sylvia-liang / qasparql Goto Github PK

Which python version should I select?

Good day, has anyone encounter KeyError: 239 when running the lcquad_test.py file?
Below are the error messages:

Traceback (most recent call last):
File "lcquad_test.py", line 642, in
question_type_classifier = SVMClassifier(os.path.join(question_type_classifier_path, "svm.model"))
File "C:\Users\mrcho\Desktop\QAsparql-master\learning\classifier\svmclassifier.py", line 52, in init
super(SVMClassifier, self).init(model_file_path)
File "C:\Users\mrcho\Desktop\QAsparql-master\learning\classifier\classifier.py", line 12, in init
self.load(model_file_path)
File "C:\Users\mrcho\Desktop\QAsparql-master\learning\classifier\classifier.py", line 28, in load
self.model = joblib.load(file_path)
File "C:\Users\mrcho\anaconda3\lib\site-packages\joblib\numpy_pickle.py", line 658, in load
obj = _unpickle(fobj, filename, mmap_mode)
File "C:\Users\mrcho\anaconda3\lib\site-packages\joblib\numpy_pickle.py", line 577, in _unpickle
obj = unpickler.load()
File "C:\Users\mrcho\anaconda3\lib\pickle.py", line 1212, in load
dispatchkey[0]
KeyError: 239

Much appreciated.

Hello,
Thanks for sharing your code. I checked the queries generated by your system and I find that you just get the triple patterns, not the complete query.
For example

...
"generated_queries": [
{
"correct": false,
"query": "?u_1 http://dbpedia.org/ontology/height ?u_0",
"target_var": "?u_1"
},
...

I am just wondering if there is an end to end service to feed your system with questions and get the answers or the complete generated queries to use them to get the answer ourselves?
Also, where is the paper associated with that system?
Thanks
Abdelghny