from scipy.io import arff
import numpy as np
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
from sklearn import metrics
from sklearn.cluster import DBSCAN

data = arff.loadarff('diamond9.arff')[0]
data_final = []
x_list = []
y_list = []

for (x, y, z) in data :
    x_list.append(x)
    y_list.append(y)
    data_final.append([x,y])

clustering = DBSCAN(eps=0.5, min_samples=2).fit(data_final)

colors = clustering.labels_

plt.scatter(x_list, y_list, c=colors, s=5)
plt.show()

silh = metrics.silhouette_score(data_final, colors, metric='euclidean')
dbsc = metrics.davies_bouldin_score(data_final, colors)
caha = metrics.calinski_harabasz_score(data_final, colors)
print("Coefficient de silhouette : ", silh)
print("Indice de Davies Bouldin : ", dbsc)
print("Indice de calinski harabasz : ", caha)