applied oo

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

 import json
 
+class HyperGraph:
 
-def do():
-    df_nodes = load_values()
+    cluster_labels = []
+    dest_cluster_labels = []
+    label_values = []
 
-    ret_val = init(df_nodes)
-    nodeIds = ret_val['nodeIds']
-    clusterlabels = ret_val['clusterlabels']
-    destIds = ret_val['destIds']
-    
-    clusterlabels = classify_input(nodeIds, clusterlabels)
+    def __init__(self):
+        pass
 
-    labelvals = calc_cluster_num(clusterlabels)
+    def classify(self):
+        df_nodes = self.load_values()
 
-    cluster = cluster_with_labels(nodeIds, clusterlabels, labelvals)
+        ret_val = self.init(df_nodes)
+        nodeIds = ret_val['nodeIds']
+        clusterlabels = ret_val['clusterlabels']
+        destIds = ret_val['destIds']
+        
+        clusterlabels = self.classify_input(nodeIds, clusterlabels)
 
-    cluster = remove_duplicates(cluster)
+        labelvals = self.calc_cluster_num(clusterlabels)
 
-    destclusterlabel = cluster_dest_ids(labelvals, cluster, destIds)
+        cluster = self.cluster_with_labels(nodeIds, clusterlabels, labelvals)
 
-def load_values():
-    with open("mult_in_out_large.json", "r") as json_file:
-        df_nodes = json.load(json_file)
+        cluster = self.remove_duplicates(cluster)
 
-    return df_nodes
+        destclusterlabel = self.cluster_dest_ids(labelvals, cluster, destIds)
 
-def init(df_nodes):
-    nodeIds = []
-    clusterlabels = []
-    destIds = []
+        self.cluster_labels = clusterlabels
+        self.dest_cluster_labels = destclusterlabel
+        self.labelvals = labelvals
 
-    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)
+    def load_values(self):
+        with open("mult_in_out_large.json", "r") as json_file:
+            df_nodes = json.load(json_file)
 
-    for row in df_nodes:
-       destIds.append(row['TransactionTo'])
+        return df_nodes
 
-    for row in range(len(nodeIds)):
-        print(nodeIds[row])
+    def init(self, df_nodes):
+        nodeIds = []
+        clusterlabels = []
+        destIds = []
 
-    print("Finish InputIDs")
-    i = 0
-    for row in range(len(nodeIds)):
-        clusterlabels.append(row)
-        i += 1
+        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)
 
-    print(i)
-    return {'nodeIds': nodeIds,
-            'clusterlabels': clusterlabels,
-            'destIds': destIds}
+        for row in df_nodes:
+            destIds.append(row['TransactionTo'])
 
-def classify_input(nodeIds, clusterlabels):
-    """" classifying Inputs"""
-    """" Labaling inputs"""
-    for row in range(len(nodeIds)):
+        for row in range(len(nodeIds)):
+            print(nodeIds[row])
 
-        for rown in range(len(nodeIds[row])):
+        print("Finish InputIDs")
+        i = 0
+        for row in range(len(nodeIds)):
+            clusterlabels.append(row)
+            i += 1
 
-            for row1 in range(len(nodeIds)):
-                for rown1 in range(len(nodeIds[row1])):
-                   if(nodeIds[row][rown]==nodeIds[row1][rown1]):
-                      # print("row:  ",row,"row1:  ",row1)
-                      if(row < row1):
-                          for row2 in clusterlabels:
-                              if( clusterlabels[row1]== clusterlabels[row2]):
-                                  clusterlabels[row2]=clusterlabels[row]
-                          clusterlabels[row1] = clusterlabels[row]
+        print(i)
+        return {'nodeIds': nodeIds,
+                'clusterlabels': clusterlabels,
+                'destIds': destIds}
 
-                      else:
-                          for row2 in clusterlabels:
-                              if (clusterlabels[row] == clusterlabels[row2]):
-                                  clusterlabels[row2] = clusterlabels[row1]
-                          clusterlabels[row] = clusterlabels[row1]
+    def classify_input(self, nodeIds, clusterlabels):
+        """" classifying Inputs"""
+        """" Labaling inputs"""
+        for row in range(len(nodeIds)):
 
