Difference between revisions of "Orange: Network Of Groups"

From OnnoWiki
Jump to navigation Jump to search
(Created page with "Sumber: https://orange.biolab.si/widget-catalog/networks/networkofgroups/ Group instances by feature and connect related groups. Inputs Network: An instance of networ...")
 
 
(6 intermediate revisions by the same user not shown)
Line 2: Line 2:
  
  
 +
Widget Network Of Groups mengelompokan (group) instance berdasarkan feature dan connect related group.
  
Group instances by feature and connect related groups.
+
==Input==
  
Inputs
+
Network: An instance of network graph.
 +
Data: Properties of a network graph.
  
    Network: An instance of network graph.
+
==Output==
    Data: Properties of a network graph.
 
  
Outputs:
+
Network: A grouped network graph.
 +
Data: Properties of the group network graph.
  
    Network: A grouped network graph.
+
Network of Groups adalah versi network dari group-by operation. Node dengan nilai atribut yang sama, di pilih dalam dropdown, will di representasikan sebagai sebuah single node.
    Data: Properties of the group network graph.
 
  
Network of Groups is the network version of the group-by operation. Nodes with the same values of the attribute, selected in the dropdown, will be represented as a single node.
+
[[File:Network-of-Groups-stamped.png|center|200px|thumb]]
  
    Information on the input and output network.
+
* Information on the input and output network.
    Select the attribute to group by.
+
* Select the attribute to group by.
    Compute weights:
+
* Compute weights:
        No weights: all weights are set to 1.
+
** No weights: all weights are set to 1.
        Number of connections: weight edges by the number of connections between the groups.
+
** Number of connections: weight edges by the number of connections between the groups.
        Sum of connection weights: weight edges by the sum of weights of connections between the groups. Normalize by geometric mean divides weights by the geometric mean of the number of connections between the two groups.
+
** Sum of connection weights: weight edges by the sum of weights of connections between the groups. Normalize by geometric mean divides weights by the geometric mean of the number of connections between the two groups.
  
Example
+
==Contoh==
 
 
In this example we are using airtraffic data set, that we loaded in the Network File widget. We see the entire data set in Network Explorer (1).
 
 
 
Then we use Network of Groups to group the network by the FAA Classifications attribute. All nodes with the same value of this attribute will be represented as a single node in the output. There is an edge between the two nodes, if they share connections in the original network.
 
 
 
The grouped network is shown in Network Explorer.
 
  
 +
Dalam contoh ini, kita akan menggunakan airtraffic dataset, yang di load menggunakan widget Network File. Kita dapat melihat seluruh data set di widget Network Explorer(1).
  
 +
Kemudian kita menggunakan widget Network of Groups untuk mengelompokan (group) dari network berdasarkan atribut FAA Classification. Semua node dengan nilai yang atribut yang sama akan di representasikan dengan single node di output. Akan ada edge antars dua (2) node, jika mereka berbagi connection di network original.
  
 +
Grouped network di perlihatkan di widget Network Explorer.
  
 +
[[File:Network-of-Groups-Example.png|center|600px|thumb]]
  
 
==Referensi==
 
==Referensi==

Latest revision as of 16:21, 6 April 2020

Sumber: https://orange.biolab.si/widget-catalog/networks/networkofgroups/


Widget Network Of Groups mengelompokan (group) instance berdasarkan feature dan connect related group.

Input

Network: An instance of network graph.
Data: Properties of a network graph.

Output

Network: A grouped network graph.
Data: Properties of the group network graph.

Network of Groups adalah versi network dari group-by operation. Node dengan nilai atribut yang sama, di pilih dalam dropdown, will di representasikan sebagai sebuah single node.

Network-of-Groups-stamped.png
  • Information on the input and output network.
  • Select the attribute to group by.
  • Compute weights:
    • No weights: all weights are set to 1.
    • Number of connections: weight edges by the number of connections between the groups.
    • Sum of connection weights: weight edges by the sum of weights of connections between the groups. Normalize by geometric mean divides weights by the geometric mean of the number of connections between the two groups.

Contoh

Dalam contoh ini, kita akan menggunakan airtraffic dataset, yang di load menggunakan widget Network File. Kita dapat melihat seluruh data set di widget Network Explorer(1).

Kemudian kita menggunakan widget Network of Groups untuk mengelompokan (group) dari network berdasarkan atribut FAA Classification. Semua node dengan nilai yang atribut yang sama akan di representasikan dengan single node di output. Akan ada edge antars dua (2) node, jika mereka berbagi connection di network original.

Grouped network di perlihatkan di widget Network Explorer.

Network-of-Groups-Example.png

Referensi

Pranala Menarik