Extracted methods

data-hub/semantic-linking-microservice/app/initialdemo/HyperGraph.py

 import json
 
-nodeIds = []
-destIds = []
-clusterlabels = []
-destclusterlabel = []
-cluster = []
-labalvlues = []
-
-def classify():
+
+def do():
     df_nodes = load_values()
 
-    for row in df_nodes:
+    ret_val = init(df_nodes)
+    nodeIds = ret_val['nodeIds']
+    clusterlabels = ret_val['clusterlabels']
+    destIds = ret_val['destIds']
+    
+    clusterlabels = classify_input(nodeIds, clusterlabels)
+
+    labelvals = calc_cluster_num(clusterlabels)
+
+    cluster = cluster_with_labels(nodeIds, clusterlabels, labelvals)
+
+    cluster = remove_duplicates(cluster)
+
+    destclusterlabel = cluster_dest_ids(labelvals, cluster, destIds)
+
+def load_values():
+    with open("mult_in_out_large.json", "r") as json_file:
+        df_nodes = json.load(json_file)
+
+    return df_nodes
+
+def init(df_nodes):
+    nodeIds = []
+    clusterlabels = []
+    destIds = []
 
+    for row in df_nodes:
         for j in range(len(row['TransactionFrom'])):
             print("   Input Ids:  ", row['TransactionFrom'][j])
         nodeIds.append(row['TransactionFrom'])
         print("This is nodes:  ", nodeIds)
 
-
     for row in df_nodes:
        destIds.append(row['TransactionTo'])
 
-
     for row in range(len(nodeIds)):
         print(nodeIds[row])
 
     print("Finish InputIDs")
     i = 0
     for row in range(len(nodeIds)):
-
         clusterlabels.append(row)
         i += 1
+
     print(i)
+    return {'nodeIds': nodeIds,
+            'clusterlabels': clusterlabels,
+            'destIds': destIds}
 
+def classify_input(nodeIds, clusterlabels):
     """" classifying Inputs"""
     """" Labaling inputs"""
     for row in range(len(nodeIds)):
@@ -55,42 +76,43 @@ def classify():
                                   clusterlabels[row2] = clusterlabels[row1]
                           clusterlabels[row] = clusterlabels[row1]
 
-
     print(clusterlabels)
     print("cluster labels:", len(clusterlabels))
     print("NodeIDs:   ", len(nodeIds))
+    return clusterlabels
 
-
-
+def calc_cluster_num(clusterlabels):
     """" Calculating the number of clusters"""
-    clusternum = 1
-    labalvlues.append(clusterlabels[0])
+    labelvals = []
+
+    labelvals.append(clusterlabels[0])
     for row in range(len(clusterlabels)):
         flag = True
-        for row1 in range(len(labalvlues)):
-          if(clusterlabels[row]== labalvlues[row1]):
+        for row1 in range(len(labelvals)):
+          if(clusterlabels[row]== labelvals[row1]):
              flag = False
 
         if (flag):
-            clusternum = + 1
-            labalvlues.append(clusterlabels[row])
-
-    print("label values (source Ids in the network):  ", labalvlues, " and the number of clusters is: ", len(labalvlues))
-
+            labelvals.append(clusterlabels[row])
 
+    print("label values (source Ids in the network):  ", labelvals, " and the number of clusters is: ", len(labelvals))
 
+    return labelvals
 
+def cluster_with_labels(nodeIds, clusterlabels, labelvals):
     """" clustering Ids according to their labels"""
+    cluster = []
 
-    for row in range(len(labalvlues)):
+    for row in range(len(labelvals)):
         cluster.append([])
         for row3 in range(len(nodeIds)):
-            if (labalvlues[row] == clusterlabels[row3]):
+            if (labelvals[row] == clusterlabels[row3]):
                 cluster[row].extend(nodeIds[row3])
     print("clusters:   ", cluster)
 
+    return cluster
 
-
+def remove_duplicates(cluster):
     """ Removing duplicating items in cluster"""
 
     flag = True
@@ -112,28 +134,26 @@ def classify():
             break
 
     print("cluster:", cluster)
+    
+    return cluster
 
-
-
-
+def cluster_dest_ids(labelvals, cluster, destIds):
     """" Clustering  Destination Ids """
+    destclusterlabel = []
+
     for row in range(len(destIds)):
         destclusterlabel.append([])
         for row2 in range(len(destIds[row])):
             flag = True
-            for rownum in range(len(labalvlues)):
+            for rownum in range(len(labelvals)):
                 for row1 in range(len(cluster[rownum])):
 
                    if(destIds[row][row2]== cluster[rownum][row1]):
-                        destclusterlabel[row].append(labalvlues[rownum])
+                        destclusterlabel[row].append(labelvals[rownum])
                         flag = False
             if(flag):
                 destclusterlabel.append(destIds[row][row2])
 
     print("destination labels (destination Ids):  ", destclusterlabel)
 
-def load_values():
-    with open("mult_in_out_large.json", "r") as json_file:
-        df_nodes = json.load(json_file)
-
-    return df_nodes
\ No newline at end of file
+    return destclusterlabel
\ No newline at end of file