p_max_cluster_count wieder eingeführt

code/main.py

@@ -22,7 +22,7 @@ p_attr_weights = {
 } # attributes that are not given in the data are not used
 p_clusteval_mode = 'silhouette'
 p_clustering_mode   = 'kmeans' # optional, default: kmeans
-# p_max_cluster_count = 25 # np.NaN # cluster-count (optional, default: np.NaN which leads to automatic k determination)
+p_max_cluster_count = np.NaN # np.NaN # cluster-count (optional, default: np.NaN which leads to automatic k determination)
 p_ocel_file_type    = 'json' # json|xml
 p_graph_file_type   = 'svg' # svg|png
 # END PARAMETERS
@@ -38,7 +38,7 @@ print('p_attr_weights:')
 print(p_attr_weights)
 print('p_clusteval_mode:    "' + str(p_clusteval_mode) + '".')
 print('p_clustering_mode:   "' + str(p_clustering_mode) + '".')
-# print('p_max_cluster_count:     "' + str(p_max_cluster_count) + '".')
+print('p_max_cluster_count:     "' + str(p_max_cluster_count) + '".')
 print('p_ocel_file_type:    "' + str(p_ocel_file_type) + '".')
 print('p_graph_file_type:   "' + str(p_graph_file_type) + '".')
 print('-------------------------------------------------------')
@@ -82,16 +82,20 @@ index_to_oid_map = res['index']
 
 algo = algorithms[p_clustering_mode]
 
-# try:
-#     max_cluster_count = int(p_max_cluster_count)
-# except:
-#     max_cluster_count = 25
+try:
+    max_cluster_count = int(p_max_cluster_count)
+except:
+    max_cluster_count = 0
 # assert max_cluster_count >= 2, 'cluster_count needs to be at least 2'
-# assert max_cluster_count < len(index_to_oid_map), 'cluster_count needs to be less than the count of distinct objects in the ocel-data.'
+# max_cluster darf jetzt auch 0 sein, dann wird by default der Algorithmus entscheiden, wieviele cluster nötig zu berechnen sind.
+assert max_cluster_count < len(index_to_oid_map), 'cluster_count needs to be less than the count of distinct objects in the ocel-data.'
 
 # cluster_count = cluster.determine_optimal_k(distance_matrix, algorithm=algo, k_max=max_cluster_count)
 
-results = clusteval(evaluate = p_clusteval_mode).fit(distance_matrix)
+if (max_cluster_count == 0):
+    results = clusteval(evaluate = p_clusteval_mode).fit(distance_matrix)
+else:
+    results = clusteval(evaluate = p_clusteval_mode, max_clust=max_cluster_count).fit(distance_matrix)
 cluster_count = results['score']['clusters'].iloc[np.where(results['score']['score'] == results['score']['score'].max())[0][0]]
 
 algo.set_params(n_clusters=cluster_count)