Difference between revisions of "Orange: Network From Distances"

From OnnoWiki
Jump to navigation Jump to search
 
(10 intermediate revisions by the same user not shown)
Line 2: Line 2:
  
  
 +
Widget Network From Distances membangun network dari distance antar instance.
  
−
Constructs a network from distances between instances.
+
==Input==
  
−
Inputs
+
Distances: A distance matrix.
  
−
    Distances: A distance matrix.
+
==Output==
  
−
Outputs
+
Network: An instance of Network Graph.
 +
Data: Attribute-valued data set.
 +
Distances: A distance matrix.
  
−
    Network: An instance of Network Graph.
+
Widget Network from Distances membangun sebuah network graph dari sebuah distance matrix yang diberikan. Graph dibangun dengan connecting node dari matrix dimana distance antar node dibawah dari threshold yang diberikan. Dengan kata lain, semua instance dengan distance di bawah threshold yang di tentukan, akan tersambung /connected.
−
    Data: Attribute-valued data set.
 
−
    Distances: A distance matrix.
 
  
−
Network from Distances constructs a network graph from a given distance matrix. Graph is constructed by connecting nodes from the matrix where the distance between nodes is below the given threshold. In other words, all instances with a distance lower than the selected threshold, will be connected.
+
[[File:Network-from-distances-stamped.png|center|600px|thumb]]
  
−
[[File:Network-from-distances-stamped.png|center|200px|thumb]]
+
* Edges:
 +
** Distance threshold: a closeness threshold for the formation of edges.
 +
** Percentile: the percentile of data instances to be connected.
 +
** Include also closest neighbors: include a number of closest neighbors to the selected instances.
 +
* Node selection:
 +
** Keep all nodes: entire network is on the output.
 +
** Components with at least X nodes: filters out nodes with less than the set number of nodes.
 +
** Largest connected component: keep only the largest cluster.
 +
* Edge weights:
 +
** Proportional to distance: weights are set to reflect the distance (closeness).
 +
** Inverted distance: weights are set to reflect the inverted distance (difference).
 +
* Information on the constructed network:
 +
** Data items on input: number of instances on the input.
 +
** Network nodes: number of nodes in the network (and the percentage of the original data).
 +
** Network edges: number of constructed edges/connections (and the average number of connections per node).
  
−
    Edges:
+
==Contoh==
−
        Distance threshold: a closeness threshold for the formation of edges.
 
−
        Percentile: the percentile of data instances to be connected.
 
−
        Include also closest neighbors: include a number of closest neighbors to the selected instances.
 
−
    Node selection:
 
−
        Keep all nodes: entire network is on the output.
 
−
        Components with at least X nodes: filters out nodes with less than the set number of nodes.
 
−
        Largest connected component: keep only the largest cluster.
 
−
    Edge weights:
 
−
        Proportional to distance: weights are set to reflect the distance (closeness).
 
−
        Inverted distance: weights are set to reflect the inverted distance (difference).
 
−
    Information on the constructed network:
 
−
        Data items on input: number of instances on the input.
 
−
        Network nodes: number of nodes in the network (and the percentage of the original data).
 
−
        Network edges: number of constructed edges/connections (and the average number of connections per node).
 
  
−
Example
+
Widget Network from Distances membuat network dari distance matrix. Ini akan mentransformasikan data set dari sebuah tabel data melalui distance matrix menjadi sebuah network graph. Widget ini sangat baik untuk memvisualisasi kesamaan sebagai sebuah graph dari connected instance.
  
−
Network from Distances creates networks from distance matrices. It can transform data sets from a data table via distance matrix into a network graph. This widget is great for visualizing instance similarity as a graph of connected instances.
+
[[File:Network-from-distances-example.png|center|600px|thumb]]
  
−
We took iris.tab to visualize instance similarity in a graph. We sent the output of File widget to Distances, where we computed Euclidean distances between rows (instances). Then we sent the output of Distances to Network from Distances, where we set the distance threshold (how similar the instances have to be to draw an edge between them) to 0.222. We kept all nodes and set edge weights to proportional to distance.
+
Kita akan mengambil iris.tab untuk memvisualisasi kesamaan instance disebuah graph. Kita kirim keluaran dari widget File ke widget Distances, dimana kita akan menghitung Euclidean distance antara dua baris (instance). Kemudian kita kirim output dari widget Distances ke widget Network from Distances, dimana kita set distance threshold (seberapa sama instance yang akan digambarkan edge antara mereka) ke 0.222. Kita akan menyimpan semua node dan set beban edge akan proporsional ke distance.
−
 
 
−
Then we observed the constructed network in a Network Explorer. We colored the nodes by iris attribute.
 
  
 +
Kita dapat mengamati network yang dibangun menggunakan widget Network Explorer. Kita mewarnai node dengan iris attribute.
  
 
==Referensi==
 
==Referensi==

Latest revision as of 16:40, 6 April 2020

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


Widget Network From Distances membangun network dari distance antar instance.

Input

Distances: A distance matrix.

Output

Network: An instance of Network Graph.
Data: Attribute-valued data set.
Distances: A distance matrix.

Widget Network from Distances membangun sebuah network graph dari sebuah distance matrix yang diberikan. Graph dibangun dengan connecting node dari matrix dimana distance antar node dibawah dari threshold yang diberikan. Dengan kata lain, semua instance dengan distance di bawah threshold yang di tentukan, akan tersambung /connected.

Network-from-distances-stamped.png
  • Edges:
    • Distance threshold: a closeness threshold for the formation of edges.
    • Percentile: the percentile of data instances to be connected.
    • Include also closest neighbors: include a number of closest neighbors to the selected instances.
  • Node selection:
    • Keep all nodes: entire network is on the output.
    • Components with at least X nodes: filters out nodes with less than the set number of nodes.
    • Largest connected component: keep only the largest cluster.
  • Edge weights:
    • Proportional to distance: weights are set to reflect the distance (closeness).
    • Inverted distance: weights are set to reflect the inverted distance (difference).
  • Information on the constructed network:
    • Data items on input: number of instances on the input.
    • Network nodes: number of nodes in the network (and the percentage of the original data).
    • Network edges: number of constructed edges/connections (and the average number of connections per node).

Contoh

Widget Network from Distances membuat network dari distance matrix. Ini akan mentransformasikan data set dari sebuah tabel data melalui distance matrix menjadi sebuah network graph. Widget ini sangat baik untuk memvisualisasi kesamaan sebagai sebuah graph dari connected instance.

Network-from-distances-example.png

Kita akan mengambil iris.tab untuk memvisualisasi kesamaan instance disebuah graph. Kita kirim keluaran dari widget File ke widget Distances, dimana kita akan menghitung Euclidean distance antara dua baris (instance). Kemudian kita kirim output dari widget Distances ke widget Network from Distances, dimana kita set distance threshold (seberapa sama instance yang akan digambarkan edge antara mereka) ke 0.222. Kita akan menyimpan semua node dan set beban edge akan proporsional ke distance.

Kita dapat mengamati network yang dibangun menggunakan widget Network Explorer. Kita mewarnai node dengan iris attribute.

Referensi


Pranala Menarik

Retrieved from "https://onnocenter.or.id/wiki/index.php?title=Orange:_Network_From_Distances&oldid=60916"