tp-analyse-donnees/tp1-kmeans.py

# -*- coding: utf-8 -*-
"""
Created on Fri Nov 19 23:08:23 2021

@author: pfaure
"""


from myplotlib import print_1d_data, print_2d_data, print_3d_data
from mydatalib import (extract_data_2d, extract_data_3d, scale_data,
                       apply_kmeans, evaluate)


path = './artificial/'
dataset_name = "xclara"

save = True

print("-----------------------------------------------------------")
print("     Chargement du dataset : " + dataset_name)
data = extract_data_2d(path + dataset_name)
print_2d_data(data, dataset_name=dataset_name+"_brute", 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 k-means pour plusieurs valeurs de k
# et evaluation de la solution
k = []
durations = []
silouettes = []
daviess = []
calinskis = []
inerties = []
iterations = []
for i in range(2, 50):
    # Application de k-means
    (model, duration) = apply_kmeans(data_scaled, k=i, init="k-means++")
    # Affichage des clusters
    print_2d_data(data_scaled, dataset_name=dataset_name,
                  method_name="k-means", k=i, c=model.labels_,
                  stop=False, save=save)
    # Evaluation de la solution de clustering
    (silouette, davies, calinski) = evaluate(data_scaled, model)
    # Enregistrement des valeurs
    k += [i]
    durations += [duration]
    silouettes += [silouette]
    daviess += [davies]
    calinskis += [calinski]
    inerties += [model.inertia_]
    iterations += [model.n_iter_]

# Affichage des résultats
print_1d_data(k, k, x_name="k", y_name="k", dataset_name=dataset_name,
              method_name="k-means", 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="k-means",
              stop=False, save=save)
print_1d_data(k, silouettes, x_name="k", y_name="coeficient_de_silhouette",
              dataset_name=dataset_name, method_name="k-means",
              stop=False, save=save)
print_1d_data(k, daviess, x_name="k", y_name="coeficient_de_Davies",
              dataset_name=dataset_name, method_name="k-means",
              stop=False, save=save)
print_1d_data(k, calinskis, x_name="k", y_name="coeficient_de_Calinski",
              dataset_name=dataset_name, method_name="k-means",
              stop=False, save=save)
print_1d_data(k, inerties, x_name="k", y_name="inertie",
              dataset_name=dataset_name, method_name="k-means",
              stop=False, save=save)
print_1d_data(k, iterations, x_name="k", y_name="nombre_d_iterations",
              dataset_name=dataset_name, method_name="k-means",
              stop=True, save=save)