def test_non_encoded_labels():
dataset = datasets.load_iris()
X = dataset.data
labels = dataset.target
assert silhouette_score(X, labels * 2 + 10) == silhouette_score(X, labels)
assert_array_equal(silhouette_samples(X, labels * 2 + 10),
silhouette_samples(X, labels))
def test_non_encoded_labels():
dataset = datasets.load_iris()
X = dataset.data
labels = dataset.target
assert_equal(
silhouette_score(X, labels * 2 + 10), silhouette_score(X, labels))
assert_array_equal(
silhouette_samples(X, labels * 2 + 10), silhouette_samples(X, labels))
def calc_metrics(topics, cluster_assignments, raw_data, soft_clustering=True):
print("Calculate KPIs...")
total_count = cluster_assignments.shape[0]
if soft_clustering:
sums = np.sum(cluster_assignments, axis=0)
counts = np.count_nonzero(cluster_assignments, axis=0)
hard_cluster = np.argsort(
cluster_assignments,
axis=1)[:, -1] # just the last column (Ascending sorted!)
# inter-cluster-sim - intra-cluster-sim / max of both
silhouette_scores = silhouette_samples(raw_data, hard_cluster)
else:
# inter-cluster-sim - intra-cluster-sim / max of both
silhouette_scores = silhouette_samples(raw_data, cluster_assignments)
for c_idx, topic in topics.items():
# Calc. KPIs
if soft_clustering:
avg_weight = sums[c_idx] / counts[c_idx]
article_ratio = counts[c_idx] / total_count
mask_nonzero = cluster_assignments[:, c_idx] > 0
std = np.std(cluster_assignments[mask_nonzero, c_idx])
median = np.median(cluster_assignments[mask_nonzero, c_idx])
top_ratio = len(np.where(hard_cluster == c_idx)[0]) / counts[c_idx]
silhouette_score = np.mean(
silhouette_scores[hard_cluster == c_idx])
#Store KPIs
topic.update({
"avg_weight": avg_weight,
"median_weight": median,
"std_weight": std,
"article_ratio": article_ratio,
"top_ratio": top_ratio,
"silhouette_score": silhouette_score
})
else:
article_ratio = len(cluster_assignments[cluster_assignments ==
c_idx]) / total_count
silhouette_score = np.mean(
silhouette_scores[cluster_assignments == c_idx])
# Store KPIs
topic.update({
"article_ratio": article_ratio,
"silhouette_score": silhouette_score
})
return #topics #inplace update!
def gerar_grafico_silhueta(amostras, y_aca):
cluster_labels = np.unique(y_aca)
n_clusters = cluster_labels.shape[0]
silhouette_vals = cluster.silhouette_samples(amostras,
y_aca,
metric='euclidean')
y_ax_lower, y_ax_upper = 0, 0
yticks = []
for i, c in enumerate(cluster_labels):
c_silhouette_vals = silhouette_vals[y_aca == c]
c_silhouette_vals.sort()
y_ax_upper += len(c_silhouette_vals)
color = cm.jet(float(i) / n_clusters)
plt.barh(range(y_ax_lower, y_ax_upper),
c_silhouette_vals,
height=1.0,
edgecolor='none',
color=color)
yticks.append((y_ax_lower + y_ax_upper) / 2.)
y_ax_lower += len(c_silhouette_vals)
silhouette_avg = np.mean(silhouette_vals)
plt.axvline(silhouette_avg, color='red', linestyle="--")
plt.yticks(yticks, cluster_labels + 1)
plt.ylabel('Cluster')
plt.xlabel('Silhouette coefficient')
plt.show()
def test_silhouette_nonzero_diag(dtype):
