hlf20010508 / kge_nfm Goto Github PK

Hello, I have a few questions about the KGE_NFM model. Have you ever run this code with datasets other than yamanishi_08 (such as BioKG, hetionet, luo's_dataset or other unmentioned datasets )?
Now，I'm trying to run the kge_nfm.py code using the BioKG dataset, but I have encountered the following problems in the process of changing the dataset. I would be happy to provide more details. Could you have a look at your convenience? Thank you.

Traceback (most recent call last):
File "kge_nfm.py", line 366, in
roc,pr,roc_s,pr_s,re_train_all,train_label,re_test_all,test_label,pred_y = train(i,10,10,50,200,True,10)
File "kge_nfm.py", line 314, in train
train_dense_features,test_dense_features = get_scaled_embeddings(model,re_train_all,re_test_all,False,n_components)
File "kge_nfm.py", line 168, in get_scaled_embeddings
[train_obj_embeddings,test_obj_embeddings] = [model.get_embeddings(x['tail'].values, embedding_type='entity') for x in [train_triples,test_triples]]
File "kge_nfm.py", line 168, in
[train_obj_embeddings,test_obj_embeddings] = [model.get_embeddings(x['tail'].values, embedding_type='entity') for x in [train_triples,test_triples]]
File "/home/zwc/anaconda3/envs/kge_nfm/lib/python3.6/site-packages/ampligraph/latent_features/models/EmbeddingModel.py", line 444, in get_embeddings
idxs = np.vectorize(lookup_dict.get)(entities)
File "/home/zwc/anaconda3/envs/kge_nfm/lib/python3.6/site-packages/numpy/lib/function_base.py", line 2108, in call
return self._vectorize_call(func=func, args=vargs)
File "/home/zwc/anaconda3/envs/kge_nfm/lib/python3.6/site-packages/numpy/lib/function_base.py", line 2195, in _vectorize_call
res = array(outputs, copy=False, subok=True, dtype=otypes[0])
TypeError: int() argument must be a string, a bytes-like object or a number, not 'NoneType'