Python sklearn.metrics.cluster.adjusted_mutual_info_score() Examples
The following are 9
code examples of sklearn.metrics.cluster.adjusted_mutual_info_score().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
sklearn.metrics.cluster
, or try the search function
.
.
Example #1
| Source File: test_supervised.py From Mastering-Elasticsearch-7.0 with MIT License | 6 votes |
|
def test_perfect_matches():
for score_func in score_funcs:
assert_equal(score_func([], []), 1.0)
assert_equal(score_func([0], [1]), 1.0)
assert_equal(score_func([0, 0, 0], [0, 0, 0]), 1.0)
assert_equal(score_func([0, 1, 0], [42, 7, 42]), 1.0)
assert_equal(score_func([0., 1., 0.], [42., 7., 42.]), 1.0)
assert_equal(score_func([0., 1., 2.], [42., 7., 2.]), 1.0)
assert_equal(score_func([0, 1, 2], [42, 7, 2]), 1.0)
score_funcs_with_changing_means = [
normalized_mutual_info_score,
adjusted_mutual_info_score,
]
means = {"min", "geometric", "arithmetic", "max"}
for score_func in score_funcs_with_changing_means:
for mean in means:
assert score_func([], [], mean) == 1.0
assert score_func([0], [1], mean) == 1.0
assert score_func([0, 0, 0], [0, 0, 0], mean) == 1.0
assert score_func([0, 1, 0], [42, 7, 42], mean) == 1.0
assert score_func([0., 1., 0.], [42., 7., 42.], mean) == 1.0
assert score_func([0., 1., 2.], [42., 7., 2.], mean) == 1.0
assert score_func([0, 1, 2], [42, 7, 2], mean) == 1.0
Example #2
| Source File: test_supervised.py From Mastering-Elasticsearch-7.0 with MIT License | 5 votes |
|
def test_future_warning():
score_funcs_with_changing_means = [
normalized_mutual_info_score,
adjusted_mutual_info_score,
]
warning_msg = "The behavior of "
args = [0, 0, 0], [0, 0, 0]
for score_func in score_funcs_with_changing_means:
assert_warns_message(FutureWarning, warning_msg, score_func, *args)
Example #3
| Source File: test_supervised.py From Mastering-Elasticsearch-7.0 with MIT License | 5 votes |
|
def test_adjusted_mutual_info_score():
# Compute the Adjusted Mutual Information and test against known values
labels_a = np.array([1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3])
labels_b = np.array([1, 1, 1, 1, 2, 1, 2, 2, 2, 2, 3, 1, 3, 3, 3, 2, 2])
# Mutual information
mi = mutual_info_score(labels_a, labels_b)
assert_almost_equal(mi, 0.41022, 5)
# with provided sparse contingency
C = contingency_matrix(labels_a, labels_b, sparse=True)
mi = mutual_info_score(labels_a, labels_b, contingency=C)
assert_almost_equal(mi, 0.41022, 5)
# with provided dense contingency
C = contingency_matrix(labels_a, labels_b)
mi = mutual_info_score(labels_a, labels_b, contingency=C)
assert_almost_equal(mi, 0.41022, 5)
# Expected mutual information
n_samples = C.sum()
emi = expected_mutual_information(C, n_samples)
assert_almost_equal(emi, 0.15042, 5)
# Adjusted mutual information
ami = adjusted_mutual_info_score(labels_a, labels_b)
assert_almost_equal(ami, 0.27502, 5)
ami = adjusted_mutual_info_score([1, 1, 2, 2], [2, 2, 3, 3])
assert_equal(ami, 1.0)
# Test with a very large array
a110 = np.array([list(labels_a) * 110]).flatten()
b110 = np.array([list(labels_b) * 110]).flatten()
ami = adjusted_mutual_info_score(a110, b110)
# This is not accurate to more than 2 places
assert_almost_equal(ami, 0.37, 2)
Example #4
| Source File: test_supervised.py From Mastering-Elasticsearch-7.0 with MIT License | 5 votes |
|
def test_exactly_zero_info_score():
# Check numerical stability when information is exactly zero
for i in np.logspace(1, 4, 4).astype(np.int):
labels_a, labels_b = (np.ones(i, dtype=np.int),
np.arange(i, dtype=np.int))
assert_equal(normalized_mutual_info_score(labels_a, labels_b), 0.0)
assert_equal(v_measure_score(labels_a, labels_b), 0.0)
assert_equal(adjusted_mutual_info_score(labels_a, labels_b), 0.0)
