# 需要导入模块: import seaborn [as 别名]

# 或者: from seaborn import set_color_codes [as 别名]

def generate_clusters(words, vectors_in_2D, print_status=True):

# HDBSCAN, i.e. hierarchical density-based spatial clustering of applications with noise (https://github.com/lmcinnes/hdbscan)

vectors = vectors_in_2D

sns.set_context('poster')

sns.set_color_codes()

plot_kwds = {'alpha' : 0.5, 's' : 500, 'linewidths': 0}

clusters = HDBSCAN(min_cluster_size=2).fit_predict(vectors)

palette = sns.color_palette("husl", np.unique(clusters).max() + 1)

colors = [palette[cluster_index] if cluster_index >= 0 else (0.0, 0.0, 0.0) for cluster_index in clusters]

fig = plt.figure(figsize=(30, 30))

plt.scatter(vectors.T[0], vectors.T[1], c=colors, **plot_kwds)

plt.axis('off')

x_vals = [i[0] for i in vectors]

y_vals = [i[1] for i in vectors]

plt.ylim(min(y_vals)-0.3, max(y_vals)+0.3)

plt.xlim(min(x_vals)-0.3, max(x_vals)+0.3)

font_path = getcwd() + '/fonts/Comfortaa-Regular.ttf'

font_property = matplotlib.font_manager.FontProperties(fname=font_path, size=24)

for i, word in enumerate(words):

if type(word) != type(None):

if type(word) != type(""):

word = unidecode(word).replace("_", " ")

else:

word = word.replace("_", " ")

text_object = plt.annotate(word, xy=(x_vals[i], y_vals[i]+0.05), font_properties=font_property, color=colors[i], ha="center")

plt.subplots_adjust(left=(500/3000), right=(2900/3000), top=1.0, bottom=(300/2700))

plt.savefig(get_visualization_file_path(print_status), bbox_inches="tight")

return clusters