-    print(clusterlabels)
-    print("cluster labels:", len(clusterlabels))
-    print("NodeIDs:   ", len(nodeIds))
-    return clusterlabels
+            for rown in range(len(nodeIds[row])):
 
-def calc_cluster_num(clusterlabels):
-    """" Calculating the number of clusters"""
-    labelvals = []
+                for row1 in range(len(nodeIds)):
+                    for rown1 in range(len(nodeIds[row1])):
+                        if(nodeIds[row][rown]==nodeIds[row1][rown1]):
+                            # print("row:  ",row,"row1:  ",row1)
+                            if(row < row1):
+                                for row2 in clusterlabels:
+                                    if( clusterlabels[row1]== clusterlabels[row2]):
+                                        clusterlabels[row2]=clusterlabels[row]
+                                clusterlabels[row1] = clusterlabels[row]
 
-    labelvals.append(clusterlabels[0])
-    for row in range(len(clusterlabels)):
-        flag = True
-        for row1 in range(len(labelvals)):
-          if(clusterlabels[row]== labelvals[row1]):
-             flag = False
-
-        if (flag):
-            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(labelvals)):
-        cluster.append([])
-        for row3 in range(len(nodeIds)):
-            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
-    while(flag):
-      for row in range(len(cluster)):
-
-        flag= False
-        for row1 in range(len(cluster[row])):
-            flag= False
-            for row2 in range (len(cluster[row])):
-                 if(row1 != row2):
-                        if(cluster[row][row1] == cluster[row][row2]):
-                           del cluster[row][row2]
-                           flag=True
-                           break
-            if(flag):
-                break
-        if(flag):
-            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])):
+                            else:
+                                for row2 in clusterlabels:
+                                    if (clusterlabels[row] == clusterlabels[row2]):
+                                        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(self, clusterlabels):
+        """" Calculating the number of clusters"""
+        labelvals = []
+
+        labelvals.append(clusterlabels[0])
+        for row in range(len(clusterlabels)):
             flag = True
-            for rownum in range(len(labelvals)):
-                for row1 in range(len(cluster[rownum])):
+            for row1 in range(len(labelvals)):
+                if(clusterlabels[row]== labelvals[row1]):
+                    flag = False
+
+            if (flag):
+                labelvals.append(clusterlabels[row])
 
-                   if(destIds[row][row2]== cluster[rownum][row1]):
-                        destclusterlabel[row].append(labelvals[rownum])
-                        flag = False
-            if(flag):
-                destclusterlabel.append(destIds[row][row2])
+        print("label values (source Ids in the network):  ", labelvals, " and the number of clusters is: ", len(labelvals))
 
-    print("destination labels (destination Ids):  ", destclusterlabel)
+        return labelvals
 
-    return destclusterlabel
\ No newline at end of file
+    def cluster_with_labels(self, nodeIds, clusterlabels, labelvals):
+        """" clustering Ids according to their labels"""
+        cluster = []
+
+        for row in range(len(labelvals)):
+            cluster.append([])
+            for row3 in range(len(nodeIds)):
+                if (labelvals[row] == clusterlabels[row3]):
+                    cluster[row].extend(nodeIds[row3])
+        print("clusters:   ", cluster)
+
+        return cluster
+
+    def remove_duplicates(self, cluster):
+        """ Removing duplicating items in cluster"""
+
+        flag = True
+        while(flag):
+            for row in range(len(cluster)):
+
+                flag= False
+                for row1 in range(len(cluster[row])):
+                    flag= False
+                    for row2 in range (len(cluster[row])):
+                        if(row1 != row2):
+                            if(cluster[row][row1] == cluster[row][row2]):
+                                del cluster[row][row2]
+                                flag=True
+                                break
+                    if(flag):
+                        break
+                if(flag):
+                    break
+
+        print("cluster:", cluster)
+        
+        return cluster
+
+    def cluster_dest_ids(self, 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(labelvals)):
+                    for row1 in range(len(cluster[rownum])):
+
+                        if(destIds[row][row2]== cluster[rownum][row1]):
+                            destclusterlabel[row].append(labelvals[rownum])
+                            flag = False
+                if(flag):
+                    destclusterlabel.append(destIds[row][row2])
+
+        print("destination labels (destination Ids):  ", destclusterlabel)
+
+        return destclusterlabel
\ No newline at end of file