def check_sample_int_distribution(sample_without_replacement):
# This test is heavily inspired from test_random.py of python-core.
#
# For the entire allowable range of 0 <= k <= N, validate that
# sample generates all possible permutations
n_population = 10
# a large number of trials prevents false negatives without slowing normal
# case
n_trials = 10000
for n_samples in range(n_population):
# Counting the number of combinations is not as good as counting the
# the number of permutations. However, it works with sampling algorithm
# that does not provide a random permutation of the subset of integer.
n_expected = comb(n_population, n_samples, exact=True)
output = {}
for i in range(n_trials):
output[frozenset(
sample_without_replacement(n_population, n_samples))] = None
if len(output) == n_expected:
break
else:
raise AssertionError(
"number of combinations != number of expected (%s != %s)" %
(len(output), n_expected))
def check_sample_int_distribution(sample_without_replacement):
# This test is heavily inspired from test_random.py of python-core.
#
# For the entire allowable range of 0 <= k <= N, validate that
# sample generates all possible permutations
n_population = 10
# a large number of trials prevents false negatives without slowing normal
# case
n_trials = 10000
for n_samples in range(n_population):
# Counting the number of combinations is not as good as counting the
# the number of permutations. However, it works with sampling algorithm
# that does not provide a random permutation of the subset of integer.
n_expected = comb(n_population, n_samples, exact=True)
output = {}
for i in range(n_trials):
output[frozenset(sample_without_replacement(n_population,
n_samples))] = None
if len(output) == n_expected:
break
else:
raise AssertionError(
"number of combinations != number of expected (%s != %s)" %
(len(output), n_expected))
def rand_index_score(labels_true, labels_pred):
labels_true, labels_pred = check_clusterings(labels_true, labels_pred)
n_samples = labels_true.shape[0]
n_classes = np.unique(labels_true).shape[0]
n_clusters = np.unique(labels_pred).shape[0]
# Special limit cases: no clustering since the data is not split;
# or trivial clustering where each document is assigned a unique cluster.
# These are perfect matches hence return 1.0.
if (n_classes == n_clusters == 1 or n_classes == n_clusters == 0
or n_classes == n_clusters == n_samples):
return 1.0
# Compute the RI using the contingency data
contingency = contingency_matrix(labels_true, labels_pred)
n = np.sum(np.sum(contingency))
t1 = comb(n, 2)
t2 = np.sum(np.sum(np.power(contingency, 2)))
nis = np.sum(np.power(np.sum(contingency, 0), 2))
njs = np.sum(np.power(np.sum(contingency, 1), 2))
t3 = 0.5 * (nis + njs)
A = t1 + t2 - t3
nc = (n * (n**2 + 1) - (n + 1) * nis - (n + 1) * njs + 2 *
(nis * njs) / n) / (2 * (n - 1))
AR = (A - nc) / (t1 - nc)
return A / t1
def binomial(k, n):
return 0 if k < 0 or k > n else comb(int(n), int(k), exact=True)
def binomial(k, n):
return 0 if k < 0 or k > n else comb(int(n), int(k), exact=True)
def _comb2(n):
# the exact version is faster for k == 2: use it by default globally in
# this module instead of the float approximate variant
return comb(n, 2, exact=1)
