def test_bad_arguments():
X, y = make_blobs(100, random_state=42)
mst = MSTClustering()
assert_raises_regex(ValueError,
"Must specify either cutoff or cutoff_frac",
mst.fit, X, y)
mst = MSTClustering(cutoff=-1)
assert_raises_regex(ValueError, "cutoff must be positive", mst.fit, X)
mst = MSTClustering()
msg = "Must call fit\(\) before get_graph_segments()"
assert_raises_regex(ValueError, msg, mst.get_graph_segments)
mst = MSTClustering(cutoff=0, metric='precomputed')
mst.fit(pairwise_distances(X))
msg = "Cannot use ``get_graph_segments`` with precomputed metric."
assert_raises_regex(ValueError, msg, mst.get_graph_segments)
def test_bad_arguments():
X, y = make_blobs(100, random_state=42)
mst = MSTClustering()
assert_raises_regex(ValueError,
"Must specify either cutoff or cutoff_frac", mst.fit,
X, y)
mst = MSTClustering(cutoff=-1)
assert_raises_regex(ValueError, "cutoff must be positive", mst.fit, X)
mst = MSTClustering()
msg = "Must call fit\(\) before get_graph_segments()"
assert_raises_regex(ValueError, msg, mst.get_graph_segments)
mst = MSTClustering(cutoff=0, metric='precomputed')
mst.fit(pairwise_distances(X))
msg = "Cannot use ``get_graph_segments`` with precomputed metric."
assert_raises_regex(ValueError, msg, mst.get_graph_segments)
def MST_clustering(filename):
with open(filename, 'r') as f:
words = f.readlines()
words = [word.rstrip() for word in words if len(word) > 4]
words = np.asarray(words)
jac_similarity = np.array([[jaccard(w1, w2) for w1 in words[:500]]
for w2 in words[:500]])
#pdb.set_trace()
mst = MSTClustering(min_cluster_size=10,
cutoff_scale=1) # cut-off scale ??
mst.fit(jac_similarity)
mst_matrix = mst.full_tree_
X_tsne = TSNE(learning_rate=100).fit_transform(mst_matrix.todense())
labels = mst.labels_
pdb.set_trace()
plt.scatter(X_tsne[:, 0], X_tsne[:, 1], c=labels)
#plot_mst(mst)
plt.show()
def get_mst(dataframe):
model = MSTClustering(cutoff_scale=2)
model.fit(dataframe)
return model.labels_
model = MSTClustering(cutoff_scale=2, approximate=False) labels = model.fit_predict(X) plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='rainbow') plt.show() plot_minimum_spanning_tree(model) plt.show() rng = np.random.RandomState(int(100 * y[-1])) noise = -14 + 28 * rng.rand(200, 2) X_noisy = np.vstack([X, noise]) y_noisy = np.concatenate([y, np.full(200, -1, dtype=int)]) plt.scatter(X_noisy[:, 0], X_noisy[:, 1], c='lightblue', cmap='spectral_r') plt.xlim(-15, 15) plt.ylim(-15, 15) plt.show() noisy_model = MSTClustering(cutoff_scale=1) noisy_model.fit(X_noisy) plot_minimum_spanning_tree(noisy_model) plt.show() noisy_model = MSTClustering(cutoff_scale=1, min_cluster_size=10) noisy_model.fit(X_noisy) plot_minimum_spanning_tree(noisy_model) plt.show()