# Make sure silhouette_samples requires diagonal to be zero.
# Non-regression test for #12178
# Construct a zero-diagonal matrix
dists = pairwise_distances(
np.array([[0.2, 0.1, 0.12, 1.34, 1.11, 1.6]], dtype=dtype).T)
labels = [0, 0, 0, 1, 1, 1]
# small values on the diagonal are OK
dists[2][2] = np.finfo(dists.dtype).eps * 10
silhouette_samples(dists, labels, metric='precomputed')
# values bigger than eps * 100 are not
dists[2][2] = np.finfo(dists.dtype).eps * 1000
with pytest.raises(ValueError, match='contains non-zero'):
silhouette_samples(dists, labels, metric='precomputed')
def test_silhouette_paper_example():
# Explicitly check per-sample results against Rousseeuw (1987)
# Data from Table 1
lower = [5.58,
7.00, 6.50,
7.08, 7.00, 3.83,
4.83, 5.08, 8.17, 5.83,
2.17, 5.75, 6.67, 6.92, 4.92,
6.42, 5.00, 5.58, 6.00, 4.67, 6.42,
3.42, 5.50, 6.42, 6.42, 5.00, 3.92, 6.17,
2.50, 4.92, 6.25, 7.33, 4.50, 2.25, 6.33, 2.75,
6.08, 6.67, 4.25, 2.67, 6.00, 6.17, 6.17, 6.92, 6.17,
5.25, 6.83, 4.50, 3.75, 5.75, 5.42, 6.08, 5.83, 6.67, 3.67,
4.75, 3.00, 6.08, 6.67, 5.00, 5.58, 4.83, 6.17, 5.67, 6.50, 6.92]
D = np.zeros((12, 12))
D[np.tril_indices(12, -1)] = lower
D += D.T
names = ['BEL', 'BRA', 'CHI', 'CUB', 'EGY', 'FRA', 'IND', 'ISR', 'USA',
'USS', 'YUG', 'ZAI']
# Data from Figure 2
labels1 = [1, 1, 2, 2, 1, 1, 2, 1, 1, 2, 2, 1]
expected1 = {'USA': .43, 'BEL': .39, 'FRA': .35, 'ISR': .30, 'BRA': .22,
'EGY': .20, 'ZAI': .19, 'CUB': .40, 'USS': .34, 'CHI': .33,
'YUG': .26, 'IND': -.04}
score1 = .28
# Data from Figure 3
labels2 = [1, 2, 3, 3, 1, 1, 2, 1, 1, 3, 3, 2]
expected2 = {'USA': .47, 'FRA': .44, 'BEL': .42, 'ISR': .37, 'EGY': .02,
'ZAI': .28, 'BRA': .25, 'IND': .17, 'CUB': .48, 'USS': .44,
'YUG': .31, 'CHI': .31}
score2 = .33
for labels, expected, score in [(labels1, expected1, score1),
(labels2, expected2, score2)]:
expected = [expected[name] for name in names]
# we check to 2dp because that's what's in the paper
pytest.approx(expected,
silhouette_samples(D, np.array(labels),
metric='precomputed'),
abs=1e-2)
pytest.approx(score,
silhouette_score(D, np.array(labels),
metric='precomputed'),
abs=1e-2)
def test_silhouette_paper_example():
# Explicitly check per-sample results against Rousseeuw (1987)
# Data from Table 1
lower = [5.58,
7.00, 6.50,
7.08, 7.00, 3.83,
4.83, 5.08, 8.17, 5.83,
2.17, 5.75, 6.67, 6.92, 4.92,
6.42, 5.00, 5.58, 6.00, 4.67, 6.42,
3.42, 5.50, 6.42, 6.42, 5.00, 3.92, 6.17,
2.50, 4.92, 6.25, 7.33, 4.50, 2.25, 6.33, 2.75,
6.08, 6.67, 4.25, 2.67, 6.00, 6.17, 6.17, 6.92, 6.17,
5.25, 6.83, 4.50, 3.75, 5.75, 5.42, 6.08, 5.83, 6.67, 3.67,
4.75, 3.00, 6.08, 6.67, 5.00, 5.58, 4.83, 6.17, 5.67, 6.50, 6.92]
D = np.zeros((12, 12))
D[np.tril_indices(12, -1)] = lower
D += D.T
names = ['BEL', 'BRA', 'CHI', 'CUB', 'EGY', 'FRA', 'IND', 'ISR', 'USA',
'USS', 'YUG', 'ZAI']
# Data from Figure 2
labels1 = [1, 1, 2, 2, 1, 1, 2, 1, 1, 2, 2, 1]
expected1 = {'USA': .43, 'BEL': .39, 'FRA': .35, 'ISR': .30, 'BRA': .22,
'EGY': .20, 'ZAI': .19, 'CUB': .40, 'USS': .34, 'CHI': .33,
'YUG': .26, 'IND': -.04}
score1 = .28
# Data from Figure 3
labels2 = [1, 2, 3, 3, 1, 1, 2, 1, 1, 3, 3, 2]
expected2 = {'USA': .47, 'FRA': .44, 'BEL': .42, 'ISR': .37, 'EGY': .02,
'ZAI': .28, 'BRA': .25, 'IND': .17, 'CUB': .48, 'USS': .44,
'YUG': .31, 'CHI': .31}
score2 = .33
for labels, expected, score in [(labels1, expected1, score1),
(labels2, expected2, score2)]:
expected = [expected[name] for name in names]
# we check to 2dp because that's what's in the paper
pytest.approx(expected,
silhouette_samples(D, np.array(labels),
metric='precomputed'),
abs=1e-2)
pytest.approx(score,
silhouette_score(D, np.array(labels),
metric='precomputed'),
abs=1e-2)
def test_cluster_size_1():
# Assert Silhouette Coefficient == 0 when there is 1 sample in a cluster
# (cluster 0). We also test the case where there are identical samples
# as the only members of a cluster (cluster 2). To our knowledge, this case
# is not discussed in reference material, and we choose for it a sample
# score of 1.
X = [[0.], [1.], [1.], [2.], [3.], [3.]]
