miamor / han-sec-new Goto Github PK

I wasn't able to generate graphs of my dataset for several reasons: in main.py file, inside load_dataset funcion, you import prep_data_n not from utils, but from the same main's folder, but there is no such file in the folder, I have deleted this line and I have considered only line 37. Then, at line 220 you call the previous function passing as parameters config_params, I noticed that in a previous project these parameters were being read from this configuration file, so I changed the paths to adapt them to my folders (I have a folder in which the reports produced by cuckoo are contained, divided into two subfolders, namely benign and malware), but I think there are several missing paths.
Next, PrepareData should return prep_data but I'm stuck here as I haven't a pretrained embedder, so self.train_and_load_embedding() is called: I have to prepare word embeddings and train node and edge embedders, but prepare function expects a not empty list to iterate on embedding_data_csv, but I haven't this list, and I don't know how to build it correctly. For the same reason, the corpus.csv file is also empty. How can I solve it?