73 lines
2.5 KiB
Python
73 lines
2.5 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Wed Dec 8 16:07:28 2021
|
|
|
|
@author: pfaure
|
|
"""
|
|
from numpy import arange
|
|
from sklearn.neighbors import NearestNeighbors
|
|
import numpy as np
|
|
|
|
from myplotlib import print_1d_data, print_2d_data
|
|
from mydatalib import extract_data_2d, scale_data, apply_mean_shift, evaluate
|
|
|
|
path = './artificial/'
|
|
dataset_name = "xclara"
|
|
method_name = "mean-shift"
|
|
save = True
|
|
|
|
print("-----------------------------------------------------------")
|
|
print(" Chargement du dataset : " + dataset_name)
|
|
data = extract_data_2d(path + dataset_name)
|
|
print_2d_data(data, dataset_name=dataset_name +
|
|
"_brutes", stop=False, save=save)
|
|
|
|
print("-----------------------------------------------------------")
|
|
print(" Mise à l'échelle")
|
|
data_scaled = scale_data(data)
|
|
print_2d_data(data_scaled, dataset_name=dataset_name +
|
|
"_scaled", stop=False, save=save)
|
|
|
|
# Application de Affinity Propagation pour plusieurs valeurs de préférence
|
|
# et evaluation de la solution
|
|
|
|
k_max = 2
|
|
|
|
k = []
|
|
durations = []
|
|
silouettes = []
|
|
daviess = []
|
|
calinskis = []
|
|
for bandwidth in arange(0.1, k_max, 0.1):
|
|
# Application du clustering
|
|
(model, duration) = apply_mean_shift(
|
|
data_scaled, bandwidth=bandwidth)
|
|
# Affichage des clusters
|
|
print_2d_data(data_scaled, dataset_name=dataset_name,
|
|
method_name=method_name, k=bandwidth,
|
|
stop=False, save=save, c=model.labels_)
|
|
# Evaluation de la solution de clustering
|
|
(silouette, davies, calinski) = evaluate(data_scaled, model)
|
|
# Enregistrement des valeurs
|
|
k += [bandwidth]
|
|
durations += [duration]
|
|
silouettes += [silouette]
|
|
daviess += [davies]
|
|
calinskis += [calinski]
|
|
|
|
# Affichage des résultats
|
|
print_1d_data(k, k, x_name="k", y_name="k", dataset_name=dataset_name,
|
|
method_name=method_name, stop=False, save=save)
|
|
print_1d_data(k, durations, x_name="k", y_name="temps_de_calcul", y_unit="ms",
|
|
dataset_name=dataset_name,
|
|
method_name=method_name, stop=False, save=save)
|
|
print_1d_data(k, silouettes, x_name="k", y_name="coeficient_de_silhouette",
|
|
dataset_name=dataset_name,
|
|
method_name=method_name, stop=False, save=save)
|
|
print_1d_data(k, daviess, x_name="k", y_name="coeficient_de_Davies",
|
|
dataset_name=dataset_name,
|
|
method_name=method_name, stop=False, save=save)
|
|
print_1d_data(k, calinskis, x_name="k", y_name="coeficient_de_Calinski",
|
|
dataset_name=dataset_name,
|
|
method_name=method_name, stop=False, save=save)
|