assert_equal(normalized_mutual_info_score(labels_a, labels_b), 0.0)
for method in ["min", "geometric", "arithmetic", "max"]:
assert adjusted_mutual_info_score(labels_a, labels_b,
method) == 0.0
assert normalized_mutual_info_score(labels_a, labels_b,
method) == 0.0
Example #5
| Source File: eval-partition-accuracy.py From topic-ensemble with Apache License 2.0 | 5 votes |
|
def validate( measure, classes, clustering ):
if measure == "nmi":
return normalized_mutual_info_score( classes, clustering )
elif measure == "ami":
return adjusted_mutual_info_score( classes, clustering )
elif measure == "ari":
return adjusted_rand_score( classes, clustering )
log.error("Unknown validation measure: %s" % measure )
return None
# --------------------------------------------------------------
Example #6
| Source File: metric.py From L2C with MIT License | 5 votes |
|
def clusterscores(self):
target,pred = self.conf2label()
NMI = normalized_mutual_info_score(target,pred)
ARI = adjusted_rand_score(target,pred)
AMI = adjusted_mutual_info_score(target,pred)
return {'NMI':NMI,'ARI':ARI,'AMI':AMI}
Example #7
| Source File: test_supervised.py From twitter-stock-recommendation with MIT License | 5 votes |
|
def test_adjusted_mutual_info_score():
# Compute the Adjusted Mutual Information and test against known values
labels_a = np.array([1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3])
labels_b = np.array([1, 1, 1, 1, 2, 1, 2, 2, 2, 2, 3, 1, 3, 3, 3, 2, 2])
# Mutual information
mi = mutual_info_score(labels_a, labels_b)
assert_almost_equal(mi, 0.41022, 5)
# with provided sparse contingency
C = contingency_matrix(labels_a, labels_b, sparse=True)
mi = mutual_info_score(labels_a, labels_b, contingency=C)
assert_almost_equal(mi, 0.41022, 5)
# with provided dense contingency
C = contingency_matrix(labels_a, labels_b)
mi = mutual_info_score(labels_a, labels_b, contingency=C)
assert_almost_equal(mi, 0.41022, 5)
# Expected mutual information
n_samples = C.sum()
emi = expected_mutual_information(C, n_samples)
assert_almost_equal(emi, 0.15042, 5)
# Adjusted mutual information
ami = adjusted_mutual_info_score(labels_a, labels_b)
assert_almost_equal(ami, 0.27502, 5)
ami = adjusted_mutual_info_score([1, 1, 2, 2], [2, 2, 3, 3])
assert_equal(ami, 1.0)
# Test with a very large array
a110 = np.array([list(labels_a) * 110]).flatten()
b110 = np.array([list(labels_b) * 110]).flatten()
ami = adjusted_mutual_info_score(a110, b110)
# This is not accurate to more than 2 places
assert_almost_equal(ami, 0.37, 2)
Example #8
| Source File: test_supervised.py From twitter-stock-recommendation with MIT License | 5 votes |
|
def test_exactly_zero_info_score():
# Check numerical stability when information is exactly zero
for i in np.logspace(1, 4, 4).astype(np.int):
labels_a, labels_b = (np.ones(i, dtype=np.int),
np.arange(i, dtype=np.int))
assert_equal(normalized_mutual_info_score(labels_a, labels_b), 0.0)
assert_equal(v_measure_score(labels_a, labels_b), 0.0)
assert_equal(adjusted_mutual_info_score(labels_a, labels_b), 0.0)
assert_equal(normalized_mutual_info_score(labels_a, labels_b), 0.0)
Example #9
| Source File: validation.py From topic-stability with Apache License 2.0 | 5 votes |
|
def evaluate( self, partition, clustered_ids ):
# no class info?
if not self.has_class_info():
return {}
# get two clusterings that we can compare
n = len(clustered_ids)
classes_subset = np.zeros( n )
for row in range(n):
classes_subset[row] = self.class_map[clustered_ids[row]]
scores = {}
scores["external-nmi"] = normalized_mutual_info_score( classes_subset, partition )
scores["external-ami"] = adjusted_mutual_info_score( classes_subset, partition )
scores["external-ari"] = adjusted_rand_score( classes_subset, partition )
return scores