labels = np.array([0, 1, 1, 1, 2, 2])
# Cluster 0: 1 sample -> score of 0 by Rousseeuw's convention
# Cluster 1: intra-cluster = [.5, .5, 1]
# inter-cluster = [1, 1, 1]
# silhouette = [.5, .5, 0]
# Cluster 2: intra-cluster = [0, 0]
# inter-cluster = [arbitrary, arbitrary]
# silhouette = [1., 1.]
silhouette = silhouette_score(X, labels)
assert not np.isnan(silhouette)
ss = silhouette_samples(X, labels)
assert_array_equal(ss, [0, .5, .5, 0, 1, 1])
def test_cluster_size_1():
# Assert Silhouette Coefficient == 0 when there is 1 sample in a cluster
# (cluster 0). We also test the case where there are identical samples
# as the only members of a cluster (cluster 2). To our knowledge, this case
# is not discussed in reference material, and we choose for it a sample
# score of 1.
X = [[0.], [1.], [1.], [2.], [3.], [3.]]
labels = np.array([0, 1, 1, 1, 2, 2])
# Cluster 0: 1 sample -> score of 0 by Rousseeuw's convention
# Cluster 1: intra-cluster = [.5, .5, 1]
# inter-cluster = [1, 1, 1]
# silhouette = [.5, .5, 0]
# Cluster 2: intra-cluster = [0, 0]
# inter-cluster = [arbitrary, arbitrary]
# silhouette = [1., 1.]
silhouette = silhouette_score(X, labels)
assert_false(np.isnan(silhouette))
ss = silhouette_samples(X, labels)
assert_array_equal(ss, [0, .5, .5, 0, 1, 1])
def test_silhouette_paper_example():
# Explicitly check per-sample results against Rousseeuw (1987)
# Data from Table 1
lower = [
5.58,
7.00,
6.50,
7.08,
7.00,
3.83,
4.83,
5.08,
8.17,
5.83,
2.17,
5.75,
6.67,
6.92,
4.92,
6.42,
5.00,
5.58,
6.00,
4.67,
6.42,
3.42,
5.50,
6.42,
6.42,
5.00,
3.92,
6.17,
2.50,
4.92,
6.25,
7.33,
4.50,
2.25,
6.33,
2.75,
6.08,
6.67,
4.25,
2.67,
6.00,
6.17,
6.17,
6.92,
6.17,
5.25,
6.83,
4.50,
3.75,
5.75,
5.42,
6.08,
5.83,
6.67,
3.67,
4.75,
3.00,
6.08,
6.67,
5.00,
5.58,
4.83,
6.17,
5.67,
6.50,
6.92,
]
D = np.zeros((12, 12))
D[np.tril_indices(12, -1)] = lower
D += D.T
names = [
"BEL",
"BRA",
"CHI",
"CUB",
"EGY",
"FRA",
"IND",
"ISR",
"USA",
"USS",
"YUG",
"ZAI",
]
# Data from Figure 2
labels1 = [1, 1, 2, 2, 1, 1, 2, 1, 1, 2, 2, 1]
expected1 = {
"USA": 0.43,
"BEL": 0.39,
"FRA": 0.35,
"ISR": 0.30,
"BRA": 0.22,
"EGY": 0.20,
"ZAI": 0.19,
"CUB": 0.40,
"USS": 0.34,
"CHI": 0.33,
"YUG": 0.26,
"IND": -0.04,
}
score1 = 0.28
# Data from Figure 3
labels2 = [1, 2, 3, 3, 1, 1, 2, 1, 1, 3, 3, 2]
expected2 = {
"USA": 0.47,
"FRA": 0.44,
"BEL": 0.42,
"ISR": 0.37,
"EGY": 0.02,
"ZAI": 0.28,
"BRA": 0.25,
"IND": 0.17,
"CUB": 0.48,
"USS": 0.44,
"YUG": 0.31,
"CHI": 0.31,
}
score2 = 0.33
for labels, expected, score in [
(labels1, expected1, score1),
(labels2, expected2, score2),
]:
expected = [expected[name] for name in names]
# we check to 2dp because that's what's in the paper
pytest.approx(
expected,
silhouette_samples(D, np.array(labels), metric="precomputed"),
abs=1e-2,
)
pytest.approx(score,
silhouette_score(D,
np.array(labels),
metric="precomputed"),
abs=1e-2)
plt.scatter(centroids[:,0], centroids[:,1], marker='x', color='k', s=50, linewidth=5)
plt.show()
pairs = itertools.combinations(centroids, 2)
for item in pairs:
plot__kmeans_scatter_in_2d(item)
# ## 6. Calculate the silhouette coefficients. (10 points)
# In[9]:
silhouette_coefficient = silhouette_score(X, kmeans_model.labels_, metric='sqeuclidean')
silhouette_coefficient
# ## 7. Assuming that the data is ordered by class labels, print the average silhouette coefficient for each class. (20 points)
# In[ ]:
silhouette_samples(X, labels, metric='sqeuclidean')
# In[ ]:
