Plotar Clusters
É criado um gráfico para mostrar o desempenho dos diferentes algoritmos de clusterização nos conjuntos de dados.
for i_dataset, (dataset, algo_params) in enumerate(datasets):
## atualizar parâmetros com valores específicos do conjunto de dados
params = default_base.copy()
params.update(algo_params)
X, y = dataset
## normalizar o conjunto de dados para facilitar a seleção de parâmetros
X = StandardScaler().fit_transform(X)
## estimar a largura de banda para a média de deslocamento
bandwidth = cluster.estimate_bandwidth(X, quantile=params["quantile"])
## matriz de conectividade para Ward estruturado
connectivity = kneighbors_graph(
X, n_neighbors=params["n_neighbors"], include_self=False
)
## tornar a conectividade simétrica
connectivity = 0.5 * (connectivity + connectivity.T)
clustering_algorithms = (
("MiniBatch\nKMeans", two_means),
("Affinity\nPropagation", affinity_propagation),
("MeanShift", ms),
("Spectral\nClustering", spectral),
("Ward", ward),
("Agglomerative\nClustering", average_linkage),
("DBSCAN", dbscan),
("HDBSCAN", hdbscan),
("OPTICS", optics),
("BIRCH", birch),
("Gaussian\nMixture", gmm),
)
for name, algorithm in clustering_algorithms:
t0 = time.time()
## capturar avisos relacionados a kneighbors_graph
with warnings.catch_warnings():
warnings.filterwarnings(
"ignore",
message="the number of connected components of the "
+ "connectivity matrix is [0-9]{1,2}"
+ " > 1. Completing it to avoid stopping the tree early.",
category=UserWarning,
)
warnings.filterwarnings(
"ignore",
message="Graph is not fully connected, spectral embedding"
+ " may not work as expected.",
category=UserWarning,
)
algorithm.fit(X)
t1 = time.time()
if hasattr(algorithm, "labels_"):
y_pred = algorithm.labels_.astype(int)
else:
y_pred = algorithm.predict(X)
plt.subplot(len(datasets), len(clustering_algorithms), plot_num)
if i_dataset == 0:
plt.title(name, size=18)
colors = np.array(
list(
islice(
cycle(
[
"#377eb8",
"#ff7f00",
"#4daf4a",
"#f781bf",
"#a65628",
"#984ea3",
"#999999",
"#e41a1c",
"#dede00",
]
),
int(max(y_pred) + 1),
)
)
)
## adicionar cor preta para outliers (se houver)
colors = np.append(colors, ["#000000"])
plt.scatter(X[:, 0], X[:, 1], s=10, color=colors[y_pred])
plt.xlim(-2.5, 2.5)
plt.ylim(-2.5, 2.5)
plt.xticks(())
plt.yticks(())
plt.text(
0.99,
0.01,
("%.2fs" % (t1 - t0)).lstrip("0"),
transform=plt.gca().transAxes,
size=15,
horizontalalignment="right",
)
plot_num += 1
plt.show()
