Corrected code

real_world/2D/agglomerative2D.py

@@ -19,7 +19,7 @@ calinski = []
 davies = []
 
 
-data = np.loadtxt('tr.data')
+data = np.loadtxt('zgo.data')
 
 for (x, y) in data :
     x_list.append(x)
@@ -37,6 +37,23 @@ for n in range(2, 20):
     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 clusters')
+
+plt.plot(range(2,20), davies, marker='o', label='Davies')
+plt.xlim(2,20)
+plt.xlabel('Nb clusters')
+
+"""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 

real_world/2D/hdbscan2D.py

@@ -19,7 +19,7 @@ calinski = []
 davies = []
 
 
-data = np.loadtxt('zgo.data')
+data = np.loadtxt('zgn.data')
 
 for (x, y) in data :
     x_list.append(x)
@@ -40,6 +40,23 @@ for n in range(2, 20):
     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)

real_world/2D/kmeans2D.py

@@ -19,7 +19,7 @@ calinski = []
 davies = []
 
 
-data = np.loadtxt('zgo.data')
+data = np.loadtxt('tr.data')
 
 for (x, y) in data :
     x_list.append(x)
@@ -38,6 +38,23 @@ for n in range(2, 20):
     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 clusters')
+
+plt.plot(range(2,20), davies, marker='o', label='Davies')
+plt.xlim(2,20)
+plt.xlabel('Nb clusters')"""
+
+plt.plot(range(2,20), calinski, marker='o')
+plt.xlim(2,20)
+plt.xlabel('Nb clusters')
+plt.ylabel('Calinski coeff')
+
+plt.legend()
+
+plt.show()
+    
 #silhouettte coefficient
 #get the index of the best result 
 m = max(silhouette)
@@ -50,7 +67,6 @@ clustering = KMeans(n_clusters=indice, init='k-means++').fit(data_final)
 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
@@ -64,8 +80,6 @@ clustering = KMeans(n_clusters=indice, init='k-means++').fit(data_final)
 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)

real_world/3D/agglomerative3D.py

@@ -26,7 +26,7 @@ for (x, y, z) in data :
     x_list.append(x)
     y_list.append(y)
     z_list.append(z)
-    data_final.append([x,y])
+    data_final.append([x,y,z])
 
 for n in range(2, 20):
 
@@ -39,7 +39,23 @@ for n in range(2, 20):
     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 clusters')
+
+plt.plot(range(2,20), davies, marker='o', label='Davies')
+plt.xlim(2,20)
+plt.xlabel('Nb clusters')"""
+
+plt.plot(range(2,20), calinski, marker='o')
+plt.xlim(2,20)
+plt.xlabel('Nb clusters')
+plt.ylabel('Calinski coeff')
+
+plt.legend()
+
+plt.show()
 #silhouettte coefficient
 #get the index of the best result 
 m = max(silhouette)

real_world/3D/dbscan3D.py

@@ -26,7 +26,7 @@ for (x, y, z) in data :
     x_list.append(x)
     y_list.append(y)
     z_list.append(z)
-    data_final.append([x,y])
+    data_final.append([x,y,z])
 
 clustering = DBSCAN(eps=0.25, min_samples=10).fit(data_final)
 colors = clustering.labels_

real_world/3D/hdbscan3D.py

@@ -20,13 +20,13 @@ calinski = []
 davies = []
 
 
-data = np.loadtxt('a.data')
+data = np.loadtxt('h.data')
 
 for (x, y, z) in data :
     x_list.append(x)
     y_list.append(y)
     z_list.append(z)
-    data_final.append([x,y])
+    data_final.append([x,y,z])
 
 #get the values of the different coefficients for different min_samples values from 2 to 20
 for n in range(2, 20):
@@ -42,6 +42,23 @@ for n in range(2, 20):
     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)

real_world/3D/kmeans3D.py

@@ -8,8 +8,6 @@ from sklearn.cluster import AgglomerativeClustering
 from sklearn.cluster import DBSCAN
 import hdbscan
 
-n_clusters = 2
-
 data_final = []
 x_list = []
 y_list = []
@@ -26,7 +24,7 @@ for (x, y, z) in data :
     x_list.append(x)
     y_list.append(y)
     z_list.append(z)
-    data_final.append([x,y])
+    data_final.append([x,y,z])
 
 for n in range(2, 20):
 
@@ -39,7 +37,24 @@ for n in range(2, 20):
     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 clusters')
+
+plt.plot(range(2,20), davies, marker='o', label='Davies')
+plt.xlim(2,20)
+plt.xlabel('Nb clusters')
+
+"""plt.plot(range(2,20), calinski, marker='o')
+plt.xlim(2,20)
+plt.xlabel('Nb clusters')
+plt.ylabel('Calinski coeff')"""
+
+plt.legend()
+
+plt.show()
 #silhouettte coefficient
 #get the index of the best result 
 m = max(silhouette)
@@ -49,7 +64,7 @@ print("Silhouette : ",  indice)
 plt.subplot(3,1,1)
 #display the best obtained result
 clustering = KMeans(n_clusters=indice, init='k-means++').fit(data_final)
-colors = clustering.fit_predict(data_final)
+colors = clustering.labels_
 plt.axes(projection='3d').scatter3D(x_list, y_list, z_list, c=colors)
 plt.show()
 
@@ -62,7 +77,7 @@ print("Davies Bouldin : ",  indice)
 plt.subplot(3,1,2)
 #display the best obtained result with davies bouldin metrics
 clustering = KMeans(n_clusters=indice, init='k-means++').fit(data_final)
-colors = clustering.fit_predict(data_final)
+colors = clustering.labels_
 plt.axes(projection='3d').scatter3D(x_list, y_list, z_list, c=colors)
 plt.show()
 
@@ -75,6 +90,6 @@ print("Calinski Harabasz : ",  indice)
 plt.subplot(3,1,3)
 #display the best obtained result
 clustering = KMeans(n_clusters=indice, init='k-means++').fit(data_final)
-colors = clustering.fit_predict(data_final)
+colors = clustering.labels_
 plt.axes(projection='3d').scatter3D(x_list, y_list, z_list, c=colors)
 plt.show()