how to run step by step

[SeekPoint]

by the way, ub16hp@UB16HP:~/ub16_prj/Hierarchical-Typing/src$ python3 build_data.py Traceback (most recent call last): File "build_data.py", line 309, in config_obj = Config(run_dir, "AIDA", "entity_linker_order") TypeError: init() takes 3 positional arguments but 4 were given ub16hp@UB16HP:~/ub16_prj/Hierarchical-Typing/src$

[izuna385]

I came across same error. In config.py, there are

` def init(self, run_dir, args):

    self.struct_weight = args.struct_weight
    self.dropout = args.dropout
    self.dataset = args.dataset
    self.encoder = args.encoder
    ...

` so, for runnning built_data.py, specifing all the parameters included in args is needed?

[MurtyShikhar]

Hi, build_data.py doesn't need to be run. All the data is provided in the google drive link (in the README).

[izuna385]

Thanks! I checked code, and setting base_dir="./dataset_dir". (and re-wrote some absolute path in code to relative path) So, the Directory structure is like this.

When setting dataset="typenet" and running deploy.py, it seems go well, so I'll going to run code. Thank you very much for your prompt response.

And also, I'm sorry for still troubling you, but is there any code for preprocessing umls database? Because, when I set dataset="umls" and ran code, but FileNotFoundError: [Errno 2] No such file or directory: './dataset_dir/meta_data_processed/entities.joblib'

Do you know how to run deploy.py for umls and Medmentions? Or, MIL_data contains something for Medmentions? (I still don't know what MIL stands for...)

[izuna385]

I'm sorry to bother you over and over. I find that to run deploy_linler.py for umls, preprocessed data of umls and Medmentions is needed to create

train_lines = joblib.load("meta_data_processed/meta_train.joblib")
dev_lines   = joblib.load("meta_data_processed/meta_dev.joblib")
test_lines  = joblib.load("meta_data_processed/meta_test.joblib")

And also I try to find code for coreting these data in this repository and Medmentions' one, but I couldn't. Is there any code for making preprocessing datas(i.e. meta_train.joblib,meta_dev.joblib,meta_test.joblib ) for Medmentions linkers?

[MurtyShikhar]

Hi, yes, this is available as well. I'll add it to the google drive soon!

[izuna385]

Thank you so much. I'll check it out later. None of the above are time critical, I'd appreciate if you can add them to drive when you have time.