integer')
# with replacement
if self.replace:
if n_max == 0:
raise ValueError("one of the dataframes is empty")
pairs = random_pairs_with_replacement(self.n, shape,
self.random_state)
# without replacement
else:
if self.n <= 0 or self.n > n_max:
raise ValueError("n must be a integer satisfying 0<n<=%s" %
n_max)
# the fraction of pairs in the sample
frac = self.n / n_max
# large dataframes
if n_max < 1e6 or frac > 0.5:
pairs = random_pairs_without_replacement(
self.n, shape, self.random_state)
# small dataframes
else:
pairs = random_pairs_without_replacement_low_memory(
self.n, shape, self.random_state)
levels = [df_a.index.values, df_b.index.values]
codes = pairs
return pandas.MultiIndex(levels=levels,
codes=codes,
verify_integrity=False)
