tp-analyse-donnees/tp3-dbscan.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Dec  8 16:07:28 2021

@author: pfaure
"""

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_DBSCAN, evaluate

path = './artificial/'
dataset_name = "s-set1"
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)

print("-----------------------------------------------------------")
print("     Calcul du voisinage")
n = 7
neighbors = NearestNeighbors(n_neighbors=n)
neighbors.fit(data_scaled)
distances, indices = neighbors.kneighbors(data_scaled)
distances = list(map(lambda x: sum(x[1:n-1])/(len(x)-1), distances))
distances = np.sort(distances, axis=0)
print_1d_data(distances, range(1, len(distances)+1), x_name="distance_moyenne",
              y_name="nombre_de_points", dataset_name=dataset_name,
              method_name="DBSCAN", stop=False, save=save)


print("-----------------------------------------------------------")
print("     Création clusters : DBSCAN")
params = []
for i in range(1, 30):
    params += [(0.1, i)]
durations = []
silouettes = []
daviess = []
calinskis = []
clusters = []
noise_points = []
for (distance, min_pts) in params:
    # Application du clustering agglomeratif
    (model, duration) = apply_DBSCAN(data_scaled, distance, min_pts)
    cl_pred = model.labels_
    # Affichage des clusters# Affichage des clusters
    print_2d_data(data_scaled, dataset_name=dataset_name,
                  method_name="DBSCAN-Eps=" +
                  str(distance)+"-Minpt="+str(min_pts),
                  k=0, stop=False, save=save, c=cl_pred)
    # Evaluation de la solution de clustering
    (silouette, davies, calinski) = evaluate(data_scaled, model)
    # Enregistrement des valeurs
    durations += [duration]
    silouettes += [silouette]
    daviess += [davies]
    calinskis += [calinski]
    clusters += [len(set(cl_pred)) - (1 if -1 in cl_pred else 0)]
    noise_points += [list(cl_pred).count(-1)]

# Affichage des résultats
params = [str(i) for i in params]
print_1d_data(params, durations, x_name="(eps,min_pts)",
              y_name="temps_de_calcul", y_unit="ms", dataset_name=dataset_name,
              method_name="DBSCAN", stop=False, save=save)
print_1d_data(params, silouettes, x_name="(eps,min_pts)",
              y_name="coeficient_de_silhouette", dataset_name=dataset_name,
              method_name="DBSCAN", stop=False, save=save)
print_1d_data(params, daviess, x_name="(eps,min_pts)",
              y_name="coeficient_de_Davies", dataset_name=dataset_name,
              method_name="DBSCAN", stop=False, save=save)
print_1d_data(params, calinskis, x_name="(eps,min_pts)",
              y_name="coeficient_de_Calinski", dataset_name=dataset_name,
              method_name="DBSCAN", stop=False, save=save)
print_1d_data(params, clusters, x_name="(eps,min_pts)",
              y_name="nombre_de_clusters", dataset_name=dataset_name,
              method_name="DBSCAN", stop=False, save=save)
print_1d_data(params, noise_points, x_name="(eps,min_pts)",
              y_name="points_de_bruit", dataset_name=dataset_name,
              method_name="DBSCAN", stop=False, save=save)