Semantic Linking: Created Classes for semantic linking logic

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

-import networkx as nx
-import matplotlib.pyplot as plt
-import pandas as pd
 import json
 
-
-
-with open("mult_in_out.json", "r") as json_file:
-    df_nodes = json.load(json_file)
-
-
 nodeIds = []
-destIds= []
-clusterlabels= []
+destIds = []
+clusterlabels = []
 destclusterlabel = []
-cluster= []
+cluster = []
 labalvlues = []
-i = 0
 
+def classify():
 
-for row in df_nodes:
+    with open("mult_in_out.json", "r") as json_file:
+        df_nodes = json.load(json_file)
 
-    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 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 range(len(nodeIds)):
-    print(nodeIds[row])
 
-print("Finish InputIDs")
-for row in range(len(nodeIds)):
+    for row in df_nodes:
+       destIds.append(row['TransactionTo'])
 
-    clusterlabels.append(row)
-    i += 1
-print(i)
 
-"""" 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)):
 
-        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]
+        clusterlabels.append(row)
+        i += 1
+    print(i)
 
-                  else:
-                      for row2 in clusterlabels:
-                          if (clusterlabels[row] == clusterlabels[row2]):
-                              clusterlabels[row2] = clusterlabels[row1]
-                      clusterlabels[row] = clusterlabels[row1]
+    """" classifying Inputs"""
+    """" Labaling inputs"""
+    for row in range(len(nodeIds)):
 
+        for rown in range(len(nodeIds[row])):
 
-print(clusterlabels)
-print("cluster labels:", len(clusterlabels))
-print("NodeIDs:   ", len(nodeIds))
+            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]
 
+                      else:
+                          for row2 in clusterlabels:
+                              if (clusterlabels[row] == clusterlabels[row2]):
+                                  clusterlabels[row2] = clusterlabels[row1]
+                          clusterlabels[row] = clusterlabels[row1]
 
 
-"""" Calculating the number of clusters"""
-clusternum = 1
-labalvlues.append(clusterlabels[0])
-for row in range(len(clusterlabels)):
-    flag = True
-    for row1 in range(len(labalvlues)):
-      if(clusterlabels[row]== labalvlues[row1]):
-         flag = False
+    print(clusterlabels)
+    print("cluster labels:", len(clusterlabels))
+    print("NodeIDs:   ", len(nodeIds))
+
 
-    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))
+    """" Calculating the number of clusters"""
+    clusternum = 1
+    labalvlues.append(clusterlabels[0])
+    for row in range(len(clusterlabels)):
+        flag = True
+        for row1 in range(len(labalvlues)):
+          if(clusterlabels[row]== labalvlues[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))
 
 
 
 
-"""" clustering Ids according to their labels"""
+    """" clustering Ids according to their labels"""
 
-for row in range(len(labalvlues)):
-    cluster.append([])
-    for row3 in range(len(nodeIds)):
-        if (labalvlues[row] == clusterlabels[row3]):
-            cluster[row].extend(nodeIds[row3])
-print("clusters:   ", cluster)
+    for row in range(len(labalvlues)):
+        cluster.append([])
+        for row3 in range(len(nodeIds)):
+            if (labalvlues[row] == clusterlabels[row3]):
+                cluster[row].extend(nodeIds[row3])
+    print("clusters:   ", cluster)
 
 
 
-""" Removing duplicating items in cluster"""
+    """ Removing duplicating items in cluster"""
 
-flag = True
-while(flag):
-  for row in range(len(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
+        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
-    if(flag):
-        break
 
-print("cluster:", cluster)
+    print("cluster:", cluster)
 
 
 
 
-"""" Clustering  Destination Ids """
-for row in range(len(destIds)):
-    destclusterlabel.append([])
-    for row2 in range(len(destIds[row])):
-        flag = True
-        for rownum in range(len(labalvlues)):
-            for row1 in range(len(cluster[rownum])):
+    """" Clustering  Destination Ids """
+    for row in range(len(destIds)):
+        destclusterlabel.append([])
+        for row2 in range(len(destIds[row])):
+            flag = True
+            for rownum in range(len(labalvlues)):
+                for row1 in range(len(cluster[rownum])):
 
-               if(destIds[row][row2]== cluster[rownum][row1]):
-                    destclusterlabel[row].append(labalvlues[rownum])
-                    flag = False
-        if(flag):
-            destclusterlabel.append(destIds[row][row2])
+                   if(destIds[row][row2]== cluster[rownum][row1]):
+                        destclusterlabel[row].append(labalvlues[rownum])
+                        flag = False
+            if(flag):
+                destclusterlabel.append(destIds[row][row2])
 
-print("destination labels (destination Ids):  ", destclusterlabel)
+    print("destination labels (destination Ids):  ", destclusterlabel)