xyjprc / hon

Code for generating Higher-order Network (HON) from data with higher-order dependencies
http://advances.sciencemag.org/content/2/5/e1600028
MIT License
64 stars 18 forks source link

Getting Higher-Order dependencies from VNF sequences in NFV #7

Open ICarvalho opened 4 years ago

ICarvalho commented 4 years ago

Hi,

I'm trying to get HOD from a dataset containing a sequences of VNFs (Virtual Network Functions), but when I give as input the data, no output is produces, like the rules. Checking the examples provided in the code, I saw that you've tested HON using numbers, by my input dataset is like this:

service_id vnf_01 vnf_02 vnf_03 vnf_04 vnf_05 vnf_06 (header)

0 wanacc0 ecrpt0 1 fw0 fw0 ecrpt0 nat0 ids0 2 fw0 ids0 nat0 lb20 3 lb23 lb23 ids3 . . .... I consider variable-length sequences I aim to extract such dependencies among them in order to predict these sequences and use it for resource allocation.

Could you please give me a guide and how I could overcome this issues?

Best regards,

Igor.

xyjprc commented 4 years ago

Hi @ICarvalho

Thank you for your interest. One simple way would be to create a dictionary to map your labels to distinct numbers, such as all wanacc0 to 0, ecrpt0 to 1, fw0 to 2, etc. This should solve your issue.

Best, Jian