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

n_clusters = 2

data_final = []
x_list = []
y_list = []

silhouette = []
calinski = []
davies = []


data = np.loadtxt('zgn.data')

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

#get the values of the different coefficients for different min_samples values from 2 to 20
for n in range(2, 20):
    clustering = hdbscan.HDBSCAN(min_samples=n)
    colors = clustering.fit_predict(data_final)
    
    silh = metrics.silhouette_score(data_final, colors, metric='euclidean')
    silhouette.append(silh)

    dbsc = metrics.davies_bouldin_score(data_final, colors)
    davies.append(dbsc)
    
    caha = metrics.calinski_harabasz_score(data_final, colors)
    calinski.append(caha)

plt.plot(range(2,20), silhouette, marker='o', label='Silhouette')
plt.xlim(2,20)
plt.xlabel('Nb minimum de voisins')

plt.plot(range(2,20), davies, marker='o', label='Davies')
plt.xlim(2,20)
plt.xlabel('Nb minimum de voisins')

"""plt.plot(range(2,20), calinski, marker='o')
plt.xlim(2,20)
plt.xlabel('Nb minimum de voisins')
plt.ylabel('Calinski coeff')"""

plt.legend()

plt.show()

#silhouettte coefficient
#get the index of the best result 
m = max(silhouette)
indice = [i for i, j in enumerate(silhouette) if j == m][0] +2
print("Silhouette : ",  indice)

plt.subplot(3,1,1)
#display the best obtained result
clustering = hdbscan.HDBSCAN(min_samples=indice)
colors = clustering.fit_predict(data_final)
plt.scatter(x_list, y_list, c=colors, s=5)

plt.show()

#davies bouldin metrics
#get the index of the best result
m = min(davies)
indice = [i for i, j in enumerate(davies) if j == m][0] +2
print("Davies Bouldin : ",  indice)

plt.subplot(3,1,2)
#display the best obtained result with davies bouldin metrics
clustering = hdbscan.HDBSCAN(min_samples=indice)
colors = clustering.fit_predict(data_final)
plt.scatter(x_list, y_list, c=colors, s=5)

plt.show()

#calinski metrics
#get the index of the best result
m = max(calinski)
indice = [i for i, j in enumerate(calinski) if j == m][0] +2
print("Calinski Harabasz : ",  indice)

plt.subplot(3,1,3)
#display the best obtained result
clustering = hdbscan.HDBSCAN(min_samples=indice)
colors = clustering.fit_predict(data_final)
plt.scatter(x_list, y_list, c=colors, s=5)

plt.show()